diff options
403 files changed, 3554 insertions, 1657 deletions
@@ -364,6 +364,11 @@ Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org> Nicolas Saenz Julienne <nsaenz@kernel.org> <nsaenzjulienne@suse.de> Nicolas Saenz Julienne <nsaenz@kernel.org> <nsaenzjulienne@suse.com> Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se> +Nikolay Aleksandrov <razor@blackwall.org> <naleksan@redhat.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@redhat.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@cumulusnetworks.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@nvidia.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@isovalent.com> Oleksandr Natalenko <oleksandr@natalenko.name> <oleksandr@redhat.com> Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net> Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com> @@ -1706,6 +1706,10 @@ S: Panoramastrasse 18 S: D-69126 Heidelberg S: Germany +N: Neil Horman +M: nhorman@tuxdriver.com +D: SCTP protocol maintainer. + N: Simon Horman M: horms@verge.net.au D: Renesas ARM/ARM64 SoC maintainer diff --git a/Documentation/admin-guide/quickly-build-trimmed-linux.rst b/Documentation/admin-guide/quickly-build-trimmed-linux.rst index ff4f4cc8522b..f08149bc53f8 100644 --- a/Documentation/admin-guide/quickly-build-trimmed-linux.rst +++ b/Documentation/admin-guide/quickly-build-trimmed-linux.rst @@ -215,12 +215,14 @@ again. reduce the compile time enormously, especially if you are running an universal kernel from a commodity Linux distribution. - There is a catch: the make target 'localmodconfig' will disable kernel - features you have not directly or indirectly through some program utilized - since you booted the system. You can reduce or nearly eliminate that risk by - using tricks outlined in the reference section; for quick testing purposes - that risk is often negligible, but it is an aspect you want to keep in mind - in case your kernel behaves oddly. + There is a catch: 'localmodconfig' is likely to disable kernel features you + did not use since you booted your Linux -- like drivers for currently + disconnected peripherals or a virtualization software not haven't used yet. + You can reduce or nearly eliminate that risk with tricks the reference + section outlines; but when building a kernel just for quick testing purposes + it is often negligible if such features are missing. But you should keep that + aspect in mind when using a kernel built with this make target, as it might + be the reason why something you only use occasionally stopped working. [:ref:`details<configuration>`] @@ -271,6 +273,9 @@ again. does nothing at all; in that case you have to manually install your kernel, as outlined in the reference section. + If you are running a immutable Linux distribution, check its documentation + and the web to find out how to install your own kernel there. + [:ref:`details<install>`] .. _another_sbs: @@ -291,29 +296,29 @@ again. version you care about, as git otherwise might retrieve the entire commit history:: - git fetch --shallow-exclude=v6.1 origin - - If you modified the sources (for example by applying a patch), you now need - to discard those modifications; that's because git otherwise will not be able - to switch to the sources of another version due to potential conflicting - changes:: - - git reset --hard + git fetch --shallow-exclude=v6.0 origin - Now checkout the version you are interested in, as explained above:: + Now switch to the version you are interested in -- but be aware the command + used here will discard any modifications you performed, as they would + conflict with the sources you want to checkout:: - git checkout --detach origin/master + git checkout --force --detach origin/master At this point you might want to patch the sources again or set/modify a build - tag, as explained earlier; afterwards adjust the build configuration to the - new codebase and build your next kernel:: + tag, as explained earlier. Afterwards adjust the build configuration to the + new codebase using olddefconfig, which will now adjust the configuration file + you prepared earlier using localmodconfig (~/linux/.config) for your next + kernel:: # reminder: if you want to apply patches, do it at this point # reminder: you might want to update your build tag at this point make olddefconfig + + Now build your kernel:: + make -j $(nproc --all) - Install the kernel as outlined above:: + Afterwards install the kernel as outlined above:: command -v installkernel && sudo make modules_install install @@ -584,11 +589,11 @@ versions and individual commits at hand at any time:: curl -L \ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/clone.bundle \ -o linux-stable.git.bundle - git clone clone.bundle ~/linux/ + git clone linux-stable.git.bundle ~/linux/ rm linux-stable.git.bundle cd ~/linux/ - git remote set-url origin - https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git + git remote set-url origin \ + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git git fetch origin git checkout --detach origin/master diff --git a/Documentation/cdrom/index.rst b/Documentation/cdrom/index.rst index e87a8785bc1a..e9b022d70939 100644 --- a/Documentation/cdrom/index.rst +++ b/Documentation/cdrom/index.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -===== -cdrom -===== +====== +CD-ROM +====== .. toctree:: :maxdepth: 1 diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml index 9b31f864e071..71364c6081ff 100644 --- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml +++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 iommus: - maxItems: 1 + maxItems: 4 power-domains: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml index 769fa5c27b76..de1d4298893b 100644 --- a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml +++ b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml @@ -21,11 +21,22 @@ properties: st,can-primary: description: - Primary and secondary mode of the bxCAN peripheral is only relevant - if the chip has two CAN peripherals. In that case they share some - of the required logic. + Primary mode of the bxCAN peripheral is only relevant if the chip has + two CAN peripherals in dual CAN configuration. In that case they share + some of the required logic. + Not to be used if the peripheral is in single CAN configuration. To avoid misunderstandings, it should be noted that ST documentation - uses the terms master/slave instead of primary/secondary. + uses the terms master instead of primary. + type: boolean + + st,can-secondary: + description: + Secondary mode of the bxCAN peripheral is only relevant if the chip + has two CAN peripherals in dual CAN configuration. In that case they + share some of the required logic. + Not to be used if the peripheral is in single CAN configuration. + To avoid misunderstandings, it should be noted that ST documentation + uses the terms slave instead of secondary. type: boolean reg: diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml index a5bb561bfcfb..31a3024ea789 100644 --- a/Documentation/devicetree/bindings/sound/tas2562.yaml +++ b/Documentation/devicetree/bindings/sound/tas2562.yaml @@ -55,7 +55,9 @@ properties: description: TDM TX current sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -72,7 +74,7 @@ examples: codec: codec@4c { compatible = "ti,tas2562"; reg = <0x4c>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; shutdown-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas2770.yaml b/Documentation/devicetree/bindings/sound/tas2770.yaml index 26088adb9dc2..8908bf1122e9 100644 --- a/Documentation/devicetree/bindings/sound/tas2770.yaml +++ b/Documentation/devicetree/bindings/sound/tas2770.yaml @@ -57,7 +57,9 @@ properties: - 1 # Falling edge '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -74,7 +76,7 @@ examples: codec: codec@41 { compatible = "ti,tas2770"; reg = <0x41>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpio = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas27xx.yaml b/Documentation/devicetree/bindings/sound/tas27xx.yaml index 8cba01316855..a876545ec87d 100644 --- a/Documentation/devicetree/bindings/sound/tas27xx.yaml +++ b/Documentation/devicetree/bindings/sound/tas27xx.yaml @@ -50,7 +50,9 @@ properties: description: TDM TX voltage sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -67,7 +69,7 @@ examples: codec: codec@38 { compatible = "ti,tas2764"; reg = <0x38>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpios = <&gpio1 15 0>; diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 164960631925..447f767c6462 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -6,8 +6,7 @@ Ramfs, rootfs and initramfs October 17, 2005 -Rob Landley <rob@landley.net> -============================= +:Author: Rob Landley <rob@landley.net> What is ramfs? -------------- diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst index d83395354250..1cf56489ed48 100644 --- a/Documentation/filesystems/sharedsubtree.rst +++ b/Documentation/filesystems/sharedsubtree.rst @@ -147,6 +147,7 @@ replicas continue to be exactly same. 3) Setting mount states +----------------------- The mount command (util-linux package) can be used to set mount states:: @@ -612,6 +613,7 @@ replicas continue to be exactly same. 6) Quiz +------- A. What is the result of the following command sequence? @@ -673,6 +675,7 @@ replicas continue to be exactly same. /mnt/1/test be? 7) FAQ +------ Q1. Why is bind mount needed? How is it different from symbolic links? symbolic links can get stale if the destination mount gets @@ -841,6 +844,7 @@ replicas continue to be exactly same. tmp usr tmp usr tmp usr 8) Implementation +----------------- 8A) Datastructure diff --git a/Documentation/fpga/index.rst b/Documentation/fpga/index.rst index f80f95667ca2..43c968871d99 100644 --- a/Documentation/fpga/index.rst +++ b/Documentation/fpga/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ==== -fpga +FPGA ==== .. toctree:: diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst index 7003bd5aeff4..6a9ea96c8bcb 100644 --- a/Documentation/locking/index.rst +++ b/Documentation/locking/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ======= -locking +Locking ======= .. toctree:: diff --git a/Documentation/pcmcia/index.rst b/Documentation/pcmcia/index.rst index 7ae1f62fca14..8067236c51ab 100644 --- a/Documentation/pcmcia/index.rst +++ b/Documentation/pcmcia/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -pcmcia +PCMCIA ====== .. toctree:: diff --git a/Documentation/s390/vfio-ap.rst b/Documentation/s390/vfio-ap.rst index d46e98c7c1ec..bb3f4c4e2885 100644 --- a/Documentation/s390/vfio-ap.rst +++ b/Documentation/s390/vfio-ap.rst @@ -551,7 +551,6 @@ These are the steps: * IOMMU_SUPPORT * S390 * ZCRYPT - * S390_AP_IOMMU * VFIO * KVM diff --git a/Documentation/staging/crc32.rst b/Documentation/staging/crc32.rst index 8a6860f33b4e..7542220967cb 100644 --- a/Documentation/staging/crc32.rst +++ b/Documentation/staging/crc32.rst @@ -1,5 +1,5 @@ ================================= -brief tutorial on CRC computation +Brief tutorial on CRC computation ================================= A CRC is a long-division remainder. You add the CRC to the message, diff --git a/Documentation/timers/index.rst b/Documentation/timers/index.rst index df510ad0c989..983f91f8f023 100644 --- a/Documentation/timers/index.rst +++ b/Documentation/timers/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -timers +Timers ====== .. toctree:: diff --git a/MAINTAINERS b/MAINTAINERS index e0ad886d3163..27ef11624748 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1677,10 +1677,7 @@ F: drivers/power/reset/arm-versatile-reboot.c F: drivers/soc/versatile/ ARM KOMEDA DRM-KMS DRIVER -M: James (Qian) Wang <james.qian.wang@arm.com> M: Liviu Dudau <liviu.dudau@arm.com> -M: Mihail Atanassov <mihail.atanassov@arm.com> -L: Mali DP Maintainers <malidp@foss.arm.com> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,komeda.yaml @@ -1701,8 +1698,6 @@ F: include/uapi/drm/panfrost_drm.h ARM MALI-DP DRM DRIVER M: Liviu Dudau <liviu.dudau@arm.com> -M: Brian Starkey <brian.starkey@arm.com> -L: Mali DP Maintainers <malidp@foss.arm.com> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,malidp.yaml @@ -4914,7 +4909,6 @@ F: drivers/media/cec/i2c/ch7322.c CIRRUS LOGIC AUDIO CODEC DRIVERS M: James Schulman <james.schulman@cirrus.com> M: David Rhodes <david.rhodes@cirrus.com> -M: Lucas Tanure <tanureal@opensource.cirrus.com> M: Richard Fitzgerald <rf@opensource.cirrus.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: patches@opensource.cirrus.com @@ -6012,7 +6006,7 @@ W: http://www.dialog-semiconductor.com/products F: Documentation/devicetree/bindings/input/da90??-onkey.txt F: Documentation/devicetree/bindings/input/dlg,da72??.txt F: Documentation/devicetree/bindings/mfd/da90*.txt -F: Documentation/devicetree/bindings/mfd/da90*.yaml +F: Documentation/devicetree/bindings/mfd/dlg,da90*.yaml F: Documentation/devicetree/bindings/regulator/da92*.txt F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/slg51000.txt @@ -6211,6 +6205,7 @@ X: Documentation/devicetree/ X: Documentation/driver-api/media/ X: Documentation/firmware-guide/acpi/ X: Documentation/i2c/ +X: Documentation/netlink/ X: Documentation/power/ X: Documentation/spi/ X: Documentation/userspace-api/media/ @@ -14566,6 +14561,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ F: drivers/connector/ F: drivers/net/ +X: drivers/net/wireless/ F: include/dt-bindings/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h @@ -14615,6 +14611,7 @@ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/core-api/netlink.rst +F: Documentation/netlink/ F: Documentation/networking/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ @@ -14629,6 +14626,7 @@ F: include/uapi/linux/netdevice.h F: lib/net_utils.c F: lib/random32.c F: net/ +X: net/bluetooth/ F: tools/net/ F: tools/testing/selftests/net/ @@ -18575,10 +18573,9 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Supported +S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ @@ -18842,12 +18839,11 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Neil Horman <nhorman@tuxdriver.com> M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> M: Xin Long <lucien.xin@gmail.com> L: linux-sctp@vger.kernel.org S: Maintained -W: http://lksctp.sourceforge.net +W: https://github.com/sctp/lksctp-tools/wiki F: Documentation/networking/sctp.rst F: include/linux/sctp.h F: include/net/sctp/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index c9e05e3540d6..00bf53f99c29 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -387,6 +387,7 @@ interrupt-names = "tx", "rx0", "rx1", "sce"; resets = <&rcc STM32F4_APB1_RESET(CAN2)>; clocks = <&rcc 0 STM32F4_APB1_CLOCK(CAN2)>; + st,can-secondary; st,gcan = <&gcan>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi index c8e6c52fb248..9f65403295ca 100644 --- a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi @@ -283,6 +283,88 @@ slew-rate = <2>; }; }; + + can1_pins_a: can1-0 { + pins1 { + pinmux = <STM32_PINMUX('A', 12, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('A', 11, AF9)>; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_b: can1-1 { + pins1 { + pinmux = <STM32_PINMUX('B', 9, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 8, AF9)>; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_c: can1-2 { + pins1 { + pinmux = <STM32_PINMUX('D', 1, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('D', 0, AF9)>; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can1_pins_d: can1-3 { + pins1 { + pinmux = <STM32_PINMUX('H', 13, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('H', 14, AF9)>; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can2_pins_a: can2-0 { + pins1 { + pinmux = <STM32_PINMUX('B', 6, AF9)>; /* CAN2_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 5, AF9)>; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can2_pins_b: can2-1 { + pins1 { + pinmux = <STM32_PINMUX('B', 13, AF9)>; /* CAN2_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 12, AF9)>; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can3_pins_a: can3-0 { + pins1 { + pinmux = <STM32_PINMUX('A', 15, AF11)>; /* CAN3_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('A', 8, AF11)>; /* CAN3_RX */ + bias-pull-up; + }; + }; + + can3_pins_b: can3-1 { + pins1 { + pinmux = <STM32_PINMUX('B', 4, AF11)>; /* CAN3_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 3, AF11)>; /* CAN3_RX */ + bias-pull-up; + }; + }; }; }; }; diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index 78d3d4b82c6c..f4db3e75d75f 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -92,7 +92,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(PMEVCNTR##n) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -100,14 +100,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, PMEVCNTR##n) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, PMEVTYPER##n) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index d6b51deb7bf0..18dc2fb3d7b7 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -13,7 +13,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(pmevcntr##n##_el0) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -21,14 +21,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, pmevcntr##n##_el0) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, pmevtyper##n##_el0) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 4cd6762bda80..dc3c072e862f 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -209,6 +209,7 @@ struct kvm_pgtable_visit_ctx { kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; + u64 start; u64 addr; u64 end; u32 level; diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index f5bcb0dc6267..7e89968bd282 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) { - if (!page_mte_tagged(page)) { + for (i = 0; i < nr_pages; i++, page++) + if (!page_mte_tagged(page)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); - set_page_mte_tagged(page); - } - } /* ensure the tags are visible before the PTE is set */ smp_wmb(); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 0119dc91abb5..d9e1355730ef 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void) memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, kuser_sz); - aarch32_vectors_page = virt_to_page(vdso_page); + aarch32_vectors_page = virt_to_page((void *)vdso_page); return 0; } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1279949599b5..4c9dcd8fc939 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -81,26 +81,34 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_kvm_prepare(); + /* + * We will check TIF_FOREIGN_FPSTATE just before entering the + * guest in kvm_arch_vcpu_ctxflush_fp() and override this to + * FP_STATE_FREE if the flag set. + */ vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - /* - * We don't currently support SME guests but if we leave - * things in streaming mode then when the guest starts running - * FPSIMD or SVE code it may generate SME traps so as a - * special case if we are in streaming mode we force the host - * state to be saved now and exit streaming mode so that we - * don't have to handle any SME traps for valid guest - * operations. Do this for ZA as well for now for simplicity. - */ if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); + /* + * If PSTATE.SM is enabled then save any pending FP + * state and disable PSTATE.SM. If we leave PSTATE.SM + * enabled and the guest does not enable SME via + * CPACR_EL1.SMEN then operations that should be valid + * may generate SME traps from EL1 to EL1 which we + * can't intercept and which would confuse the guest. + * + * Do the same for PSTATE.ZA in the case where there + * is state in the registers which has not already + * been saved, this is very unlikely to happen. + */ if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { vcpu->arch.fp_state = FP_STATE_FREE; fpsimd_save_and_flush_cpu_state(); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index c41166f1a1dd..e78a08a72a3c 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -177,9 +177,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + break; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + break; + default: return false; + } /* Valid trap. Switch the context: */ diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 3d61bd3e591d..5282cb9ca4cf 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,8 +58,9 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; + const u64 start; u64 addr; - u64 end; + const u64 end; }; static bool kvm_phys_is_valid(u64 phys) @@ -201,6 +202,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, + .start = data->start, .addr = data->addr, .end = data->end, .level = level, @@ -293,6 +295,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { + .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, @@ -349,7 +352,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, } struct hyp_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; }; @@ -407,13 +410,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { + u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; if (!kvm_block_mapping_supported(ctx, phys)) return false; - data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; @@ -576,7 +578,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) } struct stage2_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; u8 owner_id; @@ -794,20 +796,43 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } +static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, + const struct stage2_map_data *data) +{ + u64 phys = data->phys; + + /* + * Stage-2 walks to update ownership data are communicated to the map + * walker using an invalid PA. Avoid offsetting an already invalid PA, + * which could overflow and make the address valid again. + */ + if (!kvm_phys_is_valid(phys)) + return phys; + + /* + * Otherwise, work out the correct PA based on how far the walk has + * gotten. + */ + return phys + (ctx->addr - ctx->start); +} + static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { + u64 phys = stage2_map_walker_phys_addr(ctx, data); + if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1))) return false; - return kvm_block_mapping_supported(ctx, data->phys); + return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; + u64 phys = stage2_map_walker_phys_addr(ctx, data); + u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; @@ -841,8 +866,6 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, stage2_make_pte(ctx, new); - if (kvm_phys_is_valid(phys)) - data->phys += granule; return 0; } diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 64c3aec0d937..0bd93a5f21ce 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu) * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there - * is no way to to describe the ASF. + * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 469d816f356f..93a47a515c13 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -616,6 +616,10 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 08978d0672e7..7fe8ba1a2851 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -47,7 +47,7 @@ static void flush_context(void) int cpu; u64 vmid; - bitmap_clear(vmid_map, 0, NUM_USER_VMIDS); + bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); @@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void) */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); - vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS), - sizeof(*vmid_map), GFP_KERNEL); + vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; @@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void) void __init kvm_arm_vmid_alloc_free(void) { - kfree(vmid_map); + bitmap_free(vmid_map); } diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 4aadcfb01754..a7bb20055ce0 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,10 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); + if (kasan_hw_tags_enabled()) + page_kasan_tag_reset(to); + if (system_supports_mte() && page_mte_tagged(from)) { - if (kasan_hw_tags_enabled()) - page_kasan_tag_reset(to); /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9e0db5c387e3..cb21ccd7940d 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -480,8 +480,8 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP 0x010000 -#define VM_FAULT_BADACCESS 0x020000 +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 85cde5bf04b7..771b79423bbc 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,8 +34,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ - $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ - $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) @@ -71,6 +69,10 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -crD +BOOTCFLAGS += $(call cc-option,-mno-prefixed) \ + $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) + ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) BOOTAFLAGS += $(CLANG_FLAGS) diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 7113f9355165..ad1872518992 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE config CRYPTO_AES_GCM_P10 tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)" - depends on PPC64 && CPU_LITTLE_ENDIAN + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX select CRYPTO_LIB_AES select CRYPTO_ALGAPI select CRYPTO_AEAD diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 678b5bdc79b1..34e14dfd8e04 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct iommu_table_group *table_group, struct device *dev); -extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); @@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group, { return 0; } - -static inline void iommu_del_device(struct device *dev) -{ -} #endif /* !CONFIG_IOMMU_API */ u64 dma_iommu_get_required_mask(struct device *dev); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 038ce8d9061d..8920862ffd79 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) /* We support DMA to/from any memory page via the iommu */ int dma_iommu_dma_supported(struct device *dev, u64 mask) { - struct iommu_table *tbl = get_iommu_table_base(dev); + struct iommu_table *tbl; if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { /* @@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } + tbl = get_iommu_table_base(dev); + if (!tbl) { dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask); return 0; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0089dd49b4cb..67f0b01e6ff5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; dma_addr = entry << tbl->it_page_shift; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); + dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); @@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; + int tcesize = (1 << tbl->it_page_shift); size = PAGE_ALIGN(size); order = get_order(size); @@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); @@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, free_pages((unsigned long)ret, order); return NULL; } - *dma_handle = mapping; + + *dma_handle = mapping | ((u64)ret & (tcesize - 1)); return ret; } @@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -1168,23 +1171,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_add_device); -void iommu_del_device(struct device *dev) -{ - /* - * Some devices might not have IOMMU table and group - * and we needn't detach them from the associated - * IOMMU groups - */ - if (!device_iommu_mapped(dev)) { - pr_debug("iommu_tce: skipping device %s with no tbl\n", - dev_name(dev)); - return; - } - - iommu_group_remove_device(dev); -} -EXPORT_SYMBOL_GPL(iommu_del_device); - /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 85bdd7d3652f..48e0eaf1ad61 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node, } inval_range: - if (!phb_io_base_phys) { + if (phb_io_base_phys) { pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n"); remap_isa_base(phb_io_base_phys, 0x10000); + return 0; } - return 0; + return -EINVAL; } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 26245aaf12b8..2297aa764ecd 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e93aefcfb83f..37043dfc1add 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = jit_data->header; proglen = jit_data->proglen; extra_pass = true; + /* During extra pass, ensure index is reset before repopulating extable entries */ + cgctx.exentry_idx = 0; goto skip_init_ctx; } diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 0d9b7609c7d5..3e2e252016f7 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -265,6 +265,7 @@ config CPM2 config FSL_ULI1575 bool "ULI1575 PCIe south bridge support" depends on FSL_SOC_BOOKE || PPC_86xx + depends on PCI select FSL_PCI select GENERIC_ISA_DMA help diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 233a50e65fce..7725492097b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -865,28 +865,3 @@ void __init pnv_pci_init(void) /* Configure IOMMU DMA hooks */ set_pci_dma_ops(&dma_iommu_ops); } - -static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block pnv_tce_iommu_bus_nb = { - .notifier_call = pnv_tce_iommu_bus_notifier, -}; - -static int __init pnv_tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7464fa6e4145..918f511837db 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) static void iommu_pseries_free_group(struct iommu_table_group *table_group, const char *node_name) { - struct iommu_table *tbl; - if (!table_group) return; - tbl = table_group->tables[0]; #ifdef CONFIG_IOMMU_API if (table_group->group) { iommu_group_put(table_group->group); BUG_ON(table_group->group); } #endif - iommu_tce_table_put(tbl); + + /* Default DMA window table is at index 0, while DDW at 1. SR-IOV + * adapters only have table on index 1. + */ + if (table_group->tables[0]) + iommu_tce_table_put(table_group->tables[0]); + + if (table_group->tables[1]) + iommu_tce_table_put(table_group->tables[1]); kfree(table_group); } @@ -1695,31 +1700,6 @@ static int __init disable_multitce(char *str) __setup("multitce=", disable_multitce); -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); - #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, struct pci_dev *pdev) diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile index c40139e9ca47..8265ff497977 100644 --- a/arch/riscv/kernel/probes/Makefile +++ b/arch/riscv/kernel/probes/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index db20c1589a98..6dab9c1be508 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -469,19 +469,11 @@ config SCHED_SMT config SCHED_MC def_bool n -config SCHED_BOOK - def_bool n - -config SCHED_DRAWER - def_bool n - config SCHED_TOPOLOGY def_bool y prompt "Topology scheduler support" select SCHED_SMT select SCHED_MC - select SCHED_BOOK - select SCHED_DRAWER help Topology scheduler support improves the CPU scheduler's decision making when dealing with machines that have multi-threading, @@ -716,7 +708,6 @@ config EADM_SCH config VFIO_CCW def_tristate n prompt "Support for VFIO-CCW subchannels" - depends on S390_CCW_IOMMU depends on VFIO select VFIO_MDEV help @@ -728,7 +719,7 @@ config VFIO_CCW config VFIO_AP def_tristate n prompt "VFIO support for AP devices" - depends on S390_AP_IOMMU && KVM + depends on KVM depends on VFIO depends on ZCRYPT select VFIO_MDEV diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 4ccf66d29fc2..be3bf03bf361 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -591,8 +591,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -703,6 +701,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 693297a2e897..769c7eed8b6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -580,8 +580,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -686,6 +684,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 33a232bb68af..6f68b39817ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -67,6 +67,7 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index 7752bd314558..5fae187f947a 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, * it cannot handle a block of data or less, but otherwise * it can handle data of arbitrary size */ - if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20) + if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX) chacha_crypt_generic(state, dst, src, bytes, nrounds); else chacha20_crypt_s390(state, dst, src, bytes, diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index a386070f1d56..3cb9d813f022 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -112,7 +112,7 @@ struct compat_statfs64 { u32 f_namelen; u32 f_frsize; u32 f_flags; - u32 f_spare[4]; + u32 f_spare[5]; }; /* diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 72604f7792c3..f85b50723dd3 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -30,7 +30,7 @@ struct statfs { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; struct statfs64 { @@ -45,7 +45,7 @@ struct statfs64 { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 8983837b3565..6b2a051e1f8a 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -10,6 +10,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) endif diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 43de939b7af1..f44f70de9661 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1935,14 +1935,13 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - unsigned long ipib = (unsigned long) reipl_block_actual; struct lowcore *abs_lc; unsigned int csum; csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); abs_lc = get_abs_lowcore(); - abs_lc->ipib = ipib; + abs_lc->ipib = __pa(reipl_block_actual); abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 9fd19530c9a5..68adf1de8888 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -95,7 +95,7 @@ out: static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) { static cpumask_t mask; - int i; + unsigned int max_cpu; cpumask_clear(&mask); if (!cpumask_test_cpu(cpu, &cpu_setup_mask)) @@ -104,9 +104,10 @@ static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) if (topology_mode != TOPOLOGY_MODE_HW) goto out; cpu -= cpu % (smp_cpu_mtid + 1); - for (i = 0; i <= smp_cpu_mtid; i++) { - if (cpumask_test_cpu(cpu + i, &cpu_setup_mask)) - cpumask_set_cpu(cpu + i, &mask); + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + if (cpumask_test_cpu(cpu, &cpu_setup_mask)) + cpumask_set_cpu(cpu, &mask); } out: cpumask_copy(dst, &mask); @@ -123,25 +124,26 @@ static void add_cpus_to_mask(struct topology_core *tl_core, unsigned int core; for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) { - unsigned int rcore; - int lcpu, i; + unsigned int max_cpu, rcore; + int cpu; rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin; - lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); - if (lcpu < 0) + cpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); + if (cpu < 0) continue; - for (i = 0; i <= smp_cpu_mtid; i++) { - topo = &cpu_topology[lcpu + i]; + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + topo = &cpu_topology[cpu]; topo->drawer_id = drawer->id; topo->book_id = book->id; topo->socket_id = socket->id; topo->core_id = rcore; - topo->thread_id = lcpu + i; + topo->thread_id = cpu; topo->dedicated = tl_core->d; - cpumask_set_cpu(lcpu + i, &drawer->mask); - cpumask_set_cpu(lcpu + i, &book->mask); - cpumask_set_cpu(lcpu + i, &socket->mask); - smp_cpu_set_polarization(lcpu + i, tl_core->pp); + cpumask_set_cpu(cpu, &drawer->mask); + cpumask_set_cpu(cpu, &book->mask); + cpumask_set_cpu(cpu, &socket->mask); + smp_cpu_set_polarization(cpu, tl_core->pp); } } } diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index dee6f66353b3..a461a950f051 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -16,7 +16,8 @@ mconsole-objs := mconsole_kern.o mconsole_user.o hostaudio-objs := hostaudio_kern.o ubd-objs := ubd_kern.o ubd_user.o port-objs := port_kern.o port_user.o -harddog-objs := harddog_kern.o harddog_user.o +harddog-objs := harddog_kern.o +harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o rtc-objs := rtc_kern.o rtc_user.o LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a) @@ -60,6 +61,7 @@ obj-$(CONFIG_PTY_CHAN) += pty.o obj-$(CONFIG_TTY_CHAN) += tty.o obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o obj-$(CONFIG_UML_WATCHDOG) += harddog.o +obj-y += $(harddog-builtin-y) $(harddog-builtin-m) obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o obj-$(CONFIG_UML_RANDOM) += random.o obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o diff --git a/arch/um/drivers/harddog.h b/arch/um/drivers/harddog.h new file mode 100644 index 000000000000..6d9ea60e7133 --- /dev/null +++ b/arch/um/drivers/harddog.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef UM_WATCHDOG_H +#define UM_WATCHDOG_H + +int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); +void stop_watchdog(int in_fd, int out_fd); +int ping_watchdog(int fd); + +#endif /* UM_WATCHDOG_H */ diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index e6d4f43deba8..60d1c6cab8a9 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -47,6 +47,7 @@ #include <linux/spinlock.h> #include <linux/uaccess.h> #include "mconsole.h" +#include "harddog.h" MODULE_LICENSE("GPL"); @@ -60,8 +61,6 @@ static int harddog_out_fd = -1; * Allow only one person to hold it open */ -extern int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); - static int harddog_open(struct inode *inode, struct file *file) { int err = -EBUSY; @@ -92,8 +91,6 @@ err: return err; } -extern void stop_watchdog(int in_fd, int out_fd); - static int harddog_release(struct inode *inode, struct file *file) { /* @@ -112,8 +109,6 @@ static int harddog_release(struct inode *inode, struct file *file) return 0; } -extern int ping_watchdog(int fd); - static ssize_t harddog_write(struct file *file, const char __user *data, size_t len, loff_t *ppos) { diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index 070468d22e39..9ed89304975e 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <errno.h> #include <os.h> +#include "harddog.h" struct dog_data { int stdin_fd; diff --git a/arch/um/drivers/harddog_user_exp.c b/arch/um/drivers/harddog_user_exp.c new file mode 100644 index 000000000000..c74d4b815d14 --- /dev/null +++ b/arch/um/drivers/harddog_user_exp.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include "harddog.h" + +#if IS_MODULE(CONFIG_UML_WATCHDOG) +EXPORT_SYMBOL(start_watchdog); +EXPORT_SYMBOL(stop_watchdog); +EXPORT_SYMBOL(ping_watchdog); +#endif diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 498dc600bd5c..0d02c4aafa6f 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -13,7 +13,9 @@ #include <linux/bitops.h> +#include <linux/bug.h> #include <linux/types.h> + #include <uapi/asm/vmx.h> #include <asm/vmxfeatures.h> diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index dd61752f4c96..4070a01c11b7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_rethook.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 123bf8b97a4b..0c9660a07b23 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -253,7 +253,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; - u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,21 +291,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } - - /* - * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate - * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's - * requested XCR0 value. The enclave's XFRM must be a subset of XCRO - * at the time of EENTER, thus adjust the allowed XFRM by the guest's - * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to - * '1' even on CPUs that don't support XSAVE. - */ - best = cpuid_entry2_find(entries, nent, 0x12, 0x1); - if (best) { - best->ecx &= guest_supported_xcr0 & 0xffffffff; - best->edx &= guest_supported_xcr0 >> 32; - best->ecx |= XFEATURE_MASK_FPSSE; - } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 0574030b071f..2261b684a7d4 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -170,12 +170,19 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, return 1; } - /* Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. */ + /* + * Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. Note + * that the allowed XFRM (XFeature Request Mask) isn't strictly bound + * by the supported XCR0. FP+SSE *must* be set in XFRM, even if XSAVE + * is unsupported, i.e. even if XCR0 itself is completely unsupported. + */ if ((u32)miscselect & ~sgx_12_0->ebx || (u32)attributes & ~sgx_12_1->eax || (u32)(attributes >> 32) & ~sgx_12_1->ebx || (u32)xfrm & ~sgx_12_1->ecx || - (u32)(xfrm >> 32) & ~sgx_12_1->edx) { + (u32)(xfrm >> 32) & ~sgx_12_1->edx || + xfrm & ~(vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE) || + (xfrm & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { kvm_inject_gp(vcpu, 0); return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ceb7c5e9cf9e..c0778ca39650 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1446,7 +1446,7 @@ static const u32 msrs_to_save_base[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, @@ -7155,6 +7155,10 @@ static void kvm_probe_msr_to_save(u32 msr_index) if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) return; break; + case MSR_IA32_TSX_CTRL: + if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) + return; + break; default: break; } diff --git a/block/fops.c b/block/fops.c index d2e6be4e3d1c..58d0aebc7313 100644 --- a/block/fops.c +++ b/block/fops.c @@ -678,6 +678,16 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return error; } +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + + if (bdev_read_only(I_BDEV(bd_inode))) + return generic_file_readonly_mmap(file, vma); + + return generic_file_mmap(file, vma); +} + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, @@ -685,7 +695,7 @@ const struct file_operations def_blk_fops = { .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .iopoll = iocb_bio_iopoll, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = blkdev_ioctl, #ifdef CONFIG_COMPAT diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index e8492b3a393a..0800a9d77558 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -516,6 +516,17 @@ static const struct dmi_system_id maingear_laptop[] = { { } }; +static const struct dmi_system_id lg_laptop[] = { + { + .ident = "LG Electronics 17U70P", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "17U70P"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; @@ -532,6 +543,7 @@ static const struct irq_override_cmp override_table[] = { { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, }; static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, diff --git a/drivers/base/class.c b/drivers/base/class.c index ac1808d1a2e8..05d9df90f621 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -320,6 +320,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; + iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -361,6 +362,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_next); void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); + subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c7ed5d69e9ee..33d3298a0da1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1120,6 +1120,11 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } +static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) +{ + io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); +} + static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; @@ -1131,8 +1136,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, - IO_URING_F_UNLOCKED); + io_uring_cmd_complete_in_task(io->cmd, + ublk_cmd_cancel_cb); } /* all io commands are canceled */ diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index c10a4aa97373..cd48033b804a 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -571,6 +571,10 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); + /* Give back zero bytes, as TPM chip has not yet fully resumed: */ + if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) + return 0; + return tpm_get_random(chip, data, max); } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 4463d0018290..586ca10b0d72 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -412,6 +412,8 @@ int tpm_pm_suspend(struct device *dev) } suspended: + chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + if (rc) dev_err(dev, "Ignoring error %d while suspending\n", rc); return 0; @@ -429,6 +431,14 @@ int tpm_pm_resume(struct device *dev) if (chip == NULL) return -ENODEV; + chip->flags &= ~TPM_CHIP_FLAG_SUSPENDED; + + /* + * Guarantee that SUSPENDED is written last, so that hwrng does not + * activate before the chip has been fully resumed. + */ + wmb(); + return 0; } EXPORT_SYMBOL_GPL(tpm_pm_resume); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 7af389806643..709b4e13bd6e 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -122,6 +122,22 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"), }, }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkStation P360 Tiny", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkStation P360 Tiny"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkPad L490", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L490"), + }, + }, {} }; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 02945d53fcef..558144fa707a 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1209,25 +1209,20 @@ static void tpm_tis_reenable_interrupts(struct tpm_chip *chip) u32 intmask; int rc; - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, true); - - /* reenable interrupts that device may have lost or - * BIOS/firmware may have disabled + /* + * Re-enable interrupts that device may have lost or BIOS/firmware may + * have disabled. */ rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), priv->irq); - if (rc < 0) - goto out; + if (rc < 0) { + dev_err(&chip->dev, "Setting IRQ failed.\n"); + return; + } intmask = priv->int_mask | TPM_GLOBAL_INT_ENABLE; - - tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); - -out: - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, false); - - return; + rc = tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); + if (rc < 0) + dev_err(&chip->dev, "Enabling interrupts failed.\n"); } int tpm_tis_resume(struct device *dev) @@ -1235,27 +1230,27 @@ int tpm_tis_resume(struct device *dev) struct tpm_chip *chip = dev_get_drvdata(dev); int ret; - ret = tpm_tis_request_locality(chip, 0); - if (ret < 0) + ret = tpm_chip_start(chip); + if (ret) return ret; if (chip->flags & TPM_CHIP_FLAG_IRQ) tpm_tis_reenable_interrupts(chip); - ret = tpm_pm_resume(dev); - if (ret) - goto out; - /* * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) tpm1_do_selftest(chip); -out: - tpm_tis_relinquish_locality(chip, 0); - return ret; + tpm_chip_stop(chip); + + ret = tpm_pm_resume(dev); + if (ret) + return ret; + + return 0; } EXPORT_SYMBOL_GPL(tpm_tis_resume); #endif diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 29904395e95f..b2f05d27167e 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -975,7 +975,7 @@ static int __init acpi_cpufreq_probe(struct platform_device *pdev) /* don't keep reloading if cpufreq_driver exists */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; pr_debug("%s\n", __func__); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1d2cfea9858a..73efbcf5513b 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -583,7 +583,7 @@ static int __init pcc_cpufreq_probe(struct platform_device *pdev) /* Skip initialization if another cpufreq driver is there. */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; if (acpi_disabled) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3c29792137a5..0aae9a1eb3d5 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1851,9 +1851,17 @@ static void hsw_crtc_disable(struct intel_atomic_state *state, intel_disable_shared_dpll(old_crtc_state); - intel_encoders_post_pll_disable(state, crtc); + if (!intel_crtc_is_bigjoiner_slave(old_crtc_state)) { + struct intel_crtc *slave_crtc; + + intel_encoders_post_pll_disable(state, crtc); - intel_dmc_disable_pipe(i915, crtc->pipe); + intel_dmc_disable_pipe(i915, crtc->pipe); + + for_each_intel_crtc_in_pipe_mask(&i915->drm, slave_crtc, + intel_crtc_bigjoiner_slave_pipes(old_crtc_state)) + intel_dmc_disable_pipe(i915, slave_crtc->pipe); + } } static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index db98c3f86e8c..6de900776e24 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -417,22 +417,6 @@ config S390_IOMMU help Support for the IOMMU API for s390 PCI devices. -config S390_CCW_IOMMU - bool "S390 CCW IOMMU Support" - depends on S390 && CCW || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - -config S390_AP_IOMMU - bool "S390 AP IOMMU Support" - depends on S390 && ZCRYPT || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - config MTK_IOMMU tristate "MediaTek IOMMU Support" depends on ARCH_MEDIATEK || COMPILE_TEST diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index c2d2792227f8..baf64540dc00 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -151,6 +151,12 @@ struct dvb_ca_private { /* mutex serializing ioctls */ struct mutex ioctl_mutex; + + /* A mutex used when a device is disconnected */ + struct mutex remove_mutex; + + /* Whether the device is disconnected */ + int exit; }; static void dvb_ca_private_free(struct dvb_ca_private *ca) @@ -187,7 +193,7 @@ static void dvb_ca_en50221_thread_wakeup(struct dvb_ca_private *ca); static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, u8 *ebuf, int ecount); static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *ebuf, int ecount); + u8 *ebuf, int ecount, int size_write_flag); /** * findstr - Safely find needle in haystack. @@ -370,7 +376,7 @@ static int dvb_ca_en50221_link_init(struct dvb_ca_private *ca, int slot) ret = dvb_ca_en50221_wait_if_status(ca, slot, STATUSREG_FR, HZ / 10); if (ret) return ret; - ret = dvb_ca_en50221_write_data(ca, slot, buf, 2); + ret = dvb_ca_en50221_write_data(ca, slot, buf, 2, CMDREG_SW); if (ret != 2) return -EIO; ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN); @@ -778,11 +784,13 @@ exit: * @buf: The data in this buffer is treated as a complete link-level packet to * be written. * @bytes_write: Size of ebuf. + * @size_write_flag: A flag on Command Register which says whether the link size + * information will be writen or not. * * return: Number of bytes written, or < 0 on error. */ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *buf, int bytes_write) + u8 *buf, int bytes_write, int size_write_flag) { struct dvb_ca_slot *sl = &ca->slot_info[slot]; int status; @@ -817,7 +825,7 @@ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, /* OK, set HC bit */ status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, - IRQEN | CMDREG_HC); + IRQEN | CMDREG_HC | size_write_flag); if (status) goto exit; @@ -1508,7 +1516,7 @@ static ssize_t dvb_ca_en50221_io_write(struct file *file, mutex_lock(&sl->slot_lock); status = dvb_ca_en50221_write_data(ca, slot, fragbuf, - fraglen + 2); + fraglen + 2, 0); mutex_unlock(&sl->slot_lock); if (status == (fraglen + 2)) { written = 1; @@ -1709,12 +1717,22 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dprintk("%s\n", __func__); - if (!try_module_get(ca->pub->owner)) + mutex_lock(&ca->remove_mutex); + + if (ca->exit) { + mutex_unlock(&ca->remove_mutex); + return -ENODEV; + } + + if (!try_module_get(ca->pub->owner)) { + mutex_unlock(&ca->remove_mutex); return -EIO; + } err = dvb_generic_open(inode, file); if (err < 0) { module_put(ca->pub->owner); + mutex_unlock(&ca->remove_mutex); return err; } @@ -1739,6 +1757,7 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dvb_ca_private_get(ca); + mutex_unlock(&ca->remove_mutex); return 0; } @@ -1758,6 +1777,8 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + /* mark the CA device as closed */ ca->open = 0; dvb_ca_en50221_thread_update_delay(ca); @@ -1768,6 +1789,13 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dvb_ca_private_put(ca); + if (dvbdev->users == 1 && ca->exit == 1) { + mutex_unlock(&ca->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&ca->remove_mutex); + } + return err; } @@ -1891,6 +1919,7 @@ int dvb_ca_en50221_init(struct dvb_adapter *dvb_adapter, } mutex_init(&ca->ioctl_mutex); + mutex_init(&ca->remove_mutex); if (signal_pending(current)) { ret = -EINTR; @@ -1933,6 +1962,14 @@ void dvb_ca_en50221_release(struct dvb_ca_en50221 *pubca) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + ca->exit = 1; + mutex_unlock(&ca->remove_mutex); + + if (ca->dvbdev->users < 1) + wait_event(ca->dvbdev->wait_queue, + ca->dvbdev->users == 1); + /* shutdown the thread if there was one */ kthread_stop(ca->thread); diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c index 398c86279b5b..7c4d86bfdd6c 100644 --- a/drivers/media/dvb-core/dvb_demux.c +++ b/drivers/media/dvb-core/dvb_demux.c @@ -115,12 +115,12 @@ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (!ccok) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("missed packet: %d instead of %d!\n", cc, (feed->cc + 1) & 0x0f); } + feed->cc = cc; if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; @@ -300,7 +300,6 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (buf[3] & 0x20) { /* adaption field present, check for discontinuity_indicator */ @@ -336,6 +335,7 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } + feed->cc = cc; if (buf[1] & 0x40) { /* PUSI=1 (is set), section boundary is here */ diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index cc0a789f09ae..bc6950a5740f 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -293,14 +293,22 @@ static int dvb_frontend_get_event(struct dvb_frontend *fe, } if (events->eventw == events->eventr) { - int ret; + struct wait_queue_entry wait; + int ret = 0; if (flags & O_NONBLOCK) return -EWOULDBLOCK; - ret = wait_event_interruptible(events->wait_queue, - dvb_frontend_test_event(fepriv, events)); - + init_waitqueue_entry(&wait, current); + add_wait_queue(&events->wait_queue, &wait); + while (!dvb_frontend_test_event(fepriv, events)) { + wait_woken(&wait, TASK_INTERRUPTIBLE, 0); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + } + remove_wait_queue(&events->wait_queue, &wait); if (ret < 0) return ret; } @@ -809,15 +817,26 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); + mutex_lock(&fe->remove_mutex); + if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) + if (!fepriv->thread) { + mutex_unlock(&fe->remove_mutex); return; + } kthread_stop(fepriv->thread); + mutex_unlock(&fe->remove_mutex); + + if (fepriv->dvbdev->users < -1) { + wait_event(fepriv->dvbdev->wait_queue, + fepriv->dvbdev->users == -1); + } + sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2761,9 +2780,13 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) - return -ENODEV; + if (fe->exit == DVB_FE_DEVICE_REMOVED) { + ret = -ENODEV; + goto err_remove_mutex; + } if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2771,7 +2794,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2794,8 +2818,10 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) - return -EINTR; + if (signal_pending(current)) { + ret = -EINTR; + goto err_remove_mutex; + } } } @@ -2807,7 +2833,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2866,6 +2893,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + + mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2887,6 +2916,9 @@ err1: err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + +err_remove_mutex: + mutex_unlock(&fe->remove_mutex); return ret; } @@ -2897,6 +2929,8 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2918,10 +2952,18 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif - if (fe->exit != DVB_FE_NO_EXIT) - wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); + + if (fe->exit != DVB_FE_NO_EXIT) { + mutex_unlock(&fe->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&fe->remove_mutex); + } + + } else { + mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3022,6 +3064,7 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); + mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8a2febf33ce2..8bb8dd34c223 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1564,15 +1564,43 @@ static long dvb_net_ioctl(struct file *file, return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl); } +static int locked_dvb_net_open(struct inode *inode, struct file *file) +{ + struct dvb_device *dvbdev = file->private_data; + struct dvb_net *dvbnet = dvbdev->priv; + int ret; + + if (mutex_lock_interruptible(&dvbnet->remove_mutex)) + return -ERESTARTSYS; + + if (dvbnet->exit) { + mutex_unlock(&dvbnet->remove_mutex); + return -ENODEV; + } + + ret = dvb_generic_open(inode, file); + + mutex_unlock(&dvbnet->remove_mutex); + + return ret; +} + static int dvb_net_close(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dvb_net *dvbnet = dvbdev->priv; + mutex_lock(&dvbnet->remove_mutex); + dvb_generic_release(inode, file); - if(dvbdev->users == 1 && dvbnet->exit == 1) + if (dvbdev->users == 1 && dvbnet->exit == 1) { + mutex_unlock(&dvbnet->remove_mutex); wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&dvbnet->remove_mutex); + } + return 0; } @@ -1580,7 +1608,7 @@ static int dvb_net_close(struct inode *inode, struct file *file) static const struct file_operations dvb_net_fops = { .owner = THIS_MODULE, .unlocked_ioctl = dvb_net_ioctl, - .open = dvb_generic_open, + .open = locked_dvb_net_open, .release = dvb_net_close, .llseek = noop_llseek, }; @@ -1599,10 +1627,13 @@ void dvb_net_release (struct dvb_net *dvbnet) { int i; + mutex_lock(&dvbnet->remove_mutex); dvbnet->exit = 1; + mutex_unlock(&dvbnet->remove_mutex); + if (dvbnet->dvbdev->users < 1) wait_event(dvbnet->dvbdev->wait_queue, - dvbnet->dvbdev->users==1); + dvbnet->dvbdev->users == 1); dvb_unregister_device(dvbnet->dvbdev); @@ -1621,6 +1652,7 @@ int dvb_net_init (struct dvb_adapter *adap, struct dvb_net *dvbnet, int i; mutex_init(&dvbnet->ioctl_mutex); + mutex_init(&dvbnet->remove_mutex); dvbnet->demux = dmx; for (i=0; i<DVB_NET_DEVICES_MAX; i++) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index e9b3ce09e534..a4b05e366ccc 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -27,6 +27,7 @@ #include <media/tuner.h> static DEFINE_MUTEX(dvbdev_mutex); +static LIST_HEAD(dvbdevfops_list); static int dvbdev_debug; module_param(dvbdev_debug, int, 0644); @@ -453,14 +454,15 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, enum dvb_device_type type, int demux_sink_pads) { struct dvb_device *dvbdev; - struct file_operations *dvbdevfops; + struct file_operations *dvbdevfops = NULL; + struct dvbdevfops_node *node = NULL, *new_node = NULL; struct device *clsdev; int minor; int id, ret; mutex_lock(&dvbdev_register_lock); - if ((id = dvbdev_get_free_id (adap, type)) < 0){ + if ((id = dvbdev_get_free_id (adap, type)) < 0) { mutex_unlock(&dvbdev_register_lock); *pdvbdev = NULL; pr_err("%s: couldn't find free device id\n", __func__); @@ -468,18 +470,45 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } *pdvbdev = dvbdev = kzalloc(sizeof(*dvbdev), GFP_KERNEL); - if (!dvbdev){ mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } - dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + /* + * When a device of the same type is probe()d more than once, + * the first allocated fops are used. This prevents memory leaks + * that can occur when the same device is probe()d repeatedly. + */ + list_for_each_entry(node, &dvbdevfops_list, list_head) { + if (node->fops->owner == adap->module && + node->type == type && + node->template == template) { + dvbdevfops = node->fops; + break; + } + } - if (!dvbdevfops){ - kfree (dvbdev); - mutex_unlock(&dvbdev_register_lock); - return -ENOMEM; + if (dvbdevfops == NULL) { + dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + if (!dvbdevfops) { + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node = kzalloc(sizeof(struct dvbdevfops_node), GFP_KERNEL); + if (!new_node) { + kfree(dvbdevfops); + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node->fops = dvbdevfops; + new_node->type = type; + new_node->template = template; + list_add_tail (&new_node->list_head, &dvbdevfops_list); } memcpy(dvbdev, template, sizeof(struct dvb_device)); @@ -490,20 +519,20 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdev->priv = priv; dvbdev->fops = dvbdevfops; init_waitqueue_head (&dvbdev->wait_queue); - dvbdevfops->owner = adap->module; - list_add_tail (&dvbdev->list_head, &adap->device_list); - down_write(&minor_rwsem); #ifdef CONFIG_DVB_DYNAMIC_MINORS for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (dvb_minors[minor] == NULL) break; - if (minor == MAX_DVB_MINORS) { + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); @@ -512,41 +541,47 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #else minor = nums2minor(adap->num, type, id); #endif - dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); - ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); if (ret) { pr_err("%s: dvb_register_media_device failed to create the mediagraph\n", __func__); - + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); return ret; } - mutex_unlock(&dvbdev_register_lock); - clsdev = device_create(dvb_class, adap->device, MKDEV(DVB_MAJOR, minor), dvbdev, "dvb%d.%s%d", adap->num, dnames[type], id); if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } + dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", adap->num, dnames[type], id, minor, minor); + mutex_unlock(&dvbdev_register_lock); return 0; } EXPORT_SYMBOL(dvb_register_device); @@ -575,7 +610,6 @@ static void dvb_free_device(struct kref *ref) { struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); - kfree (dvbdev->fops); kfree (dvbdev); } @@ -1081,9 +1115,17 @@ error: static void __exit exit_dvbdev(void) { + struct dvbdevfops_node *node, *next; + class_destroy(dvb_class); cdev_del(&dvb_device_cdev); unregister_chrdev_region(MKDEV(DVB_MAJOR, 0), MAX_DVB_MINORS); + + list_for_each_entry_safe(node, next, &dvbdevfops_list, list_head) { + list_del (&node->list_head); + kfree(node->fops); + kfree(node); + } } subsys_initcall(init_dvbdev); diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c index 1f1753f2ab1a..0782f8377eb2 100644 --- a/drivers/media/dvb-frontends/mn88443x.c +++ b/drivers/media/dvb-frontends/mn88443x.c @@ -798,7 +798,7 @@ MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id); static struct i2c_driver mn88443x_driver = { .driver = { .name = "mn88443x", - .of_match_table = of_match_ptr(mn88443x_of_match), + .of_match_table = mn88443x_of_match, }, .probe_new = mn88443x_probe, .remove = mn88443x_remove, diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 8287851b5ffd..d85bfbb77a25 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -697,7 +697,7 @@ static void netup_unidvb_dma_fini(struct netup_unidvb_dev *ndev, int num) netup_unidvb_dma_enable(dma, 0); msleep(50); cancel_work_sync(&dma->work); - del_timer(&dma->timeout); + del_timer_sync(&dma->timeout); } static int netup_unidvb_dma_setup(struct netup_unidvb_dev *ndev) @@ -887,12 +887,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, ndev->lmmio0, (u32)pci_resource_len(pci_dev, 0), ndev->lmmio1, (u32)pci_resource_len(pci_dev, 1), pci_dev->irq); - if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, - "netup_unidvb", pci_dev) < 0) { - dev_err(&pci_dev->dev, - "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); - goto irq_request_err; - } + ndev->dma_size = 2 * 188 * NETUP_DMA_BLOCKS_COUNT * NETUP_DMA_PACKETS_COUNT; ndev->dma_virt = dma_alloc_coherent(&pci_dev->dev, @@ -933,6 +928,14 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, dev_err(&pci_dev->dev, "netup_unidvb: DMA setup failed\n"); goto dma_setup_err; } + + if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, + "netup_unidvb", pci_dev) < 0) { + dev_err(&pci_dev->dev, + "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); + goto dma_setup_err; + } + dev_info(&pci_dev->dev, "netup_unidvb: device has been initialized\n"); return 0; @@ -951,8 +954,6 @@ spi_setup_err: dma_free_coherent(&pci_dev->dev, ndev->dma_size, ndev->dma_virt, ndev->dma_phys); dma_alloc_err: - free_irq(pci_dev->irq, pci_dev); -irq_request_err: iounmap(ndev->lmmio1); pci_bar1_error: iounmap(ndev->lmmio0); diff --git a/drivers/media/usb/dvb-usb-v2/ce6230.c b/drivers/media/usb/dvb-usb-v2/ce6230.c index 44540de1a206..d3b5cb4a24da 100644 --- a/drivers/media/usb/dvb-usb-v2/ce6230.c +++ b/drivers/media/usb/dvb-usb-v2/ce6230.c @@ -101,6 +101,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_READ; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; @@ -117,6 +121,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, } else { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_WRITE; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; diff --git a/drivers/media/usb/dvb-usb-v2/ec168.c b/drivers/media/usb/dvb-usb-v2/ec168.c index 7ed0ab9e429b..0e4773fc025c 100644 --- a/drivers/media/usb/dvb-usb-v2/ec168.c +++ b/drivers/media/usb/dvb-usb-v2/ec168.c @@ -115,6 +115,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = READ_DEMOD; req.value = 0; req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -131,6 +135,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } } else { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_DEMOD; req.value = msg[i].buf[1]; /* val */ req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -139,6 +147,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = ec168_ctrl_msg(d, &req); i += 1; } else { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_I2C; req.value = msg[i].buf[0]; /* val */ req.index = 0x0100 + msg[i].addr; /* I2C addr */ diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 795a012d4020..f7884bb56fcc 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -176,6 +176,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1 || msg[1].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { /* return demod page from driver cache */ @@ -189,6 +193,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if (msg[0].len < 2) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_RD; @@ -217,8 +225,16 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { + if (msg[0].len < 2) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* save demod page for later demod access */ dev->page = msg[0].buf[1]; ret = 0; @@ -231,6 +247,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if ((msg[0].len < 23) && (!dev->new_i2c_write)) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_WR; diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 7d78ee09be5e..a31c6f82f4e9 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -988,6 +988,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* write/read request */ if (i + 1 < num && (msg[i + 1].flags & I2C_M_RD)) { req = 0xB9; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (msg[i].len << 8); length = msg[i + 1].len + 6; @@ -1001,6 +1005,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* demod 16bit addr */ req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (2 << 8); length = msg[i].len - 2; @@ -1026,6 +1034,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n } else { req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = msg[i].buf[0] & 0x00FF; value = msg[i].addr + (1 << 8); length = msg[i].len - 1; diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c index 2756815a780b..32134be16914 100644 --- a/drivers/media/usb/dvb-usb/digitv.c +++ b/drivers/media/usb/dvb-usb/digitv.c @@ -63,6 +63,10 @@ static int digitv_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num warn("more than 2 i2c messages at a time is not handled yet. TODO."); for (i = 0; i < num; i++) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } /* write/read request */ if (i+1 < num && (msg[i+1].flags & I2C_M_RD)) { if (digitv_ctrl_msg(d, USB_READ_COFDM, msg[i].buf[0], NULL, 0, diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 0ca764282c76..8747960e6146 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -946,7 +946,7 @@ static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6]) for (i = 0; i < 6; i++) { obuf[1] = 0xf0 + i; if (i2c_transfer(&d->i2c_adap, msg, 2) != 2) - break; + return -1; else mac[i] = ibuf[0]; } diff --git a/drivers/media/usb/pvrusb2/Kconfig b/drivers/media/usb/pvrusb2/Kconfig index 9501b10b31aa..0df10270dbdf 100644 --- a/drivers/media/usb/pvrusb2/Kconfig +++ b/drivers/media/usb/pvrusb2/Kconfig @@ -37,6 +37,7 @@ config VIDEO_PVRUSB2_DVB bool "pvrusb2 ATSC/DVB support" default y depends on VIDEO_PVRUSB2 && DVB_CORE + depends on VIDEO_PVRUSB2=m || DVB_CORE=y select DVB_LGDT330X if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1409 if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1411 if MEDIA_SUBDRV_AUTOSELECT diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index 38822cedd93a..c4474d4c44e2 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1544,8 +1544,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 3ceccafd701b..b190007c01be 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -95,7 +95,7 @@ config CAN_AT91 config CAN_BXCAN tristate "STM32 Basic Extended CAN (bxCAN) devices" - depends on OF || ARCH_STM32 || COMPILE_TEST + depends on ARCH_STM32 || COMPILE_TEST depends on HAS_IOMEM select CAN_RX_OFFLOAD help diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c index e26ccd41e3cb..027a8a162fe4 100644 --- a/drivers/net/can/bxcan.c +++ b/drivers/net/can/bxcan.c @@ -118,7 +118,7 @@ #define BXCAN_FiR1_REG(b) (0x40 + (b) * 8) #define BXCAN_FiR2_REG(b) (0x44 + (b) * 8) -#define BXCAN_FILTER_ID(primary) (primary ? 0 : 14) +#define BXCAN_FILTER_ID(cfg) ((cfg) == BXCAN_CFG_DUAL_SECONDARY ? 14 : 0) /* Filter primary register (FMR) bits */ #define BXCAN_FMR_CANSB_MASK GENMASK(13, 8) @@ -135,6 +135,12 @@ enum bxcan_lec_code { BXCAN_LEC_UNUSED }; +enum bxcan_cfg { + BXCAN_CFG_SINGLE = 0, + BXCAN_CFG_DUAL_PRIMARY, + BXCAN_CFG_DUAL_SECONDARY +}; + /* Structure of the message buffer */ struct bxcan_mb { u32 id; /* can identifier */ @@ -167,7 +173,7 @@ struct bxcan_priv { struct regmap *gcan; int tx_irq; int sce_irq; - bool primary; + enum bxcan_cfg cfg; struct clk *clk; spinlock_t rmw_lock; /* lock for read-modify-write operations */ unsigned int tx_head; @@ -202,17 +208,17 @@ static inline void bxcan_rmw(struct bxcan_priv *priv, void __iomem *addr, spin_unlock_irqrestore(&priv->rmw_lock, flags); } -static void bxcan_disable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_disable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); regmap_update_bits(priv->gcan, BXCAN_FA1R_REG, fmask, 0); } -static void bxcan_enable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_enable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); /* Filter settings: @@ -680,7 +686,7 @@ static int bxcan_chip_start(struct net_device *ndev) BXCAN_BTR_BRP_MASK | BXCAN_BTR_TS1_MASK | BXCAN_BTR_TS2_MASK | BXCAN_BTR_SJW_MASK, set); - bxcan_enable_filters(priv, priv->primary); + bxcan_enable_filters(priv, priv->cfg); /* Clear all internal status */ priv->tx_head = 0; @@ -806,7 +812,7 @@ static void bxcan_chip_stop(struct net_device *ndev) BXCAN_IER_EPVIE | BXCAN_IER_EWGIE | BXCAN_IER_FOVIE1 | BXCAN_IER_FFIE1 | BXCAN_IER_FMPIE1 | BXCAN_IER_FOVIE0 | BXCAN_IER_FFIE0 | BXCAN_IER_FMPIE0 | BXCAN_IER_TMEIE, 0); - bxcan_disable_filters(priv, priv->primary); + bxcan_disable_filters(priv, priv->cfg); bxcan_enter_sleep_mode(priv); priv->can.state = CAN_STATE_STOPPED; } @@ -931,7 +937,7 @@ static int bxcan_probe(struct platform_device *pdev) struct clk *clk = NULL; void __iomem *regs; struct regmap *gcan; - bool primary; + enum bxcan_cfg cfg; int err, rx_irq, tx_irq, sce_irq; regs = devm_platform_ioremap_resource(pdev, 0); @@ -946,7 +952,13 @@ static int bxcan_probe(struct platform_device *pdev) return PTR_ERR(gcan); } - primary = of_property_read_bool(np, "st,can-primary"); + if (of_property_read_bool(np, "st,can-primary")) + cfg = BXCAN_CFG_DUAL_PRIMARY; + else if (of_property_read_bool(np, "st,can-secondary")) + cfg = BXCAN_CFG_DUAL_SECONDARY; + else + cfg = BXCAN_CFG_SINGLE; + clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { dev_err(dev, "failed to get clock\n"); @@ -992,7 +1004,7 @@ static int bxcan_probe(struct platform_device *pdev) priv->clk = clk; priv->tx_irq = tx_irq; priv->sce_irq = sce_irq; - priv->primary = primary; + priv->cfg = cfg; priv->can.clock.freq = clk_get_rate(clk); spin_lock_init(&priv->rmw_lock); priv->tx_head = 0; diff --git a/drivers/net/can/dev/skb.c b/drivers/net/can/dev/skb.c index 241ec636e91f..f6d05b3ef59a 100644 --- a/drivers/net/can/dev/skb.c +++ b/drivers/net/can/dev/skb.c @@ -54,7 +54,8 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, /* check flag whether this packet has to be looped back */ if (!(dev->flags & IFF_ECHO) || (skb->protocol != htons(ETH_P_CAN) && - skb->protocol != htons(ETH_P_CANFD))) { + skb->protocol != htons(ETH_P_CANFD) && + skb->protocol != htons(ETH_P_CANXL))) { kfree_skb(skb); return 0; } diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 53e8a914c88b..be189edb256c 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -71,10 +71,12 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14) /* Shared receive buffer registers */ #define KVASER_PCIEFD_SRB_BASE 0x1f200 +#define KVASER_PCIEFD_SRB_FIFO_LAST_REG (KVASER_PCIEFD_SRB_BASE + 0x1f4) #define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200) #define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204) #define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c) #define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210) +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG (KVASER_PCIEFD_SRB_BASE + 0x214) #define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218) /* EPCS flash controller registers */ #define KVASER_PCIEFD_SPI_BASE 0x1fc00 @@ -111,6 +113,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); /* DMA support */ #define KVASER_PCIEFD_SRB_STAT_DMA BIT(24) +/* SRB current packet level */ +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK 0xff + /* DMA Enable */ #define KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE BIT(0) @@ -526,7 +531,7 @@ static int kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) KVASER_PCIEFD_KCAN_IRQ_TOF | KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TAE | KVASER_PCIEFD_KCAN_IRQ_TAL | KVASER_PCIEFD_KCAN_IRQ_FDIC | KVASER_PCIEFD_KCAN_IRQ_BPP | - KVASER_PCIEFD_KCAN_IRQ_TAR | KVASER_PCIEFD_KCAN_IRQ_TFD; + KVASER_PCIEFD_KCAN_IRQ_TAR; iowrite32(msk, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); @@ -554,6 +559,8 @@ static void kvaser_pciefd_setup_controller(struct kvaser_pciefd_can *can) if (can->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) mode |= KVASER_PCIEFD_KCAN_MODE_LOM; + else + mode &= ~KVASER_PCIEFD_KCAN_MODE_LOM; mode |= KVASER_PCIEFD_KCAN_MODE_EEN; mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; @@ -572,7 +579,7 @@ static void kvaser_pciefd_start_controller_flush(struct kvaser_pciefd_can *can) spin_lock_irqsave(&can->lock, irq); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); @@ -615,7 +622,7 @@ static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); @@ -719,6 +726,7 @@ static int kvaser_pciefd_stop(struct net_device *netdev) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); del_timer(&can->bec_poll_timer); } + can->can.state = CAN_STATE_STOPPED; close_candev(netdev); return ret; @@ -1007,8 +1015,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) SET_NETDEV_DEV(netdev, &pcie->pci->dev); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | - KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); pcie->can[i] = can; @@ -1058,6 +1065,7 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) { int i; u32 srb_status; + u32 srb_packet_count; dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT]; /* Disable the DMA */ @@ -1085,6 +1093,15 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + /* Empty Rx FIFO */ + srb_packet_count = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG) & + KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK; + while (srb_packet_count) { + /* Drop current packet in FIFO */ + ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_FIFO_LAST_REG); + srb_packet_count--; + } + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) { dev_err(&pcie->pci->dev, "DMA not idle before enabling\n"); @@ -1425,9 +1442,6 @@ static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, cmd = KVASER_PCIEFD_KCAN_CMD_AT; cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); - - iowrite32(KVASER_PCIEFD_KCAN_IRQ_TFD, - can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); } else if (p->header[0] & KVASER_PCIEFD_SPACK_IDET && p->header[0] & KVASER_PCIEFD_SPACK_IRM && cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && @@ -1714,15 +1728,6 @@ static int kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) if (irq & KVASER_PCIEFD_KCAN_IRQ_TOF) netdev_err(can->can.dev, "Tx FIFO overflow\n"); - if (irq & KVASER_PCIEFD_KCAN_IRQ_TFD) { - u8 count = ioread32(can->reg_base + - KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; - - if (count == 0) - iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, - can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); - } - if (irq & KVASER_PCIEFD_KCAN_IRQ_BPP) netdev_err(can->can.dev, "Fail to change bittiming, when not in reset mode\n"); @@ -1824,6 +1829,11 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, if (err) goto err_teardown_can_ctrls; + err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (err) + goto err_teardown_can_ctrls; + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); @@ -1844,11 +1854,6 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); - err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, - IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); - if (err) - goto err_teardown_can_ctrls; - err = kvaser_pciefd_reg_candev(pcie); if (err) goto err_free_irq; @@ -1856,6 +1861,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: + /* Disable PCI interrupts */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG); free_irq(pcie->pci->irq, pcie); err_teardown_can_ctrls: diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index aec9d4fd20e3..d19b6303b91f 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -276,7 +276,7 @@ /* Offset 0x10: Extended Port Control Command */ #define MV88E6393X_PORT_EPC_CMD 0x10 #define MV88E6393X_PORT_EPC_CMD_BUSY 0x8000 -#define MV88E6393X_PORT_EPC_CMD_WRITE 0x0300 +#define MV88E6393X_PORT_EPC_CMD_WRITE 0x3000 #define MV88E6393X_PORT_EPC_INDEX_PORT_ETYPE 0x02 /* Offset 0x11: Extended Port Control Data */ diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 919027cf2012..c37d2e537230 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -120,6 +120,22 @@ static void a5psw_port_mgmtfwd_set(struct a5psw *a5psw, int port, bool enable) a5psw_port_pattern_set(a5psw, port, A5PSW_PATTERN_MGMTFWD, enable); } +static void a5psw_port_tx_enable(struct a5psw *a5psw, int port, bool enable) +{ + u32 mask = A5PSW_PORT_ENA_TX(port); + u32 reg = enable ? mask : 0; + + /* Even though the port TX is disabled through TXENA bit in the + * PORT_ENA register, it can still send BPDUs. This depends on the tag + * configuration added when sending packets from the CPU port to the + * switch port. Indeed, when using forced forwarding without filtering, + * even disabled ports will be able to send packets that are tagged. + * This allows to implement STP support when ports are in a state where + * forwarding traffic should be stopped but BPDUs should still be sent. + */ + a5psw_reg_rmw(a5psw, A5PSW_PORT_ENA, mask, reg); +} + static void a5psw_port_enable_set(struct a5psw *a5psw, int port, bool enable) { u32 port_ena = 0; @@ -292,6 +308,22 @@ static int a5psw_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) return 0; } +static void a5psw_port_learning_set(struct a5psw *a5psw, int port, bool learn) +{ + u32 mask = A5PSW_INPUT_LEARN_DIS(port); + u32 reg = !learn ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + +static void a5psw_port_rx_block_set(struct a5psw *a5psw, int port, bool block) +{ + u32 mask = A5PSW_INPUT_LEARN_BLOCK(port); + u32 reg = block ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, bool set) { @@ -308,6 +340,14 @@ static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, a5psw_reg_writel(a5psw, offsets[i], a5psw->bridged_ports); } +static void a5psw_port_set_standalone(struct a5psw *a5psw, int port, + bool standalone) +{ + a5psw_port_learning_set(a5psw, port, !standalone); + a5psw_flooding_set_resolution(a5psw, port, !standalone); + a5psw_port_mgmtfwd_set(a5psw, port, standalone); +} + static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, @@ -323,8 +363,7 @@ static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, } a5psw->br_dev = bridge.dev; - a5psw_flooding_set_resolution(a5psw, port, true); - a5psw_port_mgmtfwd_set(a5psw, port, false); + a5psw_port_set_standalone(a5psw, port, false); return 0; } @@ -334,8 +373,7 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, { struct a5psw *a5psw = ds->priv; - a5psw_flooding_set_resolution(a5psw, port, false); - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); /* No more ports bridged */ if (a5psw->bridged_ports == BIT(A5PSW_CPU_PORT)) @@ -344,28 +382,35 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - u32 mask = A5PSW_INPUT_LEARN_DIS(port) | A5PSW_INPUT_LEARN_BLOCK(port); + bool learning_enabled, rx_enabled, tx_enabled; struct a5psw *a5psw = ds->priv; - u32 reg = 0; switch (state) { case BR_STATE_DISABLED: case BR_STATE_BLOCKING: - reg |= A5PSW_INPUT_LEARN_DIS(port); - reg |= A5PSW_INPUT_LEARN_BLOCK(port); - break; case BR_STATE_LISTENING: - reg |= A5PSW_INPUT_LEARN_DIS(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = false; break; case BR_STATE_LEARNING: - reg |= A5PSW_INPUT_LEARN_BLOCK(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = true; break; case BR_STATE_FORWARDING: - default: + rx_enabled = true; + tx_enabled = true; + learning_enabled = true; break; + default: + dev_err(ds->dev, "invalid STP state: %d\n", state); + return; } - a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); + a5psw_port_learning_set(a5psw, port, learning_enabled); + a5psw_port_rx_block_set(a5psw, port, !rx_enabled); + a5psw_port_tx_enable(a5psw, port, tx_enabled); } static void a5psw_port_fast_age(struct dsa_switch *ds, int port) @@ -673,7 +718,7 @@ static int a5psw_setup(struct dsa_switch *ds) } /* Configure management port */ - reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_DISCARD; + reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_ENABLE; a5psw_reg_writel(a5psw, A5PSW_MGMT_CFG, reg); /* Set pattern 0 to forward all frame to mgmt port */ @@ -722,13 +767,15 @@ static int a5psw_setup(struct dsa_switch *ds) if (dsa_port_is_unused(dp)) continue; - /* Enable egress flooding for CPU port */ - if (dsa_port_is_cpu(dp)) + /* Enable egress flooding and learning for CPU port */ + if (dsa_port_is_cpu(dp)) { a5psw_flooding_set_resolution(a5psw, port, true); + a5psw_port_learning_set(a5psw, port, true); + } - /* Enable management forward only for user ports */ + /* Enable standalone mode for user ports */ if (dsa_port_is_user(dp)) - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); } return 0; diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index c67abd49c013..b869192eef3f 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -19,6 +19,7 @@ #define A5PSW_PORT_OFFSET(port) (0x400 * (port)) #define A5PSW_PORT_ENA 0x8 +#define A5PSW_PORT_ENA_TX(port) BIT(port) #define A5PSW_PORT_ENA_RX_SHIFT 16 #define A5PSW_PORT_ENA_TX_RX(port) (BIT((port) + A5PSW_PORT_ENA_RX_SHIFT) | \ BIT(port)) @@ -36,7 +37,7 @@ #define A5PSW_INPUT_LEARN_BLOCK(p) BIT(p) #define A5PSW_MGMT_CFG 0x20 -#define A5PSW_MGMT_CFG_DISCARD BIT(7) +#define A5PSW_MGMT_CFG_ENABLE BIT(6) #define A5PSW_MODE_CFG 0x24 #define A5PSW_MODE_STATS_RESET BIT(31) diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index d2f4358cc550..ba3e7aa1a28f 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -66,8 +66,10 @@ static int max_interrupt_work = 20; #include <linux/timer.h> #include <linux/ethtool.h> #include <linux/bitops.h> - #include <linux/uaccess.h> + +#include <net/Space.h> + #include <asm/io.h> #include <asm/dma.h> diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 0a9118b8be0c..bc9c81dc00fd 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -52,6 +52,7 @@ static const char version2[] = #include <linux/etherdevice.h> #include <linux/jiffies.h> #include <linux/platform_device.h> +#include <net/Space.h> #include <asm/io.h> diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c index 6e62c37c9400..7465650c8078 100644 --- a/drivers/net/ethernet/8390/smc-ultra.c +++ b/drivers/net/ethernet/8390/smc-ultra.c @@ -66,6 +66,7 @@ static const char version[] = #include <linux/isapnp.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <net/Space.h> #include <asm/io.h> #include <asm/irq.h> diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index 5b00c452bede..119021d41451 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -37,6 +37,7 @@ static const char version[] = #include <linux/delay.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <net/Space.h> #include <asm/io.h> diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index 8971665a4b2a..6cf38180cc01 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -59,6 +59,7 @@ static const char version[] = "lance.c:v1.16 2006/11/09 dplatt@3do.com, becker@c #include <linux/skbuff.h> #include <linux/mm.h> #include <linux/bitops.h> +#include <net/Space.h> #include <asm/io.h> #include <asm/dma.h> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f28ffc31df22..eca0c92c0c84 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3450,7 +3450,7 @@ err_clk_disable: return ret; } -static void bcmgenet_netif_stop(struct net_device *dev) +static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -3465,6 +3465,8 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); + if (stop_phy) + phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); @@ -3485,7 +3487,7 @@ static int bcmgenet_close(struct net_device *dev) netif_dbg(priv, ifdown, dev, "bcmgenet_close\n"); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, false); /* Really kill the PHY state machine and disconnect from it */ phy_disconnect(dev->phydev); @@ -4303,7 +4305,7 @@ static int bcmgenet_suspend(struct device *d) netif_device_detach(dev); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, true); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 06a0c00af99c..276c32c3926a 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -72,6 +72,8 @@ #include <linux/gfp.h> #include <linux/io.h> +#include <net/Space.h> + #include <asm/irq.h> #include <linux/atomic.h> #if ALLOW_DMA diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 42ec6ca3bf03..577d94821b3e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3798,7 +3798,6 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { netdev_err(fep->netdev, "NOT enough BD for SG!\n"); - xdp_return_frame(frame); return NETDEV_TX_BUSY; } @@ -4478,9 +4477,11 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_resume_and_get(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) - return ret; + dev_err(&pdev->dev, + "Failed to resume device in remove callback (%pe)\n", + ERR_PTR(ret)); cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -4493,8 +4494,13 @@ fec_drv_remove(struct platform_device *pdev) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); - clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); + /* After pm_runtime_get_sync() failed, the clks are still off, so skip + * disabling them again. + */ + if (ret >= 0) { + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + } pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index cbbab5b2b402..b85c412683dd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -331,9 +331,25 @@ static int hclge_comm_cmd_csq_done(struct hclge_comm_hw *hw) return head == hw->cmq.csq.next_to_use; } -static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, +static u32 hclge_get_cmdq_tx_timeout(u16 opcode, u32 tx_timeout) +{ + static const struct hclge_cmdq_tx_timeout_map cmdq_tx_timeout_map[] = { + {HCLGE_OPC_CFG_RST_TRIGGER, HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS}, + }; + u32 i; + + for (i = 0; i < ARRAY_SIZE(cmdq_tx_timeout_map); i++) + if (cmdq_tx_timeout_map[i].opcode == opcode) + return cmdq_tx_timeout_map[i].tx_timeout; + + return tx_timeout; +} + +static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, u16 opcode, bool *is_completed) { + u32 cmdq_tx_timeout = hclge_get_cmdq_tx_timeout(opcode, + hw->cmq.tx_timeout); u32 timeout = 0; do { @@ -343,7 +359,7 @@ static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, } udelay(1); timeout++; - } while (timeout < hw->cmq.tx_timeout); + } while (timeout < cmdq_tx_timeout); } static int hclge_comm_cmd_convert_err_code(u16 desc_ret) @@ -407,7 +423,8 @@ static int hclge_comm_cmd_check_result(struct hclge_comm_hw *hw, * if multi descriptors to be sent, use the first one to check */ if (HCLGE_COMM_SEND_SYNC(le16_to_cpu(desc->flag))) - hclge_comm_wait_for_resp(hw, &is_completed); + hclge_comm_wait_for_resp(hw, le16_to_cpu(desc->opcode), + &is_completed); if (!is_completed) ret = -EBADE; @@ -529,7 +546,7 @@ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw) cmdq->crq.desc_num = HCLGE_COMM_NIC_CMQ_DESC_NUM; /* Setup Tx write back timeout */ - cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT; + cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT; /* Setup queue rings */ ret = hclge_comm_alloc_cmd_queue(hw, HCLGE_COMM_TYPE_CSQ); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h index de72ecbfd5ad..18f1b4bf362d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h @@ -54,7 +54,8 @@ #define HCLGE_COMM_NIC_SW_RST_RDY BIT(HCLGE_COMM_NIC_SW_RST_RDY_B) #define HCLGE_COMM_NIC_CMQ_DESC_NUM_S 3 #define HCLGE_COMM_NIC_CMQ_DESC_NUM 1024 -#define HCLGE_COMM_CMDQ_TX_TIMEOUT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS 500000 enum hclge_opcode_type { /* Generic commands */ @@ -360,6 +361,11 @@ struct hclge_comm_caps_bit_map { u16 local_bit; }; +struct hclge_cmdq_tx_timeout_map { + u32 opcode; + u32 tx_timeout; +}; + struct hclge_comm_firmware_compat_cmd { __le32 compat; u8 rsv[20]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 4c3e90a1c4d0..d385ffc21876 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -130,7 +130,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "tx_bd_queue", .cmd = HNAE3_DBG_CMD_TX_BD, .dentry = HNS3_DBG_DENTRY_TX_BD, - .buf_len = HNS3_DBG_READ_LEN_4MB, + .buf_len = HNS3_DBG_READ_LEN_5MB, .init = hns3_dbg_bd_file_init, }, { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h index 97578eabb7d8..4a5ef8a90a10 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h @@ -10,6 +10,7 @@ #define HNS3_DBG_READ_LEN_128KB 0x20000 #define HNS3_DBG_READ_LEN_1MB 0x100000 #define HNS3_DBG_READ_LEN_4MB 0x400000 +#define HNS3_DBG_READ_LEN_5MB 0x500000 #define HNS3_DBG_WRITE_LEN 1024 #define HNS3_DBG_DATA_STR_LEN 32 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 4fb5406c1951..2689b108f7df 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8053,12 +8053,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET && - hdev->reset_type != HNAE3_FLR_RESET) { - hclge_mac_stop_phy(hdev); - hclge_update_link_status(hdev); - return; + if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) { + hclge_pfc_pause_en_cfg(hdev, HCLGE_PFC_TX_RX_DISABLE, + HCLGE_PFC_DISABLE); + if (hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { + hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); + return; + } } hclge_reset_tqp(handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 4a33f65190e2..922c0da3660c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -171,8 +171,8 @@ int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) return hclge_cmd_send(&hdev->hw, &desc, 1); } -static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, - u8 pfc_bitmap) +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap) { struct hclge_desc desc; struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 68f28a98e380..dd6f1fd486cf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -164,6 +164,9 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; +#define HCLGE_PFC_DISABLE 0 +#define HCLGE_PFC_TX_RX_DISABLE 0 + struct hclge_pfc_en_cmd { u8 tx_rx_en_bitmap; u8 pri_en_bitmap; @@ -235,6 +238,8 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); void hclge_tm_pfc_info_update(struct hclge_dev *hdev); int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev, bool init); +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index f24046250341..dd08989a4c7c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1436,7 +1436,10 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) * might happen in case reset assertion was made by PF. Yes, this also * means we might end up waiting bit more even for VF reset. */ - msleep(5000); + if (hdev->reset_type == HNAE3_VF_FULL_RESET) + msleep(5000); + else + msleep(500); return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 9afbbdac3590..7c0578b5457b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2238,11 +2238,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - iavf_set_queue_vlan_tag_loc(adapter); was_mac_changed = !ether_addr_equal(netdev->dev_addr, diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index c6d4926f0fcf..850db8e0e6b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -932,10 +932,9 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { - first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; + first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->tx_flags |= (skb->priority & 0x7) << - ICE_TX_FLAGS_VLAN_PR_S; + first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 450317dfcca7..11ae0e41f518 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2745,6 +2745,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + vsi->stat_offsets_loaded = false; + if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -2793,6 +2795,9 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + + vsi->stat_offsets_loaded = false; + /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index f1dca59bd844..588ad8696756 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1171,7 +1171,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1286,7 +1286,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1340,7 +1340,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1653,7 +1653,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4fcf2d07eb85..059bd911c51d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1664,8 +1664,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) { td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1; - td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + td_tag = first->vid; } dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -1998,7 +1997,7 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { - first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; + first->vid = skb_vlan_tag_get(skb); if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; else @@ -2388,8 +2387,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | (ICE_TX_CTX_DESC_IL2TAG2 << ICE_TXD_CTX_QW1_CMD_S)); - offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + offload.cd_l2tag2 = first->vid; } /* set up TSO offload */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fff0efe28373..166413fc33f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -127,10 +127,6 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) #define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) -#define ICE_TX_FLAGS_VLAN_M 0xffff0000 -#define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 -#define ICE_TX_FLAGS_VLAN_PR_S 29 -#define ICE_TX_FLAGS_VLAN_S 16 #define ICE_XDP_PASS 0 #define ICE_XDP_CONSUMED BIT(0) @@ -182,8 +178,9 @@ struct ice_tx_buf { unsigned int gso_segs; unsigned int nr_frags; /* used for mbuf XDP */ }; - u32 type:16; /* &ice_tx_buf_type */ - u32 tx_flags:16; + u32 tx_flags:12; + u32 type:4; /* &ice_tx_buf_type */ + u32 vid:16; DEFINE_DMA_UNMAP_LEN(len); DEFINE_DMA_UNMAP_ADDR(dma); }; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 89fd6982df09..bf74a2f3a4f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -186,6 +186,25 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) } /** + * ice_check_vf_ready_for_reset - check if VF is ready to be reset + * @vf: VF to check if it's ready to be reset + * + * The purpose of this function is to ensure that the VF is not in reset, + * disabled, and is both initialized and active, thus enabling us to safely + * initialize another reset. + */ +int ice_check_vf_ready_for_reset(struct ice_vf *vf) +{ + int ret; + + ret = ice_check_vf_ready_for_cfg(vf); + if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ret = -EAGAIN; + + return ret; +} + +/** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure * @is_vflr: true if VFLR was issued, false if not diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e3cda6fb71ab..a38ef00a3679 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -215,6 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); +int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 97243c616d5d..f4a524f80b11 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3955,6 +3955,7 @@ error_handler: ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 205d577bdbba..caf91c6f52b4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -426,7 +426,7 @@ void igb_mta_set(struct e1000_hw *hw, u32 hash_value) static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) { u32 hash_value, hash_mask; - u8 bit_shift = 0; + u8 bit_shift = 1; /* Register count multiplied by bits per register */ hash_mask = (hw->mac.mta_reg_count * 32) - 1; @@ -434,7 +434,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) /* For a mc_filter_type of 0, bit_shift is the number of left-shifts * where 0xFF would still fall within the hash mask. */ - while (hash_mask >> bit_shift != 0xFF) + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) bit_shift++; /* The portion of the address that is used for the hash table diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h index 094374df42b8..38b8b10b03cd 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.h +++ b/drivers/net/ethernet/netronome/nfp/nic/main.h @@ -8,7 +8,7 @@ #ifdef CONFIG_DCB /* DCB feature definitions */ -#define NFP_NET_MAX_DSCP 4 +#define NFP_NET_MAX_DSCP 64 #define NFP_NET_MAX_TC IEEE_8021QAZ_MAX_TCS #define NFP_NET_MAX_PRIO 8 #define NFP_DCB_CFG_STRIDE 256 diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index d916877b5a9a..be395cd8770b 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -378,7 +378,9 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data) efx->net_dev = net_dev; SET_NETDEV_DEV(net_dev, &efx->pci_dev->dev); - net_dev->features |= efx->type->offload_features; + /* enable all supported features except rx-fcs and rx-all */ + net_dev->features |= efx->type->offload_features & + ~(NETIF_F_RXFCS | NETIF_F_RXALL); net_dev->hw_features |= efx->type->offload_features; net_dev->hw_enc_features |= efx->type->offload_features; net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG | diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 4ef05bad4613..d61dfa250feb 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -5077,6 +5077,8 @@ err_out_iounmap: cas_shutdown(cp); mutex_unlock(&cp->pm_mutex); + vfree(cp->fw_data); + pci_iounmap(pdev, cp->regs); diff --git a/drivers/net/mdio/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index 1e0c206d0f2e..da2001ea1f99 100644 --- a/drivers/net/mdio/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -291,7 +291,8 @@ static int i2c_rollball_mii_cmd(struct mii_bus *bus, int bus_addr, u8 cmd, return i2c_transfer_rollball(i2c, msgs, ARRAY_SIZE(msgs)); } -static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) +static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg) { u8 buf[4], res[6]; int bus_addr, ret; @@ -302,7 +303,7 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return 0xffff; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; @@ -322,8 +323,8 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return val; } -static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, - u16 val) +static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg, u16 val) { int bus_addr, ret; u8 buf[6]; @@ -333,7 +334,7 @@ static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, return 0; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; buf[4] = val >> 8; @@ -405,8 +406,8 @@ struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, return ERR_PTR(ret); } - mii->read = i2c_mii_read_rollball; - mii->write = i2c_mii_write_rollball; + mii->read_c45 = i2c_mii_read_rollball; + mii->write_c45 = i2c_mii_write_rollball; break; default: mii->read = i2c_mii_read_default_c22; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index f19d48c94fe0..72f25e778840 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -873,7 +873,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, switch (compat->an_mode) { case DW_AN_C73: - if (phylink_autoneg_inband(mode)) { + if (test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, advertising)) { ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index d75f526a20a4..76f5a2402fb0 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -44,6 +44,7 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_STRAP_STS2 0x006f #define DP83867_RGMIIDCTL 0x0086 +#define DP83867_DSP_FFE_CFG 0x012c #define DP83867_RXFCFG 0x0134 #define DP83867_RXFPMD1 0x0136 #define DP83867_RXFPMD2 0x0137 @@ -941,8 +942,27 @@ static int dp83867_phy_reset(struct phy_device *phydev) usleep_range(10, 20); - return phy_modify(phydev, MII_DP83867_PHYCTRL, + err = phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); + if (err < 0) + return err; + + /* Configure the DSP Feedforward Equalizer Configuration register to + * improve short cable (< 1 meter) performance. This will not affect + * long cable performance. + */ + err = phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_DSP_FFE_CFG, + 0x0e81); + if (err < 0) + return err; + + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + if (err < 0) + return err; + + usleep_range(10, 20); + + return 0; } static void dp83867_link_change_notify(struct phy_device *phydev) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a4111f1be375..e237949deee6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2225,6 +2225,10 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, ASSERT_RTNL(); + /* Mask out unsupported advertisements */ + linkmode_and(config.advertising, kset->link_modes.advertising, + pl->supported); + if (pl->phydev) { /* We can rely on phylib for this update; we also do not need * to update the pl->link_config settings: @@ -2249,10 +2253,6 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, config = pl->link_config; - /* Mask out unsupported advertisements */ - linkmode_and(config.advertising, kset->link_modes.advertising, - pl->supported); - /* FIXME: should we reject autoneg if phy/mac does not support it? */ switch (kset->base.autoneg) { case AUTONEG_DISABLE: diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d4d0a41a905a..d75456adc62a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1977,6 +1977,14 @@ napi_busy: int queue_len; spin_lock_bh(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock_bh(&queue->lock); + rcu_read_unlock(); + err = -EBUSY; + goto free_skb; + } + __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); @@ -2512,6 +2520,13 @@ build: if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock(&queue->lock); + kfree_skb(skb); + return -EBUSY; + } + __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a12ae26db0e2..56ca1d270304 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1868,6 +1868,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget) return received; } +static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + virtnet_napi_tx_disable(&vi->sq[qp_index].napi); + napi_disable(&vi->rq[qp_index].napi); + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); +} + +static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + struct net_device *dev = vi->dev; + int err; + + err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, + vi->rq[qp_index].napi.napi_id); + if (err < 0) + return err; + + err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) + goto err_xdp_reg_mem_model; + + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); + + return 0; + +err_xdp_reg_mem_model: + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); + return err; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -1881,22 +1913,20 @@ static int virtnet_open(struct net_device *dev) if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); - err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id); + err = virtnet_enable_queue_pair(vi, i); if (err < 0) - return err; - - err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err < 0) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - return err; - } - - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); + goto err_enable_qp; } return 0; + +err_enable_qp: + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + + for (i--; i >= 0; i--) + virtnet_disable_queue_pair(vi, i); + return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) @@ -2305,11 +2335,8 @@ static int virtnet_close(struct net_device *dev) /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_tx_disable(&vi->sq[i].napi); - napi_disable(&vi->rq[i].napi); - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_disable_queue_pair(vi, i); return 0; } diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 9fc7c088a539..67b4bac048e5 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -651,7 +651,7 @@ struct b43_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; diff --git a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h index 6b0cec467938..f49365d14619 100644 --- a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h +++ b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h @@ -379,7 +379,7 @@ struct b43legacy_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; #define B43legacy_PHYMODE(phytype) (1 << (phytype)) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index ff710b0b5071..00679a990e3d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -1039,6 +1039,11 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, struct brcmf_sdio_dev *sdiodev; struct brcmf_bus *bus_if; + if (!id) { + dev_err(&func->dev, "Error no sdio_device_id passed for %x:%x\n", func->vendor, func->device); + return -ENODEV; + } + brcmf_dbg(SDIO, "Enter\n"); brcmf_dbg(SDIO, "Class=%x\n", func->class); brcmf_dbg(SDIO, "sdio vendor ID: 0x%04x\n", func->vendor); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 59f3e9c5e139..80220685f5e4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -2394,6 +2394,9 @@ static void brcmf_pcie_debugfs_create(struct device *dev) } #endif +/* Forward declaration for pci_match_id() call */ +static const struct pci_device_id brcmf_pcie_devid_table[]; + static int brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -2404,6 +2407,14 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct brcmf_core *core; struct brcmf_bus *bus; + if (!id) { + id = pci_match_id(brcmf_pcie_devid_table, pdev); + if (!id) { + pci_err(pdev, "Error could not find pci_device_id for %x:%x\n", pdev->vendor, pdev->device); + return -ENODEV; + } + } + brcmf_dbg(PCIE, "Enter %x:%x\n", pdev->vendor, pdev->device); ret = -ENOMEM; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index 246843aeb696..2178675ae1a4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1331,6 +1331,9 @@ brcmf_usb_disconnect_cb(struct brcmf_usbdev_info *devinfo) brcmf_usb_detach(devinfo); } +/* Forward declaration for usb_match_id() call */ +static const struct usb_device_id brcmf_usb_devid_table[]; + static int brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -1342,6 +1345,14 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) u32 num_of_eps; u8 endpoint_num, ep; + if (!id) { + id = usb_match_id(intf, brcmf_usb_devid_table); + if (!id) { + dev_err(&intf->dev, "Error could not find matching usb_device_id\n"); + return -ENODEV; + } + } + brcmf_dbg(USB, "Enter 0x%04x:0x%04x\n", id->idVendor, id->idProduct); devinfo = kzalloc(sizeof(*devinfo), GFP_ATOMIC); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 5f4a51310add..cb9181f05501 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -38,7 +38,7 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = { }, { .ident = "ASUS", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek COMPUTER INC."), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), }, }, {} diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index d9faaae01abd..55219974b92b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -1664,14 +1664,10 @@ static __le32 iwl_get_mon_reg(struct iwl_fw_runtime *fwrt, u32 alloc_id, } static void * -iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, - struct iwl_dump_ini_region_data *reg_data, +iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, u32 alloc_id, struct iwl_fw_ini_monitor_dump *data, const struct iwl_fw_mon_regs *addrs) { - struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; - u32 alloc_id = le32_to_cpu(reg->dram_alloc_id); - if (!iwl_trans_grab_nic_access(fwrt->trans)) { IWL_ERR(fwrt, "Failed to get monitor header\n"); return NULL; @@ -1702,8 +1698,10 @@ iwl_dump_ini_mon_dram_fill_header(struct iwl_fw_runtime *fwrt, void *data, u32 data_len) { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; + struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; + u32 alloc_id = le32_to_cpu(reg->dram_alloc_id); - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump, &fwrt->trans->cfg->mon_dram_regs); } @@ -1713,8 +1711,10 @@ iwl_dump_ini_mon_smem_fill_header(struct iwl_fw_runtime *fwrt, void *data, u32 data_len) { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; + struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; + u32 alloc_id = le32_to_cpu(reg->internal_buffer.alloc_id); - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump, &fwrt->trans->cfg->mon_smem_regs); } @@ -1725,7 +1725,10 @@ iwl_dump_ini_mon_dbgi_fill_header(struct iwl_fw_runtime *fwrt, { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, + /* no offset calculation later */ + IWL_FW_INI_ALLOCATION_ID_DBGC1, + mon_dump, &fwrt->trans->cfg->mon_dbgi_regs); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 3963a0d4ed04..652a603c4500 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -526,6 +526,11 @@ iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif, rcu_read_lock(); sta = rcu_dereference(mvm->fw_id_to_mac_id[mvmvif->deflink.ap_sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + return PTR_ERR_OR_ZERO(sta); + } + if (sta->mfp && (peer->ftm.trigger_based || peer->ftm.non_trigger_based)) FTM_PUT_FLAG(PMF); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index b35c96cf7ad2..205c09bc9863 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1091,7 +1091,7 @@ static const struct dmi_system_id dmi_tas_approved_list[] = { }, { .ident = "LENOVO", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Lenovo"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), }, }, { .ident = "DELL", @@ -1727,8 +1727,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm) iwl_mvm_tas_init(mvm); iwl_mvm_leds_sync(mvm); - if (fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) { + if (iwl_rfi_supported(mvm)) { if (iwl_mvm_eval_dsm_rfi(mvm) == DSM_VALUE_RFI_ENABLE) iwl_rfi_send_config_cmd(mvm, NULL); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c index eb828de40a3c..3814915cb1a6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c @@ -123,11 +123,13 @@ int iwl_mvm_link_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (mvmvif->link[i]->phy_ctxt) count++; - /* FIXME: IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM should be - * defined per HW - */ - if (count >= IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM) - return -EINVAL; + if (vif->type == NL80211_IFTYPE_AP) { + if (count > mvm->fw->ucode_capa.num_beacons) + return -EOPNOTSUPP; + /* this should be per HW or such */ + } else if (count >= IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM) { + return -EOPNOTSUPP; + } } /* Catch early if driver tries to activate or deactivate a link diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 0f01b62357c6..17f788a5ff6b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2022 Intel Corporation + * Copyright (C) 2012-2014, 2018-2023 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3607,7 +3607,8 @@ static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; /* Beacon interval check - firmware will crash if the beacon * interval is less than 16. We can't avoid connecting at all, @@ -3616,14 +3617,11 @@ static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm, * wpa_s will blocklist the AP... */ - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { - struct ieee80211_link_sta *link_sta = - link_sta_dereference_protected(sta, i); + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); - if (!link_conf || !link_sta) + if (!link_conf) continue; if (link_conf->beacon_int < IWL_MVM_MIN_BEACON_INTERVAL_TU) { @@ -3645,24 +3643,23 @@ static void iwl_mvm_vif_set_he_support(struct ieee80211_hw *hw, bool is_sta) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { - struct ieee80211_link_sta *link_sta = - link_sta_dereference_protected(sta, i); + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); - if (!link_conf || !link_sta || !mvmvif->link[i]) + if (!link_conf || !mvmvif->link[link_id]) continue; link_conf->he_support = link_sta->he_cap.has_he; if (is_sta) { - mvmvif->link[i]->he_ru_2mhz_block = false; + mvmvif->link[link_id]->he_ru_2mhz_block = false; if (link_sta->he_cap.has_he) - iwl_mvm_check_he_obss_narrow_bw_ru(hw, vif, i, + iwl_mvm_check_he_obss_narrow_bw_ru(hw, vif, + link_id, link_conf); } } @@ -3675,6 +3672,7 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, struct iwl_mvm_sta_state_ops *callbacks) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + struct ieee80211_link_sta *link_sta; unsigned int i; int ret; @@ -3699,15 +3697,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, NL80211_TDLS_SETUP); } - for (i = 0; i < ARRAY_SIZE(sta->link); i++) { - struct ieee80211_link_sta *link_sta; - - link_sta = link_sta_dereference_protected(sta, i); - if (!link_sta) - continue; - + for_each_sta_active_link(vif, sta, link_sta, i) link_sta->agg.max_rc_amsdu_len = 1; - } + ieee80211_sta_recalc_aggregates(sta); if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) @@ -3725,7 +3717,8 @@ iwl_mvm_sta_state_auth_to_assoc(struct ieee80211_hw *hw, { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; lockdep_assert_held(&mvm->mutex); @@ -3751,14 +3744,13 @@ iwl_mvm_sta_state_auth_to_assoc(struct ieee80211_hw *hw, if (!mvm->mld_api_is_used) goto out; - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); if (WARN_ON(!link_conf)) return -EINVAL; - if (!mvmvif->link[i]) + if (!mvmvif->link[link_id]) continue; iwl_mvm_link_changed(mvm, vif, link_conf, @@ -3889,6 +3881,9 @@ int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw, * from the AP now. */ iwl_mvm_reset_cca_40mhz_workaround(mvm, vif); + + /* Also free dup data just in case any assertions below fail */ + kfree(mvm_sta->dup_data); } mutex_lock(&mvm->mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index fbc2d5ed1006..7fb66c570959 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -906,11 +906,12 @@ iwl_mvm_mld_change_vif_links(struct ieee80211_hw *hw, n_active++; } - if (vif->type == NL80211_IFTYPE_AP && - n_active > mvm->fw->ucode_capa.num_beacons) - return -EOPNOTSUPP; - else if (n_active > 1) + if (vif->type == NL80211_IFTYPE_AP) { + if (n_active > mvm->fw->ucode_capa.num_beacons) + return -EOPNOTSUPP; + } else if (n_active > 1) { return -EOPNOTSUPP; + } } for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 0bfdf4462755..85a4ce8449ad 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -667,15 +667,15 @@ int iwl_mvm_mld_add_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, ret = iwl_mvm_mld_alloc_sta_links(mvm, vif, sta); if (ret) return ret; - } - spin_lock_init(&mvm_sta->lock); + spin_lock_init(&mvm_sta->lock); - if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) - ret = iwl_mvm_alloc_sta_after_restart(mvm, vif, sta); - else ret = iwl_mvm_sta_init(mvm, vif, sta, IWL_MVM_INVALID_STA, STATION_TYPE_PEER); + } else { + ret = iwl_mvm_alloc_sta_after_restart(mvm, vif, sta); + } + if (ret) goto err; @@ -728,7 +728,7 @@ int iwl_mvm_mld_update_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); struct ieee80211_link_sta *link_sta; unsigned int link_id; - int ret = 0; + int ret = -EINVAL; lockdep_assert_held(&mvm->mutex); @@ -791,8 +791,6 @@ int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, lockdep_assert_held(&mvm->mutex); - kfree(mvm_sta->dup_data); - /* flush its queues here since we are freeing mvm_sta */ for_each_sta_active_link(vif, sta, link_sta, link_id) { struct iwl_mvm_link_sta *mvm_link_sta = diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 6e7470d3a826..9e5008e0e47f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -2347,6 +2347,7 @@ int iwl_mvm_mld_update_sta_keys(struct iwl_mvm *mvm, u32 old_sta_mask, u32 new_sta_mask); +bool iwl_rfi_supported(struct iwl_mvm *mvm); int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_table); struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 6d18a1fd649b..fdf60afb0f3f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -445,6 +445,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp *mcc_resp = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kmemdup(mcc_resp, resp_len, GFP_KERNEL); @@ -456,6 +461,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp_v3 *mcc_resp_v3 = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp_v3->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp_v3, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kzalloc(resp_len, GFP_KERNEL); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index bb77bc9aa821..2ecd32bed752 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2020 - 2021 Intel Corporation + * Copyright (C) 2020 - 2022 Intel Corporation */ #include "mvm.h" @@ -70,6 +70,16 @@ static const struct iwl_rfi_lut_entry iwl_rfi_table[IWL_RFI_LUT_SIZE] = { PHY_BAND_6, PHY_BAND_6,}}, }; +bool iwl_rfi_supported(struct iwl_mvm *mvm) +{ + /* The feature depends on a platform bugfix, so for now + * it's always disabled. + * When the platform support detection is implemented we should + * check FW TLV and platform support instead. + */ + return false; +} + int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_table) { int ret; @@ -81,7 +91,7 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t .len[0] = sizeof(cmd), }; - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) + if (!iwl_rfi_supported(mvm)) return -EOPNOTSUPP; lockdep_assert_held(&mvm->mutex); @@ -113,7 +123,7 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm) .flags = CMD_WANT_SKB, }; - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) + if (!iwl_rfi_supported(mvm)) return ERR_PTR(-EOPNOTSUPP); mutex_lock(&mvm->mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index a4c1e3bf4ff1..23266d0c9ce4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2691,6 +2691,8 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, return; lq_sta = mvm_sta; + + spin_lock(&lq_sta->pers.lock); iwl_mvm_hwrate_to_tx_rate_v1(lq_sta->last_rate_n_flags, info->band, &info->control.rates[0]); info->control.rates[0].count = 1; @@ -2705,6 +2707,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band, &txrc->reported_rate); } + spin_unlock(&lq_sta->pers.lock); } static void *rs_drv_alloc_sta(void *mvm_rate, struct ieee80211_sta *sta, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index e1d02c260e69..6226e4e54a51 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -691,6 +691,11 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) rcu_read_lock(); sta = rcu_dereference(buf->mvm->fw_id_to_mac_id[sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + goto out; + } + mvmsta = iwl_mvm_sta_from_mac80211(sta); /* SN is set to the last expired frame + 1 */ @@ -712,6 +717,8 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) entries[index].e.reorder_time + 1 + RX_REORDER_BUF_TIMEOUT_MQ); } + +out: spin_unlock(&buf->lock); } @@ -2512,7 +2519,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, RCU_INIT_POINTER(mvm->csa_tx_blocked_vif, NULL); /* Unblock BCAST / MCAST station */ iwl_mvm_modify_all_sta_disable_tx(mvm, mvmvif, false); - cancel_delayed_work_sync(&mvm->cs_tx_unblock_dwork); + cancel_delayed_work(&mvm->cs_tx_unblock_dwork); } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 5469d634e289..05a54a69c135 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -281,7 +281,7 @@ static void iwl_mvm_rx_agg_session_expired(struct timer_list *t) * A-MDPU and hence the timer continues to run. Then, the * timer expires and sta is NULL. */ - if (!sta) + if (IS_ERR_OR_NULL(sta)) goto unlock; mvm_sta = iwl_mvm_sta_from_mac80211(sta); @@ -2089,9 +2089,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, lockdep_assert_held(&mvm->mutex); - if (iwl_mvm_has_new_rx_api(mvm)) - kfree(mvm_sta->dup_data); - ret = iwl_mvm_drain_sta(mvm, mvm_sta, true); if (ret) return ret; @@ -3785,6 +3782,9 @@ static inline u8 *iwl_mvm_get_mac_addr(struct iwl_mvm *mvm, u8 sta_id = mvmvif->deflink.ap_sta_id; sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id], lockdep_is_held(&mvm->mutex)); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) + return NULL; + return sta->addr; } @@ -3822,6 +3822,11 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm, if (keyconf->cipher == WLAN_CIPHER_SUITE_TKIP) { addr = iwl_mvm_get_mac_addr(mvm, vif, sta); + if (!addr) { + IWL_ERR(mvm, "Failed to find mac address\n"); + return -EINVAL; + } + /* get phase 1 key from mac80211 */ ieee80211_get_key_rx_seq(keyconf, 0, &seq); ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 10d7178f1071..00719e130438 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1875,7 +1875,7 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, mvmsta = iwl_mvm_sta_from_staid_rcu(mvm, sta_id); sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); - if (WARN_ON_ONCE(!sta || !sta->wme)) { + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta) || !sta->wme)) { rcu_read_unlock(); return; } diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h index a5ec0f631385..fabf637bdf7f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h @@ -173,7 +173,7 @@ enum { #define MT_TXS5_MPDU_TX_CNT GENMASK(31, 23) #define MT_TXS6_MPDU_FAIL_CNT GENMASK(31, 23) - +#define MT_TXS7_MPDU_RETRY_BYTE GENMASK(22, 0) #define MT_TXS7_MPDU_RETRY_CNT GENMASK(31, 23) /* RXD DW0 */ diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index ee0fbfcd07d6..d39a3cc5e381 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -608,7 +608,8 @@ bool mt76_connac2_mac_fill_txs(struct mt76_dev *dev, struct mt76_wcid *wcid, /* PPDU based reporting */ if (FIELD_GET(MT_TXS0_TXS_FORMAT, txs) > 1) { stats->tx_bytes += - le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE); + le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE) - + le32_get_bits(txs_data[7], MT_TXS7_MPDU_RETRY_BYTE); stats->tx_packets += le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_CNT); stats->tx_failed += diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 130eb7b4fd91..39a4a73ef8e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1088,7 +1088,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, else if (beacon && mvif->beacon_rates_idx) idx = mvif->beacon_rates_idx; - txwi[6] |= FIELD_PREP(MT_TXD6_TX_RATE, idx); + txwi[6] |= cpu_to_le32(FIELD_PREP(MT_TXD6_TX_RATE, idx)); txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE); } } diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index 8eafbf1cee71..808c1c895113 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1803,6 +1803,7 @@ struct rtl8xxxu_priv { u32 rege9c; u32 regeb4; u32 regebc; + u32 regrcr; int next_mbox; int nr_out_eps; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index fd8c8c6d53d6..831639d73657 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -4171,6 +4171,7 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) RCR_ACCEPT_MGMT_FRAME | RCR_HTC_LOC_CTRL | RCR_APPEND_PHYSTAT | RCR_APPEND_ICV | RCR_APPEND_MIC; rtl8xxxu_write32(priv, REG_RCR, val32); + priv->regrcr = val32; if (fops->init_reg_rxfltmap) { /* Accept all data frames */ @@ -6501,7 +6502,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, unsigned int *total_flags, u64 multicast) { struct rtl8xxxu_priv *priv = hw->priv; - u32 rcr = rtl8xxxu_read32(priv, REG_RCR); + u32 rcr = priv->regrcr; dev_dbg(&priv->udev->dev, "%s: changed_flags %08x, total_flags %08x\n", __func__, changed_flags, *total_flags); @@ -6547,6 +6548,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, */ rtl8xxxu_write32(priv, REG_RCR, rcr); + priv->regrcr = rcr; *total_flags &= (FIF_ALLMULTI | FIF_FCSFAIL | FIF_BCN_PRBRESP_PROMISC | FIF_CONTROL | FIF_OTHER_BSS | FIF_PSPOLL | diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index 7aa6edad0d01..a6c024cab7ee 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -918,7 +918,7 @@ static void rtw_ops_sta_rc_update(struct ieee80211_hw *hw, struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv; if (changed & IEEE80211_RC_BW_CHANGED) - rtw_update_sta_info(rtwdev, si, true); + ieee80211_queue_work(rtwdev->hw, &si->rc_work); } const struct ieee80211_ops rtw_ops = { diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 5bf6b4581557..d30a191c9291 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -319,6 +319,17 @@ static u8 rtw_acquire_macid(struct rtw_dev *rtwdev) return mac_id; } +static void rtw_sta_rc_work(struct work_struct *work) +{ + struct rtw_sta_info *si = container_of(work, struct rtw_sta_info, + rc_work); + struct rtw_dev *rtwdev = si->rtwdev; + + mutex_lock(&rtwdev->mutex); + rtw_update_sta_info(rtwdev, si, true); + mutex_unlock(&rtwdev->mutex); +} + int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, struct ieee80211_vif *vif) { @@ -329,12 +340,14 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, if (si->mac_id >= RTW_MAX_MAC_ID_NUM) return -ENOSPC; + si->rtwdev = rtwdev; si->sta = sta; si->vif = vif; si->init_ra_lv = 1; ewma_rssi_init(&si->avg_rssi); for (i = 0; i < ARRAY_SIZE(sta->txq); i++) rtw_txq_init(rtwdev, sta->txq[i]); + INIT_WORK(&si->rc_work, rtw_sta_rc_work); rtw_update_sta_info(rtwdev, si, true); rtw_fw_media_status_report(rtwdev, si->mac_id, true); @@ -353,6 +366,8 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv; int i; + cancel_work_sync(&si->rc_work); + rtw_release_macid(rtwdev, si->mac_id); if (fw_exist) rtw_fw_media_status_report(rtwdev, si->mac_id, false); diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index a563285e90ed..9e841f6991a9 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -743,6 +743,7 @@ struct rtw_txq { DECLARE_EWMA(rssi, 10, 16); struct rtw_sta_info { + struct rtw_dev *rtwdev; struct ieee80211_sta *sta; struct ieee80211_vif *vif; @@ -767,6 +768,8 @@ struct rtw_sta_info { bool use_cfg_mask; struct cfg80211_bitrate_mask *mask; + + struct work_struct rc_work; }; enum rtw_bfee_role { diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c index af0459a79899..06fce7c3adda 100644 --- a/drivers/net/wireless/realtek/rtw88/sdio.c +++ b/drivers/net/wireless/realtek/rtw88/sdio.c @@ -87,11 +87,6 @@ static void rtw_sdio_writew(struct rtw_dev *rtwdev, u16 val, u32 addr, u8 buf[2]; int i; - if (rtw_sdio_use_memcpy_io(rtwdev, addr, 2)) { - sdio_writew(rtwsdio->sdio_func, val, addr, err_ret); - return; - } - *(__le16 *)buf = cpu_to_le16(val); for (i = 0; i < 2; i++) { @@ -125,9 +120,6 @@ static u16 rtw_sdio_readw(struct rtw_dev *rtwdev, u32 addr, int *err_ret) u8 buf[2]; int i; - if (rtw_sdio_use_memcpy_io(rtwdev, addr, 2)) - return sdio_readw(rtwsdio->sdio_func, addr, err_ret); - for (i = 0; i < 2; i++) { buf[i] = sdio_readb(rtwsdio->sdio_func, addr + i, err_ret); if (*err_ret) diff --git a/drivers/net/wireless/realtek/rtw88/usb.h b/drivers/net/wireless/realtek/rtw88/usb.h index 30647f0dd61c..ad1d7955c6a5 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.h +++ b/drivers/net/wireless/realtek/rtw88/usb.h @@ -78,7 +78,7 @@ struct rtw_usb { u8 pipe_interrupt; u8 pipe_in; u8 out_ep[RTW_USB_EP_MAX]; - u8 qsel_to_ep[TX_DESC_QSEL_MAX]; + int qsel_to_ep[TX_DESC_QSEL_MAX]; u8 usb_txagg_num; struct workqueue_struct *txwq, *rxwq; diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index b8019cfc11b2..512de491a064 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -1425,6 +1425,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = { .wde_size4 = {RTW89_WDE_PG_64, 0, 4096,}, /* PCIE 64 */ .wde_size6 = {RTW89_WDE_PG_64, 512, 0,}, + /* 8852B PCIE SCC */ + .wde_size7 = {RTW89_WDE_PG_64, 510, 2,}, /* DLFW */ .wde_size9 = {RTW89_WDE_PG_64, 0, 1024,}, /* 8852C DLFW */ @@ -1449,6 +1451,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = { .wde_qt4 = {0, 0, 0, 0,}, /* PCIE 64 */ .wde_qt6 = {448, 48, 0, 16,}, + /* 8852B PCIE SCC */ + .wde_qt7 = {446, 48, 0, 16,}, /* 8852C DLFW */ .wde_qt17 = {0, 0, 0, 0,}, /* 8852C PCIE SCC */ diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index a8d9847ef0b4..6ba633ccdd03 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -792,6 +792,7 @@ struct rtw89_mac_size_set { const struct rtw89_dle_size wde_size0; const struct rtw89_dle_size wde_size4; const struct rtw89_dle_size wde_size6; + const struct rtw89_dle_size wde_size7; const struct rtw89_dle_size wde_size9; const struct rtw89_dle_size wde_size18; const struct rtw89_dle_size wde_size19; @@ -804,6 +805,7 @@ struct rtw89_mac_size_set { const struct rtw89_wde_quota wde_qt0; const struct rtw89_wde_quota wde_qt4; const struct rtw89_wde_quota wde_qt6; + const struct rtw89_wde_quota wde_qt7; const struct rtw89_wde_quota wde_qt17; const struct rtw89_wde_quota wde_qt18; const struct rtw89_ple_quota ple_qt4; diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c index eaa2ea0586bc..6da1b603a9a9 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c @@ -18,25 +18,25 @@ RTW8852B_FW_BASENAME "-" __stringify(RTW8852B_FW_FORMAT_MAX) ".bin" static const struct rtw89_hfc_ch_cfg rtw8852b_hfc_chcfg_pcie[] = { - {5, 343, grp_0}, /* ACH 0 */ - {5, 343, grp_0}, /* ACH 1 */ - {5, 343, grp_0}, /* ACH 2 */ - {5, 343, grp_0}, /* ACH 3 */ + {5, 341, grp_0}, /* ACH 0 */ + {5, 341, grp_0}, /* ACH 1 */ + {4, 342, grp_0}, /* ACH 2 */ + {4, 342, grp_0}, /* ACH 3 */ {0, 0, grp_0}, /* ACH 4 */ {0, 0, grp_0}, /* ACH 5 */ {0, 0, grp_0}, /* ACH 6 */ {0, 0, grp_0}, /* ACH 7 */ - {4, 344, grp_0}, /* B0MGQ */ - {4, 344, grp_0}, /* B0HIQ */ + {4, 342, grp_0}, /* B0MGQ */ + {4, 342, grp_0}, /* B0HIQ */ {0, 0, grp_0}, /* B1MGQ */ {0, 0, grp_0}, /* B1HIQ */ {40, 0, 0} /* FWCMDQ */ }; static const struct rtw89_hfc_pub_cfg rtw8852b_hfc_pubcfg_pcie = { - 448, /* Group 0 */ + 446, /* Group 0 */ 0, /* Group 1 */ - 448, /* Public Max */ + 446, /* Public Max */ 0 /* WP threshold */ }; @@ -49,13 +49,13 @@ static const struct rtw89_hfc_param_ini rtw8852b_hfc_param_ini_pcie[] = { }; static const struct rtw89_dle_mem rtw8852b_dle_mem_pcie[] = { - [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size6, - &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt6, - &rtw89_mac_size.wde_qt6, &rtw89_mac_size.ple_qt18, + [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size7, + &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt7, + &rtw89_mac_size.wde_qt7, &rtw89_mac_size.ple_qt18, &rtw89_mac_size.ple_qt58}, - [RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size6, - &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt6, - &rtw89_mac_size.wde_qt6, &rtw89_mac_size.ple_qt18, + [RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size7, + &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt7, + &rtw89_mac_size.wde_qt7, &rtw89_mac_size.ple_qt18, &rtw89_mac_size.ple_qt_52b_wow}, [RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &rtw89_mac_size.wde_size9, &rtw89_mac_size.ple_size8, &rtw89_mac_size.wde_qt4, diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 9a8faaf4c6b6..89c7a1420381 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -5964,10 +5964,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) ret = -ENOMEM; goto out_free; } + param.pmsr_capa = pmsr_capa; + ret = parse_pmsr_capa(info->attrs[HWSIM_ATTR_PMSR_SUPPORT], pmsr_capa, info); if (ret) goto out_free; - param.pmsr_capa = pmsr_capa; } ret = mac80211_hwsim_new_radio(info, ¶m); diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index c066b0040a3f..829515a601b3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -565,24 +565,32 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) struct ipc_mux_config mux_cfg; struct iosm_imem *ipc_imem; u8 ctrl_chl_idx = 0; + int ret; ipc_imem = container_of(instance, struct iosm_imem, run_state_worker); if (ipc_imem->phase != IPC_P_RUN) { dev_err(ipc_imem->dev, "Modem link down. Exit run state worker."); - return; + goto err_out; } if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag)) ipc_devlink_deinit(ipc_imem->ipc_devlink); - if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg)) - ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + ret = ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg); + if (ret < 0) + goto err_out; + + ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + if (!ipc_imem->mux) + goto err_out; + + ret = ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); + if (ret < 0) + goto err_ipc_mux_deinit; - ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); - if (ipc_imem->mux) - ipc_imem->mux->wwan = ipc_imem->wwan; + ipc_imem->mux->wwan = ipc_imem->wwan; while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) { if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) { @@ -622,6 +630,13 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) /* Complete all memory stores after setting bit */ smp_mb__after_atomic(); + + return; + +err_ipc_mux_deinit: + ipc_mux_deinit(ipc_imem->mux); +err_out: + ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY_LINK_DOWN); } static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 66b90cc4c346..109cf8930488 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -77,8 +77,8 @@ out: } /* Initialize wwan channel */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type) +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type) { struct ipc_chnl_cfg chnl_cfg = { 0 }; @@ -87,7 +87,7 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* If modem version is invalid (0xffffffff), do not initialize WWAN. */ if (ipc_imem->cp_version == -1) { dev_err(ipc_imem->dev, "invalid CP version"); - return; + return -EIO; } ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels); @@ -104,9 +104,13 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* WWAN registration. */ ipc_imem->wwan = ipc_wwan_init(ipc_imem, ipc_imem->dev); - if (!ipc_imem->wwan) + if (!ipc_imem->wwan) { dev_err(ipc_imem->dev, "failed to register the ipc_wwan interfaces"); + return -ENOMEM; + } + + return 0; } /* Map SKB to DMA for transfer */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index f8afb217d9e2..026c5bd0f999 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -91,9 +91,11 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id, * MUX. * @ipc_imem: Pointer to iosm_imem struct. * @mux_type: Type of mux protocol. + * + * Return: 0 on success and failure value on error */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type); +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type); /** * ipc_imem_sys_devlink_open - Open a Flash/CD Channel link to CP diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 226fc1703e90..91256e005b84 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -45,6 +45,7 @@ #define T7XX_PCI_IREG_BASE 0 #define T7XX_PCI_EREG_BASE 2 +#define T7XX_INIT_TIMEOUT 20 #define PM_SLEEP_DIS_TIMEOUT_MS 20 #define PM_ACK_TIMEOUT_MS 1500 #define PM_AUTOSUSPEND_MS 20000 @@ -96,6 +97,7 @@ static int t7xx_pci_pm_init(struct t7xx_pci_dev *t7xx_dev) spin_lock_init(&t7xx_dev->md_pm_lock); init_completion(&t7xx_dev->sleep_lock_acquire); init_completion(&t7xx_dev->pm_sr_ack); + init_completion(&t7xx_dev->init_done); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_INIT); device_init_wakeup(&pdev->dev, true); @@ -124,6 +126,7 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); + complete_all(&t7xx_dev->init_done); } static int t7xx_pci_pm_reinit(struct t7xx_pci_dev *t7xx_dev) @@ -529,6 +532,20 @@ static void t7xx_pci_shutdown(struct pci_dev *pdev) __t7xx_pci_pm_suspend(pdev); } +static int t7xx_pci_pm_prepare(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct t7xx_pci_dev *t7xx_dev; + + t7xx_dev = pci_get_drvdata(pdev); + if (!wait_for_completion_timeout(&t7xx_dev->init_done, T7XX_INIT_TIMEOUT * HZ)) { + dev_warn(dev, "Not ready for system sleep.\n"); + return -ETIMEDOUT; + } + + return 0; +} + static int t7xx_pci_pm_suspend(struct device *dev) { return __t7xx_pci_pm_suspend(to_pci_dev(dev)); @@ -555,6 +572,7 @@ static int t7xx_pci_pm_runtime_resume(struct device *dev) } static const struct dev_pm_ops t7xx_pci_pm_ops = { + .prepare = t7xx_pci_pm_prepare, .suspend = t7xx_pci_pm_suspend, .resume = t7xx_pci_pm_resume, .resume_noirq = t7xx_pci_pm_resume_noirq, diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index 112efa534eac..f08f1ab74469 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -69,6 +69,7 @@ struct t7xx_pci_dev { struct t7xx_modem *md; struct t7xx_ccmni_ctrl *ccmni_ctlb; bool rgu_pci_irq_en; + struct completion init_done; /* Low Power Items */ struct list_head md_pm_entities; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ccb6eb1282f8..1f0cbb77b249 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3585,6 +3585,9 @@ static ssize_t nvme_sysfs_delete(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + if (device_remove_file_self(dev, attr)) nvme_delete_ctrl_sync(ctrl); return count; @@ -5045,7 +5048,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) * that were missed. We identify persistent discovery controllers by * checking that they started once before, hence are reconnecting back. */ - if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && nvme_discovery_ctrl(ctrl)) nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); @@ -5056,6 +5059,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) } nvme_change_uevent(ctrl, "NVME_EVENT=connected"); + set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); } EXPORT_SYMBOL_GPL(nvme_start_ctrl); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 9e6e56c20ec9..316f3e4ca7cc 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -163,7 +163,9 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log->temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1] && + !(data->ctrl->quirks & + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH))) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 9171452e2f6d..2bc159a318ff 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -884,7 +884,6 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) return; - blk_mark_disk_dead(head->disk); /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bf46f122e9e1..a2d4f59e0535 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -149,6 +149,11 @@ enum nvme_quirks { * Reports garbage in the namespace identifiers (eui64, nguid, uuid). */ NVME_QUIRK_BOGUS_NID = (1 << 18), + + /* + * No temperature thresholds for channels other than 0 (Composite). + */ + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 7f25c0fe3a0b..32244582fdb0 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2956,7 +2956,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, * over a single page. */ dev->ctrl.max_hw_sectors = min_t(u32, - NVME_MAX_KB_SZ << 1, dma_max_mapping_size(&pdev->dev) >> 9); + NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9); dev->ctrl.max_segments = NVME_MAX_SEGS; /* @@ -3402,6 +3402,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x2646, 0x5013), /* Kingston KC3000, Kingston FURY Renegade */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x2646, 0x5018), /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x2646, 0x5016), /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */ @@ -3441,6 +3443,10 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x10ec, 0x5763), /* TEAMGROUP T-FORCE CARDEA ZERO Z330 SSD */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x10ec, 0x5765), /* TEAMGROUP MP33 2TB SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index ade1369fe5ed..113c509bf6d0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -127,6 +127,8 @@ static int prepare_itcw(struct itcw *, unsigned int, unsigned int, int, struct dasd_device *, struct dasd_device *, unsigned int, int, unsigned int, unsigned int, unsigned int, unsigned int); +static int dasd_eckd_query_pprc_status(struct dasd_device *, + struct dasd_pprc_data_sc4 *); /* initial attempt at a probe function. this can be simplified once * the other detection code is gone */ @@ -3733,6 +3735,26 @@ static int count_exts(unsigned int from, unsigned int to, int trks_per_ext) return count; } +static int dasd_in_copy_relation(struct dasd_device *device) +{ + struct dasd_pprc_data_sc4 *temp; + int rc; + + if (!dasd_eckd_pprc_enabled(device)) + return 0; + + temp = kzalloc(sizeof(*temp), GFP_KERNEL); + if (!temp) + return -ENOMEM; + + rc = dasd_eckd_query_pprc_status(device, temp); + if (!rc) + rc = temp->dev_info[0].state; + + kfree(temp); + return rc; +} + /* * Release allocated space for a given range or an entire volume. */ @@ -3749,6 +3771,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, int cur_to_trk, cur_from_trk; struct dasd_ccw_req *cqr; u32 beg_cyl, end_cyl; + int copy_relation; struct ccw1 *ccw; int trks_per_ext; size_t ras_size; @@ -3760,6 +3783,10 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, if (dasd_eckd_ras_sanity_checks(device, first_trk, last_trk)) return ERR_PTR(-EINVAL); + copy_relation = dasd_in_copy_relation(device); + if (copy_relation < 0) + return ERR_PTR(copy_relation); + rq = req ? blk_mq_rq_to_pdu(req) : NULL; features = &private->features; @@ -3788,9 +3815,11 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, /* * This bit guarantees initialisation of tracks within an extent that is * not fully specified, but is only supported with a certain feature - * subset. + * subset and for devices not in a copy relation. */ - ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); + if (features->feature[56] & 0x01 && !copy_relation) + ras_data->op_flags.guarantee_init = 1; + ras_data->lss = private->conf.ned->ID; ras_data->dev_addr = private->conf.ned->unit_addr; ras_data->nr_exts = nr_exts; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 8eb089b99cde..d5c43e9b5128 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1111,6 +1111,8 @@ static void io_subchannel_verify(struct subchannel *sch) cdev = sch_get_cdev(sch); if (cdev) dev_fsm_event(cdev, DEV_EVENT_VERIFY); + else + css_schedule_eval(sch->schid); } static void io_subchannel_terminate_path(struct subchannel *sch, u8 mask) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 5ea6249d8180..641f0dbb65a9 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -95,7 +95,7 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, " lgr 1,%[token]\n" " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) - : [state] "d" ((unsigned long)state), [token] "d" (token) + : [state] "a" ((unsigned long)state), [token] "d" (token) : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 5a05d1cdfec2..a8def50c149b 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1293,6 +1293,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return PTR_ERR(kkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1426,6 +1427,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1552,6 +1554,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, protkey, &protkeylen); DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) { kfree(protkey); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..0226c9279cef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1463,6 +1463,8 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) struct Scsi_Host *host = cmd->device->host; int rtn = 0; + atomic_inc(&cmd->device->iorequest_cnt); + /* check if the device is still usable */ if (unlikely(cmd->device->sdev_state == SDEV_DEL)) { /* in SDEV_DEL we error all commands. DID_NO_CONNECT @@ -1483,6 +1485,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) */ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, "queuecommand : device blocked\n")); + atomic_dec(&cmd->device->iorequest_cnt); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1515,6 +1518,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) trace_scsi_dispatch_cmd_start(cmd); rtn = host->hostt->queuecommand(host, cmd); if (rtn) { + atomic_dec(&cmd->device->iorequest_cnt); trace_scsi_dispatch_cmd_error(cmd, rtn); if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && rtn != SCSI_MLQUEUE_TARGET_BUSY) @@ -1761,7 +1765,6 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, goto out_dec_host_busy; } - atomic_inc(&cmd->device->iorequest_cnt); return BLK_STS_OK; out_dec_host_busy: diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d9ce379c4d2e..e6bc622954cf 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1780,7 +1780,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; - payload_sz = sizeof(cmd_request->mpb); + payload_sz = 0; if (scsi_sg_count(scmnd)) { unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset); @@ -1789,10 +1789,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) unsigned long hvpfn, hvpfns_to_add; int j, i = 0, sg_count; - if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { + payload_sz = (hvpg_count * sizeof(u64) + + sizeof(struct vmbus_packet_mpb_array)); - payload_sz = (hvpg_count * sizeof(u64) + - sizeof(struct vmbus_packet_mpb_array)); + if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { payload = kzalloc(payload_sz, GFP_ATOMIC); if (!payload) return SCSI_MLQUEUE_DEVICE_BUSY; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index d76e923fbc6a..c0aee5dc5237 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -54,6 +54,21 @@ static int ring_interrupt_index(const struct tb_ring *ring) return bit; } +static void nhi_mask_interrupt(struct tb_nhi *nhi, int mask, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + return; + iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); +} + +static void nhi_clear_interrupt(struct tb_nhi *nhi, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + ring); + else + iowrite32(~0, nhi->iobase + REG_RING_INT_CLEAR + ring); +} + /* * ring_interrupt_active() - activate/deactivate interrupts for a single ring * @@ -61,8 +76,8 @@ static int ring_interrupt_index(const struct tb_ring *ring) */ static void ring_interrupt_active(struct tb_ring *ring, bool active) { - int reg = REG_RING_INTERRUPT_BASE + - ring_interrupt_index(ring) / 32 * 4; + int index = ring_interrupt_index(ring) / 32 * 4; + int reg = REG_RING_INTERRUPT_BASE + index; int interrupt_bit = ring_interrupt_index(ring) & 31; int mask = 1 << interrupt_bit; u32 old, new; @@ -123,7 +138,11 @@ static void ring_interrupt_active(struct tb_ring *ring, bool active) "interrupt for %s %d is already %s\n", RING_TYPE(ring), ring->hop, active ? "enabled" : "disabled"); - iowrite32(new, ring->nhi->iobase + reg); + + if (active) + iowrite32(new, ring->nhi->iobase + reg); + else + nhi_mask_interrupt(ring->nhi, mask, index); } /* @@ -136,11 +155,11 @@ static void nhi_disable_interrupts(struct tb_nhi *nhi) int i = 0; /* disable interrupts */ for (i = 0; i < RING_INTERRUPT_REG_COUNT(nhi); i++) - iowrite32(0, nhi->iobase + REG_RING_INTERRUPT_BASE + 4 * i); + nhi_mask_interrupt(nhi, ~0, 4 * i); /* clear interrupt status bits */ for (i = 0; i < RING_NOTIFY_REG_COUNT(nhi); i++) - ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + 4 * i); + nhi_clear_interrupt(nhi, 4 * i); } /* ring helper methods */ diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index faef165a919c..6ba295815477 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -93,6 +93,8 @@ struct ring_desc { #define REG_RING_INTERRUPT_BASE 0x38200 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32) +#define REG_RING_INTERRUPT_MASK_CLEAR_BASE 0x38208 + #define REG_INT_THROTTLING_RATE 0x38c00 /* Interrupt Vector Allocation */ diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index f801b1f5b46c..af0e1c070187 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1012,7 +1012,7 @@ static int brcmuart_probe(struct platform_device *pdev) of_property_read_u32(np, "clock-frequency", &clk_rate); /* See if a Baud clock has been specified */ - baud_mux_clk = of_clk_get_by_name(np, "sw_baud"); + baud_mux_clk = devm_clk_get(dev, "sw_baud"); if (IS_ERR(baud_mux_clk)) { if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; @@ -1032,7 +1032,7 @@ static int brcmuart_probe(struct platform_device *pdev) if (clk_rate == 0) { dev_err(dev, "clock-frequency or clk not defined\n"); ret = -EINVAL; - goto release_dma; + goto err_clk_disable; } dev_dbg(dev, "DMA is %senabled\n", priv->dma_enabled ? "" : "not "); @@ -1119,6 +1119,8 @@ err1: serial8250_unregister_port(priv->line); err: brcmuart_free_bufs(dev, priv); +err_clk_disable: + clk_disable_unprepare(baud_mux_clk); release_dma: if (priv->dma_enabled) brcmuart_arbitration(priv, 0); @@ -1133,6 +1135,7 @@ static int brcmuart_remove(struct platform_device *pdev) hrtimer_cancel(&priv->hrt); serial8250_unregister_port(priv->line); brcmuart_free_bufs(&pdev->dev, priv); + clk_disable_unprepare(priv->baud_mux_clk); if (priv->dma_enabled) brcmuart_arbitration(priv, 0); return 0; diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 64770c62bbec..b406cba10b0e 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,9 +40,13 @@ #define PCI_DEVICE_ID_COMMTECH_4224PCIE 0x0020 #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_SUBDEVICE_ID_USR_2980 0x0128 +#define PCI_SUBDEVICE_ID_USR_2981 0x0129 + #define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 #define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 #define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 @@ -829,6 +833,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { (kernel_ulong_t)&bd \ } +#define USR_DEVICE(devid, sdevid, bd) { \ + PCI_DEVICE_SUB( \ + PCI_VENDOR_ID_USR, \ + PCI_DEVICE_ID_EXAR_##devid, \ + PCI_VENDOR_ID_EXAR, \ + PCI_SUBDEVICE_ID_USR_##sdevid), 0, 0, \ + (kernel_ulong_t)&bd \ + } + static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), @@ -853,6 +866,10 @@ static const struct pci_device_id exar_pci_tbl[] = { IBM_DEVICE(XR17C152, SATURN_SERIAL_ONE_PORT, pbn_exar_ibm_saturn), + /* USRobotics USR298x-OEM PCI Modems */ + USR_DEVICE(XR17C152, 2980, pbn_exar_XR17C15x), + USR_DEVICE(XR17C152, 2981, pbn_exar_XR17C15x), + /* Exar Corp. XR17C15[248] Dual/Quad/Octal UART */ EXAR_DEVICE(EXAR, XR17C152, pbn_exar_XR17C15x), EXAR_DEVICE(EXAR, XR17C154, pbn_exar_XR17C15x), diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index c55be6fda0ca..e80c4f6551a1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1920,6 +1920,8 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_SUBDEVICE_ID_SIIG_DUAL_30 0x2530 #define PCI_VENDOR_ID_ADVANTECH 0x13fe #define PCI_DEVICE_ID_INTEL_CE4100_UART 0x2e66 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600 0x1600 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600_1611 0x1611 #define PCI_DEVICE_ID_ADVANTECH_PCI3620 0x3620 #define PCI_DEVICE_ID_ADVANTECH_PCI3618 0x3618 #define PCI_DEVICE_ID_ADVANTECH_PCIf618 0xf618 @@ -4085,6 +4087,9 @@ static SIMPLE_DEV_PM_OPS(pciserial_pm_ops, pciserial_suspend_one, pciserial_resume_one); static const struct pci_device_id serial_pci_tbl[] = { + { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI1600, + PCI_DEVICE_ID_ADVANTECH_PCI1600_1611, PCI_ANY_ID, 0, 0, + pbn_b0_4_921600 }, /* Advantech use PCI_DEVICE_ID_ADVANTECH_PCI3620 (0x3620) as 'PCI_SUBVENDOR_ID' */ { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI3620, PCI_DEVICE_ID_ADVANTECH_PCI3620, 0x0001, 0, 0, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fe8d79c4ae95..c153ba3a018a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -669,6 +669,7 @@ EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port + * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c index 59e25f2b6632..4b2512eef577 100644 --- a/drivers/tty/serial/arc_uart.c +++ b/drivers/tty/serial/arc_uart.c @@ -606,10 +606,11 @@ static int arc_serial_probe(struct platform_device *pdev) } uart->baud = val; - port->membase = of_iomap(np, 0); - if (!port->membase) + port->membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(port->membase)) { /* No point of dev_err since UART itself is hosed here */ - return -ENXIO; + return PTR_ERR(port->membase); + } port->irq = irq_of_parse_and_map(np, 0); diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 08dc3e2a729c..8582479f0211 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1664,19 +1664,18 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) uport->private_data = &port->private_data; platform_set_drvdata(pdev, port); - ret = uart_add_one_port(drv, uport); - if (ret) - return ret; - irq_set_status_flags(uport->irq, IRQ_NOAUTOEN); ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr, IRQF_TRIGGER_HIGH, port->name, uport); if (ret) { dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret); - uart_remove_one_port(drv, uport); return ret; } + ret = uart_add_one_port(drv, uport); + if (ret) + return ret; + /* * Set pm_runtime status as ACTIVE so that wakeup_irq gets * enabled/disabled from dev_pm_arm_wake_irq during system diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 498ba9c0ee93..829c4be66f3b 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -656,10 +656,17 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) } } - /* The vcs_size might have changed while we slept to grab - * the user buffer, so recheck. + /* The vc might have been freed or vcs_size might have changed + * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ + vc = vcs_vc(inode, &viewed); + if (!vc) { + if (written) + break; + ret = -ENXIO; + goto unlock_out; + } size = vcs_size(vc, attr, false); if (size < 0) { if (written) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 202ff71e1b58..51b3c6ae781d 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -150,7 +150,8 @@ static int ufshcd_mcq_config_nr_queues(struct ufs_hba *hba) u32 hba_maxq, rem, tot_queues; struct Scsi_Host *host = hba->host; - hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities); + /* maxq is 0 based value */ + hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities) + 1; tot_queues = UFS_MCQ_NUM_DEV_CMD_QUEUES + read_queues + poll_queues + rw_queues; @@ -265,7 +266,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof(struct utp_transfer_cmd_desc)); + return div_u64(addr, ufshcd_get_ucd_size(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 45fd374fe56c..e7e79f515e14 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2849,10 +2849,10 @@ static void ufshcd_map_queues(struct Scsi_Host *shost) static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) { struct utp_transfer_cmd_desc *cmd_descp = (void *)hba->ucdl_base_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); u16 response_offset = offsetof(struct utp_transfer_cmd_desc, response_upiu); u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); @@ -3761,7 +3761,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) size_t utmrdl_size, utrdl_size, ucdl_size; /* Allocate memory for UTP command descriptors */ - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * hba->nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * hba->nutrs; hba->ucdl_base_addr = dmam_alloc_coherent(hba->dev, ucdl_size, &hba->ucdl_dma_addr, @@ -3861,7 +3861,7 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); - cmd_desc_size = sizeof_utp_transfer_cmd_desc(hba); + cmd_desc_size = ufshcd_get_ucd_size(hba); cmd_desc_dma_addr = hba->ucdl_dma_addr; for (i = 0; i < hba->nutrs; i++) { @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof(struct utp_transfer_cmd_desc) * nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 4bb6d304eb4b..311007b1d904 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1928,6 +1928,8 @@ static int usbtmc_ioctl_request(struct usbtmc_device_data *data, if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + if (request.req.wLength == 0) /* Length-0 requests are never IN */ + request.req.bRequestType &= ~USB_DIR_IN; is_in = request.req.bRequestType & USB_DIR_IN; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 0beaab932e7d..7b2ce013cc5b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1137,7 +1137,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_set_incr_burst_type(dwc); - dwc3_phy_power_on(dwc); + ret = dwc3_phy_power_on(dwc); if (ret) goto err_exit_phy; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index d56457c02996..1f043c31a096 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1116,6 +1116,7 @@ struct dwc3_scratchpad_array { * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. * @wakeup_configured: set if the device is configured for remote wakeup. + * @suspended: set to track suspend event due to U3/L2. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1332,6 +1333,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; unsigned wakeup_configured:1; + unsigned suspended:1; u16 imod_interval; diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index e4a2560b9dc0..ebf03468fac4 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -332,6 +332,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -350,6 +355,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -395,6 +402,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -414,6 +426,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -463,6 +477,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -493,6 +512,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -509,6 +530,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -526,10 +548,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -548,12 +576,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -566,6 +600,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -584,6 +620,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -603,10 +640,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -616,12 +658,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -645,6 +690,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -657,6 +707,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -667,6 +719,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -679,6 +736,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -688,12 +747,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -703,12 +769,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -718,12 +791,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -733,12 +813,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -748,12 +835,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -798,6 +892,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -827,6 +926,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -839,6 +940,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -851,6 +957,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -910,6 +1018,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->debug_root = root; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c0ca4d12f95d..d831f5acf7b5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2440,6 +2440,7 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) return -EINVAL; } dwc3_resume_gadget(dwc); + dwc->suspended = false; dwc->link_state = DWC3_LINK_STATE_U0; } @@ -2699,6 +2700,21 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) return ret; } +static int dwc3_gadget_soft_connect(struct dwc3 *dwc) +{ + /* + * In the Synopsys DWC_usb31 1.90a programming guide section + * 4.1.9, it specifies that for a reconnect after a + * device-initiated disconnect requires a core soft reset + * (DCTL.CSftRst) before enabling the run/stop bit. + */ + dwc3_core_soft_reset(dwc); + + dwc3_event_buffers_setup(dwc); + __dwc3_gadget_start(dwc); + return dwc3_gadget_run_stop(dwc, true); +} + static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -2737,21 +2753,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) synchronize_irq(dwc->irq_gadget); - if (!is_on) { + if (!is_on) ret = dwc3_gadget_soft_disconnect(dwc); - } else { - /* - * In the Synopsys DWC_usb31 1.90a programming guide section - * 4.1.9, it specifies that for a reconnect after a - * device-initiated disconnect requires a core soft reset - * (DCTL.CSftRst) before enabling the run/stop bit. - */ - dwc3_core_soft_reset(dwc); - - dwc3_event_buffers_setup(dwc); - __dwc3_gadget_start(dwc); - ret = dwc3_gadget_run_stop(dwc, true); - } + else + ret = dwc3_gadget_soft_connect(dwc); pm_runtime_put(dwc->dev); @@ -3938,6 +3943,8 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) { int reg; + dwc->suspended = false; + dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RX_DET); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -3962,6 +3969,8 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) { u32 reg; + dwc->suspended = false; + /* * Ideally, dwc3_reset_gadget() would trigger the function * drivers to stop any active transfers through ep disable. @@ -4180,6 +4189,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc, unsigned int evtinfo) { + dwc->suspended = false; + /* * TODO take core out of low power mode when that's * implemented. @@ -4277,6 +4288,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, if (dwc->gadget->wakeup_armed) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); + dwc->suspended = false; } break; case DWC3_LINK_STATE_U1: @@ -4303,8 +4315,10 @@ static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; - if (dwc->link_state != next && next == DWC3_LINK_STATE_U3) + if (!dwc->suspended && next == DWC3_LINK_STATE_U3) { + dwc->suspended = true; dwc3_suspend_gadget(dwc); + } dwc->link_state = next; } @@ -4655,42 +4669,39 @@ void dwc3_gadget_exit(struct dwc3 *dwc) int dwc3_gadget_suspend(struct dwc3 *dwc) { unsigned long flags; + int ret; if (!dwc->gadget_driver) return 0; - dwc3_gadget_run_stop(dwc, false); + ret = dwc3_gadget_soft_disconnect(dwc); + if (ret) + goto err; spin_lock_irqsave(&dwc->lock, flags); dwc3_disconnect_gadget(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; + +err: + /* + * Attempt to reset the controller's state. Likely no + * communication can be established until the host + * performs a port reset. + */ + if (dwc->softconnect) + dwc3_gadget_soft_connect(dwc); + + return ret; } int dwc3_gadget_resume(struct dwc3 *dwc) { - int ret; - if (!dwc->gadget_driver || !dwc->softconnect) return 0; - ret = __dwc3_gadget_start(dwc); - if (ret < 0) - goto err0; - - ret = dwc3_gadget_run_stop(dwc, true); - if (ret < 0) - goto err1; - - return 0; - -err1: - __dwc3_gadget_stop(dwc); - -err0: - return ret; + return dwc3_gadget_soft_connect(dwc); } void dwc3_gadget_process_pending_events(struct dwc3 *dwc) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 6956ad8ba8dd..a366abb45623 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> +#include <linux/string_helpers.h> #include <linux/usb/composite.h> #include "u_ether.h" @@ -965,6 +966,8 @@ int gether_get_host_addr_cdc(struct net_device *net, char *host_addr, int len) dev = netdev_priv(net); snprintf(host_addr, len, "%pm", dev->host_mac); + string_upper(host_addr, host_addr); + return strlen(host_addr); } EXPORT_SYMBOL_GPL(gether_get_host_addr_cdc); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 4641153e9706..52e6d2e84e35 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,10 +37,6 @@ static const struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. - * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related - * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked, - * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are - * called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -52,7 +48,6 @@ struct usb_udc { struct list_head list; bool vbus; bool started; - struct mutex connect_lock; }; static struct class *udc_class; @@ -692,9 +687,17 @@ out: } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */ -static int usb_gadget_connect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) { int ret = 0; @@ -703,15 +706,10 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->connected) - goto out; - - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. - * - * udc first needs to be started before gadget can be pulled up. */ gadget->connected = true; goto out; @@ -726,32 +724,22 @@ out: return ret; } +EXPORT_SYMBOL_GPL(usb_gadget_connect); /** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Following a successful disconnect, invoke the ->disconnect() callback + * for the current gadget driver so that UDC drivers don't need to. * * Returns zero on success, else negative errno. */ -int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_connect); - -/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */ -static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +int usb_gadget_disconnect(struct usb_gadget *gadget) { int ret = 0; @@ -763,12 +751,10 @@ static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) if (!gadget->connected) goto out; - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. - * - * udc should have been started before gadget being pulled down. */ gadget->connected = false; goto out; @@ -788,30 +774,6 @@ out: return ret; } - -/** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. - * - * Following a successful disconnect, invoke the ->disconnect() callback - * for the current gadget driver so that UDC drivers don't need to. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_disconnect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_disconnect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** @@ -832,11 +794,10 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) if (gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); if (gadget->connected) { - ret = usb_gadget_disconnect_locked(gadget); + ret = usb_gadget_disconnect(gadget); if (ret) - goto unlock; + goto out; /* * If gadget was being connected before deactivation, we want @@ -846,8 +807,6 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; -unlock: - mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_deactivate(gadget, ret); @@ -871,7 +830,6 @@ int usb_gadget_activate(struct usb_gadget *gadget) if (!gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); gadget->deactivated = false; /* @@ -879,8 +837,7 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); + ret = usb_gadget_connect(gadget); out: trace_usb_gadget_activate(gadget, ret); @@ -1121,13 +1078,12 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -/* Acquire connect_lock before calling this function. */ -static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) +static void usb_udc_connect_control(struct usb_udc *udc) { - if (udc->vbus && udc->started) - usb_gadget_connect_locked(udc->gadget); + if (udc->vbus) + usb_gadget_connect(udc->gadget); else - usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_disconnect(udc->gadget); } /** @@ -1143,12 +1099,10 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; - mutex_lock(&udc->connect_lock); if (udc) { udc->vbus = status; - usb_udc_connect_control_locked(udc); + usb_udc_connect_control(udc); } - mutex_unlock(&udc->connect_lock); } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1170,7 +1124,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start_locked - tells usb device controller to start up + * usb_gadget_udc_start - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1181,11 +1135,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. - * - * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline int usb_gadget_udc_start(struct usb_udc *udc) { int ret; @@ -1202,7 +1153,7 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) } /** - * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1211,11 +1162,8 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. - * - * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline void usb_gadget_udc_stop(struct usb_udc *udc) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1374,7 +1322,6 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; - mutex_init(&udc->connect_lock); udc->started = false; @@ -1576,15 +1523,11 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - mutex_lock(&udc->connect_lock); - ret = usb_gadget_udc_start_locked(udc); - if (ret) { - mutex_unlock(&udc->connect_lock); + ret = usb_gadget_udc_start(udc); + if (ret) goto err_start; - } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_udc_connect_control(udc); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1615,14 +1558,12 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(gadget); + usb_gadget_disconnect(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_stop(udc); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1708,15 +1649,11 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_udc_start_locked(udc); - usb_gadget_connect_locked(udc->gadget); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_start(udc); + usb_gadget_connect(udc->gadget); } else if (sysfs_streq(buf, "disconnect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(udc->gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_disconnect(udc->gadget); + usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 3592f757fe05..7bd2fddde770 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -119,11 +119,13 @@ static int uhci_pci_init(struct usb_hcd *hcd) uhci->rh_numports = uhci_count_ports(hcd); - /* Intel controllers report the OverCurrent bit active on. - * VIA controllers report it active off, so we'll adjust the - * bit value. (It's not standardized in the UHCI spec.) + /* + * Intel controllers report the OverCurrent bit active on. VIA + * and ZHAOXIN controllers report it active off, so we'll adjust + * the bit value. (It's not standardized in the UHCI spec.) */ - if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA) + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA || + to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) uhci->oc_low = 1; /* HP's server management chip requires a longer port reset delay. */ diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ddb79f23fb3b..79b3691f373f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/acpi.h> #include <linux/reset.h> +#include <linux/suspend.h> #include "xhci.h" #include "xhci-trace.h" @@ -387,7 +388,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI) - xhci->quirks |= XHCI_BROKEN_D3COLD; + xhci->quirks |= XHCI_BROKEN_D3COLD_S2I; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; @@ -801,9 +802,16 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * Systems with the TI redriver that loses port status change events * need to have the registers polled during D3, so avoid D3cold. */ - if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD)) + if (xhci->quirks & XHCI_COMP_MODE_QUIRK) pci_d3cold_disable(pdev); +#ifdef CONFIG_SUSPEND + /* d3cold is broken, but only when s2idle is used */ + if (pm_suspend_target_state == PM_SUSPEND_TO_IDLE && + xhci->quirks & (XHCI_BROKEN_D3COLD_S2I)) + pci_d3cold_disable(pdev); +#endif + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) xhci_pme_quirk(hcd); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 1ad12d5a4857..2bc82b3a2f98 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -276,6 +276,26 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring, trace_xhci_inc_enq(ring); } +static int xhci_num_trbs_to(struct xhci_segment *start_seg, union xhci_trb *start, + struct xhci_segment *end_seg, union xhci_trb *end, + unsigned int num_segs) +{ + union xhci_trb *last_on_seg; + int num = 0; + int i = 0; + + do { + if (start_seg == end_seg && end >= start) + return num + (end - start); + last_on_seg = &start_seg->trbs[TRBS_PER_SEGMENT - 1]; + num += last_on_seg - start; + start_seg = start_seg->next; + start = start_seg->trbs; + } while (i++ <= num_segs); + + return -EINVAL; +} + /* * Check to see if there's room to enqueue num_trbs on the ring and make sure * enqueue pointer will not advance into dequeue segment. See rules above. @@ -2140,6 +2160,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; + int trbs_freed; ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); @@ -2209,9 +2230,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, } /* Update ring dequeue pointer */ + trbs_freed = xhci_num_trbs_to(ep_ring->deq_seg, ep_ring->dequeue, + td->last_trb_seg, td->last_trb, + ep_ring->num_segs); + if (trbs_freed < 0) + xhci_dbg(xhci, "Failed to count freed trbs at TD finish\n"); + else + ep_ring->num_trbs_free += trbs_freed; ep_ring->dequeue = td->last_trb; ep_ring->deq_seg = td->last_trb_seg; - ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); return xhci_td_cleanup(xhci, td, ep_ring, td->status); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 08d721921b7b..6b690ec91ff3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1901,7 +1901,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) -#define XHCI_BROKEN_D3COLD BIT_ULL(41) +#define XHCI_BROKEN_D3COLD_S2I BIT_ULL(41) #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 8931df5a85fd..c54e9805da53 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -406,22 +406,25 @@ static DEF_SCSI_QCMD(queuecommand) ***********************************************************************/ /* Command timeout and abort */ -static int command_abort(struct scsi_cmnd *srb) +static int command_abort_matching(struct us_data *us, struct scsi_cmnd *srb_match) { - struct us_data *us = host_to_us(srb->device->host); - - usb_stor_dbg(us, "%s called\n", __func__); - /* * us->srb together with the TIMED_OUT, RESETTING, and ABORTING * bits are protected by the host lock. */ scsi_lock(us_to_host(us)); - /* Is this command still active? */ - if (us->srb != srb) { + /* is there any active pending command to abort ? */ + if (!us->srb) { scsi_unlock(us_to_host(us)); usb_stor_dbg(us, "-- nothing to abort\n"); + return SUCCESS; + } + + /* Does the command match the passed srb if any ? */ + if (srb_match && us->srb != srb_match) { + scsi_unlock(us_to_host(us)); + usb_stor_dbg(us, "-- pending command mismatch\n"); return FAILED; } @@ -444,6 +447,14 @@ static int command_abort(struct scsi_cmnd *srb) return SUCCESS; } +static int command_abort(struct scsi_cmnd *srb) +{ + struct us_data *us = host_to_us(srb->device->host); + + usb_stor_dbg(us, "%s called\n", __func__); + return command_abort_matching(us, srb); +} + /* * This invokes the transport reset mechanism to reset the state of the * device @@ -455,6 +466,9 @@ static int device_reset(struct scsi_cmnd *srb) usb_stor_dbg(us, "%s called\n", __func__); + /* abort any pending command before reset */ + command_abort_matching(us, NULL); + /* lock the device pointers and do the reset */ mutex_lock(&(us->dev_mutex)); result = us->transport_reset(us); diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 8f3e884222ad..66de880b28d0 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -516,6 +516,10 @@ static ssize_t pin_assignment_show(struct device *dev, mutex_unlock(&dp->lock); + /* get_current_pin_assignments can return 0 when no matching pin assignments are found */ + if (len == 0) + len++; + buf[len - 1] = '\n'; return len; } diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 8b075ca82ef6..438cc40660a1 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -886,6 +886,9 @@ static void tps6598x_remove(struct i2c_client *client) { struct tps6598x *tps = i2c_get_clientdata(client); + if (!client->irq) + cancel_delayed_work_sync(&tps->wq_poll); + tps6598x_disconnect(tps, 0); typec_unregister_port(tps->port); usb_role_switch_put(tps->role_sw); diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 96e91570cdd3..0fdf5f46802c 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -124,7 +124,7 @@ config FB_PROVIDE_GET_FB_UNMAPPED_AREA depends on FB help Allow generic frame-buffer to provide get_fb_unmapped_area - function. + function to provide shareable character device support on nommu. menuconfig FB_FOREIGN_ENDIAN bool "Framebuffer foreign endianness support" diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index b02e4e645035..cba2b113b28b 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3498,11 +3498,6 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info, if (ret) goto atyfb_setup_generic_fail; #endif - if (!(aty_ld_le32(CRTC_GEN_CNTL, par) & CRTC_EXT_DISP_EN)) - par->clk_wr_offset = (inb(R_GENMO) & 0x0CU) >> 2; - else - par->clk_wr_offset = aty_ld_8(CLOCK_CNTL, par) & 0x03U; - /* according to ATI, we should use clock 3 for acelerated mode */ par->clk_wr_offset = 3; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e808dc86001c..28739f1cb5e7 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1468,7 +1468,7 @@ __releases(&info->lock) } #if defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && !defined(CONFIG_MMU) -unsigned long get_fb_unmapped_area(struct file *filp, +static unsigned long get_fb_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { diff --git a/drivers/video/fbdev/i810/i810_dvt.c b/drivers/video/fbdev/i810/i810_dvt.c index b4b3670667ab..2082b5c92e8f 100644 --- a/drivers/video/fbdev/i810/i810_dvt.c +++ b/drivers/video/fbdev/i810/i810_dvt.c @@ -14,6 +14,7 @@ #include "i810_regs.h" #include "i810.h" +#include "i810_main.h" struct mode_registers std_modes[] = { /* 640x480 @ 60Hz */ @@ -276,7 +277,7 @@ void i810fb_fill_var_timings(struct fb_var_screeninfo *var) var->upper_margin = total - (yres + var->lower_margin + var->vsync_len); } -u32 i810_get_watermark(struct fb_var_screeninfo *var, +u32 i810_get_watermark(const struct fb_var_screeninfo *var, struct i810fb_par *par) { struct mode_registers *params = &par->regs; diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c index 1eaa35c27835..477789cff8e0 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c @@ -491,7 +491,8 @@ static int tpo_td043_probe(struct spi_device *spi) ddata->vcc_reg = devm_regulator_get(&spi->dev, "vcc"); if (IS_ERR(ddata->vcc_reg)) { - r = dev_err_probe(&spi->dev, r, "failed to get LCD VCC regulator\n"); + r = dev_err_probe(&spi->dev, PTR_ERR(ddata->vcc_reg), + "failed to get LCD VCC regulator\n"); goto err_regulator; } diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 14c9215284c5..686a234f3899 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -741,7 +741,7 @@ ngleClearOverlayPlanes(struct stifb_info *fb, int mask, int data) packed_len = (fb->info.var.xres << 16) | fb->info.var.yres; NGLE_SET_DSTXY(fb, packed_dst); - /* Write zeroes to overlay planes */ + /* Write zeroes to overlay planes */ NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb, IBOvals(RopSrc, MaskAddrOffset(0), BitmapExtent08, StaticReg(0), @@ -1297,14 +1297,14 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) break; default: #ifdef FALLBACK_TO_1BPP - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- now trying 1bpp mode instead\n", fb->id); bpp = 1; /* default to 1 bpp */ break; #else - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- skipping.\n", fb->id); diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 216d49c9d47e..dabc30a09f96 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -27,6 +27,8 @@ #include <video/udlfb.h> #include "edid.h" +#define OUT_EP_NUM 1 /* The endpoint number we will use */ + static const struct fb_fix_screeninfo dlfb_fix = { .id = "udlfb", .type = FB_TYPE_PACKED_PIXELS, @@ -1541,24 +1543,16 @@ static const struct device_attribute fb_device_attrs[] = { static int dlfb_select_std_channel(struct dlfb_data *dlfb) { int ret; - void *buf; static const u8 set_def_chn[] = { 0x57, 0xCD, 0xDC, 0xA7, 0x1C, 0x88, 0x5E, 0x15, 0x60, 0xFE, 0xC6, 0x97, 0x16, 0x3D, 0x47, 0xF2 }; - buf = kmemdup(set_def_chn, sizeof(set_def_chn), GFP_KERNEL); - - if (!buf) - return -ENOMEM; - - ret = usb_control_msg(dlfb->udev, usb_sndctrlpipe(dlfb->udev, 0), - NR_USB_REQUEST_CHANNEL, + ret = usb_control_msg_send(dlfb->udev, 0, NR_USB_REQUEST_CHANNEL, (USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0, - buf, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT); - - kfree(buf); + &set_def_chn, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT, + GFP_KERNEL); return ret; } @@ -1652,7 +1646,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, struct fb_info *info; int retval; struct usb_device *usbdev = interface_to_usbdev(intf); - struct usb_endpoint_descriptor *out; + static u8 out_ep[] = {OUT_EP_NUM + USB_DIR_OUT, 0}; /* usb initialization */ dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); @@ -1666,9 +1660,9 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb->udev = usb_get_dev(usbdev); usb_set_intfdata(intf, dlfb); - retval = usb_find_common_endpoints(intf->cur_altsetting, NULL, &out, NULL, NULL); - if (retval) { - dev_err(&intf->dev, "Device should have at lease 1 bulk endpoint!\n"); + if (!usb_check_bulk_endpoints(intf, out_ep)) { + dev_err(&intf->dev, "Invalid DisplayLink device!\n"); + retval = -EINVAL; goto error; } @@ -1927,7 +1921,8 @@ retry: } /* urb->transfer_buffer_length set to actual before submit */ - usb_fill_bulk_urb(urb, dlfb->udev, usb_sndbulkpipe(dlfb->udev, 1), + usb_fill_bulk_urb(urb, dlfb->udev, + usb_sndbulkpipe(dlfb->udev, OUT_EP_NUM), buf, size, dlfb_urb_completion, unode); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 29cf00220b09..4c0f22acf53d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3942,7 +3942,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct dentry *dentry; struct ceph_cap *cap; char *path; - int pathlen = 0, err = 0; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3965,6 +3965,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) cap = __get_cap_for_mds(ci, mds); if (!cap) { spin_unlock(&ci->i_ceph_lock); + err = 0; goto out_err; } dout(" adding %p ino %llx.%llx cap %p %lld %s\n", diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 87007203f130..0b236ebd989f 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1111,6 +1111,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 414685c5d530..5f8fd20951af 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -424,8 +424,8 @@ struct smb_version_operations { /* check for STATUS_NETWORK_SESSION_EXPIRED */ bool (*is_session_expired)(char *); /* send oplock break response */ - int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, - struct cifsInodeInfo *); + int (*oplock_response)(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, + __u16 net_fid, struct cifsInodeInfo *cifs_inode); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, struct kstatfs *); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c5fcefdfd797..ba7f2e09d6c8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4881,9 +4881,9 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; - bool purge_cache = false; - struct cifs_deferred_close *dclose; - bool is_deferred = false; + bool purge_cache = false, oplock_break_cancelled; + __u64 persistent_fid, volatile_fid; + __u16 net_fid; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4924,28 +4924,28 @@ oplock_break_ack: * file handles but cached, then schedule deferred close immediately. * So, new open will not use cached handle. */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - spin_unlock(&CIFS_I(inode)->deferred_lock); - if (!CIFS_CACHE_HANDLE(cinode) && is_deferred && - cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { + if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); - } + persistent_fid = cfile->fid.persistent_fid; + volatile_fid = cfile->fid.volatile_fid; + net_fid = cfile->fid.netfid; + oplock_break_cancelled = cfile->oplock_break_cancelled; + + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do * not bother sending an oplock release if session to server still is * disconnected since oplock already released by the server */ - if (!cfile->oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, - cinode); + if (!oplock_break_cancelled) { + rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index abda6148be10..7d1b3fc014d9 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -897,12 +897,11 @@ cifs_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } static int -cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { - return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false, - CIFS_CACHE_READ(cinode) ? 1 : 0); + return CIFSSMBLock(0, tcon, net_fid, current->tgid, 0, 0, 0, 0, + LOCKING_ANDX_OPLOCK_RELEASE, false, CIFS_CACHE_READ(cinode) ? 1 : 0); } static int diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a295e4c2d54e..5065398665f1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2383,15 +2383,14 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) } static int -smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) return SMB2_lease_break(0, tcon, cinode->lease_key, smb2_get_lease_state(cinode)); - return SMB2_oplock_break(0, tcon, fid->persistent_fid, - fid->volatile_fid, + return SMB2_oplock_break(0, tcon, persistent_fid, volatile_fid, CIFS_CACHE_READ(cinode) ? 1 : 0); } diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 4ed379f9b1aa..4882a812ea86 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -351,7 +351,8 @@ int ksmbd_conn_handler_loop(void *p) break; /* 4 for rfc1002 length field */ - size = pdu_size + 4; + /* 1 for implied bcc[0] */ + size = pdu_size + 4 + 1; conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 2e54ded4d92c..6d1ccb999893 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1449,11 +1449,12 @@ struct lease_ctx_info *parse_lease_state(void *open_req) * smb2_find_context_vals() - find a particular context info in open request * @open_req: buffer containing smb2 file open(create) request * @tag: context name to search for + * @tag_len: the length of tag * * Return: pointer to requested context, NULL if @str context not found * or error pointer if name length is invalid. */ -struct create_context *smb2_find_context_vals(void *open_req, const char *tag) +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len) { struct create_context *cc; unsigned int next = 0; @@ -1492,7 +1493,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) return ERR_PTR(-EINVAL); name = (char *)cc + name_off; - if (memcmp(name, tag, name_len) == 0) + if (name_len == tag_len && !memcmp(name, tag, name_len)) return cc; remain_len -= next; diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 09753448f779..4b0fe6da7694 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -118,7 +118,7 @@ void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp); void create_mxac_rsp_buf(char *cc, int maximal_access); void create_disk_id_rsp_buf(char *cc, __u64 file_id, __u64 vol_id); void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp); -struct create_context *smb2_find_context_vals(void *open_req, const char *str); +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len); struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key); int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index fbdde426dd01..0ffe663b7590 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -416,8 +416,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) /* * Allow a message that padded to 8byte boundary. + * Linux 4.19.217 with smb 3.0.2 are sometimes + * sending messages where the cls_len is exactly + * 8 bytes less than len. */ - if (clc_len < len && (len - clc_len) < 8) + if (clc_len < len && (len - clc_len) <= 8) goto validate_credit; pr_err_ratelimited( diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index cb93fd231f4e..717bcd20545b 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1356,7 +1356,7 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, struct authenticate_message *authblob; struct ksmbd_user *user; char *name; - unsigned int auth_msg_len, name_off, name_len, secbuf_len; + unsigned int name_off, name_len, secbuf_len; secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { @@ -1366,9 +1366,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, authblob = user_authblob(conn, req); name_off = le32_to_cpu(authblob->UserName.BufferOffset); name_len = le16_to_cpu(authblob->UserName.Length); - auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len; - if (auth_msg_len < (u64)name_off + name_len) + if (secbuf_len < (u64)name_off + name_len) return NULL; name = smb_strndup_from_utf16((const char *)authblob + name_off, @@ -2464,7 +2463,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, return -ENOENT; /* Parse SD BUFFER create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER, 4); if (!context) return -ENOENT; else if (IS_ERR(context)) @@ -2666,7 +2665,7 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateContextsOffset) { /* Parse non-durable handle create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2686,7 +2685,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST); + SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2697,7 +2696,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_TIMEWARP_REQUEST); + SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2709,7 +2708,7 @@ int smb2_open(struct ksmbd_work *work) if (tcon->posix_extensions) { context = smb2_find_context_vals(req, - SMB2_CREATE_TAG_POSIX); + SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -3107,7 +3106,7 @@ int smb2_open(struct ksmbd_work *work) struct create_alloc_size_req *az_req; az_req = (struct create_alloc_size_req *)smb2_find_context_vals(req, - SMB2_CREATE_ALLOCATION_SIZE); + SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); goto err_out; @@ -3134,7 +3133,7 @@ int smb2_open(struct ksmbd_work *work) err); } - context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID); + context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index bb94949bc223..04ba95b83d16 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -77,9 +77,9 @@ static const unsigned long nlm_grace_period_min = 0; static const unsigned long nlm_grace_period_max = 240; static const unsigned long nlm_timeout_min = 3; static const unsigned long nlm_timeout_max = 20; -static const int nlm_port_min = 0, nlm_port_max = 65535; #ifdef CONFIG_SYSCTL +static const int nlm_port_min = 0, nlm_port_max = 65535; static struct ctl_table_header * nlm_sysctl_table; #endif diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7b8f17ee5224..c159817d1282 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -153,18 +153,6 @@ static int exports_net_open(struct net *net, struct file *file) return 0; } -static int exports_proc_open(struct inode *inode, struct file *file) -{ - return exports_net_open(current->nsproxy->net_ns, file); -} - -static const struct proc_ops exports_proc_ops = { - .proc_open = exports_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); @@ -1458,6 +1446,19 @@ static struct file_system_type nfsd_fs_type = { MODULE_ALIAS_FS("nfsd"); #ifdef CONFIG_PROC_FS + +static int exports_proc_open(struct inode *inode, struct file *file) +{ + return exports_net_open(current->nsproxy->net_ns, file); +} + +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + static int create_proc_exports_entry(void) { struct proc_dir_entry *entry; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 4183819ea082..72a906a053dc 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1365,19 +1365,19 @@ TRACE_EVENT(nfsd_cb_setup, __field(u32, cl_id) __field(unsigned long, authflavor) __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) - __array(unsigned char, netid, 8) + __string(netid, netid) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - strlcpy(__entry->netid, netid, sizeof(__entry->netid)); + __assign_str(netid, netid); __entry->authflavor = authflavor; __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x proto=%s flavor=%s", __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, - __entry->netid, show_nfsd_authflavor(__entry->authflavor)) + __get_str(netid), show_nfsd_authflavor(__entry->authflavor)) ); TRACE_EVENT(nfsd_cb_setup_err, diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1310d2d5feb3..a8ce522ac747 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -917,6 +917,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -929,6 +930,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); diff --git a/fs/statfs.c b/fs/statfs.c index 0ba34c135593..96d1c3edf289 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -130,6 +130,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -158,7 +159,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -171,6 +171,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -182,7 +183,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b441e633f4dd..c0ffe203a602 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1376,8 +1376,6 @@ enum blk_unique_id { BLK_UID_NAA = 3, }; -#define NFL4_UFLG_MASK 0x0000003F - struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 947a60b801db..d7779a18b24f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -12,11 +12,10 @@ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ - && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); - +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9deeaeb457bb..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -74,6 +74,7 @@ struct class { struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; int __must_check class_register(const struct class *class); diff --git a/include/linux/phy.h b/include/linux/phy.h index c5a0dc829714..6478838405a0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1900,10 +1900,8 @@ void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); -#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -#endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24aa159d29a7..fbc4bd423b35 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -176,7 +176,7 @@ extern struct svc_rdma_recv_ctxt * extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); -extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); +extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 867479204840..a6b12631db21 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -23,7 +23,7 @@ struct svc_xprt_ops { int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); - void (*xpo_release_rqst)(struct svc_rqst *); + void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 77693389c3f9..6a1e8f157255 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_SUSPENDED = BIT(8), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2448e98854f..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -443,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index e7c44870f20d..367d5381217b 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,7 +686,10 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected. + * got disconnected). + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_frontend. */ struct dvb_frontend { @@ -704,6 +707,7 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; + struct mutex remove_mutex; }; /** diff --git a/include/media/dvb_net.h b/include/media/dvb_net.h index 9980b1dd750b..4a921ea96091 100644 --- a/include/media/dvb_net.h +++ b/include/media/dvb_net.h @@ -39,6 +39,9 @@ struct net_device; * @exit: flag to indicate when the device is being removed. * @demux: pointer to &struct dmx_demux. * @ioctl_mutex: protect access to this struct. + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_net. * * Currently, the core supports up to %DVB_NET_DEVICES_MAX (10) network * devices. @@ -51,6 +54,7 @@ struct dvb_net { unsigned int exit:1; struct dmx_demux *demux; struct mutex ioctl_mutex; + struct mutex remove_mutex; }; /** diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index 29d25c8a6f13..8958e5e2fc5b 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -194,6 +194,21 @@ struct dvb_device { }; /** + * struct dvbdevfops_node - fops nodes registered in dvbdevfops_list + * + * @fops: Dynamically allocated fops for ->owner registration + * @type: type of dvb_device + * @template: dvb_device used for registration + * @list_head: list_head for dvbdevfops_list + */ +struct dvbdevfops_node { + struct file_operations *fops; + enum dvb_device_type type; + const struct dvb_device *template; + struct list_head list_head; +}; + +/** * dvb_device_get - Increase dvb_device reference * * @dvbdev: pointer to struct dvb_device diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 9fa291a04621..2b12725de9c0 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -497,29 +497,6 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } -/* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock(), or RTNL. - */ -static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) -{ - struct nh_info *nhi; - - if (nh->is_group) { - struct nh_group *nh_grp; - - nh_grp = rcu_dereference_rtnl(nh->nh_grp); - nh = nexthop_mpath_select(nh_grp, 0); - if (!nh) - return NULL; - } - - nhi = rcu_dereference_rtnl(nh->nh_info); - if (nhi->family == AF_INET6) - return &nhi->fib6_nh; - - return NULL; -} - static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/include/sound/hda-mlink.h b/include/sound/hda-mlink.h index dbc47af08135..4f44f0bd5388 100644 --- a/include/sound/hda-mlink.h +++ b/include/sound/hda-mlink.h @@ -44,6 +44,9 @@ int hdac_bus_eml_sdw_power_down_unlocked(struct hdac_bus *bus, int sublink); int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num); +int hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir); + void hda_bus_ml_put_all(struct hdac_bus *bus); void hda_bus_ml_reset_losidv(struct hdac_bus *bus); int hda_bus_ml_resume(struct hdac_bus *bus); @@ -51,6 +54,7 @@ int hda_bus_ml_suspend(struct hdac_bus *bus); struct hdac_ext_link *hdac_bus_eml_ssp_get_hlink(struct hdac_bus *bus); struct hdac_ext_link *hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus); +struct hdac_ext_link *hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus); struct mutex *hdac_bus_eml_get_mutex(struct hdac_bus *bus, bool alt, int elid); @@ -144,6 +148,13 @@ hdac_bus_eml_sdw_power_down_unlocked(struct hdac_bus *bus, int sublink) { return static inline int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num) { return 0; } +static inline int +hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir) +{ + return 0; +} + static inline void hda_bus_ml_put_all(struct hdac_bus *bus) { } static inline void hda_bus_ml_reset_losidv(struct hdac_bus *bus) { } static inline int hda_bus_ml_resume(struct hdac_bus *bus) { return 0; } @@ -155,6 +166,9 @@ hdac_bus_eml_ssp_get_hlink(struct hdac_bus *bus) { return NULL; } static inline struct hdac_ext_link * hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus) { return NULL; } +static inline struct hdac_ext_link * +hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus) { return NULL; } + static inline struct mutex * hdac_bus_eml_get_mutex(struct hdac_bus *bus, bool alt, int elid) { return NULL; } diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index bbc37877aaff..e9ec7e4eb982 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -183,7 +183,7 @@ #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_INTERLEAVING_STYLE 1906 #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_FMT_CFG 1907 #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_SAMPLE_TYPE 1908 -#define SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX 1909 +#define SOF_TKN_CAVS_AUDIO_FORMAT_INPUT_PIN_INDEX 1909 /* intentional token numbering discontinuity, reserved for future use */ #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_RATE 1930 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_BIT_DEPTH 1931 @@ -194,6 +194,7 @@ #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_INTERLEAVING_STYLE 1936 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_FMT_CFG 1937 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_SAMPLE_TYPE 1938 +#define SOF_TKN_CAVS_AUDIO_FORMAT_OUTPUT_PIN_INDEX 1939 /* intentional token numbering discontinuity, reserved for future use */ #define SOF_TKN_CAVS_AUDIO_FORMAT_IBS 1970 #define SOF_TKN_CAVS_AUDIO_FORMAT_OBS 1971 diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..df1d04f7a542 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1133,7 +1133,7 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif -static inline size_t sizeof_utp_transfer_cmd_desc(const struct ufs_hba *hba) +static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); } diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9abb3905bc8e..18d36842faf5 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -17,36 +17,30 @@ struct fprobe_rethook_node { struct rethook_node node; unsigned long entry_ip; + unsigned long entry_parent_ip; char data[]; }; -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct fprobe_rethook_node *fpr; struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret; + int ret = 0; fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } if (fp->exit_handler) { rh = rethook_try_get(fp->rethook); if (!rh) { fp->nmissed++; - goto out; + return; } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; + fpr->entry_parent_ip = parent_ip; if (fp->entry_data_size) entry_data = fpr->data; } @@ -61,23 +55,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, else rethook_hook(rh, ftrace_get_regs(fregs), true); } -out: +} + +static void fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + __fprobe_handler(ip, parent_ip, ops, fregs); ftrace_test_recursion_unlock(bit); + } NOKPROBE_SYMBOL(fprobe_handler); static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - struct fprobe *fp = container_of(ops, struct fprobe, ops); + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions called before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } if (unlikely(kprobe_running())) { fp->nmissed++; return; } + kprobe_busy_begin(); - fprobe_handler(ip, parent_ip, ops, fregs); + __fprobe_handler(ip, parent_ip, ops, fregs); kprobe_busy_end(); + ftrace_test_recursion_unlock(bit); } static void fprobe_exit_handler(struct rethook_node *rh, void *data, @@ -85,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + int bit; if (!fp || fprobe_disabled(fp)) return; fpr = container_of(rh, struct fprobe_rethook_node, node); + /* + * we need to assure no calls to traceable functions in-between the + * end of fprobe_handler and the beginning of fprobe_exit_handler. + */ + bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + fp->exit_handler(fp, fpr->entry_ip, regs, fp->entry_data_size ? (void *)fpr->data : NULL); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(fprobe_exit_handler); diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 32c3dfdb4d6a..60f6cb2b486b 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -288,7 +288,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, * These loops must be protected from rethook_free_rcu() because those * are accessing 'rhn->rethook'. */ - preempt_disable(); + preempt_disable_notrace(); /* * Run the handler on the shadow stack. Do not unlink the list here because @@ -321,7 +321,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, first = first->next; rethook_recycle(rhn); } - preempt_enable(); + preempt_enable_notrace(); return correct_ret_addr; } diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 110a36479dce..8ebc43d4cc8c 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5317,15 +5317,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, mt = mte_node_type(mas->node); pivots = ma_pivots(mas_mn(mas), mt); - if (offset) - mas->min = pivots[offset - 1] + 1; - - if (offset < mt_pivots[mt]) - mas->max = pivots[offset]; - - if (mas->index < mas->min) - mas->index = mas->min; - + min = mas_safe_min(mas, pivots, offset); + if (mas->index < min) + mas->index = min; mas->last = mas->index + size - 1; return 0; } diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2aafc46a4aaf..392fb273e7bd 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -29,7 +29,7 @@ * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ -#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..fe10436d9911 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -237,7 +237,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; @@ -246,14 +247,18 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..6d0cd2840cf0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -805,6 +805,7 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -814,13 +815,13 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 44ddaf5d601e..02f7f414aade 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1331,31 +1331,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); -#ifdef CONFIG_ZPOOL - /* - * Move the zspage to front of pool's LRU. - * - * Note that this is swap-specific, so by definition there are no ongoing - * accesses to the memory while the page is swapped out that would make - * it "hot". A new entry is hot, then ages to the tail until it gets either - * written back or swaps back in. - * - * Furthermore, map is also called during writeback. We must not put an - * isolated page on the LRU mid-reclaim. - * - * As a result, only update the LRU when the page is mapped for write - * when it's first instantiated. - * - * This is a deviation from the other backends, which perform this update - * in the allocation function (zbud_alloc, z3fold_alloc). - */ - if (mm == ZS_MM_WO) { - if (!list_empty(&zspage->lru)) - list_del(&zspage->lru); - list_add(&zspage->lru, &pool->lru); - } -#endif - /* * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls @@ -1525,9 +1500,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1550,6 +1524,14 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); +out: +#ifdef CONFIG_ZPOOL + /* Add/move zspage to beginning of LRU */ + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); +#endif + spin_unlock(&pool->lock); return handle; diff --git a/mm/zswap.c b/mm/zswap.c index e1e621d0b6a0..59da2a415fbb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1020,6 +1020,22 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) goto fail; case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Having a local reference to the zswap entry doesn't exclude + * swapping from invalidating and recycling the swap slot. Once + * the swapcache is secured against concurrent swapping to and + * from the slot, recheck that the entry is still current before + * writing. + */ + spin_lock(&tree->lock); + if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { + spin_unlock(&tree->lock); + delete_from_swap_cache(page_folio(page)); + ret = -ENOMEM; + goto fail; + } + spin_unlock(&tree->lock); + /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 870e4935d6e6..b90781b9ece6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -109,8 +109,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ - if (veth->h_vlan_proto != vlan->vlan_proto || - vlan->flags & VLAN_FLAG_REORDER_HDR) { + if (vlan->flags & VLAN_FLAG_REORDER_HDR || + veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); diff --git a/net/atm/resources.c b/net/atm/resources.c index 2b2d33eeaf20..995d29e7fb13 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -400,6 +400,7 @@ done: return error; } +#ifdef CONFIG_PROC_FS void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&atm_dev_mutex); @@ -415,3 +416,4 @@ void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &atm_devs, pos); } +#endif diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index 2b053289f016..efb096025151 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -27,6 +27,10 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg); +bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *v_last); +int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, + u16 vid, u32 tun_id, bool *changed); #ifdef CONFIG_BRIDGE_VLAN_FILTERING /* br_vlan_tunnel.c */ @@ -43,10 +47,6 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan_group *vg); int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan); -bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *v_last); -int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, - u16 vid, u32 tun_id, bool *changed); #else static inline int vlan_tunnel_init(struct net_bridge_vlan_group *vg) { diff --git a/net/can/isotp.c b/net/can/isotp.c index a750259cb79c..84f9aba02901 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1139,7 +1139,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) + if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 7e90f9e61d9b..1790469b2580 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -798,7 +798,7 @@ static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, struct j1939_sk_buff_cb *skcb; int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE)) + if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (flags & MSG_ERRQUEUE) diff --git a/net/devlink/core.c b/net/devlink/core.c index 777b091ef74d..c23ebabadc52 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -204,11 +204,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (ret < 0) goto err_xa_alloc; - devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier(&devlink->netdevice_nb); - if (ret) - goto err_register_netdevice_notifier; - devlink->dev = dev; devlink->ops = ops; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); @@ -233,8 +228,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, return devlink; -err_register_netdevice_notifier: - xa_erase(&devlinks, devlink->index); err_xa_alloc: kfree(devlink); return NULL; @@ -266,8 +259,6 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->params); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); - xa_erase(&devlinks, devlink->index); devlink_put(devlink); @@ -303,6 +294,10 @@ static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; +static struct notifier_block devlink_port_netdevice_nb = { + .notifier_call = devlink_port_netdevice_event, +}; + static int __init devlink_init(void) { int err; @@ -311,6 +306,9 @@ static int __init devlink_init(void) if (err) goto out; err = register_pernet_subsys(&devlink_pernet_ops); + if (err) + goto out; + err = register_netdevice_notifier(&devlink_port_netdevice_nb); out: WARN_ON(err); diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index e133f423294a..62921b2eb0d3 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -50,7 +50,6 @@ struct devlink { u8 reload_failed:1; refcount_t refcount; struct rcu_work rwork; - struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index dffca2f9bfa7..cd0254968076 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -7073,10 +7073,9 @@ int devlink_port_netdevice_event(struct notifier_block *nb, struct devlink_port *devlink_port = netdev->devlink_port; struct devlink *devlink; - devlink = container_of(nb, struct devlink, netdevice_nb); - - if (!devlink_port || devlink_port->devlink != devlink) + if (!devlink_port) return NOTIFY_OK; + devlink = devlink_port->devlink; switch (event) { case NETDEV_POST_INIT: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 39bda2b1066e..06d2573685ca 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -829,6 +829,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); + } else { + ctl_sk->sk_mark = 0; + ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -836,7 +839,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -935,7 +937,6 @@ static void tcp_v4_send_ack(const struct sock *sk, &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2438da5ff6da..bac768d36cc1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2491,7 +2491,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh_bh(rt->nh); + fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); @@ -2556,14 +2556,14 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; - node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { - node = rcu_dereference_bh( + node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); @@ -2593,7 +2593,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); + n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; @@ -2619,12 +2619,12 @@ iter_table: } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU_BH) + __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; - rcu_read_lock_bh(); + rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; @@ -2645,7 +2645,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) - __releases(RCU_BH) + __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; @@ -2653,7 +2653,7 @@ static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); - rcu_read_unlock_bh(); + rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a4ecfc9d2593..da80974ad23a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1015,12 +1015,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); + proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } @@ -1043,24 +1045,25 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, break; } - if (t->parms.erspan_ver == 1) + if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else if (t->parms.erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto tx_err; + } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ - proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) - : htons(ETH_P_ERSPAN2); gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ diff --git a/net/key/af_key.c b/net/key/af_key.c index a815f5ab4c49..31ab12fd720a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1940,7 +1940,8 @@ static u32 gen_reqid(struct net *net) } static int -parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) +parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, + struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; @@ -1958,9 +1959,12 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; - if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) + if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { + if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && + pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) + return -EINVAL; t->optional = 1; - else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { + } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; @@ -2002,7 +2006,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; - if ((err = parse_ipsecrequest(xp, rq)) < 0) + if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7317e4a5d1ff..86b2036d73ff 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1578,9 +1578,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); - /* abort any running channel switch */ + /* abort any running channel switch or color change */ mutex_lock(&local->mtx); link_conf->csa_active = false; + link_conf->color_change_active = false; if (link->csa_block_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); @@ -3589,7 +3590,7 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_t EXPORT_SYMBOL(ieee80211_channel_switch_disconnect); static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, - u32 *changed) + u64 *changed) { int err; @@ -3632,7 +3633,7 @@ static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - u32 changed = 0; + u64 changed = 0; int err; sdata_assert_lock(sdata); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index dbc34fbe7c8f..77c90ed8f5d7 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -258,7 +258,8 @@ ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata, static enum nl80211_chan_width ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, - struct ieee80211_chanctx_conf *conf) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; struct ieee80211_vif *vif = &sdata->vif; @@ -267,13 +268,14 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { enum nl80211_chan_width width = NL80211_CHAN_WIDTH_20_NOHT; - struct ieee80211_bss_conf *link_conf = - rcu_dereference(sdata->vif.link_conf[link_id]); + struct ieee80211_link_data *link = + rcu_dereference(sdata->link[link_id]); - if (!link_conf) + if (!link) continue; - if (rcu_access_pointer(link_conf->chanctx_conf) != conf) + if (link != rsvd_for && + rcu_access_pointer(link->conf->chanctx_conf) != &ctx->conf) continue; switch (vif->type) { @@ -287,7 +289,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, * point, so take the width from the chandef, but * account also for TDLS peers */ - width = max(link_conf->chandef.width, + width = max(link->conf->chandef.width, ieee80211_get_max_required_bw(sdata, link_id)); break; case NL80211_IFTYPE_P2P_DEVICE: @@ -296,7 +298,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_OCB: - width = link_conf->chandef.width; + width = link->conf->chandef.width; break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_UNSPECIFIED: @@ -316,7 +318,8 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, static enum nl80211_chan_width ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, - struct ieee80211_chanctx_conf *conf) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { struct ieee80211_sub_if_data *sdata; enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; @@ -328,7 +331,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, if (!ieee80211_sdata_running(sdata)) continue; - width = ieee80211_get_chanctx_vif_max_required_bw(sdata, conf); + width = ieee80211_get_chanctx_vif_max_required_bw(sdata, ctx, + rsvd_for); max_bw = max(max_bw, width); } @@ -336,8 +340,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, /* use the configured bandwidth in case of monitor interface */ sdata = rcu_dereference(local->monitor_sdata); if (sdata && - rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == conf) - max_bw = max(max_bw, conf->def.width); + rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == &ctx->conf) + max_bw = max(max_bw, ctx->conf.def.width); rcu_read_unlock(); @@ -349,8 +353,10 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, * the max of min required widths of all the interfaces bound to this * channel context. */ -static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) +static u32 +_ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -370,7 +376,7 @@ static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, return 0; } - max_bw = ieee80211_get_chanctx_max_required_bw(local, &ctx->conf); + max_bw = ieee80211_get_chanctx_max_required_bw(local, ctx, rsvd_for); /* downgrade chandef up to max_bw */ min_def = ctx->conf.def; @@ -448,9 +454,10 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, * channel context. */ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { - u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx); + u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); if (!changed) return; @@ -464,10 +471,11 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ieee80211_chan_bw_change(local, ctx, false); } -static void ieee80211_change_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_chanctx *old_ctx, - const struct cfg80211_chan_def *chandef) +static void _ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef, + struct ieee80211_link_data *rsvd_for) { u32 changed; @@ -492,7 +500,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, true); if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { - ieee80211_recalc_chanctx_min_def(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); return; } @@ -502,7 +510,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, /* check if min chanctx also changed */ changed = IEEE80211_CHANCTX_CHANGE_WIDTH | - _ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); drv_change_chanctx(local, ctx, changed); if (!local->use_chanctx) { @@ -514,6 +522,14 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, false); } +static void ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef) +{ + _ieee80211_change_chanctx(local, ctx, old_ctx, chandef, NULL); +} + static struct ieee80211_chanctx * ieee80211_find_chanctx(struct ieee80211_local *local, const struct cfg80211_chan_def *chandef, @@ -638,7 +654,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = false; - ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx, NULL); return ctx; } @@ -855,6 +871,9 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, } if (new_ctx) { + /* recalc considering the link we'll use it for now */ + ieee80211_recalc_chanctx_min_def(local, new_ctx, link); + ret = drv_assign_vif_chanctx(local, sdata, link->conf, new_ctx); if (ret) goto out; @@ -873,12 +892,12 @@ out: ieee80211_recalc_chanctx_chantype(local, curr_ctx); ieee80211_recalc_smps_chanctx(local, curr_ctx); ieee80211_recalc_radar_chanctx(local, curr_ctx); - ieee80211_recalc_chanctx_min_def(local, curr_ctx); + ieee80211_recalc_chanctx_min_def(local, curr_ctx, NULL); } if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) { ieee80211_recalc_txpower(sdata, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); } if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && @@ -1270,7 +1289,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) ieee80211_link_update_chandef(link, &link->reserved_chandef); - ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef); + _ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef, link); vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; @@ -1300,7 +1319,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx); - ieee80211_recalc_chanctx_min_def(local, new_ctx); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); @@ -1665,7 +1684,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_chanctx_chantype(local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx, NULL); list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, reserved_chanctx_list) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a0a7839cb961..b0372e76f373 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2537,7 +2537,8 @@ int ieee80211_chanctx_refcount(struct ieee80211_local *local, void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx); + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for); bool ieee80211_is_radar_required(struct ieee80211_local *local); void ieee80211_dfs_cac_timer(unsigned long data); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index de5d69f21306..db0d0132c58c 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -67,7 +67,7 @@ __entry->min_freq_offset = (c)->chan ? (c)->chan->freq_offset : 0; \ __entry->min_chan_width = (c)->width; \ __entry->min_center_freq1 = (c)->center_freq1; \ - __entry->freq1_offset = (c)->freq1_offset; \ + __entry->min_freq1_offset = (c)->freq1_offset; \ __entry->min_center_freq2 = (c)->center_freq2; #define MIN_CHANDEF_PR_FMT " min_control:%d.%03d MHz min_width:%d min_center: %d.%03d/%d MHz" #define MIN_CHANDEF_PR_ARG __entry->min_control_freq, __entry->min_freq_offset, \ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a3327407552..0d9fbc8458fd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3791,6 +3791,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, ieee80211_tx_result r; struct ieee80211_vif *vif = txq->vif; int q = vif->hw_queue[txq->ac]; + unsigned long flags; bool q_stopped; WARN_ON_ONCE(softirq_count() == 0); @@ -3799,9 +3800,9 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, return NULL; begin: - spin_lock(&local->queue_stop_reason_lock); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); q_stopped = local->queue_stop_reasons[q]; - spin_unlock(&local->queue_stop_reason_lock); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); if (unlikely(q_stopped)) { /* mark for waking later */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1527d6aafc14..4bf76150925d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3015,7 +3015,7 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata, chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - ieee80211_recalc_chanctx_min_def(local, chanctx); + ieee80211_recalc_chanctx_min_def(local, chanctx, NULL); } unlock: mutex_unlock(&local->chanctx_mtx); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d40544cd61a6..69c8c8c7e9b8 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2976,7 +2976,9 @@ nla_put_failure: return -1; } +#if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; +#endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { @@ -3460,10 +3462,12 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return 0; } +#if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; +#endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 59fb8320ab4d..dc5675962de4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3865,12 +3865,10 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { - struct nft_rule *rule = nft_trans_rule(trans); - if (trans->msg_type == NFT_MSG_NEWRULE && trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) - return rule; + return nft_trans_rule(trans); } return ERR_PTR(-ENOENT); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 19ea4d3c3553..2f114aa10f1a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -221,7 +221,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev; + struct nft_rbtree_elem *rbe_prev = NULL; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); @@ -229,17 +229,21 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, return -ENOMEM; /* search for expired end interval coming before this element. */ - do { + while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev)) break; prev = rb_prev(prev); - } while (prev != NULL); + } + + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + atomic_dec(&set->nelems); + } - rb_erase(&rbe_prev->node, &priv->root); rb_erase(&rbe->node, &priv->root); - atomic_sub(2, &set->nelems); + atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); nft_set_gc_batch_complete(gcb); @@ -268,7 +272,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; - struct rb_node *node, *parent, **p, *first = NULL; + struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); int d, err; @@ -307,7 +311,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ - for (node = first; node != NULL; node = rb_next(node)) { + for (node = first; node != NULL; node = next) { + next = rb_next(node); + rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index e9ca007718b7..0f23e5e8e03e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,12 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; unsigned int nsh_len, mac_len; __be16 proto; - int nhoff; skb_reset_network_header(skb); - nhoff = skb->network_header - skb->mac_header; mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -108,15 +107,14 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, - skb->network_header - nhoff, - mac_len); + mac_offset, mac_len); goto out; } for (skb = segs; skb; skb = skb->next) { skb->protocol = htons(ETH_P_NSH); __skb_push(skb, nsh_len); - skb_set_mac_header(skb, -nhoff); + skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 212c5d57465a..9734e1d9f991 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -639,6 +639,16 @@ gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf, ret = write_bytes_to_xdr_buf(buf, offset, data, len); +#if IS_ENABLED(CONFIG_KUNIT) + /* + * CBC-CTS does not define an output IV but RFC 3962 defines it as the + * penultimate block of ciphertext, so copy that into the IV buffer + * before returning. + */ + if (encrypt) + memcpy(iv, data, crypto_sync_skcipher_ivsize(cipher)); +#endif + out: kfree(data); return ret; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 26367cf4c17a..79967b6925bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1052,7 +1052,7 @@ static int __svc_register(struct net *net, const char *progname, #endif } - trace_svc_register(progname, version, protocol, port, family, error); + trace_svc_register(progname, version, family, protocol, port, error); return error; } @@ -1416,7 +1416,7 @@ err_bad_rpc: /* Only RPCv2 supported */ xdr_stream_encode_u32(xdr, RPC_VERSION); xdr_stream_encode_u32(xdr, RPC_VERSION); - goto sendit; + return 1; /* don't wrap */ err_bad_auth: dprintk("svc: authentication failed (%d)\n", @@ -1432,7 +1432,7 @@ err_bad_auth: err_bad_prog: dprintk("svc: unknown program %d\n", rqstp->rq_prog); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_UNAVAIL); + *rqstp->rq_accept_statp = rpc_prog_unavail; goto sendit; err_bad_vers: @@ -1440,7 +1440,12 @@ err_bad_vers: rqstp->rq_vers, rqstp->rq_prog, progp->pg_name); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_MISMATCH); + *rqstp->rq_accept_statp = rpc_prog_mismatch; + + /* + * svc_authenticate() has already added the verifier and + * advanced the stream just past rq_accept_statp. + */ xdr_stream_encode_u32(xdr, process.mismatch.lovers); xdr_stream_encode_u32(xdr, process.mismatch.hivers); goto sendit; @@ -1449,19 +1454,19 @@ err_bad_proc: svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROC_UNAVAIL); + *rqstp->rq_accept_statp = rpc_proc_unavail; goto sendit; err_garbage_args: svc_printk(rqstp, "failed to decode RPC header\n"); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_GARBAGE_ARGS); + *rqstp->rq_accept_statp = rpc_garbage_args; goto sendit; err_system_err: serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_SYSTEM_ERR); + *rqstp->rq_accept_statp = rpc_system_err; goto sendit; } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 84e5d7d31481..13a14897bc17 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -532,13 +532,23 @@ void svc_reserve(struct svc_rqst *rqstp, int space) } EXPORT_SYMBOL_GPL(svc_reserve); +static void free_deferred(struct svc_xprt *xprt, struct svc_deferred_req *dr) +{ + if (!dr) + return; + + xprt->xpt_ops->xpo_release_ctxt(xprt, dr->xprt_ctxt); + kfree(dr); +} + static void svc_xprt_release(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; - xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; - kfree(rqstp->rq_deferred); + free_deferred(xprt, rqstp->rq_deferred); rqstp->rq_deferred = NULL; svc_rqst_release_pages(rqstp); @@ -1054,7 +1064,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_unlock_bh(&serv->sv_lock); while ((dr = svc_deferred_dequeue(xprt)) != NULL) - kfree(dr); + free_deferred(xprt, dr); call_xpt_users(xprt); svc_xprt_put(xprt); @@ -1176,8 +1186,8 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) { spin_unlock(&xprt->xpt_lock); trace_svc_defer_drop(dr); + free_deferred(xprt, dr); svc_xprt_put(xprt); - kfree(dr); return; } dr->xprt = NULL; @@ -1222,14 +1232,14 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->addrlen = rqstp->rq_addrlen; dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; - dr->xprt_ctxt = rqstp->rq_xprt_ctxt; - rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; + rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; @@ -1262,6 +1272,8 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; rqstp->rq_xprt_ctxt = dr->xprt_ctxt; + + dr->xprt_ctxt = NULL; svc_xprt_received(rqstp->rq_xprt); return dr->argslen << 2; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index a51c9b989d58..63fe7a338992 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -121,27 +121,27 @@ static void svc_reclassify_socket(struct socket *sock) #endif /** - * svc_tcp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_tcp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_tcp_release_rqst(struct svc_rqst *rqstp) +static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { } /** - * svc_udp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_udp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_udp_release_rqst(struct svc_rqst *rqstp) +static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { - struct sk_buff *skb = rqstp->rq_xprt_ctxt; + struct sk_buff *skb = ctxt; - if (skb) { - rqstp->rq_xprt_ctxt = NULL; + if (skb) consume_skb(skb); - } } union svc_pktinfo_u { @@ -696,7 +696,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_udp_release_rqst(rqstp); + svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; svc_set_cmsg_data(rqstp, cmh); @@ -768,7 +769,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_udp_release_rqst, + .xpo_release_ctxt = svc_udp_release_ctxt, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, @@ -895,6 +896,9 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) trace_svcsock_accept_err(xprt, serv->sv_name, err); return NULL; } + if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL))) + return NULL; + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_getpeername(newsock, sin); @@ -935,7 +939,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) return &newsvsk->sk_xprt; failed: - sock_release(newsock); + sockfd_put(newsock); return NULL; } @@ -1298,7 +1302,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_tcp_release_rqst(rqstp); + svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); @@ -1343,7 +1348,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_tcp_release_rqst, + .xpo_release_ctxt = svc_tcp_release_ctxt, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, @@ -1430,7 +1435,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct socket *sock, int flags) { - struct file *filp = NULL; struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); @@ -1439,14 +1443,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, if (!svsk) return ERR_PTR(-ENOMEM); - if (!sock->file) { - filp = sock_alloc_file(sock, O_NONBLOCK, NULL); - if (IS_ERR(filp)) { - kfree(svsk); - return ERR_CAST(filp); - } - } - inet = sock->sk; if (pmap_register) { @@ -1456,8 +1452,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, inet->sk_protocol, ntohs(inet_sk(inet)->inet_sport)); if (err < 0) { - if (filp) - fput(filp); kfree(svsk); return ERR_PTR(err); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 1c658fa43063..a22fe7587fa6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -239,21 +239,20 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, } /** - * svc_rdma_release_rqst - Release transport-specific per-rqst resources - * @rqstp: svc_rqst being released + * svc_rdma_release_ctxt - Release transport-specific per-rqst resources + * @xprt: the transport which owned the context + * @vctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * * Ensure that the recv_ctxt is released whether or not a Reply * was sent. For example, the client could close the connection, * or svc_process could drop an RPC, before the Reply is sent. */ -void svc_rdma_release_rqst(struct svc_rqst *rqstp) +void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *vctxt) { - struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; - struct svc_xprt *xprt = rqstp->rq_xprt; + struct svc_rdma_recv_ctxt *ctxt = vctxt; struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - rqstp->rq_xprt_ctxt = NULL; if (ctxt) svc_rdma_recv_ctxt_put(rdma, ctxt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 416b298f74dd..ca04f7a6a085 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, .xpo_result_payload = svc_rdma_result_payload, - .xpo_release_rqst = svc_rdma_release_rqst, + .xpo_release_ctxt = svc_rdma_release_ctxt, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, .xpo_has_wspace = svc_rdma_has_wspace, diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 35cac7733fd3..53881406e200 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -541,6 +541,19 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id) return mtu; } +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) +{ + int mtu = TIPC_MIN_BEARER_MTU; + struct tipc_bearer *b; + + rcu_read_lock(); + b = bearer_get(net, bearer_id); + if (b) + mtu += b->encap_hlen; + rcu_read_unlock(); + return mtu; +} + /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, @@ -1138,8 +1151,8 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP - if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) { + if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < + b->encap_hlen + TIPC_MIN_BEARER_MTU) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 490ad6e5f7a3..bd0cc5c287ef 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -146,6 +146,7 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * @@ -170,6 +171,7 @@ struct tipc_bearer { u32 identity; struct tipc_discoverer *disc; char net_plane; + u16 encap_hlen; unsigned long up; refcount_t refcnt; }; @@ -232,6 +234,7 @@ int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, diff --git a/net/tipc/link.c b/net/tipc/link.c index b3ce24823f50..2eff1c7949cb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2200,7 +2200,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u32 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2239,6 +2239,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: + msg_max = msg_max_pkt(hdr); + if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) + break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -2283,8 +2286,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); - if (l->mtu > msg_max_pkt(hdr)) - l->mtu = msg_max_pkt(hdr); + if (l->mtu > msg_max) + l->mtu = msg_max; break; case STATE_MSG: diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c2bb818704c8..0a85244fd618 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -738,8 +738,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; - if (tipc_mtu_bad(dev, sizeof(struct iphdr) + - sizeof(struct udphdr))) { + b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); + if (tipc_mtu_bad(dev, b->encap_hlen)) { err = -EINVAL; goto err; } @@ -760,6 +760,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; + b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 413407bb646c..efb8a0937a13 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1462,7 +1462,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; - } else if (timeout == 0) { + } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index a1382255fab3..c501db7bbdb3 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation */ #include <linux/kernel.h> #include <linux/slab.h> @@ -540,6 +540,10 @@ static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, /* skip the TBTT offset */ pos++; + /* ignore entries with invalid BSSID */ + if (!is_valid_ether_addr(pos)) + return -EINVAL; + memcpy(entry->bssid, pos, ETH_ALEN); pos += ETH_ALEN; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index bef28c6187eb..408f5e55744e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -378,7 +378,7 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, break; default: xdo->dev = NULL; - dev_put(dev); + netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 35279c220bd7..1f99dc469027 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,52 +310,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } -static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type, unsigned short family) -{ - struct sec_path *sp; - - sp = skb_sec_path(skb); - if (sp && (sp->len || sp->olen) && - !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) - goto discard; - - XFRM_SPI_SKB_CB(skb)->family = family; - if (family == AF_INET) { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; - } else { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; - } - - return xfrm_input(skb, nexthdr, spi, encap_type); -discard: - kfree_skb(skb); - return 0; -} - -static int xfrmi4_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); -} - -static int xfrmi6_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0, 0, AF_INET6); -} - -static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); -} - -static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); -} - static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -991,8 +945,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrmi6_rcv, - .input_handler = xfrmi6_input, + .handler = xfrm6_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -1042,8 +996,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrmi4_rcv, - .input_handler = xfrmi4_input, + .handler = xfrm4_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5c61ec04b839..6d15788b5123 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3312,7 +3312,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, - unsigned short family) + unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); @@ -3323,7 +3323,8 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && - xfrm_state_addr_cmp(tmpl, x, family)); + xfrm_state_addr_cmp(tmpl, x, family)) && + (if_id == 0 || if_id == x->if_id); } /* @@ -3335,7 +3336,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, - unsigned short family) + unsigned short family, u32 if_id) { int idx = start; @@ -3345,7 +3346,7 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star } else start = -1; for (; idx < sp->len; idx++) { - if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) + if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) @@ -3712,12 +3713,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; - if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK && - !xfrm_nr) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); - goto reject; - } - if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; @@ -3730,7 +3725,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(tpp[i], sp, k, family); + k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ @@ -3745,9 +3740,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } - if (if_id) - secpath_reset(skb); - xfrm_pols_put(pols, npols); return 1; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d720e163ae6e..c34a2a06ca94 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1770,7 +1770,7 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, } static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { u16 prev_family; int i; @@ -1796,6 +1796,10 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, switch (ut[i].mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + if (ut[i].optional && dir == XFRM_POLICY_OUT) { + NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy"); + return -EINVAL; + } break; default: if (ut[i].family != prev_family) { @@ -1833,7 +1837,7 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, } static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_TMPL]; @@ -1844,7 +1848,7 @@ static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, int nr = nla_len(rt) / sizeof(*utmpl); int err; - err = validate_tmpl(nr, utmpl, pol->family, extack); + err = validate_tmpl(nr, utmpl, pol->family, dir, extack); if (err) return err; @@ -1921,7 +1925,7 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, if (err) goto error; - if (!(err = copy_from_user_tmpl(xp, attrs, extack))) + if (!(err = copy_from_user_tmpl(xp, attrs, p->dir, extack))) err = copy_from_user_sec_ctx(xp, attrs); if (err) goto error; @@ -1980,6 +1984,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) { xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); security_xfrm_policy_free(xp->security); kfree(xp); return err; @@ -3499,7 +3504,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, return NULL; nr = ((len - sizeof(*p)) / sizeof(*ut)); - if (validate_tmpl(nr, ut, p->sel.family, NULL)) + if (validate_tmpl(nr, ut, p->sel.family, p->dir, NULL)) return NULL; if (p->dir > XFRM_POLICY_OUT) diff --git a/sound/core/oss/pcm_plugin.h b/sound/core/oss/pcm_plugin.h index 46e273bd4a78..50a6b50f5db4 100644 --- a/sound/core/oss/pcm_plugin.h +++ b/sound/core/oss/pcm_plugin.h @@ -141,6 +141,14 @@ int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_channel, void *snd_pcm_plug_buf_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t size); void snd_pcm_plug_buf_unlock(struct snd_pcm_substream *plug, void *ptr); +#else + +static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } +static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } +static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } + +#endif + snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, const char *ptr, snd_pcm_uframes_t size, int in_kernel); @@ -151,14 +159,6 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames); -#else - -static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } -static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } -static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } - -#endif - #ifdef PLUGIN_DEBUG #define pdprintf(fmt, args...) printk(KERN_DEBUG "plugin: " fmt, ##args) #else diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index a15f55b0dce3..295163bb8abb 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -259,8 +259,10 @@ int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x) return err; err = init_stream(dg00x, &dg00x->tx_stream); - if (err < 0) + if (err < 0) { destroy_stream(dg00x, &dg00x->rx_stream); + return err; + } err = amdtp_domain_init(&dg00x->domain); if (err < 0) { diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c index 62f45847b351..7d882b33d45e 100644 --- a/sound/pci/cs46xx/cs46xx_lib.c +++ b/sound/pci/cs46xx/cs46xx_lib.c @@ -531,7 +531,7 @@ static int load_firmware(struct snd_cs46xx *chip) return err; } -int snd_cs46xx_download_image(struct snd_cs46xx *chip) +static __maybe_unused int snd_cs46xx_download_image(struct snd_cs46xx *chip) { int idx, err; unsigned int offset = 0; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index fc114e522480..dbf7aa88e0e3 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1155,8 +1155,8 @@ static bool path_has_mixer(struct hda_codec *codec, int path_idx, int ctl_type) return path && path->ctls[ctl_type]; } -static const char * const channel_name[4] = { - "Front", "Surround", "CLFE", "Side" +static const char * const channel_name[] = { + "Front", "Surround", "CLFE", "Side", "Back", }; /* give some appropriate ctl name prefix for the given line out channel */ @@ -1182,7 +1182,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, /* multi-io channels */ if (ch >= cfg->line_outs) - return channel_name[ch]; + goto fixed_name; switch (cfg->line_out_type) { case AUTO_PIN_SPEAKER_OUT: @@ -1234,6 +1234,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, if (cfg->line_outs == 1 && !spec->multi_ios) return "Line Out"; + fixed_name: if (ch >= ARRAY_SIZE(channel_name)) { snd_BUG(); return "PCM"; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 64a944016c78..5c0b1a09fd57 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4589,6 +4589,11 @@ HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 172ffc2c332b..a7e4765eff80 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7063,6 +7063,8 @@ enum { ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_FIXUP_DISABLE_DAC3, ALC285_FIXUP_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -8033,6 +8035,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC245_FIXUP_CS35L41_SPI_2 + }, + [ALC285_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9363,7 +9381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x103c, 0x8158, "HP", ALC256_FIXUP_HP_HEADSET_MIC), - SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), @@ -9458,7 +9476,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9469,8 +9487,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b65, "HP ProBook 455 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b70, "HP EliteBook 835 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b72, "HP EliteBook 845 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b74, "HP EliteBook 845W G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b77, "HP ElieBook 865 G10", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), @@ -9480,7 +9503,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -9500,6 +9525,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), @@ -9522,6 +9549,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), @@ -9618,6 +9646,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x7724, "Clevo L140AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11663,6 +11692,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), + SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 0bc6e4066d0f..4406a5def076 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -311,6 +311,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "8A22"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "System76"), + DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"), + } + }, {} }; diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 46762f7f1449..d1677d76d018 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -852,10 +852,11 @@ static void cs35l56_dsp_work(struct work_struct *work) */ if (cs35l56->sdw_peripheral) { cs35l56->sdw_irq_no_unmask = true; - cancel_work_sync(&cs35l56->sdw_irq_work); + flush_work(&cs35l56->sdw_irq_work); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_MASK_1, 0); sdw_read_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1, 0xFF); + flush_work(&cs35l56->sdw_irq_work); } ret = cs35l56_mbox_send(cs35l56, CS35L56_MBOX_CMD_SHUTDOWN); diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c index 00b60369b029..c29324403e9d 100644 --- a/sound/soc/codecs/ssm2602.c +++ b/sound/soc/codecs/ssm2602.c @@ -53,6 +53,18 @@ static const struct reg_default ssm2602_reg[SSM2602_CACHEREGNUM] = { { .reg = 0x09, .def = 0x0000 } }; +/* + * ssm2602 register patch + * Workaround for playback distortions after power up: activates digital + * core, and then powers on output, DAC, and whole chip at the same time + */ + +static const struct reg_sequence ssm2602_patch[] = { + { SSM2602_ACTIVE, 0x01 }, + { SSM2602_PWR, 0x07 }, + { SSM2602_RESET, 0x00 }, +}; + /*Appending several "None"s just for OSS mixer use*/ static const char *ssm2602_input_select[] = { @@ -598,6 +610,9 @@ static int ssm260x_component_probe(struct snd_soc_component *component) return ret; } + regmap_register_patch(ssm2602->regmap, ssm2602_patch, + ARRAY_SIZE(ssm2602_patch)); + /* set the update bits */ regmap_update_bits(ssm2602->regmap, SSM2602_LINVOL, LINVOL_LRIN_BOTH, LINVOL_LRIN_BOTH); diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c index acdf98b2ee9c..ca20cade6840 100644 --- a/sound/soc/dwc/dwc-i2s.c +++ b/sound/soc/dwc/dwc-i2s.c @@ -132,13 +132,13 @@ static irqreturn_t i2s_irq_handler(int irq, void *dev_id) /* Error Handling: TX */ if (isr[i] & ISR_TXFO) { - dev_err(dev->dev, "TX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "TX overrun (ch_id=%d)\n", i); irq_valid = true; } /* Error Handling: TX */ if (isr[i] & ISR_RXFO) { - dev_err(dev->dev, "RX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "RX overrun (ch_id=%d)\n", i); irq_valid = true; } } diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 94341e4352b3..3f08082a55be 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -1159,7 +1159,7 @@ static int fsl_micfil_probe(struct platform_device *pdev) ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); if (ret) { dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; + goto err_pm_disable; } fsl_micfil_dai.capture.formats = micfil->soc->formats; @@ -1169,9 +1169,20 @@ static int fsl_micfil_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); + goto err_pm_disable; } return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void fsl_micfil_remove(struct platform_device *pdev) +{ + pm_runtime_disable(&pdev->dev); } static int __maybe_unused fsl_micfil_runtime_suspend(struct device *dev) @@ -1232,6 +1243,7 @@ static const struct dev_pm_ops fsl_micfil_pm_ops = { static struct platform_driver fsl_micfil_driver = { .probe = fsl_micfil_probe, + .remove_new = fsl_micfil_remove, .driver = { .name = "fsl-micfil-dai", .pm = &fsl_micfil_pm_ops, diff --git a/sound/soc/jz4740/jz4740-i2s.c b/sound/soc/jz4740/jz4740-i2s.c index 6d9cfe0a5041..d0f6c945d9ae 100644 --- a/sound/soc/jz4740/jz4740-i2s.c +++ b/sound/soc/jz4740/jz4740-i2s.c @@ -218,18 +218,48 @@ static int jz4740_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return 0; } +static int jz4740_i2s_get_i2sdiv(unsigned long mclk, unsigned long rate, + unsigned long i2sdiv_max) +{ + unsigned long div, rate1, rate2, err1, err2; + + div = mclk / (64 * rate); + if (div == 0) + div = 1; + + rate1 = mclk / (64 * div); + rate2 = mclk / (64 * (div + 1)); + + err1 = abs(rate1 - rate); + err2 = abs(rate2 - rate); + + /* + * Choose the divider that produces the smallest error in the + * output rate and reject dividers with a 5% or higher error. + * In the event that both dividers are outside the acceptable + * error margin, reject the rate to prevent distorted audio. + * (The number 5% is arbitrary.) + */ + if (div <= i2sdiv_max && err1 <= err2 && err1 < rate/20) + return div; + if (div < i2sdiv_max && err2 < rate/20) + return div + 1; + + return -EINVAL; +} + static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { struct jz4740_i2s *i2s = snd_soc_dai_get_drvdata(dai); struct regmap_field *div_field; + unsigned long i2sdiv_max; unsigned int sample_size; - uint32_t ctrl; - int div; + uint32_t ctrl, conf; + int div = 1; regmap_read(i2s->regmap, JZ_REG_AIC_CTRL, &ctrl); - - div = clk_get_rate(i2s->clk_i2s) / (64 * params_rate(params)); + regmap_read(i2s->regmap, JZ_REG_AIC_CONF, &conf); switch (params_format(params)) { case SNDRV_PCM_FORMAT_S8: @@ -258,11 +288,27 @@ static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, ctrl &= ~JZ_AIC_CTRL_MONO_TO_STEREO; div_field = i2s->field_i2sdiv_playback; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_playback.msb, + i2s->soc_info->field_i2sdiv_playback.lsb); } else { ctrl &= ~JZ_AIC_CTRL_INPUT_SAMPLE_SIZE; ctrl |= FIELD_PREP(JZ_AIC_CTRL_INPUT_SAMPLE_SIZE, sample_size); div_field = i2s->field_i2sdiv_capture; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_capture.msb, + i2s->soc_info->field_i2sdiv_capture.lsb); + } + + /* + * Only calculate I2SDIV if we're supplying the bit or frame clock. + * If the codec is supplying both clocks then the divider output is + * unused, and we don't want it to limit the allowed sample rates. + */ + if (conf & (JZ_AIC_CONF_BIT_CLK_MASTER | JZ_AIC_CONF_SYNC_CLK_MASTER)) { + div = jz4740_i2s_get_i2sdiv(clk_get_rate(i2s->clk_i2s), + params_rate(params), i2sdiv_max); + if (div < 0) + return div; } regmap_write(i2s->regmap, JZ_REG_AIC_CTRL, ctrl); diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-clk.c b/sound/soc/mediatek/mt8186/mt8186-afe-clk.c index a6b4f29049bb..539e3a023bc4 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-afe-clk.c @@ -644,9 +644,3 @@ int mt8186_init_clock(struct mtk_base_afe *afe) return 0; } - -void mt8186_deinit_clock(void *priv) -{ - struct mtk_base_afe *afe = priv; - mt8186_audsys_clk_unregister(afe); -} diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-clk.h b/sound/soc/mediatek/mt8186/mt8186-afe-clk.h index d5988717d8f2..a9d59e506d9a 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-afe-clk.h @@ -81,7 +81,6 @@ enum { struct mtk_base_afe; int mt8186_set_audio_int_bus_parent(struct mtk_base_afe *afe, int clk_id); int mt8186_init_clock(struct mtk_base_afe *afe); -void mt8186_deinit_clock(void *priv); int mt8186_afe_enable_cgs(struct mtk_base_afe *afe); void mt8186_afe_disable_cgs(struct mtk_base_afe *afe); int mt8186_afe_enable_clock(struct mtk_base_afe *afe); diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c b/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c index 41172a82103e..a868a04ed4e7 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c +++ b/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c @@ -2848,10 +2848,6 @@ static int mt8186_afe_pcm_dev_probe(struct platform_device *pdev) return ret; } - ret = devm_add_action_or_reset(dev, mt8186_deinit_clock, (void *)afe); - if (ret) - return ret; - /* init memif */ afe->memif_32bit_supported = 0; afe->memif_size = MT8186_MEMIF_NUM; diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c index 578969ca91c8..5666be6b1bd2 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c @@ -84,6 +84,29 @@ static const struct afe_gate aud_clks[CLK_AUD_NR_CLK] = { GATE_AUD2(CLK_AUD_ETDM_OUT1_BCLK, "aud_etdm_out1_bclk", "top_audio", 24), }; +static void mt8186_audsys_clk_unregister(void *data) +{ + struct mtk_base_afe *afe = data; + struct mt8186_afe_private *afe_priv = afe->platform_priv; + struct clk *clk; + struct clk_lookup *cl; + int i; + + if (!afe_priv) + return; + + for (i = 0; i < CLK_AUD_NR_CLK; i++) { + cl = afe_priv->lookup[i]; + if (!cl) + continue; + + clk = cl->clk; + clk_unregister_gate(clk); + + clkdev_drop(cl); + } +} + int mt8186_audsys_clk_register(struct mtk_base_afe *afe) { struct mt8186_afe_private *afe_priv = afe->platform_priv; @@ -124,27 +147,6 @@ int mt8186_audsys_clk_register(struct mtk_base_afe *afe) afe_priv->lookup[i] = cl; } - return 0; + return devm_add_action_or_reset(afe->dev, mt8186_audsys_clk_unregister, afe); } -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe) -{ - struct mt8186_afe_private *afe_priv = afe->platform_priv; - struct clk *clk; - struct clk_lookup *cl; - int i; - - if (!afe_priv) - return; - - for (i = 0; i < CLK_AUD_NR_CLK; i++) { - cl = afe_priv->lookup[i]; - if (!cl) - continue; - - clk = cl->clk; - clk_unregister_gate(clk); - - clkdev_drop(cl); - } -} diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h index b8d6a06e11e8..897a2914dc19 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h @@ -10,6 +10,5 @@ #define _MT8186_AUDSYS_CLK_H_ int mt8186_audsys_clk_register(struct mtk_base_afe *afe); -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe); #endif diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c index 4e0c48a36159..749e856dc601 100644 --- a/sound/soc/sof/amd/acp-ipc.c +++ b/sound/soc/sof/amd/acp-ipc.c @@ -209,7 +209,12 @@ int acp_sof_ipc_msg_data(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sp acp_mailbox_read(sdev, offset, p, sz); } else { struct snd_pcm_substream *substream = sps->substream; - struct acp_dsp_stream *stream = substream->runtime->private_data; + struct acp_dsp_stream *stream; + + if (!substream || !substream->runtime) + return -ESTRPIPE; + + stream = substream->runtime->private_data; if (!stream) return -ESTRPIPE; diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index b42b5982cbbc..d547318e0d32 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -438,8 +438,8 @@ void snd_sof_handle_fw_exception(struct snd_sof_dev *sdev, const char *msg) /* should we prevent DSP entering D3 ? */ if (!sdev->ipc_dump_printed) dev_info(sdev->dev, - "preventing DSP entering D3 state to preserve context\n"); - pm_runtime_get_noresume(sdev->dev); + "Attempting to prevent DSP from entering D3 state to preserve context\n"); + pm_runtime_get_if_in_use(sdev->dev); } /* dump vital information to the logs */ diff --git a/sound/soc/sof/intel/hda-mlink.c b/sound/soc/sof/intel/hda-mlink.c index 775582ab7494..b7cbf66badf5 100644 --- a/sound/soc/sof/intel/hda-mlink.c +++ b/sound/soc/sof/intel/hda-mlink.c @@ -19,6 +19,9 @@ #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_MLINK) +/* worst-case number of sublinks is used for sublink refcount array allocation only */ +#define HDAML_MAX_SUBLINKS (AZX_ML_LCTL_CPA_SHIFT - AZX_ML_LCTL_SPA_SHIFT) + /** * struct hdac_ext2_link - HDAudio extended+alternate link * @@ -33,6 +36,7 @@ * @leptr: extended link pointer * @eml_lock: mutual exclusion to access shared registers e.g. CPA/SPA bits * in LCTL register + * @sublink_ref_count: array of refcounts, required to power-manage sublinks independently * @base_ptr: pointer to shim/ip/shim_vs space * @instance_offset: offset between each of @slcount instances managed by link * @shim_offset: offset to SHIM register base @@ -53,6 +57,7 @@ struct hdac_ext2_link { u32 leptr; struct mutex eml_lock; /* prevent concurrent access to e.g. CPA/SPA */ + int sublink_ref_count[HDAML_MAX_SUBLINKS]; /* internal values computed from LCAP contents */ void __iomem *base_ptr; @@ -68,6 +73,7 @@ struct hdac_ext2_link { #define AZX_REG_SDW_SHIM_OFFSET 0x0 #define AZX_REG_SDW_IP_OFFSET 0x100 #define AZX_REG_SDW_VS_SHIM_OFFSET 0x6000 +#define AZX_REG_SDW_SHIM_PCMSyCM(y) (0x16 + 0x4 * (y)) /* only one instance supported */ #define AZX_REG_INTEL_DMIC_SHIM_OFFSET 0x0 @@ -91,7 +97,7 @@ struct hdac_ext2_link { */ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, - void __iomem *ml_addr, int link_idx) + void __iomem *remap_addr, void __iomem *ml_addr, int link_idx) { struct hdac_ext_link *hlink = &h2link->hext_link; u32 base_offset; @@ -126,15 +132,16 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, h2link->slcount); /* find IP ID and offsets */ - h2link->leptr = readl(hlink->ml_addr + AZX_REG_ML_LEPTR); + h2link->leptr = readl(ml_addr + AZX_REG_ML_LEPTR); h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); base_offset = FIELD_GET(AZX_REG_ML_LEPTR_PTR, h2link->leptr); - h2link->base_ptr = hlink->ml_addr + base_offset; + h2link->base_ptr = remap_addr + base_offset; switch (h2link->elid) { case AZX_REG_ML_LEPTR_ID_SDW: + h2link->instance_offset = AZX_REG_SDW_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_SDW_SHIM_OFFSET; h2link->ip_offset = AZX_REG_SDW_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_SDW_VS_SHIM_OFFSET; @@ -149,6 +156,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, base_offset); break; case AZX_REG_ML_LEPTR_ID_INTEL_SSP: + h2link->instance_offset = AZX_REG_INTEL_SSP_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_INTEL_SSP_SHIM_OFFSET; h2link->ip_offset = AZX_REG_INTEL_SSP_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_INTEL_SSP_VS_SHIM_OFFSET; @@ -333,6 +341,21 @@ static void hdaml_link_set_lsdiid(u32 __iomem *lsdiid, int dev_num) writel(val, lsdiid); } +static void hdaml_shim_map_stream_ch(u16 __iomem *pcmsycm, int lchan, int hchan, + int stream_id, int dir) +{ + u16 val; + + val = readw(pcmsycm); + + u16p_replace_bits(&val, lchan, GENMASK(3, 0)); + u16p_replace_bits(&val, hchan, GENMASK(7, 4)); + u16p_replace_bits(&val, stream_id, GENMASK(13, 8)); + u16p_replace_bits(&val, dir, BIT(15)); + + writew(val, pcmsycm); +} + static void hdaml_lctl_offload_enable(u32 __iomem *lctl, bool enable) { u32 val = readl(lctl); @@ -364,7 +387,7 @@ static int hda_ml_alloc_h2link(struct hdac_bus *bus, int index) hlink->bus = bus; hlink->ml_addr = bus->mlcap + AZX_ML_BASE + (AZX_ML_INTERVAL * index); - ret = hdaml_lnk_enum(bus->dev, h2link, hlink->ml_addr, index); + ret = hdaml_lnk_enum(bus->dev, h2link, bus->remap_addr, hlink->ml_addr, index); if (ret < 0) { kfree(h2link); return ret; @@ -641,8 +664,13 @@ static int hdac_bus_eml_power_up_base(struct hdac_bus *bus, bool alt, int elid, if (eml_lock) mutex_lock(&h2link->eml_lock); - if (++hlink->ref_count > 1) - goto skip_init; + if (!alt) { + if (++hlink->ref_count > 1) + goto skip_init; + } else { + if (++h2link->sublink_ref_count[sublink] > 1) + goto skip_init; + } ret = hdaml_link_init(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); @@ -684,9 +712,13 @@ static int hdac_bus_eml_power_down_base(struct hdac_bus *bus, bool alt, int elid if (eml_lock) mutex_lock(&h2link->eml_lock); - if (--hlink->ref_count > 0) - goto skip_shutdown; - + if (!alt) { + if (--hlink->ref_count > 0) + goto skip_shutdown; + } else { + if (--h2link->sublink_ref_count[sublink] > 0) + goto skip_shutdown; + } ret = hdaml_link_shutdown(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); skip_shutdown: @@ -740,6 +772,40 @@ int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num) return 0; } EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_set_lsdiid, SND_SOC_SOF_HDA_MLINK); +/* + * the 'y' parameter comes from the PCMSyCM hardware register naming. 'y' refers to the + * PDI index, i.e. the FIFO used for RX or TX + */ +int hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir) +{ + struct hdac_ext2_link *h2link; + u16 __iomem *pcmsycm; + u16 val; + + h2link = find_ext2_link(bus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!h2link) + return -ENODEV; + + pcmsycm = h2link->base_ptr + h2link->shim_offset + + h2link->instance_offset * sublink + + AZX_REG_SDW_SHIM_PCMSyCM(y); + + mutex_lock(&h2link->eml_lock); + + hdaml_shim_map_stream_ch(pcmsycm, 0, hweight32(channel_mask), + stream_id, dir); + + mutex_unlock(&h2link->eml_lock); + + val = readw(pcmsycm); + + dev_dbg(bus->dev, "channel_mask %#x stream_id %d dir %d pcmscm %#x\n", + channel_mask, stream_id, dir, val); + + return 0; +} EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_map_stream_ch, SND_SOC_SOF_HDA_MLINK); + void hda_bus_ml_put_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink; @@ -836,6 +902,18 @@ struct hdac_ext_link *hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus) } EXPORT_SYMBOL_NS(hdac_bus_eml_dmic_get_hlink, SND_SOC_SOF_HDA_MLINK); +struct hdac_ext_link *hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus) +{ + struct hdac_ext2_link *h2link; + + h2link = find_ext2_link(bus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!h2link) + return NULL; + + return &h2link->hext_link; +} +EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_get_hlink, SND_SOC_SOF_HDA_MLINK); + int hdac_bus_eml_enable_offload(struct hdac_bus *bus, bool alt, int elid, bool enable) { struct hdac_ext2_link *h2link; diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c index fc1eb8e2de2c..ba4ef290b634 100644 --- a/sound/soc/sof/ipc3-topology.c +++ b/sound/soc/sof/ipc3-topology.c @@ -2103,10 +2103,13 @@ static int sof_ipc3_dai_config(struct snd_sof_dev *sdev, struct snd_sof_widget * * For the case of PAUSE/HW_FREE, since there are no quirks, flags can be used as is. */ - if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) + if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) { + /* Clear stale command */ + config->flags &= ~SOF_DAI_CONFIG_FLAGS_CMD_MASK; config->flags |= flags; - else + } else { config->flags = flags; + } /* only send the IPC if the widget is set up in the DSP */ if (swidget->use_count > 0) { diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index 059eebf0a687..5abe616a2054 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -59,7 +59,7 @@ static const struct sof_topology_token ipc4_in_audio_format_tokens[] = { audio_fmt.interleaving_style)}, {SOF_TKN_CAVS_AUDIO_FORMAT_IN_FMT_CFG, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, audio_fmt.fmt_cfg)}, - {SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + {SOF_TKN_CAVS_AUDIO_FORMAT_INPUT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, pin_index)}, {SOF_TKN_CAVS_AUDIO_FORMAT_IBS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, buffer_size)}, @@ -79,7 +79,7 @@ static const struct sof_topology_token ipc4_out_audio_format_tokens[] = { audio_fmt.interleaving_style)}, {SOF_TKN_CAVS_AUDIO_FORMAT_OUT_FMT_CFG, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, audio_fmt.fmt_cfg)}, - {SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + {SOF_TKN_CAVS_AUDIO_FORMAT_OUTPUT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, pin_index)}, {SOF_TKN_CAVS_AUDIO_FORMAT_OBS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, buffer_size)}, diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 567db32173a8..d0ab6f390734 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -643,16 +643,17 @@ static int sof_pcm_probe(struct snd_soc_component *component) "%s/%s", plat_data->tplg_filename_prefix, plat_data->tplg_filename); - if (!tplg_filename) - return -ENOMEM; + if (!tplg_filename) { + ret = -ENOMEM; + goto pm_error; + } ret = snd_sof_load_topology(component, tplg_filename); - if (ret < 0) { + if (ret < 0) dev_err(component->dev, "error: failed to load DSP topology %d\n", ret); - return ret; - } +pm_error: pm_runtime_mark_last_busy(component->dev); pm_runtime_put_autosuspend(component->dev); diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c index 2fdbc53ca715..2b232442e84b 100644 --- a/sound/soc/sof/pm.c +++ b/sound/soc/sof/pm.c @@ -164,7 +164,7 @@ static int sof_resume(struct device *dev, bool runtime_resume) ret = tplg_ops->set_up_all_pipelines(sdev, false); if (ret < 0) { dev_err(sdev->dev, "Failed to restore pipeline after resume %d\n", ret); - return ret; + goto setup_fail; } } @@ -178,6 +178,18 @@ static int sof_resume(struct device *dev, bool runtime_resume) dev_err(sdev->dev, "ctx_restore IPC error during resume: %d\n", ret); } +setup_fail: +#if IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE) + if (ret < 0) { + /* + * Debugfs cannot be read in runtime suspend, so cache + * the contents upon failure. This allows to capture + * possible DSP coredump information. + */ + sof_cache_debugfs(sdev); + } +#endif + return ret; } diff --git a/sound/soc/sof/sof-client-probes.c b/sound/soc/sof/sof-client-probes.c index fff126808bc0..8d9e9d5f40e4 100644 --- a/sound/soc/sof/sof-client-probes.c +++ b/sound/soc/sof/sof-client-probes.c @@ -218,12 +218,7 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = ipc->points_info(cdev, &desc, &num_desc); if (ret < 0) - goto exit; - - pm_runtime_mark_last_busy(dev); - err = pm_runtime_put_autosuspend(dev); - if (err < 0) - dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + goto pm_error; for (i = 0; i < num_desc; i++) { offset = strlen(buf); @@ -241,6 +236,13 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = simple_read_from_buffer(to, count, ppos, buf, strlen(buf)); kfree(desc); + +pm_error: + pm_runtime_mark_last_busy(dev); + err = pm_runtime_put_autosuspend(dev); + if (err < 0) + dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + exit: kfree(buf); return ret; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index d3d536b0a8f5..f160dc454b44 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -586,6 +586,10 @@ static int sof_copy_tuples(struct snd_sof_dev *sdev, struct snd_soc_tplg_vendor_ if (*num_copied_tuples == tuples_size) return 0; } + + /* stop when we've found the required token instances */ + if (found == num_tokens * token_instance_num) + return 0; } /* next array */ @@ -1261,7 +1265,7 @@ static int sof_widget_parse_tokens(struct snd_soc_component *scomp, struct snd_s if (num_sets > 1) { struct snd_sof_tuple *new_tuples; - num_tuples += token_list[object_token_list[i]].count * num_sets; + num_tuples += token_list[object_token_list[i]].count * (num_sets - 1); new_tuples = krealloc(swidget->tuples, sizeof(*new_tuples) * num_tuples, GFP_KERNEL); if (!new_tuples) { diff --git a/sound/usb/format.c b/sound/usb/format.c index 4b1c5ba121f3..ab5fed9f55b6 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -423,6 +423,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x0e41, 0x424b): /* Line6 Pod Go */ case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f7ddd73a8c0f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd5..cb8ca46213be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43e..3aedae61af4f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..e8d7ebbca1a4 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab0..bc48a4dabe5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f758..d055b82d22cc 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -10,13 +10,6 @@ .section .noinstr.text, "ax" /* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - -/* * memcpy - Copy a memory block. * * Input: @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2c..7c59a704c458 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6..7ce02a223732 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d92..a87bbbbca2d4 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b..dba7c5a5b25e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305..4b7f2df66b99 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,7 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328c..737318b1c1d9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f..f23d9a16507f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abe..0aa955aa8246 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f..70268442f7ee 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bc..1593c5dcaa9e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1057,14 +1057,32 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff87..9ca040bfb1aa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d..80b9f6287fe2 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d..ef1ed645097c 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296..6188e19d3129 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db..1b9fef7efcdc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b..247c72fdfb9d 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842..abd26c95f1aa 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f..c57be48d65bb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f..b9ad32f21e57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd..1f9047553942 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733..0402adbf7d92 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d3..f9e2316601e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c7382408..e9c46d336a8e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d1..437b9867acb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd0..875c766222e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb..9570a88d6d1c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb..a522202cf684 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df4..1a2154f28b7b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22..1ef772b40e04 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b6..11080ccffd51 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa30..65a46d659c0a 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9f..66a6f657bd6f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b..4b8bc19392a4 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae77..620fc5bd2217 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5..21ef6c9be816 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a30..eb6f12c0343d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1..b442ed4acfbb 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ad..f57a8f274025 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021f..80349685cf4d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e931..e890c261ad26 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012..fccd8ec4d1b0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163f..a1e2da0a9a6d 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,79 +88,98 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf..1c52cb05c900 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4..7e961d24a885 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbf..e50535f45977 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c74906..733ead151c63 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e6274..c05148ea400c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f704995..b154fbb15d54 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5..3a8b9bffa022 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea8811926..499539d1c479 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e60..a211348d3204 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe70..fd5c740512c5 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..1d48226ae75d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc4..c7ed51b0c1ef 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include <linux/stddef.h> // for define __always_inline #include <linux/bpf.h> #include <linux/types.h> #include <linux/perf_event.h> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6..2f5910b31fa9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -290,6 +290,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -828,26 +829,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) @@ -1725,9 +1726,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2114,12 @@ retry_open: group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc..df8928745fc6 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf032..4ce931cccb63 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c6859302..5e9c657dd3f7 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd614..34ba840ae19a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf29..bf5a6c14dfcd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7..1566a206ba42 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e4..a7a59c6bacda 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..2506621e75df 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $CASENO $result $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f2..0f5e88c8f4ff 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5..f96282362811 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up @@ -254,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -272,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..50aab6b57da3 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..479802a892d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3962,18 +3962,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); - BUG_ON(r == -EBUSY); + r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); - kvm_put_kvm_no_destroy(kvm); - goto unlock_vcpu_destroy; + if (r < 0) + goto kvm_put_xa_release; + + if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { + r = -EINVAL; + goto kvm_put_xa_release; } /* @@ -3988,6 +3989,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_release: + kvm_put_kvm_no_destroy(kvm); + xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); @@ -5184,7 +5188,20 @@ static void hardware_disable_all(void) static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); - int r = 0; + int r; + + /* + * Do not enable hardware virtualization if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling + * after kvm_reboot() is called. Note, this relies on system_state + * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops + * hook instead of registering a dedicated reboot notifier (the latter + * runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) + return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() @@ -5197,6 +5214,8 @@ static int hardware_enable_all(void) cpus_read_lock(); mutex_lock(&kvm_lock); + r = 0; + kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); @@ -5213,26 +5232,24 @@ static int hardware_enable_all(void) return r; } -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static void kvm_shutdown(void) { /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - static int kvm_suspend(void) { /* @@ -5263,6 +5280,7 @@ static void kvm_resume(void) static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, + .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) @@ -5967,7 +5985,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (r) return r; - register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); #endif @@ -6039,7 +6056,6 @@ err_cpu_kick_mask: err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; @@ -6065,7 +6081,6 @@ void kvm_exit(void) kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); |