diff options
326 files changed, 5122 insertions, 3162 deletions
@@ -803,6 +803,7 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@onelan.co.uk> Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net> Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws> Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com> +Umang Jain <uajain@igalia.com> <umang.jain@ideasonboard.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com> Uwe Kleine-König <u.kleine-koenig@pengutronix.de> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a51ab4656854..6c42061ca20e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -608,6 +608,24 @@ ccw_timeout_log [S390] See Documentation/arch/s390/common_io.rst for details. + cfi= [X86-64] Set Control Flow Integrity checking features + when CONFIG_FINEIBT is enabled. + Format: feature[,feature...] + Default: auto + + auto: Use FineIBT if IBT available, otherwise kCFI. + Under FineIBT, enable "paranoid" mode when + FRED is not available. + off: Turn off CFI checking. + kcfi: Use kCFI (disable FineIBT). + fineibt: Use FineIBT (even if IBT not available). + norand: Do not re-randomize CFI hashes. + paranoid: Add caller hash checking under FineIBT. + bhi: Enable register poisoning to stop speculation + across FineIBT. (Disabled by default.) + warn: Do not enforce CFI checking: warn only. + debug: Report CFI initialization details. + cgroup_disable= [KNL] Disable a particular controller or optional feature Format: {name of the controller(s) or feature(s) to disable} The effects of cgroup_disable=foo are: diff --git a/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml b/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml index 9845a187bdf6..232252e8825e 100644 --- a/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml +++ b/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml @@ -44,7 +44,7 @@ properties: patternProperties: # All other properties should be child nodes with unit-address and 'reg' - "^[a-zA-Z][a-zA-Z0-9,+\\-._]{0,63}@[0-9a-fA-F]+$": + "@[0-9a-f]+$": type: object additionalProperties: true properties: diff --git a/Documentation/devicetree/bindings/bus/renesas,bsc.yaml b/Documentation/devicetree/bindings/bus/renesas,bsc.yaml index f53a37785413..ff3c78317d28 100644 --- a/Documentation/devicetree/bindings/bus/renesas,bsc.yaml +++ b/Documentation/devicetree/bindings/bus/renesas,bsc.yaml @@ -41,6 +41,18 @@ properties: interrupts: maxItems: 1 +patternProperties: + # All other properties should be child nodes with unit-address and 'reg' + "@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + reg: + maxItems: 1 + + required: + - reg + required: - reg diff --git a/Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml b/Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml new file mode 100644 index 000000000000..3faa7954e411 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/hisilicon,hix5hd2-i2c.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/i2c/hisilicon,hix5hd2-i2c.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# +title: I2C for HiSilicon hix5hd2 chipset platform + +maintainers: + - Wei Yan <sledge.yanwei@huawei.com> + +allOf: + - $ref: /schemas/i2c/i2c-controller.yaml# + +properties: + compatible: + enum: + - hisilicon,hix5hd2-i2c + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-frequency: + description: Desired I2C bus frequency in Hz + default: 100000 + +required: + - compatible + - reg + - interrupts + - clocks + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/clock/hix5hd2-clock.h> + + i2c@f8b10000 { + compatible = "hisilicon,hix5hd2-i2c"; + reg = <0xf8b10000 0x1000>; + interrupts = <0 38 4>; + clocks = <&clock HIX5HD2_I2C0_RST>; + #address-cells = <1>; + #size-cells = <0>; + }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt b/Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt deleted file mode 100644 index f98b37401e6e..000000000000 --- a/Documentation/devicetree/bindings/i2c/i2c-hix5hd2.txt +++ /dev/null @@ -1,24 +0,0 @@ -I2C for Hisilicon hix5hd2 chipset platform - -Required properties: -- compatible: Must be "hisilicon,hix5hd2-i2c" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: interrupt number to the cpu. -- #address-cells = <1>; -- #size-cells = <0>; -- clocks: phandles to input clocks. - -Optional properties: -- clock-frequency: Desired I2C bus frequency in Hz, otherwise defaults to 100000 -- Child nodes conforming to i2c bus binding - -Examples: -I2C0@f8b10000 { - compatible = "hisilicon,hix5hd2-i2c"; - reg = <0xf8b10000 0x1000>; - interrupts = <0 38 4>; - clocks = <&clock HIX5HD2_I2C0_RST>; - #address-cells = <1>; - #size-cells = <0>; -} diff --git a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml index 69ac5db8b914..17ce39c19ab1 100644 --- a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml @@ -10,9 +10,11 @@ maintainers: - Chris Packham <chris.packham@alliedtelesis.co.nz> description: - The RTL9300 SoC has two I2C controllers. Each of these has an SCL line (which + RTL9300 SoCs have two I2C controllers. Each of these has an SCL line (which if not-used for SCL can be a GPIO). There are 8 common SDA lines that can be assigned to either I2C controller. + RTL9310 SoCs have equal capabilities but support 12 common SDA lines which + can be assigned to either I2C controller. properties: compatible: @@ -23,11 +25,19 @@ properties: - realtek,rtl9302c-i2c - realtek,rtl9303-i2c - const: realtek,rtl9301-i2c - - const: realtek,rtl9301-i2c + - items: + - enum: + - realtek,rtl9311-i2c + - realtek,rtl9312-i2c + - realtek,rtl9313-i2c + - const: realtek,rtl9310-i2c + - enum: + - realtek,rtl9301-i2c + - realtek,rtl9310-i2c reg: items: - - description: Register offset and size this I2C controller. + - description: Register offset and size of this I2C controller. "#address-cells": const: 1 @@ -35,19 +45,44 @@ properties: "#size-cells": const: 0 + realtek,scl: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + The SCL line number of this I2C controller. + enum: [ 0, 1 ] + patternProperties: - '^i2c@[0-7]$': + '^i2c@[0-9ab]$': $ref: /schemas/i2c/i2c-controller.yaml unevaluatedProperties: false properties: reg: - description: The SDA pin associated with the I2C bus. + description: The SDA line number associated with the I2C bus. maxItems: 1 required: - reg + +allOf: + - if: + properties: + compatible: + contains: + const: realtek,rtl9310-i2c + then: + required: + - realtek,scl + - if: + properties: + compatible: + contains: + const: realtek,rtl9301-i2c + then: + patternProperties: + '^i2c@[89ab]$': false + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml index ebde06173578..3d7195e9461c 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml +++ b/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml @@ -85,7 +85,7 @@ properties: - for eMMC, the maximum supported frequency is 200MHz, - for SD/SDIO cards the SDR104 mode has a max supported frequency of 208MHz, - - some mmc host controllers do support a max frequency upto + - some mmc host controllers do support a max frequency up to 384MHz. So, lets keep the maximum supported value here. diff --git a/Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml b/Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml new file mode 100644 index 000000000000..b8f46536fd5a --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/apm,xgene-rtc.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/apm,xgene-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: APM X-Gene Real Time Clock + +maintainers: + - Khuong Dinh <khuong@os.amperecomputing.com> + +properties: + compatible: + const: apm,xgene-rtc + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + '#clock-cells': + const: 1 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + - '#clock-cells' + - clocks + +additionalProperties: false + +examples: + - | + rtc@10510000 { + compatible = "apm,xgene-rtc"; + reg = <0x10510000 0x400>; + interrupts = <0x0 0x46 0x4>; + #clock-cells = <1>; + clocks = <&rtcclk 0>; + }; diff --git a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt b/Documentation/devicetree/bindings/rtc/isil,isl12057.txt deleted file mode 100644 index ff7c43555199..000000000000 --- a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt +++ /dev/null @@ -1,74 +0,0 @@ -Intersil ISL12057 I2C RTC/Alarm chip - -ISL12057 is a trivial I2C device (it has simple device tree bindings, -consisting of a compatible field, an address and possibly an interrupt -line). - -Nonetheless, it also supports an option boolean property -("wakeup-source") to handle the specific use-case found -on at least three in-tree users of the chip (NETGEAR ReadyNAS 102, 104 -and 2120 ARM-based NAS); On those devices, the IRQ#2 pin of the chip -(associated with the alarm supported by the driver) is not connected -to the SoC but to a PMIC. It allows the device to be powered up when -RTC alarm rings. In order to mark the device has a wakeup source and -get access to the 'wakealarm' sysfs entry, this specific property can -be set when the IRQ#2 pin of the chip is not connected to the SoC but -can wake up the device. - -Required properties supported by the device: - - - "compatible": must be "isil,isl12057" - - "reg": I2C bus address of the device - -Optional properties: - - - "wakeup-source": mark the chip as a wakeup source, independently of - the availability of an IRQ line connected to the SoC. - - -Example isl12057 node without IRQ#2 pin connected (no alarm support): - - isl12057: isl12057@68 { - compatible = "isil,isl12057"; - reg = <0x68>; - }; - - -Example isl12057 node with IRQ#2 pin connected to main SoC via MPP6 (note -that the pinctrl-related properties below are given for completeness and -may not be required or may be different depending on your system or -SoC, and the main function of the MPP used as IRQ line, i.e. -"interrupt-parent" and "interrupts" are usually sufficient): - - pinctrl { - ... - - rtc_alarm_pin: rtc_alarm_pin { - marvell,pins = "mpp6"; - marvell,function = "gpio"; - }; - - ... - - }; - - ... - - isl12057: isl12057@68 { - compatible = "isil,isl12057"; - reg = <0x68>; - pinctrl-0 = <&rtc_alarm_pin>; - pinctrl-names = "default"; - interrupt-parent = <&gpio0>; - interrupts = <6 IRQ_TYPE_EDGE_FALLING>; - }; - - -Example isl12057 node without IRQ#2 pin connected to the SoC but to a -PMIC, allowing the device to be started based on configured alarm: - - isl12057: isl12057@68 { - compatible = "isil,isl12057"; - reg = <0x68>; - wakeup-source; - }; diff --git a/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml b/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml index 1e6277e524c2..f7013cd8fc20 100644 --- a/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml +++ b/Documentation/devicetree/bindings/rtc/nxp,pcf85063.yaml @@ -65,16 +65,6 @@ allOf: - if: properties: compatible: - contains: - enum: - - nxp,pcf85063 - then: - properties: - quartz-load-femtofarads: - const: 7000 - - if: - properties: - compatible: not: contains: enum: diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml b/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml index bf4e11d6dffb..338874e7ed7f 100644 --- a/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.yaml @@ -13,9 +13,6 @@ properties: compatible: oneOf: - enum: - - samsung,s3c2410-rtc - - samsung,s3c2416-rtc - - samsung,s3c2443-rtc - samsung,s3c6410-rtc - items: - enum: @@ -29,19 +26,12 @@ properties: maxItems: 1 clocks: - description: - Must contain a list of phandle and clock specifier for the rtc - clock and in the case of a s3c6410 compatible controller, also - a source clock. - minItems: 1 maxItems: 2 clock-names: - description: - Must contain "rtc" and for a s3c6410 compatible controller - also "rtc_src". - minItems: 1 - maxItems: 2 + items: + - const: rtc + - const: rtc_src interrupts: description: @@ -54,30 +44,6 @@ properties: allOf: - $ref: rtc.yaml# - - if: - properties: - compatible: - contains: - enum: - - samsung,s3c6410-rtc - - samsung,exynos3250-rtc - then: - properties: - clocks: - minItems: 2 - maxItems: 2 - clock-names: - items: - - const: rtc - - const: rtc_src - else: - properties: - clocks: - minItems: 1 - maxItems: 1 - clock-names: - items: - - const: rtc unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml index 5e0c7cd25cc6..b47822370d6f 100644 --- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml @@ -38,6 +38,8 @@ properties: - dallas,ds1672 # Extremely Accurate I²C RTC with Integrated Crystal and SRAM - dallas,ds3232 + # Dallas m41t00 Real-time Clock + - dallas,m41t00 # SD2405AL Real-Time Clock - dfrobot,sd2405al # EM Microelectronic EM3027 RTC @@ -83,8 +85,8 @@ properties: - via,vt8500-rtc # I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC - whwave,sd3078 - # Xircom X1205 I2C RTC - - xircom,x1205 + # Xicor/Intersil X1205 I2C RTC + - xicor,x1205 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/rtc/xgene-rtc.txt b/Documentation/devicetree/bindings/rtc/xgene-rtc.txt deleted file mode 100644 index fd195c358446..000000000000 --- a/Documentation/devicetree/bindings/rtc/xgene-rtc.txt +++ /dev/null @@ -1,28 +0,0 @@ -* APM X-Gene Real Time Clock - -RTC controller for the APM X-Gene Real Time Clock - -Required properties: -- compatible : Should be "apm,xgene-rtc" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: IRQ line for the RTC. -- #clock-cells: Should be 1. -- clocks: Reference to the clock entry. - -Example: - -rtcclk: rtcclk { - compatible = "fixed-clock"; - #clock-cells = <1>; - clock-frequency = <100000000>; - clock-output-names = "rtcclk"; -}; - -rtc: rtc@10510000 { - compatible = "apm,xgene-rtc"; - reg = <0x0 0x10510000 0x0 0x400>; - interrupts = <0x0 0x46 0x4>; - #clock-cells = <1>; - clocks = <&rtcclk 0>; -}; diff --git a/Documentation/fb/aty128fb.rst b/Documentation/fb/aty128fb.rst index 3f107718f933..0da8070a5521 100644 --- a/Documentation/fb/aty128fb.rst +++ b/Documentation/fb/aty128fb.rst @@ -1,8 +1,6 @@ -================= -What is aty128fb? -================= - -.. [This file is cloned from VesaFB/matroxfb] +========================================= +aty128fb - ATI Rage128 framebuffer driver +========================================= This is a driver for a graphic framebuffer for ATI Rage128 based devices on Intel and PPC boxes. diff --git a/Documentation/fb/efifb.rst b/Documentation/fb/efifb.rst index 6badff64756f..3d4aab406dee 100644 --- a/Documentation/fb/efifb.rst +++ b/Documentation/fb/efifb.rst @@ -1,6 +1,6 @@ -============== -What is efifb? -============== +=================================== +efifb - Generic EFI platform driver +=================================== This is a generic EFI platform driver for systems with UEFI firmware. The system must be booted via the EFI stub for this to be usable. efifb supports diff --git a/Documentation/fb/ep93xx-fb.rst b/Documentation/fb/ep93xx-fb.rst index 1dd67f4688c7..93b3494f5309 100644 --- a/Documentation/fb/ep93xx-fb.rst +++ b/Documentation/fb/ep93xx-fb.rst @@ -41,7 +41,6 @@ your board initialisation function:: ep93xx_register_fb(&some_board_fb_info); -===================== Video Attribute Flags ===================== @@ -79,7 +78,6 @@ EP93XXFB_USE_SDCSN2 Use SDCSn[2] for the framebuffer. EP93XXFB_USE_SDCSN3 Use SDCSn[3] for the framebuffer. =============================== ====================================== -================== Platform callbacks ================== @@ -101,7 +99,6 @@ obtained as follows:: /* Board specific framebuffer setup */ } -====================== Setting the video mode ====================== @@ -119,7 +116,6 @@ set when the module is installed:: modprobe ep93xx-fb video=320x240 -============== Screenpage bug ============== diff --git a/Documentation/fb/gxfb.rst b/Documentation/fb/gxfb.rst index 5738709bccbb..3fda485606bd 100644 --- a/Documentation/fb/gxfb.rst +++ b/Documentation/fb/gxfb.rst @@ -1,8 +1,6 @@ -============= -What is gxfb? -============= - -.. [This file is cloned from VesaFB/aty128fb] +======================================= +gxfb - AMD Geode GX2 framebuffer driver +======================================= This is a graphics framebuffer driver for AMD Geode GX2 based processors. diff --git a/Documentation/fb/index.rst b/Documentation/fb/index.rst index 33e3c49f8856..e2f7488b6e2e 100644 --- a/Documentation/fb/index.rst +++ b/Documentation/fb/index.rst @@ -4,42 +4,52 @@ Frame Buffer ============ +General information +=================== + +.. toctree:: + :maxdepth: 1 + + api + cmap_xfbdev + deferred_io + fbcon + framebuffer + internals + modedb + +Driver documentation +==================== + .. toctree:: - :maxdepth: 1 - - api - arkfb - aty128fb - cirrusfb - cmap_xfbdev - deferred_io - efifb - ep93xx-fb - fbcon - framebuffer - gxfb - intel810 - internals - lxfb - matroxfb - metronomefb - modedb - pvr2fb - pxafb - s3fb - sa1100fb - sh7760fb - sisfb - sm501 - sm712fb - sstfb - tgafb - tridentfb - udlfb - uvesafb - vesafb - viafb - vt8623fb + :maxdepth: 1 + + arkfb + aty128fb + cirrusfb + efifb + ep93xx-fb + gxfb + intel810 + lxfb + matroxfb + metronomefb + pvr2fb + pxafb + s3fb + sa1100fb + sh7760fb + sisfb + sm501 + sm712fb + sstfb + tgafb + tridentfb + udlfb + uvesafb + vesafb + viafb + vt8623fb .. only:: subproject and html diff --git a/Documentation/fb/lxfb.rst b/Documentation/fb/lxfb.rst index 863e6b98fbae..0a176ab376e3 100644 --- a/Documentation/fb/lxfb.rst +++ b/Documentation/fb/lxfb.rst @@ -1,9 +1,6 @@ -============= -What is lxfb? -============= - -.. [This file is cloned from VesaFB/aty128fb] - +====================================== +lxfb - AMD Geode LX framebuffer driver +====================================== This is a graphics framebuffer driver for AMD Geode LX based processors. diff --git a/Documentation/fb/matroxfb.rst b/Documentation/fb/matroxfb.rst index 6158c49c8571..8ac7534a2e61 100644 --- a/Documentation/fb/matroxfb.rst +++ b/Documentation/fb/matroxfb.rst @@ -1,9 +1,6 @@ -================= -What is matroxfb? -================= - -.. [This file is cloned from VesaFB. Thanks go to Gerd Knorr] - +================================================ +matroxfb - Framebuffer driver for Matrox devices +================================================ This is a driver for a graphic framebuffer for Matrox devices on Alpha, Intel and PPC boxes. diff --git a/Documentation/fb/pvr2fb.rst b/Documentation/fb/pvr2fb.rst index fcf2c21c8fcf..315ce085a585 100644 --- a/Documentation/fb/pvr2fb.rst +++ b/Documentation/fb/pvr2fb.rst @@ -1,6 +1,6 @@ -=============== -What is pvr2fb? -=============== +=============================================== +pvr2fb - PowerVR 2 graphics frame buffer driver +=============================================== This is a driver for PowerVR 2 based graphics frame buffers, such as the one found in the Dreamcast. diff --git a/Documentation/fb/sa1100fb.rst b/Documentation/fb/sa1100fb.rst index 67e2650e017d..c5ca019b361a 100644 --- a/Documentation/fb/sa1100fb.rst +++ b/Documentation/fb/sa1100fb.rst @@ -1,9 +1,6 @@ -================= -What is sa1100fb? -================= - -.. [This file is cloned from VesaFB/matroxfb] - +================================================= +sa1100fb - SA-1100 LCD graphic framebuffer driver +================================================= This is a driver for a graphic framebuffer for the SA-1100 LCD controller. diff --git a/Documentation/fb/sisfb.rst b/Documentation/fb/sisfb.rst index 8f4e502ea12e..9982f5ee0560 100644 --- a/Documentation/fb/sisfb.rst +++ b/Documentation/fb/sisfb.rst @@ -1,6 +1,6 @@ -============== -What is sisfb? -============== +===================================== +sisfb - SiS framebuffer device driver +===================================== sisfb is a framebuffer device driver for SiS (Silicon Integrated Systems) graphics chips. Supported are: diff --git a/Documentation/fb/sm712fb.rst b/Documentation/fb/sm712fb.rst index 8e000f80b5bc..abbc6efae25f 100644 --- a/Documentation/fb/sm712fb.rst +++ b/Documentation/fb/sm712fb.rst @@ -1,6 +1,6 @@ -================ -What is sm712fb? -================ +========================================================== +sm712fb - Silicon Motion SM712 graphics framebuffer driver +========================================================== This is a graphics framebuffer driver for Silicon Motion SM712 based processors. diff --git a/Documentation/fb/tgafb.rst b/Documentation/fb/tgafb.rst index 0c50d2134aa4..f0944da1ea5e 100644 --- a/Documentation/fb/tgafb.rst +++ b/Documentation/fb/tgafb.rst @@ -1,6 +1,6 @@ -============== -What is tgafb? -============== +======================================= +tgafb - TGA graphics framebuffer driver +======================================= This is a driver for DECChip 21030 based graphics framebuffers, a.k.a. TGA cards, which are usually found in older Digital Alpha systems. The diff --git a/Documentation/fb/udlfb.rst b/Documentation/fb/udlfb.rst index 99cfbb7a1922..9e75ac6b07c3 100644 --- a/Documentation/fb/udlfb.rst +++ b/Documentation/fb/udlfb.rst @@ -1,6 +1,6 @@ -============== -What is udlfb? -============== +================================== +udlfb - DisplayLink USB 2.0 driver +================================== This is a driver for DisplayLink USB 2.0 era graphics chips. diff --git a/Documentation/fb/vesafb.rst b/Documentation/fb/vesafb.rst index f890a4f5623b..d8241e38bb28 100644 --- a/Documentation/fb/vesafb.rst +++ b/Documentation/fb/vesafb.rst @@ -1,6 +1,6 @@ -=============== -What is vesafb? -=============== +=========================================== +vesafb - Generic graphic framebuffer driver +=========================================== This is a generic driver for a graphic framebuffer on intel boxes. diff --git a/Documentation/sound/cards/emu-mixer.rst b/Documentation/sound/cards/emu-mixer.rst index d87a6338d3d8..edcedada4c96 100644 --- a/Documentation/sound/cards/emu-mixer.rst +++ b/Documentation/sound/cards/emu-mixer.rst @@ -66,7 +66,7 @@ FX-bus name='Clock Source',index=0 --------------------------- -This control allows switching the word clock between interally generated +This control allows switching the word clock between internally generated 44.1 or 48 kHz, or a number of external sources. Note: the sources for the 1616 CardBus card are unclear. Please report your diff --git a/MAINTAINERS b/MAINTAINERS index 3a27901781c2..46126ce2f968 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5694,6 +5694,7 @@ M: Xiubo Li <xiubli@redhat.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ +B: https://tracker.ceph.com/ T: git https://github.com/ceph/ceph-client.git F: include/linux/ceph/ F: include/linux/crush/ @@ -5705,6 +5706,7 @@ M: Ilya Dryomov <idryomov@gmail.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ +B: https://tracker.ceph.com/ T: git https://github.com/ceph/ceph-client.git F: Documentation/filesystems/ceph.rst F: fs/ceph/ @@ -18338,6 +18340,7 @@ F: Documentation/core-api/symbol-namespaces.rst F: scripts/nsdeps NTB AMD DRIVER +M: Basavaraj Natikar <Basavaraj.Natikar@amd.com> M: Shyam Sundar S K <Shyam-sundar.S-k@amd.com> L: ntb@lists.linux.dev S: Supported @@ -19245,6 +19248,7 @@ M: Rob Herring <robh@kernel.org> M: Saravana Kannan <saravanak@google.com> L: devicetree@vger.kernel.org S: Maintained +Q: http://patchwork.kernel.org/project/devicetree/list/ W: http://www.devicetree.org/ C: irc://irc.libera.chat/devicetree T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git @@ -19265,7 +19269,7 @@ M: Krzysztof Kozlowski <krzk+dt@kernel.org> M: Conor Dooley <conor+dt@kernel.org> L: devicetree@vger.kernel.org S: Maintained -Q: http://patchwork.ozlabs.org/project/devicetree-bindings/list/ +Q: http://patchwork.kernel.org/project/devicetree/list/ C: irc://irc.libera.chat/devicetree T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git F: Documentation/devicetree/ @@ -21356,6 +21360,7 @@ R: Dongsheng Yang <dongsheng.yang@easystack.cn> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ +B: https://tracker.ceph.com/ T: git https://github.com/ceph/ceph-client.git F: Documentation/ABI/testing/sysfs-bus-rbd F: drivers/block/rbd.c @@ -23906,7 +23911,7 @@ F: drivers/media/i2c/imx274.c SONY IMX283 SENSOR DRIVER M: Kieran Bingham <kieran.bingham@ideasonboard.com> -M: Umang Jain <umang.jain@ideasonboard.com> +R: Umang Jain <uajain@igalia.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media.git diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 0940c162f1f7..47fd9662d800 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -31,6 +31,9 @@ config PARISC select HAVE_KERNEL_UNCOMPRESSED select HAVE_PCI select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP + select PERF_USE_VMALLOC select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/parisc/include/asm/perf_event.h b/arch/parisc/include/asm/perf_event.h index 1e0fd8ba6c03..8a2925029d15 100644 --- a/arch/parisc/include/asm/perf_event.h +++ b/arch/parisc/include/asm/perf_event.h @@ -1,6 +1,12 @@ #ifndef __ASM_PARISC_PERF_EVENT_H #define __ASM_PARISC_PERF_EVENT_H -/* Empty, just to avoid compiling error */ +#include <asm/psw.h> + +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->gr[0] = KERNEL_PSW; \ + (regs)->iaoq[0] = (__ip); \ + asm volatile("copy %%sp, %0\n":"=r"((regs)->gr[30])); \ +} #endif /* __ASM_PARISC_PERF_EVENT_H */ diff --git a/arch/parisc/include/uapi/asm/ioctls.h b/arch/parisc/include/uapi/asm/ioctls.h index 82d1148c6379..74b4027a4e80 100644 --- a/arch/parisc/include/uapi/asm/ioctls.h +++ b/arch/parisc/include/uapi/asm/ioctls.h @@ -10,10 +10,10 @@ #define TCSETS _IOW('T', 17, struct termios) /* TCSETATTR */ #define TCSETSW _IOW('T', 18, struct termios) /* TCSETATTRD */ #define TCSETSF _IOW('T', 19, struct termios) /* TCSETATTRF */ -#define TCGETA _IOR('T', 1, struct termio) -#define TCSETA _IOW('T', 2, struct termio) -#define TCSETAW _IOW('T', 3, struct termio) -#define TCSETAF _IOW('T', 4, struct termio) +#define TCGETA 0x40125401 +#define TCSETA 0x80125402 +#define TCSETAW 0x80125403 +#define TCSETAF 0x80125404 #define TCSBRK _IO('T', 5) #define TCXONC _IO('T', 6) #define TCFLSH _IO('T', 7) diff --git a/arch/parisc/include/uapi/asm/perf_regs.h b/arch/parisc/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..1ae687bb3d3c --- /dev/null +++ b/arch/parisc/include/uapi/asm/perf_regs.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_PARISC_PERF_REGS_H +#define _UAPI_ASM_PARISC_PERF_REGS_H + +/* see struct user_regs_struct */ +enum perf_event_parisc_regs { + PERF_REG_PARISC_R0, /* PSW is in gr[0] */ + PERF_REG_PARISC_R1, + PERF_REG_PARISC_R2, + PERF_REG_PARISC_R3, + PERF_REG_PARISC_R4, + PERF_REG_PARISC_R5, + PERF_REG_PARISC_R6, + PERF_REG_PARISC_R7, + PERF_REG_PARISC_R8, + PERF_REG_PARISC_R9, + PERF_REG_PARISC_R10, + PERF_REG_PARISC_R11, + PERF_REG_PARISC_R12, + PERF_REG_PARISC_R13, + PERF_REG_PARISC_R14, + PERF_REG_PARISC_R15, + PERF_REG_PARISC_R16, + PERF_REG_PARISC_R17, + PERF_REG_PARISC_R18, + PERF_REG_PARISC_R19, + PERF_REG_PARISC_R20, + PERF_REG_PARISC_R21, + PERF_REG_PARISC_R22, + PERF_REG_PARISC_R23, + PERF_REG_PARISC_R24, + PERF_REG_PARISC_R25, + PERF_REG_PARISC_R26, + PERF_REG_PARISC_R27, + PERF_REG_PARISC_R28, + PERF_REG_PARISC_R29, + PERF_REG_PARISC_R30, + PERF_REG_PARISC_R31, + + PERF_REG_PARISC_SR0, + PERF_REG_PARISC_SR1, + PERF_REG_PARISC_SR2, + PERF_REG_PARISC_SR3, + PERF_REG_PARISC_SR4, + PERF_REG_PARISC_SR5, + PERF_REG_PARISC_SR6, + PERF_REG_PARISC_SR7, + + PERF_REG_PARISC_IAOQ0, + PERF_REG_PARISC_IAOQ1, + PERF_REG_PARISC_IASQ0, + PERF_REG_PARISC_IASQ1, + + PERF_REG_PARISC_SAR, /* CR11 */ + PERF_REG_PARISC_IIR, /* CR19 */ + PERF_REG_PARISC_ISR, /* CR20 */ + PERF_REG_PARISC_IOR, /* CR21 */ + PERF_REG_PARISC_IPSW, /* CR22 */ + + PERF_REG_PARISC_MAX +}; + +#endif /* _UAPI_ASM_PARISC_PERF_REGS_H */ diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index d5055ba33722..9157bc8bdf41 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += topology.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_regs.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KEXEC_CORE) += kexec.o relocate_kernel.o diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 1e793f770f71..1f8936fc2292 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -995,6 +995,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) struct pdc_system_map_mod_info pdc_mod_info; struct pdc_module_path mod_path; + memset(&iodc_data, 0, sizeof(iodc_data)); status = pdc_iodc_read(&count, hpa, 0, &iodc_data, sizeof(iodc_data)); if (status != PDC_OK) { @@ -1012,6 +1013,11 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) mod_index = 0; do { + /* initialize device path for old machines */ + memset(&mod_path, 0xff, sizeof(mod_path)); + get_node_path(dev->dev.parent, &mod_path.path); + mod_path.path.mod = dev->hw_path; + memset(&pdc_mod_info, 0, sizeof(pdc_mod_info)); status = pdc_system_map_find_mods(&pdc_mod_info, &mod_path, mod_index++); } while (status == PDC_OK && pdc_mod_info.mod_addr != hpa); diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index c69f6d5946e9..042343492a28 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -464,7 +464,8 @@ int pdc_system_map_find_mods(struct pdc_system_map_mod_info *pdc_mod_info, unsigned long flags; spin_lock_irqsave(&pdc_lock, flags); - retval = mem_pdc_call(PDC_SYSTEM_MAP, PDC_FIND_MODULE, __pa(pdc_result), + memcpy(pdc_result2, mod_path, sizeof(*mod_path)); + retval = mem_pdc_call(PDC_SYSTEM_MAP, PDC_FIND_MODULE, __pa(pdc_result), __pa(pdc_result2), mod_index); convert_to_wide(pdc_result); memcpy(pdc_mod_info, pdc_result, sizeof(*pdc_mod_info)); diff --git a/arch/parisc/kernel/perf_event.c b/arch/parisc/kernel/perf_event.c new file mode 100644 index 000000000000..f90b83886ab4 --- /dev/null +++ b/arch/parisc/kernel/perf_event.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Performance event support for parisc + * + * Copyright (C) 2025 by Helge Deller <deller@gmx.de> + */ + +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <asm/unwind.h> + +void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + + struct unwind_frame_info info; + + unwind_frame_init_task(&info, current, NULL); + while (1) { + if (unwind_once(&info) < 0 || info.ip == 0) + break; + + if (!__kernel_text_address(info.ip) || + perf_callchain_store(entry, info.ip)) + return; + } +} diff --git a/arch/parisc/kernel/perf_regs.c b/arch/parisc/kernel/perf_regs.c new file mode 100644 index 000000000000..68458e2f6197 --- /dev/null +++ b/arch/parisc/kernel/perf_regs.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Copyright (C) 2025 by Helge Deller <deller@gmx.de> */ + +#include <linux/perf_event.h> +#include <linux/perf_regs.h> +#include <asm/ptrace.h> + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + switch (idx) { + case PERF_REG_PARISC_R0 ... PERF_REG_PARISC_R31: + return regs->gr[idx - PERF_REG_PARISC_R0]; + case PERF_REG_PARISC_SR0 ... PERF_REG_PARISC_SR7: + return regs->sr[idx - PERF_REG_PARISC_SR0]; + case PERF_REG_PARISC_IASQ0 ... PERF_REG_PARISC_IASQ1: + return regs->iasq[idx - PERF_REG_PARISC_IASQ0]; + case PERF_REG_PARISC_IAOQ0 ... PERF_REG_PARISC_IAOQ1: + return regs->iasq[idx - PERF_REG_PARISC_IAOQ0]; + case PERF_REG_PARISC_SAR: /* CR11 */ + return regs->sar; + case PERF_REG_PARISC_IIR: /* CR19 */ + return regs->iir; + case PERF_REG_PARISC_ISR: /* CR20 */ + return regs->isr; + case PERF_REG_PARISC_IOR: /* CR21 */ + return regs->ior; + case PERF_REG_PARISC_IPSW: /* CR22 */ + return regs->ipsw; + }; + WARN_ON_ONCE((u32)idx >= PERF_REG_PARISC_MAX); + return 0; +} + +#define REG_RESERVED (~((1ULL << PERF_REG_PARISC_MAX) - 1)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + if (!IS_ENABLED(CONFIG_64BIT)) + return PERF_SAMPLE_REGS_ABI_32; + + if (test_tsk_thread_flag(task, TIF_32BIT)) + return PERF_SAMPLE_REGS_ABI_32; + + return PERF_SAMPLE_REGS_ABI_64; +} + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b9b3d527bc90..4c7c5df80bd0 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -31,6 +31,7 @@ #include <linux/uaccess.h> #include <linux/kdebug.h> #include <linux/kfence.h> +#include <linux/perf_event.h> #include <asm/assembly.h> #include <asm/io.h> @@ -633,6 +634,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) /* Assist Exception Trap, i.e. floating point exception. */ die_if_kernel("Floating point exception", regs, 0); /* quiet */ __inc_irq_stat(irq_fpassist_count); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); handle_fpe(regs); return; diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 00e97204783e..fb64d9ce0b17 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -13,6 +13,7 @@ #include <linux/uaccess.h> #include <linux/sysctl.h> #include <linux/unaligned.h> +#include <linux/perf_event.h> #include <asm/hardirq.h> #include <asm/traps.h> #include "unaligned.h" @@ -378,6 +379,7 @@ void handle_unaligned(struct pt_regs *regs) int ret = ERR_NOTHANDLED; __inc_irq_stat(irq_unaligned_count); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->ior); /* log a message with pacing */ if (user_mode(regs)) { diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index 69d65ffab312..03165c82dfdb 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -41,7 +41,6 @@ unsigned long raw_copy_from_user(void *dst, const void __user *src, mtsp(get_kernel_space(), SR_TEMP2); /* Check region is user accessible */ - if (start) while (start < end) { if (!prober_user(SR_TEMP1, start)) { newlen = (start - (unsigned long) src); diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index feecf1a6ddb4..d74d4c52ccd0 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -215,6 +215,28 @@ SECTIONS ELF_DETAILS /* + * Make sure that the .got.plt is either completely empty or it + * contains only the three reserved double words. + */ + .got.plt : { + *(.got.plt) + } + ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!") + + /* + * Sections that should stay zero sized, which is safer to + * explicitly check instead of blindly discarding. + */ + .plt : { + *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt) + } + ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") + .rela.dyn : { + *(.rela.*) *(.rela_*) + } + ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") + + /* * uncompressed image info used by the decompressor * it should match struct vmlinux_info */ @@ -244,28 +266,6 @@ SECTIONS #endif } :NONE - /* - * Make sure that the .got.plt is either completely empty or it - * contains only the three reserved double words. - */ - .got.plt : { - *(.got.plt) - } - ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!") - - /* - * Sections that should stay zero sized, which is safer to - * explicitly check instead of blindly discarding. - */ - .plt : { - *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt) - } - ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") - .rela.dyn : { - *(.rela.*) *(.rela_*) - } - ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") - /* Sections to be discarded */ DISCARDS /DISCARD/ : { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d034a987c6e..fa3b616af03a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -412,10 +412,6 @@ config HAVE_INTEL_TXT def_bool y depends on INTEL_IOMMU && ACPI -config X86_64_SMP - def_bool y - depends on X86_64 && SMP - config ARCH_SUPPORTS_UPROBES def_bool y diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler index c827f694fb72..b1c59fb0a4c9 100644 --- a/arch/x86/Kconfig.assembler +++ b/arch/x86/Kconfig.assembler @@ -1,26 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. -config AS_AVX512 - def_bool $(as-instr,vpmovm2b %k1$(comma)%zmm5) - help - Supported by binutils >= 2.25 and LLVM integrated assembler - -config AS_GFNI - def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2) - help - Supported by binutils >= 2.30 and LLVM integrated assembler - -config AS_VAES - def_bool $(as-instr,vaesenc %ymm0$(comma)%ymm1$(comma)%ymm2) - help - Supported by binutils >= 2.30 and LLVM integrated assembler - -config AS_VPCLMULQDQ - def_bool $(as-instr,vpclmulqdq \$0x10$(comma)%ymm0$(comma)%ymm1$(comma)%ymm2) - help - Supported by binutils >= 2.30 and LLVM integrated assembler - config AS_WRUSS def_bool $(as-instr64,wrussq %rax$(comma)(%rbx)) help diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 8518ae214c9b..79e15971529d 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -27,7 +27,7 @@ static inline bool variable_test_bit(int nr, const void *addr) bool v; const u32 *p = addr; - asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr)); + asm("btl %2,%1" : "=@ccc" (v) : "m" (*p), "Ir" (nr)); return v; } diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 60580836daf7..a3c58ebe3662 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -155,15 +155,15 @@ static inline void wrgs32(u32 v, addr_t addr) static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len) { bool diff; - asm volatile("fs repe cmpsb" CC_SET(nz) - : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len)); + asm volatile("fs repe cmpsb" + : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len) { bool diff; - asm volatile("gs repe cmpsb" CC_SET(nz) - : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len)); + asm volatile("gs repe cmpsb" + : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index f35369bb14c5..b25c6a9303b7 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -32,8 +32,8 @@ int memcmp(const void *s1, const void *s2, size_t len) { bool diff; - asm("repe cmpsb" CC_SET(nz) - : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len)); + asm("repe cmpsb" + : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig index d9c6fc78cf33..48d3076b6053 100644 --- a/arch/x86/crypto/Kconfig +++ b/arch/x86/crypto/Kconfig @@ -306,7 +306,7 @@ config CRYPTO_ARIA_AESNI_AVX2_X86_64 config CRYPTO_ARIA_GFNI_AVX512_X86_64 tristate "Ciphers: ARIA with modes: ECB, CTR (AVX512/GFNI)" - depends on 64BIT && AS_GFNI + depends on 64BIT select CRYPTO_SKCIPHER select CRYPTO_ALGAPI select CRYPTO_ARIA diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index dfba7e5e88ea..2d30d5d36145 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -46,10 +46,8 @@ obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o aesni-intel-$(CONFIG_64BIT) += aes-ctr-avx-x86_64.o \ aes-gcm-aesni-x86_64.o \ - aes-xts-avx-x86_64.o -ifeq ($(CONFIG_AS_VAES)$(CONFIG_AS_VPCLMULQDQ),yy) -aesni-intel-$(CONFIG_64BIT) += aes-gcm-avx10-x86_64.o -endif + aes-xts-avx-x86_64.o \ + aes-gcm-avx10-x86_64.o obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o diff --git a/arch/x86/crypto/aes-ctr-avx-x86_64.S b/arch/x86/crypto/aes-ctr-avx-x86_64.S index bbbfd80f5a50..2745918f68ee 100644 --- a/arch/x86/crypto/aes-ctr-avx-x86_64.S +++ b/arch/x86/crypto/aes-ctr-avx-x86_64.S @@ -552,7 +552,6 @@ SYM_TYPED_FUNC_START(aes_xctr_crypt_aesni_avx) _aes_ctr_crypt 1 SYM_FUNC_END(aes_xctr_crypt_aesni_avx) -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) .set VL, 32 .set USE_AVX512, 0 SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx2) @@ -570,4 +569,3 @@ SYM_FUNC_END(aes_ctr64_crypt_vaes_avx512) SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx512) _aes_ctr_crypt 1 SYM_FUNC_END(aes_xctr_crypt_vaes_avx512) -#endif // CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S index db79cdf81588..a30753a3e207 100644 --- a/arch/x86/crypto/aes-xts-avx-x86_64.S +++ b/arch/x86/crypto/aes-xts-avx-x86_64.S @@ -886,7 +886,6 @@ SYM_TYPED_FUNC_START(aes_xts_decrypt_aesni_avx) _aes_xts_crypt 0 SYM_FUNC_END(aes_xts_decrypt_aesni_avx) -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) .set VL, 32 .set USE_AVX512, 0 SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2) @@ -904,4 +903,3 @@ SYM_FUNC_END(aes_xts_encrypt_vaes_avx512) SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx512) _aes_xts_crypt 0 SYM_FUNC_END(aes_xts_decrypt_vaes_avx512) -#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */ diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 061b1ced93c5..d953ac470aae 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -828,10 +828,8 @@ static struct skcipher_alg skcipher_algs_##suffix[] = {{ \ }} DEFINE_AVX_SKCIPHER_ALGS(aesni_avx, "aesni-avx", 500); -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) DEFINE_AVX_SKCIPHER_ALGS(vaes_avx2, "vaes-avx2", 600); DEFINE_AVX_SKCIPHER_ALGS(vaes_avx512, "vaes-avx512", 800); -#endif /* The common part of the x86_64 AES-GCM key struct */ struct aes_gcm_key { @@ -912,17 +910,8 @@ struct aes_gcm_key_avx10 { #define FLAG_RFC4106 BIT(0) #define FLAG_ENC BIT(1) #define FLAG_AVX BIT(2) -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) -# define FLAG_AVX10_256 BIT(3) -# define FLAG_AVX10_512 BIT(4) -#else - /* - * This should cause all calls to the AVX10 assembly functions to be - * optimized out, avoiding the need to ifdef each call individually. - */ -# define FLAG_AVX10_256 0 -# define FLAG_AVX10_512 0 -#endif +#define FLAG_AVX10_256 BIT(3) +#define FLAG_AVX10_512 BIT(4) static inline struct aes_gcm_key * aes_gcm_key_get(struct crypto_aead *tfm, int flags) @@ -1519,7 +1508,6 @@ DEFINE_GCM_ALGS(aesni_avx, FLAG_AVX, "generic-gcm-aesni-avx", "rfc4106-gcm-aesni-avx", AES_GCM_KEY_AESNI_SIZE, 500); -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) /* aes_gcm_algs_vaes_avx10_256 */ DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256, "generic-gcm-vaes-avx10_256", "rfc4106-gcm-vaes-avx10_256", @@ -1529,7 +1517,6 @@ DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256, DEFINE_GCM_ALGS(vaes_avx10_512, FLAG_AVX10_512, "generic-gcm-vaes-avx10_512", "rfc4106-gcm-vaes-avx10_512", AES_GCM_KEY_AVX10_SIZE, 800); -#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */ static int __init register_avx_algs(void) { @@ -1551,7 +1538,6 @@ static int __init register_avx_algs(void) * Similarly, the assembler support was added at about the same time. * For simplicity, just always check for VAES and VPCLMULQDQ together. */ -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_VAES) || !boot_cpu_has(X86_FEATURE_VPCLMULQDQ) || @@ -1592,7 +1578,7 @@ static int __init register_avx_algs(void) ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512)); if (err) return err; -#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */ + return 0; } @@ -1607,12 +1593,10 @@ static void unregister_avx_algs(void) { unregister_skciphers(skcipher_algs_aesni_avx); unregister_aeads(aes_gcm_algs_aesni_avx); -#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) unregister_skciphers(skcipher_algs_vaes_avx2); unregister_skciphers(skcipher_algs_vaes_avx512); unregister_aeads(aes_gcm_algs_vaes_avx10_256); unregister_aeads(aes_gcm_algs_vaes_avx10_512); -#endif } #else /* CONFIG_X86_64 */ static struct aead_alg aes_gcm_algs_aesni[0]; diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index 9556dacd9841..932fb17308e7 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -295,7 +295,6 @@ vpshufb t1, t0, t2; \ vpxor t2, x7, x7; -#ifdef CONFIG_AS_GFNI #define aria_sbox_8way_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ t0, t1, t2, t3, \ @@ -318,8 +317,6 @@ vgf2p8affineinvqb $0, t2, x3, x3; \ vgf2p8affineinvqb $0, t2, x7, x7 -#endif /* CONFIG_AS_GFNI */ - #define aria_sbox_8way(x0, x1, x2, x3, \ x4, x5, x6, x7, \ t0, t1, t2, t3, \ @@ -561,7 +558,6 @@ y4, y5, y6, y7, \ mem_tmp, 8); -#ifdef CONFIG_AS_GFNI #define aria_fe_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ y0, y1, y2, y3, \ @@ -719,8 +715,6 @@ y4, y5, y6, y7, \ mem_tmp, 8); -#endif /* CONFIG_AS_GFNI */ - /* NB: section is mergeable, all elements must be aligned 16-byte blocks */ .section .rodata.cst16, "aM", @progbits, 16 .align 16 @@ -772,7 +766,6 @@ .Ltf_hi__x2__and__fwd_aff: .octa 0x3F893781E95FE1576CDA64D2BA0CB204 -#ifdef CONFIG_AS_GFNI /* AES affine: */ #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) .Ltf_aff_bitmatrix: @@ -871,7 +864,6 @@ BV8(0, 0, 0, 0, 0, 1, 0, 0), BV8(0, 0, 0, 0, 0, 0, 1, 0), BV8(0, 0, 0, 0, 0, 0, 0, 1)) -#endif /* CONFIG_AS_GFNI */ /* 4-bit mask */ .section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 @@ -1140,7 +1132,6 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_ctr_crypt_16way) RET; SYM_FUNC_END(aria_aesni_avx_ctr_crypt_16way) -#ifdef CONFIG_AS_GFNI SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way) /* input: * %r9: rk @@ -1359,4 +1350,3 @@ SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way) FRAME_END RET; SYM_FUNC_END(aria_aesni_avx_gfni_ctr_crypt_16way) -#endif /* CONFIG_AS_GFNI */ diff --git a/arch/x86/crypto/aria-aesni-avx2-asm_64.S b/arch/x86/crypto/aria-aesni-avx2-asm_64.S index c60fa2980630..ed53d4f46bd7 100644 --- a/arch/x86/crypto/aria-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx2-asm_64.S @@ -302,7 +302,6 @@ vpbroadcastb ((round * 16) + idx + 4)(rk), t0; \ vpxor t0, x7, x7; -#ifdef CONFIG_AS_GFNI #define aria_sbox_8way_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ t0, t1, t2, t3, \ @@ -325,7 +324,6 @@ vgf2p8affineinvqb $0, t2, x3, x3; \ vgf2p8affineinvqb $0, t2, x7, x7 -#endif /* CONFIG_AS_GFNI */ #define aria_sbox_8way(x0, x1, x2, x3, \ x4, x5, x6, x7, \ t0, t1, t2, t3, \ @@ -598,7 +596,7 @@ aria_load_state_8way(y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, 8); -#ifdef CONFIG_AS_GFNI + #define aria_fe_gfni(x0, x1, x2, x3, \ x4, x5, x6, x7, \ y0, y1, y2, y3, \ @@ -752,7 +750,6 @@ aria_load_state_8way(y0, y1, y2, y3, \ y4, y5, y6, y7, \ mem_tmp, 8); -#endif /* CONFIG_AS_GFNI */ .section .rodata.cst32.shufb_16x16b, "aM", @progbits, 32 .align 32 @@ -806,7 +803,6 @@ .Ltf_hi__x2__and__fwd_aff: .octa 0x3F893781E95FE1576CDA64D2BA0CB204 -#ifdef CONFIG_AS_GFNI .section .rodata.cst8, "aM", @progbits, 8 .align 8 /* AES affine: */ @@ -868,8 +864,6 @@ BV8(0, 0, 0, 0, 0, 0, 1, 0), BV8(0, 0, 0, 0, 0, 0, 0, 1)) -#endif /* CONFIG_AS_GFNI */ - /* 4-bit mask */ .section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 .align 4 @@ -1219,7 +1213,6 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_ctr_crypt_32way) RET; SYM_FUNC_END(aria_aesni_avx2_ctr_crypt_32way) -#ifdef CONFIG_AS_GFNI SYM_FUNC_START_LOCAL(__aria_aesni_avx2_gfni_crypt_32way) /* input: * %r9: rk @@ -1438,4 +1431,3 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_ctr_crypt_32way) FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_ctr_crypt_32way) -#endif /* CONFIG_AS_GFNI */ diff --git a/arch/x86/crypto/aria_aesni_avx2_glue.c b/arch/x86/crypto/aria_aesni_avx2_glue.c index 007b250f774c..1487a49bfbac 100644 --- a/arch/x86/crypto/aria_aesni_avx2_glue.c +++ b/arch/x86/crypto/aria_aesni_avx2_glue.c @@ -26,7 +26,6 @@ asmlinkage void aria_aesni_avx2_ctr_crypt_32way(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); EXPORT_SYMBOL_GPL(aria_aesni_avx2_ctr_crypt_32way); -#ifdef CONFIG_AS_GFNI asmlinkage void aria_aesni_avx2_gfni_encrypt_32way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_encrypt_32way); @@ -37,7 +36,6 @@ asmlinkage void aria_aesni_avx2_gfni_ctr_crypt_32way(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_ctr_crypt_32way); -#endif /* CONFIG_AS_GFNI */ static struct aria_avx_ops aria_ops; @@ -213,7 +211,7 @@ static int __init aria_avx2_init(void) return -ENODEV; } - if (boot_cpu_has(X86_FEATURE_GFNI) && IS_ENABLED(CONFIG_AS_GFNI)) { + if (boot_cpu_has(X86_FEATURE_GFNI)) { aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way; aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way; aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way; diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c index 4c88ef4eba82..e4e3d78915a5 100644 --- a/arch/x86/crypto/aria_aesni_avx_glue.c +++ b/arch/x86/crypto/aria_aesni_avx_glue.c @@ -26,7 +26,6 @@ asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); EXPORT_SYMBOL_GPL(aria_aesni_avx_ctr_crypt_16way); -#ifdef CONFIG_AS_GFNI asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_encrypt_16way); @@ -37,7 +36,6 @@ asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_ctr_crypt_16way); -#endif /* CONFIG_AS_GFNI */ static struct aria_avx_ops aria_ops; @@ -199,7 +197,7 @@ static int __init aria_avx_init(void) return -ENODEV; } - if (boot_cpu_has(X86_FEATURE_GFNI) && IS_ENABLED(CONFIG_AS_GFNI)) { + if (boot_cpu_has(X86_FEATURE_GFNI)) { aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way; aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way; aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way; diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 94519688b007..77e2d920a640 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -99,7 +99,7 @@ For 32-bit we have the following conventions - kernel is built with .endif .endm -.macro CLEAR_REGS clear_bp=1 +.macro CLEAR_REGS clear_callee=1 /* * Sanitize registers of values that a speculation attack might * otherwise want to exploit. The lower registers are likely clobbered @@ -113,20 +113,19 @@ For 32-bit we have the following conventions - kernel is built with xorl %r9d, %r9d /* nospec r9 */ xorl %r10d, %r10d /* nospec r10 */ xorl %r11d, %r11d /* nospec r11 */ + .if \clear_callee xorl %ebx, %ebx /* nospec rbx */ - .if \clear_bp xorl %ebp, %ebp /* nospec rbp */ - .endif xorl %r12d, %r12d /* nospec r12 */ xorl %r13d, %r13d /* nospec r13 */ xorl %r14d, %r14d /* nospec r14 */ xorl %r15d, %r15d /* nospec r15 */ - + .endif .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_bp=1 unwind_hint=1 +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_callee=1 unwind_hint=1 PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret unwind_hint=\unwind_hint - CLEAR_REGS clear_bp=\clear_bp + CLEAR_REGS clear_callee=\clear_callee .endm .macro POP_REGS pop_rdi=1 diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S index 907bd233c6c1..fafbd3e68cb8 100644 --- a/arch/x86/entry/entry_64_fred.S +++ b/arch/x86/entry/entry_64_fred.S @@ -97,8 +97,7 @@ SYM_FUNC_START(asm_fred_entry_from_kvm) push %rdi /* fred_ss handed in by the caller */ push %rbp pushf - mov $__KERNEL_CS, %rax - push %rax + push $__KERNEL_CS /* * Unlike the IDT event delivery, FRED _always_ pushes an error code @@ -112,18 +111,37 @@ SYM_FUNC_START(asm_fred_entry_from_kvm) push %rax /* Return RIP */ push $0 /* Error code, 0 for IRQ/NMI */ - PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0 + PUSH_AND_CLEAR_REGS clear_callee=0 unwind_hint=0 + movq %rsp, %rdi /* %rdi -> pt_regs */ + /* + * At this point: {rdi, rsi, rdx, rcx, r8, r9}, {r10, r11}, {rax, rdx} + * are clobbered, which corresponds to: arguments, extra caller-saved + * and return. All registers a C function is allowed to clobber. + * + * Notably, the callee-saved registers: {rbx, r12, r13, r14, r15} + * are untouched, with the exception of rbp, which carries the stack + * frame and will be restored before exit. + * + * Further calling another C function will not alter this state. + */ call __fred_entry_from_kvm /* Call the C entry point */ - POP_REGS - ERETS -1: + /* - * Objtool doesn't understand what ERETS does, this hint tells it that - * yes, we'll reach here and with what stack state. A save/restore pair - * isn't strictly needed, but it's the simplest form. + * When FRED, use ERETS to potentially clear NMIs, otherwise simply + * restore the stack pointer. + */ + ALTERNATIVE "nop; nop; mov %rbp, %rsp", \ + __stringify(add $C_PTREGS_SIZE, %rsp; ERETS), \ + X86_FEATURE_FRED + +1: /* + * Objtool doesn't understand ERETS, and the cfi register state is + * different from initial_func_cfi due to PUSH_REGS. Tell it the state + * is similar to where UNWIND_HINT_SAVE is. */ UNWIND_HINT_RESTORE + pop %rbp RET diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index afdbda2dd7b7..e890fd37e9c2 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -17,7 +17,6 @@ #include <asm/desc.h> #include <asm/e820/api.h> #include <asm/sev.h> -#include <asm/ibt.h> #include <asm/hypervisor.h> #include <hyperv/hvhdk.h> #include <asm/mshyperv.h> @@ -37,7 +36,45 @@ #include <linux/export.h> void *hv_hypercall_pg; + +#ifdef CONFIG_X86_64 +static u64 __hv_hyperfail(u64 control, u64 param1, u64 param2) +{ + return U64_MAX; +} + +DEFINE_STATIC_CALL(__hv_hypercall, __hv_hyperfail); + +u64 hv_std_hypercall(u64 control, u64 param1, u64 param2) +{ + u64 hv_status; + + register u64 __r8 asm("r8") = param2; + asm volatile ("call " STATIC_CALL_TRAMP_STR(__hv_hypercall) + : "=a" (hv_status), ASM_CALL_CONSTRAINT, + "+c" (control), "+d" (param1), "+r" (__r8) + : : "cc", "memory", "r9", "r10", "r11"); + + return hv_status; +} + +typedef u64 (*hv_hypercall_f)(u64 control, u64 param1, u64 param2); + +static inline void hv_set_hypercall_pg(void *ptr) +{ + hv_hypercall_pg = ptr; + + if (!ptr) + ptr = &__hv_hyperfail; + static_call_update(__hv_hypercall, (hv_hypercall_f)ptr); +} +#else +static inline void hv_set_hypercall_pg(void *ptr) +{ + hv_hypercall_pg = ptr; +} EXPORT_SYMBOL_GPL(hv_hypercall_pg); +#endif union hv_ghcb * __percpu *hv_ghcb_pg; @@ -330,7 +367,7 @@ static int hv_suspend(void) * pointer is restored on resume. */ hv_hypercall_pg_saved = hv_hypercall_pg; - hv_hypercall_pg = NULL; + hv_set_hypercall_pg(NULL); /* Disable the hypercall page in the hypervisor */ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); @@ -356,7 +393,7 @@ static void hv_resume(void) vmalloc_to_pfn(hv_hypercall_pg_saved); wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - hv_hypercall_pg = hv_hypercall_pg_saved; + hv_set_hypercall_pg(hv_hypercall_pg_saved); hv_hypercall_pg_saved = NULL; /* @@ -476,8 +513,8 @@ void __init hyperv_init(void) if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present) goto skip_hypercall_pg_init; - hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, - VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, MODULES_VADDR, + MODULES_END, GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); if (hv_hypercall_pg == NULL) @@ -515,27 +552,9 @@ void __init hyperv_init(void) wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); } -skip_hypercall_pg_init: - /* - * Some versions of Hyper-V that provide IBT in guest VMs have a bug - * in that there's no ENDBR64 instruction at the entry to the - * hypercall page. Because hypercalls are invoked via an indirect call - * to the hypercall page, all hypercall attempts fail when IBT is - * enabled, and Linux panics. For such buggy versions, disable IBT. - * - * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall - * page, so if future Linux kernel versions enable IBT for 32-bit - * builds, additional hypercall page hackery will be required here - * to provide an ENDBR32. - */ -#ifdef CONFIG_X86_KERNEL_IBT - if (cpu_feature_enabled(X86_FEATURE_IBT) && - *(u32 *)hv_hypercall_pg != gen_endbr()) { - setup_clear_cpu_cap(X86_FEATURE_IBT); - pr_warn("Disabling IBT because of Hyper-V bug\n"); - } -#endif + hv_set_hypercall_pg(hv_hypercall_pg); +skip_hypercall_pg_init: /* * hyperv_init() is called before LAPIC is initialized: see * apic_intr_mode_init() -> x86_platform.apic_post_init() and diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index a4615b889f3e..651771534cae 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -385,9 +385,23 @@ int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu) return ret; } +u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2) +{ + u64 hv_status; + + register u64 __r8 asm("r8") = param2; + asm volatile("vmmcall" + : "=a" (hv_status), ASM_CALL_CONSTRAINT, + "+c" (control), "+d" (param1), "+r" (__r8) + : : "cc", "memory", "r9", "r10", "r11"); + + return hv_status; +} + #else static inline void hv_ghcb_msr_write(u64 msr, u64 value) {} static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} +u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2) { return U64_MAX; } #endif /* CONFIG_AMD_MEM_ENCRYPT */ #ifdef CONFIG_INTEL_TDX_GUEST @@ -437,6 +451,7 @@ u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2) #else static inline void hv_tdx_msr_write(u64 msr, u64 value) {} static inline void hv_tdx_msr_read(u64 msr, u64 *value) {} +u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2) { return U64_MAX; } #endif /* CONFIG_INTEL_TDX_GUEST */ #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index 02bae8e0758b..4c305305871b 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -23,8 +23,7 @@ static inline bool __must_check rdrand_long(unsigned long *v) unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" - CC_SET(c) - : CC_OUT(c) (ok), [out] "=r" (*v)); + : "=@ccc" (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); @@ -35,8 +34,7 @@ static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile("rdseed %[out]" - CC_SET(c) - : CC_OUT(c) (ok), [out] "=r" (*v)); + : "=@ccc" (ok), [out] "=r" (*v)); return ok; } diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index f963848024a5..d5c8d3afe196 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -122,18 +122,6 @@ static __always_inline __pure void *rip_rel_ptr(void *p) } #endif -/* - * Macros to generate condition code outputs from inline assembly, - * The output operand must be type "bool". - */ -#ifdef __GCC_ASM_FLAG_OUTPUTS__ -# define CC_SET(c) "\n\t/* output condition code " #c "*/\n" -# define CC_OUT(c) "=@cc" #c -#else -# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n" -# define CC_OUT(c) [_cc_ ## c] "=qm" -#endif - #ifdef __KERNEL__ # include <asm/extable_fixup_types.h> diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index a835f891164d..c2ce213f2b9b 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -99,8 +99,7 @@ static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, { bool negative; asm_inline volatile(LOCK_PREFIX "xorb %2,%1" - CC_SET(s) - : CC_OUT(s) (negative), WBYTE_ADDR(addr) + : "=@ccs" (negative), WBYTE_ADDR(addr) : "iq" ((char)mask) : "memory"); return negative; } @@ -149,8 +148,7 @@ arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) bool oldbit; asm(__ASM_SIZE(bts) " %2,%1" - CC_SET(c) - : CC_OUT(c) (oldbit) + : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -175,8 +173,7 @@ arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) bool oldbit; asm volatile(__ASM_SIZE(btr) " %2,%1" - CC_SET(c) - : CC_OUT(c) (oldbit) + : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -187,8 +184,7 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) bool oldbit; asm volatile(__ASM_SIZE(btc) " %2,%1" - CC_SET(c) - : CC_OUT(c) (oldbit) + : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; @@ -211,8 +207,7 @@ static __always_inline bool constant_test_bit_acquire(long nr, const volatile un bool oldbit; asm volatile("testb %2,%1" - CC_SET(nz) - : CC_OUT(nz) (oldbit) + : "=@ccnz" (oldbit) : "m" (((unsigned char *)addr)[nr >> 3]), "i" (1 << (nr & 7)) :"memory"); @@ -225,8 +220,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l bool oldbit; asm volatile(__ASM_SIZE(bt) " %2,%1" - CC_SET(c) - : CC_OUT(c) (oldbit) + : "=@ccc" (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 20fcb8507ad1..880ca15073ed 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -5,14 +5,19 @@ #include <linux/stringify.h> #include <linux/instrumentation.h> #include <linux/objtool.h> +#include <asm/asm.h> /* * Despite that some emulators terminate on UD2, we use it for WARN(). */ -#define ASM_UD2 ".byte 0x0f, 0x0b" +#define ASM_UD2 _ASM_BYTES(0x0f, 0x0b) #define INSN_UD2 0x0b0f #define LEN_UD2 2 +#define ASM_UDB _ASM_BYTES(0xd6) +#define INSN_UDB 0xd6 +#define LEN_UDB 1 + /* * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit. */ @@ -26,7 +31,7 @@ #define BUG_UD2 0xfffe #define BUG_UD1 0xfffd #define BUG_UD1_UBSAN 0xfffc -#define BUG_EA 0xffea +#define BUG_UDB 0xffd6 #define BUG_LOCK 0xfff0 #ifdef CONFIG_GENERIC_BUG diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index 976b90a3d190..c40b9ebc1fb4 100644 --- a/arch/x86/include/asm/cfi.h +++ b/arch/x86/include/asm/cfi.h @@ -71,12 +71,10 @@ * * __cfi_foo: * endbr64 - * subl 0x12345678, %r10d - * jz foo - * ud2 - * nop + * subl 0x12345678, %eax + * jne.32,pn foo+3 * foo: - * osp nop3 # was endbr64 + * nopl -42(%rax) # was endbr64 * ... code here ... * ret * @@ -86,9 +84,9 @@ * indirect caller: * lea foo(%rip), %r11 * ... - * movl $0x12345678, %r10d - * subl $16, %r11 - * nop4 + * movl $0x12345678, %eax + * lea -0x10(%r11), %r11 + * nop5 * call *%r11 * */ diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index b61f32c3459f..a88b06f1c35e 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -166,8 +166,7 @@ extern void __add_wrong_size(void) { \ volatile u8 *__ptr = (volatile u8 *)(_ptr); \ asm_inline volatile(lock "cmpxchgb %[new], %[ptr]" \ - CC_SET(z) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [ptr] "+m" (*__ptr), \ [old] "+a" (__old) \ : [new] "q" (__new) \ @@ -178,8 +177,7 @@ extern void __add_wrong_size(void) { \ volatile u16 *__ptr = (volatile u16 *)(_ptr); \ asm_inline volatile(lock "cmpxchgw %[new], %[ptr]" \ - CC_SET(z) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [ptr] "+m" (*__ptr), \ [old] "+a" (__old) \ : [new] "r" (__new) \ @@ -190,8 +188,7 @@ extern void __add_wrong_size(void) { \ volatile u32 *__ptr = (volatile u32 *)(_ptr); \ asm_inline volatile(lock "cmpxchgl %[new], %[ptr]" \ - CC_SET(z) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [ptr] "+m" (*__ptr), \ [old] "+a" (__old) \ : [new] "r" (__new) \ @@ -202,8 +199,7 @@ extern void __add_wrong_size(void) { \ volatile u64 *__ptr = (volatile u64 *)(_ptr); \ asm_inline volatile(lock "cmpxchgq %[new], %[ptr]" \ - CC_SET(z) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [ptr] "+m" (*__ptr), \ [old] "+a" (__old) \ : [new] "r" (__new) \ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 371f7906019e..1f80a62be969 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -46,8 +46,7 @@ static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new bool ret; \ \ asm_inline volatile(_lock "cmpxchg8b %[ptr]" \ - CC_SET(e) \ - : CC_OUT(e) (ret), \ + : "=@ccz" (ret), \ [ptr] "+m" (*(_ptr)), \ "+a" (o.low), "+d" (o.high) \ : "b" (n.low), "c" (n.high) \ @@ -125,8 +124,7 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 ALTERNATIVE(_lock_loc \ "call cmpxchg8b_emu", \ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \ - CC_SET(e) \ - : ALT_OUTPUT_SP(CC_OUT(e) (ret), \ + : ALT_OUTPUT_SP("=@ccz" (ret), \ "+a" (o.low), "+d" (o.high)) \ : "b" (n.low), "c" (n.high), \ [ptr] "S" (_ptr) \ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 71d1e72ed879..5afea056fb20 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -66,8 +66,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old, bool ret; \ \ asm_inline volatile(_lock "cmpxchg16b %[ptr]" \ - CC_SET(e) \ - : CC_OUT(e) (ret), \ + : "=@ccz" (ret), \ [ptr] "+m" (*(_ptr)), \ "+a" (o.low), "+d" (o.high) \ : "b" (n.low), "c" (n.high) \ diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h index 28d845257303..5e45d6424722 100644 --- a/arch/x86/include/asm/ibt.h +++ b/arch/x86/include/asm/ibt.h @@ -59,10 +59,10 @@ static __always_inline __attribute_const__ u32 gen_endbr(void) static __always_inline __attribute_const__ u32 gen_endbr_poison(void) { /* - * 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it - * will be unique to (former) ENDBR sites. + * 4 byte NOP that isn't NOP4, such that it will be unique to (former) + * ENDBR sites. Additionally it carries UDB as immediate. */ - return 0x001f0f66; /* osp nopl (%rax) */ + return 0xd6401f0f; /* nopl -42(%rax) */ } static inline bool __is_endbr(u32 val) @@ -70,10 +70,6 @@ static inline bool __is_endbr(u32 val) if (val == gen_endbr_poison()) return true; - /* See cfi_fineibt_bhi_preamble() */ - if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5) - return true; - val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */ return val == gen_endbr(); } diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index a4ec27c67988..abd637e54e94 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -460,17 +460,12 @@ __visible noinstr void func(struct pt_regs *regs, \ #endif void idt_install_sysvec(unsigned int n, const void *function); - -#ifdef CONFIG_X86_FRED void fred_install_sysvec(unsigned int vector, const idtentry_t function); -#else -static inline void fred_install_sysvec(unsigned int vector, const idtentry_t function) { } -#endif #define sysvec_install(vector, function) { \ - if (cpu_feature_enabled(X86_FEATURE_FRED)) \ + if (IS_ENABLED(CONFIG_X86_FRED)) \ fred_install_sysvec(vector, function); \ - else \ + if (!cpu_feature_enabled(X86_FEATURE_FRED)) \ idt_install_sysvec(vector, asm_##function); \ } diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index abc4659f5809..605abd02158d 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -6,6 +6,7 @@ #include <linux/nmi.h> #include <linux/msi.h> #include <linux/io.h> +#include <linux/static_call.h> #include <asm/nospec-branch.h> #include <asm/paravirt.h> #include <asm/msr.h> @@ -39,16 +40,21 @@ static inline unsigned char hv_get_nmi_reason(void) return 0; } -#if IS_ENABLED(CONFIG_HYPERV) -extern bool hyperv_paravisor_present; +extern u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2); +extern u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2); +extern u64 hv_std_hypercall(u64 control, u64 param1, u64 param2); +#if IS_ENABLED(CONFIG_HYPERV) extern void *hv_hypercall_pg; extern union hv_ghcb * __percpu *hv_ghcb_pg; bool hv_isolation_type_snp(void); bool hv_isolation_type_tdx(void); -u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2); + +#ifdef CONFIG_X86_64 +DECLARE_STATIC_CALL(hv_hypercall, hv_std_hypercall); +#endif /* * DEFAULT INIT GPAT and SEGMENT LIMIT value in struct VMSA @@ -65,37 +71,15 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) { u64 input_address = input ? virt_to_phys(input) : 0; u64 output_address = output ? virt_to_phys(output) : 0; - u64 hv_status; #ifdef CONFIG_X86_64 - if (hv_isolation_type_tdx() && !hyperv_paravisor_present) - return hv_tdx_hypercall(control, input_address, output_address); - - if (hv_isolation_type_snp() && !hyperv_paravisor_present) { - __asm__ __volatile__("mov %[output_address], %%r8\n" - "vmmcall" - : "=a" (hv_status), ASM_CALL_CONSTRAINT, - "+c" (control), "+d" (input_address) - : [output_address] "r" (output_address) - : "cc", "memory", "r8", "r9", "r10", "r11"); - return hv_status; - } - - if (!hv_hypercall_pg) - return U64_MAX; - - __asm__ __volatile__("mov %[output_address], %%r8\n" - CALL_NOSPEC - : "=a" (hv_status), ASM_CALL_CONSTRAINT, - "+c" (control), "+d" (input_address) - : [output_address] "r" (output_address), - THUNK_TARGET(hv_hypercall_pg) - : "cc", "memory", "r8", "r9", "r10", "r11"); + return static_call_mod(hv_hypercall)(control, input_address, output_address); #else u32 input_address_hi = upper_32_bits(input_address); u32 input_address_lo = lower_32_bits(input_address); u32 output_address_hi = upper_32_bits(output_address); u32 output_address_lo = lower_32_bits(output_address); + u64 hv_status; if (!hv_hypercall_pg) return U64_MAX; @@ -108,48 +92,30 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) "D"(output_address_hi), "S"(output_address_lo), THUNK_TARGET(hv_hypercall_pg) : "cc", "memory"); -#endif /* !x86_64 */ return hv_status; +#endif /* !x86_64 */ } /* Fast hypercall with 8 bytes of input and no output */ static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1) { - u64 hv_status; - #ifdef CONFIG_X86_64 - if (hv_isolation_type_tdx() && !hyperv_paravisor_present) - return hv_tdx_hypercall(control, input1, 0); - - if (hv_isolation_type_snp() && !hyperv_paravisor_present) { - __asm__ __volatile__( - "vmmcall" - : "=a" (hv_status), ASM_CALL_CONSTRAINT, - "+c" (control), "+d" (input1) - :: "cc", "r8", "r9", "r10", "r11"); - } else { - __asm__ __volatile__(CALL_NOSPEC - : "=a" (hv_status), ASM_CALL_CONSTRAINT, - "+c" (control), "+d" (input1) - : THUNK_TARGET(hv_hypercall_pg) - : "cc", "r8", "r9", "r10", "r11"); - } + return static_call_mod(hv_hypercall)(control, input1, 0); #else - { - u32 input1_hi = upper_32_bits(input1); - u32 input1_lo = lower_32_bits(input1); - - __asm__ __volatile__ (CALL_NOSPEC - : "=A"(hv_status), - "+c"(input1_lo), - ASM_CALL_CONSTRAINT - : "A" (control), - "b" (input1_hi), - THUNK_TARGET(hv_hypercall_pg) - : "cc", "edi", "esi"); - } -#endif + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u64 hv_status; + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), + ASM_CALL_CONSTRAINT + : "A" (control), + "b" (input1_hi), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "edi", "esi"); return hv_status; +#endif } static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) @@ -162,45 +128,24 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) /* Fast hypercall with 16 bytes of input */ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2) { - u64 hv_status; - #ifdef CONFIG_X86_64 - if (hv_isolation_type_tdx() && !hyperv_paravisor_present) - return hv_tdx_hypercall(control, input1, input2); - - if (hv_isolation_type_snp() && !hyperv_paravisor_present) { - __asm__ __volatile__("mov %[input2], %%r8\n" - "vmmcall" - : "=a" (hv_status), ASM_CALL_CONSTRAINT, - "+c" (control), "+d" (input1) - : [input2] "r" (input2) - : "cc", "r8", "r9", "r10", "r11"); - } else { - __asm__ __volatile__("mov %[input2], %%r8\n" - CALL_NOSPEC - : "=a" (hv_status), ASM_CALL_CONSTRAINT, - "+c" (control), "+d" (input1) - : [input2] "r" (input2), - THUNK_TARGET(hv_hypercall_pg) - : "cc", "r8", "r9", "r10", "r11"); - } + return static_call_mod(hv_hypercall)(control, input1, input2); #else - { - u32 input1_hi = upper_32_bits(input1); - u32 input1_lo = lower_32_bits(input1); - u32 input2_hi = upper_32_bits(input2); - u32 input2_lo = lower_32_bits(input2); - - __asm__ __volatile__ (CALL_NOSPEC - : "=A"(hv_status), - "+c"(input1_lo), ASM_CALL_CONSTRAINT - : "A" (control), "b" (input1_hi), - "D"(input2_hi), "S"(input2_lo), - THUNK_TARGET(hv_hypercall_pg) - : "cc"); - } -#endif + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u32 input2_hi = upper_32_bits(input2); + u32 input2_lo = lower_32_bits(input2); + u64 hv_status; + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), ASM_CALL_CONSTRAINT + : "A" (control), "b" (input1_hi), + "D"(input2_hi), "S"(input2_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc"); return hv_status; +#endif } static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index c69e269937c5..76b95bd1a405 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -1,21 +1,8 @@ +/* SPDX-License-Identifier: LGPL-2.0+ */ /* Generic MTRR (Memory Type Range Register) ioctls. Copyright (C) 1997-1999 Richard Gooch - This library is free software; you can redistribute it and/or - modify it under the terms of the GNU Library General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later version. - - This library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Library General Public License for more details. - - You should have received a copy of the GNU Library General Public - License along with this library; if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - Richard Gooch may be reached by email at rgooch@atnf.csiro.au The postal address is: Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia. diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 6ca6516c7492..e4815e15dc9a 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -36,9 +36,7 @@ static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx) static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx) { - /* "monitorx %eax, %ecx, %edx" */ - asm volatile(".byte 0x0f, 0x01, 0xfa" - :: "a" (eax), "c" (ecx), "d"(edx)); + asm volatile("monitorx" :: "a" (eax), "c" (ecx), "d"(edx)); } static __always_inline void __mwait(u32 eax, u32 ecx) @@ -80,9 +78,7 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx) { /* No need for TSA buffer clearing on AMD */ - /* "mwaitx %eax, %ebx, %ecx" */ - asm volatile(".byte 0x0f, 0x01, 0xfb" - :: "a" (eax), "b" (ebx), "c" (ecx)); + asm volatile("mwaitx" :: "a" (eax), "b" (ebx), "c" (ecx)); } /* diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index b0d03b6c279b..332428caaed2 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -309,8 +309,7 @@ do { \ \ asm qual (__pcpu_op_##size("cmpxchg") "%[nval], " \ __percpu_arg([var]) \ - CC_SET(z) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [oval] "+a" (pco_old__), \ [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pco_new__) \ @@ -367,8 +366,7 @@ do { \ asm_inline qual ( \ ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ - CC_SET(z) \ - : ALT_OUTPUT_SP(CC_OUT(z) (success), \ + : ALT_OUTPUT_SP("=@ccz" (success), \ [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), "+d" (old__.high)) \ : "b" (new__.low), "c" (new__.high), \ @@ -436,8 +434,7 @@ do { \ asm_inline qual ( \ ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ - CC_SET(z) \ - : ALT_OUTPUT_SP(CC_OUT(z) (success), \ + : ALT_OUTPUT_SP("=@ccz" (success), \ [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), "+d" (old__.high)) \ : "b" (new__.low), "c" (new__.high), \ @@ -585,8 +582,7 @@ do { \ bool oldbit; \ \ asm volatile("btl %[nr], " __percpu_arg([var]) \ - CC_SET(c) \ - : CC_OUT(c) (oldbit) \ + : "=@ccc" (oldbit) \ : [var] "m" (__my_cpu_var(_var)), \ [nr] "rI" (_nr)); \ oldbit; \ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 3821ee3fae35..54c8fc430684 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -6,37 +6,15 @@ #define __CLOBBERS_MEM(clb...) "memory", ## clb -#ifndef __GCC_ASM_FLAG_OUTPUTS__ - -/* Use asm goto */ - -#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ -({ \ - bool c = false; \ - asm goto (fullop "; j" #cc " %l[cc_label]" \ - : : [var] "m" (_var), ## __VA_ARGS__ \ - : clobbers : cc_label); \ - if (0) { \ -cc_label: c = true; \ - } \ - c; \ -}) - -#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */ - -/* Use flags output or a set instruction */ - #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ ({ \ bool c; \ - asm_inline volatile (fullop CC_SET(cc) \ - : [var] "+m" (_var), CC_OUT(cc) (c) \ + asm_inline volatile (fullop \ + : [var] "+m" (_var), "=@cc" #cc (c) \ : __VA_ARGS__ : clobbers); \ c; \ }) -#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */ - #define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \ __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index f9046c4b9a2b..0e6c0940100f 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -491,8 +491,7 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) /* "pvalidate" mnemonic support in binutils 2.36 and newer */ asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t" - CC_SET(c) - : CC_OUT(c) (no_rmpupdate), "=a"(rc) + : "=@ccc"(no_rmpupdate), "=a"(rc) : "a"(vaddr), "c"(rmp_psize), "d"(validate) : "memory", "cc"); diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index c72d46175374..5c03aaa89014 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -83,8 +83,7 @@ static inline int __const_sigismember(sigset_t *set, int _sig) static inline int __gen_sigismember(sigset_t *set, int _sig) { bool ret; - asm("btl %2,%1" CC_SET(c) - : CC_OUT(c) (ret) : "m"(*set), "Ir"(_sig-1)); + asm("btl %2,%1" : "=@ccc"(ret) : "m"(*set), "Ir"(_sig-1)); return ret; } diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index fde2bd7af19e..46aa2c9c1bda 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -75,9 +75,7 @@ static inline u32 rdpkru(void) * "rdpkru" instruction. Places PKRU contents in to EAX, * clears EDX and requires that ecx=0. */ - asm volatile(".byte 0x0f,0x01,0xee\n\t" - : "=a" (pkru), "=d" (edx) - : "c" (ecx)); + asm volatile("rdpkru" : "=a" (pkru), "=d" (edx) : "c" (ecx)); return pkru; } @@ -89,8 +87,7 @@ static inline void wrpkru(u32 pkru) * "wrpkru" instruction. Loads contents in EAX to PKRU, * requires that ecx = edx = 0. */ - asm volatile(".byte 0x0f,0x01,0xef\n\t" - : : "a" (pkru), "c"(ecx), "d"(edx)); + asm volatile("wrpkru" : : "a" (pkru), "c"(ecx), "d"(edx)); } #else @@ -287,8 +284,7 @@ static inline int enqcmds(void __iomem *dst, const void *src) * See movdir64b()'s comment on operand specification. */ asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" - CC_SET(z) - : CC_OUT(z) (zf), "+m" (*__dst) + : "=@ccz" (zf), "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); /* Submission failure is indicated via EFLAGS.ZF=1 */ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 5337f1be18f6..f2d142a0a862 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -178,9 +178,9 @@ void int3_emulate_ret(struct pt_regs *regs) } static __always_inline -void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) +bool __emulate_cc(unsigned long flags, u8 cc) { - static const unsigned long jcc_mask[6] = { + static const unsigned long cc_mask[6] = { [0] = X86_EFLAGS_OF, [1] = X86_EFLAGS_CF, [2] = X86_EFLAGS_ZF, @@ -193,15 +193,21 @@ void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned lo bool match; if (cc < 0xc) { - match = regs->flags & jcc_mask[cc >> 1]; + match = flags & cc_mask[cc >> 1]; } else { - match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ - ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); + match = ((flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ + ((flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); if (cc >= 0xe) - match = match || (regs->flags & X86_EFLAGS_ZF); + match = match || (flags & X86_EFLAGS_ZF); } - if ((match && !invert) || (!match && invert)) + return (match && !invert) || (!match && invert); +} + +static __always_inline +void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) +{ + if (__emulate_cc(regs->flags, cc)) ip += disp; int3_emulate_jmp(regs, ip); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 3a7755c1a441..91a3fb8ae7ff 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -378,7 +378,7 @@ do { \ asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ @@ -397,7 +397,7 @@ do { \ asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ @@ -417,11 +417,10 @@ do { \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ - CC_SET(z) \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[errout]) \ - : CC_OUT(z) (success), \ + : "=@ccz" (success), \ [errout] "+r" (__err), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 79ae9cb50019..8ee5ff547357 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -147,10 +147,10 @@ static void *its_init_thunk(void *thunk, int reg) /* * When ITS uses indirect branch thunk the fineibt_paranoid * caller sequence doesn't fit in the caller site. So put the - * remaining part of the sequence (<ea> + JNE) into the ITS + * remaining part of the sequence (UDB + JNE) into the ITS * thunk. */ - bytes[i++] = 0xea; /* invalid instruction */ + bytes[i++] = 0xd6; /* UDB */ bytes[i++] = 0x75; /* JNE */ bytes[i++] = 0xfd; @@ -163,7 +163,7 @@ static void *its_init_thunk(void *thunk, int reg) reg -= 8; } bytes[i++] = 0xff; - bytes[i++] = 0xe0 + reg; /* jmp *reg */ + bytes[i++] = 0xe0 + reg; /* JMP *reg */ bytes[i++] = 0xcc; return thunk + offset; @@ -713,20 +713,33 @@ static inline bool is_jcc32(struct insn *insn) #if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL) /* - * CALL/JMP *%\reg + * [CS]{,3} CALL/JMP *%\reg [INT3]* */ -static int emit_indirect(int op, int reg, u8 *bytes) +static int emit_indirect(int op, int reg, u8 *bytes, int len) { + int cs = 0, bp = 0; int i = 0; u8 modrm; + /* + * Set @len to the excess bytes after writing the instruction. + */ + len -= 2 + (reg >= 8); + WARN_ON_ONCE(len < 0); + switch (op) { case CALL_INSN_OPCODE: modrm = 0x10; /* Reg = 2; CALL r/m */ + /* + * Additional NOP is better than prefix decode penalty. + */ + if (len <= 3) + cs = len; break; case JMP32_INSN_OPCODE: modrm = 0x20; /* Reg = 4; JMP r/m */ + bp = len; break; default: @@ -734,6 +747,9 @@ static int emit_indirect(int op, int reg, u8 *bytes) return -1; } + while (cs--) + bytes[i++] = 0x2e; /* CS-prefix */ + if (reg >= 8) { bytes[i++] = 0x41; /* REX.B prefix */ reg -= 8; @@ -745,6 +761,9 @@ static int emit_indirect(int op, int reg, u8 *bytes) bytes[i++] = 0xff; /* opcode */ bytes[i++] = modrm; + while (bp--) + bytes[i++] = 0xcc; /* INT3 */ + return i; } @@ -918,20 +937,11 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) return emit_its_trampoline(addr, insn, reg, bytes); #endif - ret = emit_indirect(op, reg, bytes + i); + ret = emit_indirect(op, reg, bytes + i, insn->length - i); if (ret < 0) return ret; i += ret; - /* - * The compiler is supposed to EMIT an INT3 after every unconditional - * JMP instruction due to AMD BTC. However, if the compiler is too old - * or MITIGATION_SLS isn't enabled, we still need an INT3 after - * indirect JMPs even on Intel. - */ - if (op == JMP32_INSN_OPCODE && i < insn->length) - bytes[i++] = INT3_INSN_OPCODE; - for (; i < insn->length;) bytes[i++] = BYTES_NOP1; @@ -970,7 +980,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) case JMP32_INSN_OPCODE: /* Check for cfi_paranoid + ITS */ dest = addr + insn.length + insn.immediate.value; - if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) { + if (dest[-1] == 0xd6 && (dest[0] & 0xf0) == 0x70) { WARN_ON_ONCE(cfi_mode != CFI_FINEIBT); continue; } @@ -1177,6 +1187,7 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } #endif enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT; +static bool cfi_debug __ro_after_init; #ifdef CONFIG_FINEIBT_BHI bool cfi_bhi __ro_after_init = false; @@ -1259,6 +1270,8 @@ static __init int cfi_parse_cmdline(char *str) } else if (!strcmp(str, "off")) { cfi_mode = CFI_OFF; cfi_rand = false; + } else if (!strcmp(str, "debug")) { + cfi_debug = true; } else if (!strcmp(str, "kcfi")) { cfi_mode = CFI_KCFI; } else if (!strcmp(str, "fineibt")) { @@ -1266,26 +1279,26 @@ static __init int cfi_parse_cmdline(char *str) } else if (!strcmp(str, "norand")) { cfi_rand = false; } else if (!strcmp(str, "warn")) { - pr_alert("CFI mismatch non-fatal!\n"); + pr_alert("CFI: mismatch non-fatal!\n"); cfi_warn = true; } else if (!strcmp(str, "paranoid")) { if (cfi_mode == CFI_FINEIBT) { cfi_paranoid = true; } else { - pr_err("Ignoring paranoid; depends on fineibt.\n"); + pr_err("CFI: ignoring paranoid; depends on fineibt.\n"); } } else if (!strcmp(str, "bhi")) { #ifdef CONFIG_FINEIBT_BHI if (cfi_mode == CFI_FINEIBT) { cfi_bhi = true; } else { - pr_err("Ignoring bhi; depends on fineibt.\n"); + pr_err("CFI: ignoring bhi; depends on fineibt.\n"); } #else - pr_err("Ignoring bhi; depends on FINEIBT_BHI=y.\n"); + pr_err("CFI: ignoring bhi; depends on FINEIBT_BHI=y.\n"); #endif } else { - pr_err("Ignoring unknown cfi option (%s).", str); + pr_err("CFI: Ignoring unknown option (%s).", str); } str = next; @@ -1300,9 +1313,9 @@ early_param("cfi", cfi_parse_cmdline); * * __cfi_\func: __cfi_\func: * movl $0x12345678,%eax // 5 endbr64 // 4 - * nop subl $0x12345678,%r10d // 7 - * nop jne __cfi_\func+6 // 2 - * nop nop3 // 3 + * nop subl $0x12345678,%eax // 5 + * nop jne.d32,pn \func+3 // 7 + * nop * nop * nop * nop @@ -1311,34 +1324,44 @@ early_param("cfi", cfi_parse_cmdline); * nop * nop * nop + * \func: \func: + * endbr64 nopl -42(%rax) * * * caller: caller: - * movl $(-0x12345678),%r10d // 6 movl $0x12345678,%r10d // 6 + * movl $(-0x12345678),%r10d // 6 movl $0x12345678,%eax // 5 * addl $-15(%r11),%r10d // 4 lea -0x10(%r11),%r11 // 4 - * je 1f // 2 nop4 // 4 + * je 1f // 2 nop5 // 5 * ud2 // 2 * 1: cs call __x86_indirect_thunk_r11 // 6 call *%r11; nop3; // 6 * + * + * Notably, the FineIBT sequences are crafted such that branches are presumed + * non-taken. This is based on Agner Fog's optimization manual, which states: + * + * "Make conditional jumps most often not taken: The efficiency and throughput + * for not-taken branches is better than for taken branches on most + * processors. Therefore, it is good to place the most frequent branch first" */ /* * <fineibt_preamble_start>: * 0: f3 0f 1e fa endbr64 - * 4: 41 81 <ea> 78 56 34 12 sub $0x12345678, %r10d - * b: 75 f9 jne 6 <fineibt_preamble_start+0x6> - * d: 0f 1f 00 nopl (%rax) + * 4: 2d 78 56 34 12 sub $0x12345678, %eax + * 9: 2e 0f 85 03 00 00 00 jne,pn 13 <fineibt_preamble_start+0x13> + * 10: 0f 1f 40 d6 nopl -0x2a(%rax) * - * Note that the JNE target is the 0xEA byte inside the SUB, this decodes as - * (bad) on x86_64 and raises #UD. + * Note that the JNE target is the 0xD6 byte inside the NOPL, this decodes as + * UDB on x86_64 and raises #UD. */ asm( ".pushsection .rodata \n" "fineibt_preamble_start: \n" " endbr64 \n" - " subl $0x12345678, %r10d \n" + " subl $0x12345678, %eax \n" "fineibt_preamble_bhi: \n" - " jne fineibt_preamble_start+6 \n" - ASM_NOP3 + " cs jne.d32 fineibt_preamble_start+0x13 \n" + "#fineibt_func: \n" + " nopl -42(%rax) \n" "fineibt_preamble_end: \n" ".popsection\n" ); @@ -1349,20 +1372,20 @@ extern u8 fineibt_preamble_end[]; #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start) #define fineibt_preamble_bhi (fineibt_preamble_bhi - fineibt_preamble_start) -#define fineibt_preamble_ud 6 -#define fineibt_preamble_hash 7 +#define fineibt_preamble_ud 0x13 +#define fineibt_preamble_hash 5 /* * <fineibt_caller_start>: - * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d - * 6: 4d 8d 5b f0 lea -0x10(%r11), %r11 - * a: 0f 1f 40 00 nopl 0x0(%rax) + * 0: b8 78 56 34 12 mov $0x12345678, %eax + * 5: 4d 8d 5b f0 lea -0x10(%r11), %r11 + * 9: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) */ asm( ".pushsection .rodata \n" "fineibt_caller_start: \n" - " movl $0x12345678, %r10d \n" + " movl $0x12345678, %eax \n" " lea -0x10(%r11), %r11 \n" - ASM_NOP4 + ASM_NOP5 "fineibt_caller_end: \n" ".popsection \n" ); @@ -1371,7 +1394,7 @@ extern u8 fineibt_caller_start[]; extern u8 fineibt_caller_end[]; #define fineibt_caller_size (fineibt_caller_end - fineibt_caller_start) -#define fineibt_caller_hash 2 +#define fineibt_caller_hash 1 #define fineibt_caller_jmp (fineibt_caller_size - 2) @@ -1388,9 +1411,9 @@ extern u8 fineibt_caller_end[]; * of adding a load. * * <fineibt_paranoid_start>: - * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d - * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d - * a: 4d 8d 5b <f0> lea -0x10(%r11), %r11 + * 0: b8 78 56 34 12 mov $0x12345678, %eax + * 5: 41 3b 43 f5 cmp -0x11(%r11), %eax + * 9: 2e 4d 8d 5b <f0> cs lea -0x10(%r11), %r11 * e: 75 fd jne d <fineibt_paranoid_start+0xd> * 10: 41 ff d3 call *%r11 * 13: 90 nop @@ -1402,13 +1425,13 @@ extern u8 fineibt_caller_end[]; */ asm( ".pushsection .rodata \n" "fineibt_paranoid_start: \n" - " movl $0x12345678, %r10d \n" - " cmpl -9(%r11), %r10d \n" - " lea -0x10(%r11), %r11 \n" + " mov $0x12345678, %eax \n" + " cmpl -11(%r11), %eax \n" + " cs lea -0x10(%r11), %r11 \n" + "#fineibt_caller_size: \n" " jne fineibt_paranoid_start+0xd \n" "fineibt_paranoid_ind: \n" - " call *%r11 \n" - " nop \n" + " cs call *%r11 \n" "fineibt_paranoid_end: \n" ".popsection \n" ); @@ -1520,51 +1543,67 @@ static int cfi_rand_preamble(s32 *start, s32 *end) return 0; } +/* + * Inline the bhi-arity 1 case: + * + * __cfi_foo: + * 0: f3 0f 1e fa endbr64 + * 4: 2d 78 56 34 12 sub $0x12345678, %eax + * 9: 49 0f 45 fa cmovne %rax, %rdi + * d: 2e 75 03 jne,pn foo+0x3 + * + * foo: + * 10: 0f 1f 40 <d6> nopl -42(%rax) + * + * Notably, this scheme is incompatible with permissive CFI + * because the CMOVcc is unconditional and RDI will have been + * clobbered. + */ +asm( ".pushsection .rodata \n" + "fineibt_bhi1_start: \n" + " cmovne %rax, %rdi \n" + " cs jne fineibt_bhi1_func + 0x3 \n" + "fineibt_bhi1_func: \n" + " nopl -42(%rax) \n" + "fineibt_bhi1_end: \n" + ".popsection \n" +); + +extern u8 fineibt_bhi1_start[]; +extern u8 fineibt_bhi1_end[]; + +#define fineibt_bhi1_size (fineibt_bhi1_end - fineibt_bhi1_start) + static void cfi_fineibt_bhi_preamble(void *addr, int arity) { + u8 bytes[MAX_INSN_SIZE]; + if (!arity) return; if (!cfi_warn && arity == 1) { - /* - * Crazy scheme to allow arity-1 inline: - * - * __cfi_foo: - * 0: f3 0f 1e fa endbr64 - * 4: 41 81 <ea> 78 56 34 12 sub 0x12345678, %r10d - * b: 49 0f 45 fa cmovne %r10, %rdi - * f: 75 f5 jne __cfi_foo+6 - * 11: 0f 1f 00 nopl (%rax) - * - * Code that direct calls to foo()+0, decodes the tail end as: - * - * foo: - * 0: f5 cmc - * 1: 0f 1f 00 nopl (%rax) - * - * which clobbers CF, but does not affect anything ABI - * wise. - * - * Notably, this scheme is incompatible with permissive CFI - * because the CMOVcc is unconditional and RDI will have been - * clobbered. - */ - const u8 magic[9] = { - 0x49, 0x0f, 0x45, 0xfa, - 0x75, 0xf5, - BYTES_NOP3, - }; - - text_poke_early(addr + fineibt_preamble_bhi, magic, 9); - + text_poke_early(addr + fineibt_preamble_bhi, + fineibt_bhi1_start, fineibt_bhi1_size); return; } - text_poke_early(addr + fineibt_preamble_bhi, - text_gen_insn(CALL_INSN_OPCODE, - addr + fineibt_preamble_bhi, - __bhi_args[arity]), - CALL_INSN_SIZE); + /* + * Replace the bytes at fineibt_preamble_bhi with a CALL instruction + * that lines up exactly with the end of the preamble, such that the + * return address will be foo+0. + * + * __cfi_foo: + * 0: f3 0f 1e fa endbr64 + * 4: 2d 78 56 34 12 sub $0x12345678, %eax + * 9: 2e 2e e8 DD DD DD DD cs cs call __bhi_args[arity] + */ + bytes[0] = 0x2e; + bytes[1] = 0x2e; + __text_gen_insn(bytes + 2, CALL_INSN_OPCODE, + addr + fineibt_preamble_bhi + 2, + __bhi_args[arity], CALL_INSN_SIZE); + + text_poke_early(addr + fineibt_preamble_bhi, bytes, 7); } static int cfi_rewrite_preamble(s32 *start, s32 *end) @@ -1655,8 +1694,6 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) { s32 *s; - BUG_ON(fineibt_paranoid_size != 20); - for (s = start; s < end; s++) { void *addr = (void *)s + *s; struct insn insn; @@ -1696,8 +1733,9 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) emit_paranoid_trampoline(addr + fineibt_caller_size, &insn, 11, bytes + fineibt_caller_size); } else { - ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); - if (WARN_ON_ONCE(ret != 3)) + int len = fineibt_paranoid_size - fineibt_paranoid_ind; + ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind, len); + if (WARN_ON_ONCE(ret != len)) continue; } @@ -1707,13 +1745,20 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) return 0; } +#define pr_cfi_debug(X...) if (cfi_debug) pr_info(X) + +#define FINEIBT_WARN(_f, _v) \ + WARN_ONCE((_f) != (_v), "FineIBT: " #_f " %ld != %d\n", _f, _v) + static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, s32 *start_cfi, s32 *end_cfi, bool builtin) { int ret; - if (WARN_ONCE(fineibt_preamble_size != 16, - "FineIBT preamble wrong size: %ld", fineibt_preamble_size)) + if (FINEIBT_WARN(fineibt_preamble_size, 20) || + FINEIBT_WARN(fineibt_preamble_bhi + fineibt_bhi1_size, 20) || + FINEIBT_WARN(fineibt_caller_size, 14) || + FINEIBT_WARN(fineibt_paranoid_size, 20)) return; if (cfi_mode == CFI_AUTO) { @@ -1734,6 +1779,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, * rewrite them. This disables all CFI. If this succeeds but any of the * later stages fails, we're without CFI. */ + pr_cfi_debug("CFI: disabling all indirect call checking\n"); ret = cfi_disable_callers(start_retpoline, end_retpoline); if (ret) goto err; @@ -1744,43 +1790,53 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, cfi_bpf_hash = cfi_rehash(cfi_bpf_hash); cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash); } + pr_cfi_debug("CFI: cfi_seed: 0x%08x\n", cfi_seed); + pr_cfi_debug("CFI: rehashing all preambles\n"); ret = cfi_rand_preamble(start_cfi, end_cfi); if (ret) goto err; + pr_cfi_debug("CFI: rehashing all indirect calls\n"); ret = cfi_rand_callers(start_retpoline, end_retpoline); if (ret) goto err; + } else { + pr_cfi_debug("CFI: rehashing disabled\n"); } switch (cfi_mode) { case CFI_OFF: if (builtin) - pr_info("Disabling CFI\n"); + pr_info("CFI: disabled\n"); return; case CFI_KCFI: + pr_cfi_debug("CFI: re-enabling all indirect call checking\n"); ret = cfi_enable_callers(start_retpoline, end_retpoline); if (ret) goto err; if (builtin) - pr_info("Using kCFI\n"); + pr_info("CFI: Using %sretpoline kCFI\n", + cfi_rand ? "rehashed " : ""); return; case CFI_FINEIBT: + pr_cfi_debug("CFI: adding FineIBT to all preambles\n"); /* place the FineIBT preamble at func()-16 */ ret = cfi_rewrite_preamble(start_cfi, end_cfi); if (ret) goto err; /* rewrite the callers to target func()-16 */ + pr_cfi_debug("CFI: rewriting indirect call sites to use FineIBT\n"); ret = cfi_rewrite_callers(start_retpoline, end_retpoline); if (ret) goto err; /* now that nobody targets func()+0, remove ENDBR there */ + pr_cfi_debug("CFI: removing old endbr insns\n"); cfi_rewrite_endbr(start_cfi, end_cfi); if (builtin) { @@ -1823,11 +1879,11 @@ static void poison_cfi(void *addr) /* * __cfi_\func: - * osp nopl (%rax) - * subl $0, %r10d - * jz 1f - * ud2 - * 1: nop + * nopl -42(%rax) + * sub $0, %eax + * jne \func+3 + * \func: + * nopl -42(%rax) */ poison_endbr(addr); poison_hash(addr + fineibt_preamble_hash); @@ -1853,12 +1909,14 @@ static void poison_cfi(void *addr) } } +#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) + /* - * When regs->ip points to a 0xEA byte in the FineIBT preamble, + * When regs->ip points to a 0xD6 byte in the FineIBT preamble, * return true and fill out target and type. * * We check the preamble by checking for the ENDBR instruction relative to the - * 0xEA instruction. + * UDB instruction. */ static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, u32 *type) { @@ -1868,10 +1926,10 @@ static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, if (!exact_endbr((void *)addr)) return false; - *target = addr + fineibt_preamble_size; + *target = addr + fineibt_prefix_size; __get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault); - *type = (u32)regs->r10 + hash; + *type = (u32)regs->ax + hash; /* * Since regs->ip points to the middle of an instruction; it cannot @@ -1909,12 +1967,12 @@ static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32 __get_kernel_nofault(&addr, regs->sp, unsigned long, Efault); *target = addr; - addr -= fineibt_preamble_size; + addr -= fineibt_prefix_size; if (!exact_endbr((void *)addr)) return false; __get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault); - *type = (u32)regs->r10 + hash; + *type = (u32)regs->ax + hash; /* * The UD2 sites are constructed with a RET immediately following, @@ -1931,7 +1989,7 @@ static bool is_paranoid_thunk(unsigned long addr) u32 thunk; __get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault); - return (thunk & 0x00FFFFFF) == 0xfd75ea; + return (thunk & 0x00FFFFFF) == 0xfd75d6; Efault: return false; @@ -1939,8 +1997,7 @@ Efault: /* * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[] - * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS - * thunk. + * sequence, or to UDB + Jcc.d8 for cfi_paranoid + ITS thunk. */ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type) { @@ -1950,8 +2007,8 @@ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, return false; if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) { - *target = regs->r11 + fineibt_preamble_size; - *type = regs->r10; + *target = regs->r11 + fineibt_prefix_size; + *type = regs->ax; /* * Since the trapping instruction is the exact, but LOCK prefixed, @@ -1963,14 +2020,14 @@ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, /* * The cfi_paranoid + ITS thunk combination results in: * - * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d - * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d - * a: 4d 8d 5b f0 lea -0x10(%r11), %r11 + * 0: b8 78 56 34 12 mov $0x12345678, %eax + * 5: 41 3b 43 f7 cmp -11(%r11), %eax + * a: 2e 3d 8d 5b f0 cs lea -0x10(%r11), %r11 * e: 2e e8 XX XX XX XX cs call __x86_indirect_paranoid_thunk_r11 * * Where the paranoid_thunk looks like: * - * 1d: <ea> (bad) + * 1d: <d6> udb * __x86_indirect_paranoid_thunk_r11: * 1e: 75 fd jne 1d * __x86_indirect_its_thunk_r11: @@ -1979,8 +2036,8 @@ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, * */ if (is_paranoid_thunk(regs->ip)) { - *target = regs->r11 + fineibt_preamble_size; - *type = regs->r10; + *target = regs->r11 + fineibt_prefix_size; + *type = regs->ax; regs->ip = *target; return true; @@ -2005,6 +2062,8 @@ bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type) static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, s32 *start_cfi, s32 *end_cfi, bool builtin) { + if (IS_ENABLED(CONFIG_CFI) && builtin) + pr_info("CFI: Using standard kCFI\n"); } #ifdef CONFIG_X86_KERNEL_IBT @@ -2321,6 +2380,7 @@ void __init alternative_instructions(void) __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); + cfi_debug = false; /* * Rewrite the retpolines, must be done before alternatives since diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 6259b474073b..32ba599a51f8 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -102,6 +102,7 @@ static void __used common(void) BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + OFFSET(C_PTREGS_SIZE, pt_regs, orig_ax); /* TLB state for the entry code */ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c index 77086cf565ec..638eb5c933e0 100644 --- a/arch/x86/kernel/cfi.c +++ b/arch/x86/kernel/cfi.c @@ -27,7 +27,7 @@ static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target, * for indirect call checks: * *  movl -<id>, %r10d ; 6 bytes - * addl -4(%reg), %r10d ; 4 bytes + * addl -<pos>(%reg), %r10d; 4 bytes * je .Ltmp1 ; 2 bytes * ud2 ; <- regs->ip * .Ltmp1: diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 25773af116bc..c4febdbcfe4d 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -38,10 +38,6 @@ bool hv_nested; struct ms_hyperv_info ms_hyperv; -/* Used in modules via hv_do_hypercall(): see arch/x86/include/asm/mshyperv.h */ -bool hyperv_paravisor_present __ro_after_init; -EXPORT_SYMBOL_GPL(hyperv_paravisor_present); - #if IS_ENABLED(CONFIG_HYPERV) static inline unsigned int hv_get_nested_msr(unsigned int reg) { @@ -288,8 +284,18 @@ static void __init x86_setup_ops_for_tsc_pg_clock(void) old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; } + +#ifdef CONFIG_X86_64 +DEFINE_STATIC_CALL(hv_hypercall, hv_std_hypercall); +EXPORT_STATIC_CALL_TRAMP_GPL(hv_hypercall); +#define hypercall_update(hc) static_call_update(hv_hypercall, hc) +#endif #endif /* CONFIG_HYPERV */ +#ifndef hypercall_update +#define hypercall_update(hc) (void)hc +#endif + static uint32_t __init ms_hyperv_platform(void) { u32 eax; @@ -484,14 +490,14 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.shared_gpa_boundary = BIT_ULL(ms_hyperv.shared_gpa_boundary_bits); - hyperv_paravisor_present = !!ms_hyperv.paravisor_present; - pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) { static_branch_enable(&isolation_type_snp); + if (!ms_hyperv.paravisor_present) + hypercall_update(hv_snp_hypercall); } else if (hv_get_isolation_type() == HV_ISOLATION_TYPE_TDX) { static_branch_enable(&isolation_type_tdx); @@ -499,6 +505,7 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED; if (!ms_hyperv.paravisor_present) { + hypercall_update(hv_tdx_hypercall); /* * Mark the Hyper-V TSC page feature as disabled * in a TDX VM without paravisor so that the diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 18cf79d6e2c5..763534d77f59 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -1,21 +1,8 @@ +// SPDX-License-Identifier: LGPL-2.0+ /* * MTRR (Memory Type Range Register) cleanup * * Copyright (C) 2009 Yinghai Lu - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Library General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Library General Public License for more details. - * - * You should have received a copy of the GNU Library General Public - * License along with this library; if not, write to the Free - * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/init.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index ecbda0341a8a..4b3d492afe17 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: LGPL-2.0+ /* Generic MTRR (Memory Type Range Register) driver. Copyright (C) 1997-2000 Richard Gooch Copyright (c) 2002 Patrick Mochel - This library is free software; you can redistribute it and/or - modify it under the terms of the GNU Library General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later version. - - This library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Library General Public License for more details. - - You should have received a copy of the GNU Library General Public - License along with this library; if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - Richard Gooch may be reached by email at rgooch@atnf.csiro.au The postal address is: Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia. diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h index 99004b02e2ed..42a088a337c5 100644 --- a/arch/x86/kernel/cpu/sgx/encls.h +++ b/arch/x86/kernel/cpu/sgx/encls.h @@ -68,7 +68,7 @@ static inline bool encls_failed(int ret) ({ \ int ret; \ asm volatile( \ - "1: .byte 0x0f, 0x01, 0xcf;\n\t" \ + "1: encls\n" \ "2:\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX) \ : "=a"(ret) \ @@ -111,8 +111,8 @@ static inline bool encls_failed(int ret) ({ \ int ret; \ asm volatile( \ - "1: .byte 0x0f, 0x01, 0xcf;\n\t" \ - " xor %%eax,%%eax;\n" \ + "1: encls\n\t" \ + "xor %%eax,%%eax\n" \ "2:\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX) \ : "=a"(ret), "=b"(rbx_out) \ diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index f79c5edc0b89..6ab9eac64670 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -97,9 +97,11 @@ void __init native_init_IRQ(void) /* Execute any quirks before the call gates are initialised: */ x86_init.irqs.pre_vector_init(); - if (cpu_feature_enabled(X86_FEATURE_FRED)) + /* FRED's IRQ path may be used even if FRED isn't fully enabled. */ + if (IS_ENABLED(CONFIG_X86_FRED)) fred_complete_exception_setup(); - else + + if (!cpu_feature_enabled(X86_FEATURE_FRED)) idt_setup_apic_and_irq_gates(); lapic_assign_system_vectors(); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 15088d14904f..201137b98fb8 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -479,6 +479,10 @@ void __nocfi machine_kexec(struct kimage *image) __ftrace_enabled_restore(save_ftrace_enabled); } +/* + * Handover to the next kernel, no CFI concern. + */ +ANNOTATE_NOCFI_SYM(machine_kexec); /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 36354b470590..6b22611e69cc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -97,7 +97,7 @@ __always_inline int is_valid_bugaddr(unsigned long addr) * Check for UD1 or UD2, accounting for Address Size Override Prefixes. * If it's a UD1, further decode to determine its use: * - * FineIBT: ea (bad) + * FineIBT: d6 udb * FineIBT: f0 75 f9 lock jne . - 6 * UBSan{0}: 67 0f b9 00 ud1 (%eax),%eax * UBSan{10}: 67 0f b9 40 10 ud1 0x10(%eax),%eax @@ -130,9 +130,9 @@ __always_inline int decode_bug(unsigned long addr, s32 *imm, int *len) WARN_ON_ONCE(!lock); return BUG_LOCK; - case 0xea: + case 0xd6: *len = addr - start; - return BUG_EA; + return BUG_UDB; case OPCODE_ESCAPE: break; @@ -341,7 +341,7 @@ static noinstr bool handle_bug(struct pt_regs *regs) } fallthrough; - case BUG_EA: + case BUG_UDB: case BUG_LOCK: if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { handled = true; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 67d4f23bab66..278f08194ec8 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -96,6 +96,7 @@ config KVM_SW_PROTECTED_VM config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL + select X86_FRED if X86_64 help Provides support for KVM on processors equipped with Intel's VT extensions, a.k.a. Virtual Machine Extensions (VMX). diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 59f93f68718a..4e3da5b497b8 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -26,6 +26,7 @@ #include <asm/debugreg.h> #include <asm/nospec-branch.h> #include <asm/ibt.h> +#include <asm/text-patching.h> #include "x86.h" #include "tss.h" @@ -166,7 +167,6 @@ #define Unaligned ((u64)2 << 41) /* Explicitly unaligned (e.g. MOVDQU) */ #define Avx ((u64)3 << 41) /* Advanced Vector Extensions */ #define Aligned16 ((u64)4 << 41) /* Aligned to 16 byte boundary (e.g. FXSAVE) */ -#define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */ #define NoWrite ((u64)1 << 45) /* No writeback */ #define SrcWrite ((u64)1 << 46) /* Write back src operand */ #define NoMod ((u64)1 << 47) /* Mod field is ignored */ @@ -203,7 +203,6 @@ struct opcode { const struct escape *esc; const struct instr_dual *idual; const struct mode_dual *mdual; - void (*fastop)(struct fastop *fake); } u; int (*check_perm)(struct x86_emulate_ctxt *ctxt); }; @@ -267,186 +266,130 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) X86_EFLAGS_PF|X86_EFLAGS_CF) #ifdef CONFIG_X86_64 -#define ON64(x) x +#define ON64(x...) x #else -#define ON64(x) +#define ON64(x...) #endif -/* - * fastop functions have a special calling convention: - * - * dst: rax (in/out) - * src: rdx (in/out) - * src2: rcx (in) - * flags: rflags (in/out) - * ex: rsi (in:fastop pointer, out:zero if exception) - * - * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for - * different operand sizes can be reached by calculation, rather than a jump - * table (which would be bigger than the code). - * - * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR - * and 1 for the straight line speculation INT3, leaves 7 bytes for the - * body of the function. Currently none is larger than 4. - */ -static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); - -#define FASTOP_SIZE 16 - -#define __FOP_FUNC(name) \ - ".align " __stringify(FASTOP_SIZE) " \n\t" \ - ".type " name ", @function \n\t" \ - name ":\n\t" \ - ASM_ENDBR \ - IBT_NOSEAL(name) - -#define FOP_FUNC(name) \ - __FOP_FUNC(#name) - -#define __FOP_RET(name) \ - "11: " ASM_RET \ - ".size " name ", .-" name "\n\t" - -#define FOP_RET(name) \ - __FOP_RET(#name) - -#define __FOP_START(op, align) \ - extern void em_##op(struct fastop *fake); \ - asm(".pushsection .text, \"ax\" \n\t" \ - ".global em_" #op " \n\t" \ - ".align " __stringify(align) " \n\t" \ - "em_" #op ":\n\t" - -#define FOP_START(op) __FOP_START(op, FASTOP_SIZE) - -#define FOP_END \ - ".popsection") - -#define __FOPNOP(name) \ - __FOP_FUNC(name) \ - __FOP_RET(name) - -#define FOPNOP() \ - __FOPNOP(__stringify(__UNIQUE_ID(nop))) - -#define FOP1E(op, dst) \ - __FOP_FUNC(#op "_" #dst) \ - "10: " #op " %" #dst " \n\t" \ - __FOP_RET(#op "_" #dst) - -#define FOP1EEX(op, dst) \ - FOP1E(op, dst) _ASM_EXTABLE_TYPE_REG(10b, 11b, EX_TYPE_ZERO_REG, %%esi) - -#define FASTOP1(op) \ - FOP_START(op) \ - FOP1E(op##b, al) \ - FOP1E(op##w, ax) \ - FOP1E(op##l, eax) \ - ON64(FOP1E(op##q, rax)) \ - FOP_END - -/* 1-operand, using src2 (for MUL/DIV r/m) */ -#define FASTOP1SRC2(op, name) \ - FOP_START(name) \ - FOP1E(op, cl) \ - FOP1E(op, cx) \ - FOP1E(op, ecx) \ - ON64(FOP1E(op, rcx)) \ - FOP_END - -/* 1-operand, using src2 (for MUL/DIV r/m), with exceptions */ -#define FASTOP1SRC2EX(op, name) \ - FOP_START(name) \ - FOP1EEX(op, cl) \ - FOP1EEX(op, cx) \ - FOP1EEX(op, ecx) \ - ON64(FOP1EEX(op, rcx)) \ - FOP_END - -#define FOP2E(op, dst, src) \ - __FOP_FUNC(#op "_" #dst "_" #src) \ - #op " %" #src ", %" #dst " \n\t" \ - __FOP_RET(#op "_" #dst "_" #src) - -#define FASTOP2(op) \ - FOP_START(op) \ - FOP2E(op##b, al, dl) \ - FOP2E(op##w, ax, dx) \ - FOP2E(op##l, eax, edx) \ - ON64(FOP2E(op##q, rax, rdx)) \ - FOP_END - -/* 2 operand, word only */ -#define FASTOP2W(op) \ - FOP_START(op) \ - FOPNOP() \ - FOP2E(op##w, ax, dx) \ - FOP2E(op##l, eax, edx) \ - ON64(FOP2E(op##q, rax, rdx)) \ - FOP_END - -/* 2 operand, src is CL */ -#define FASTOP2CL(op) \ - FOP_START(op) \ - FOP2E(op##b, al, cl) \ - FOP2E(op##w, ax, cl) \ - FOP2E(op##l, eax, cl) \ - ON64(FOP2E(op##q, rax, cl)) \ - FOP_END - -/* 2 operand, src and dest are reversed */ -#define FASTOP2R(op, name) \ - FOP_START(name) \ - FOP2E(op##b, dl, al) \ - FOP2E(op##w, dx, ax) \ - FOP2E(op##l, edx, eax) \ - ON64(FOP2E(op##q, rdx, rax)) \ - FOP_END - -#define FOP3E(op, dst, src, src2) \ - __FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \ - #op " %" #src2 ", %" #src ", %" #dst " \n\t"\ - __FOP_RET(#op "_" #dst "_" #src "_" #src2) - -/* 3-operand, word-only, src2=cl */ -#define FASTOP3WCL(op) \ - FOP_START(op) \ - FOPNOP() \ - FOP3E(op##w, ax, dx, cl) \ - FOP3E(op##l, eax, edx, cl) \ - ON64(FOP3E(op##q, rax, rdx, cl)) \ - FOP_END - -/* Special case for SETcc - 1 instruction per cc */ -#define FOP_SETCC(op) \ - FOP_FUNC(op) \ - #op " %al \n\t" \ - FOP_RET(op) - -FOP_START(setcc) -FOP_SETCC(seto) -FOP_SETCC(setno) -FOP_SETCC(setc) -FOP_SETCC(setnc) -FOP_SETCC(setz) -FOP_SETCC(setnz) -FOP_SETCC(setbe) -FOP_SETCC(setnbe) -FOP_SETCC(sets) -FOP_SETCC(setns) -FOP_SETCC(setp) -FOP_SETCC(setnp) -FOP_SETCC(setl) -FOP_SETCC(setnl) -FOP_SETCC(setle) -FOP_SETCC(setnle) -FOP_END; - -FOP_START(salc) -FOP_FUNC(salc) -"pushf; sbb %al, %al; popf \n\t" -FOP_RET(salc) -FOP_END; +#define EM_ASM_START(op) \ +static int em_##op(struct x86_emulate_ctxt *ctxt) \ +{ \ + unsigned long flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; \ + int bytes = 1, ok = 1; \ + if (!(ctxt->d & ByteOp)) \ + bytes = ctxt->dst.bytes; \ + switch (bytes) { + +#define __EM_ASM(str) \ + asm("push %[flags]; popf \n\t" \ + "10: " str \ + "pushf; pop %[flags] \n\t" \ + "11: \n\t" \ + : "+a" (ctxt->dst.val), \ + "+d" (ctxt->src.val), \ + [flags] "+D" (flags), \ + "+S" (ok) \ + : "c" (ctxt->src2.val)) + +#define __EM_ASM_1(op, dst) \ + __EM_ASM(#op " %%" #dst " \n\t") + +#define __EM_ASM_1_EX(op, dst) \ + __EM_ASM(#op " %%" #dst " \n\t" \ + _ASM_EXTABLE_TYPE_REG(10b, 11f, EX_TYPE_ZERO_REG, %%esi)) + +#define __EM_ASM_2(op, dst, src) \ + __EM_ASM(#op " %%" #src ", %%" #dst " \n\t") + +#define __EM_ASM_3(op, dst, src, src2) \ + __EM_ASM(#op " %%" #src2 ", %%" #src ", %%" #dst " \n\t") + +#define EM_ASM_END \ + } \ + ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); \ + return !ok ? emulate_de(ctxt) : X86EMUL_CONTINUE; \ +} + +/* 1-operand, using "a" (dst) */ +#define EM_ASM_1(op) \ + EM_ASM_START(op) \ + case 1: __EM_ASM_1(op##b, al); break; \ + case 2: __EM_ASM_1(op##w, ax); break; \ + case 4: __EM_ASM_1(op##l, eax); break; \ + ON64(case 8: __EM_ASM_1(op##q, rax); break;) \ + EM_ASM_END + +/* 1-operand, using "c" (src2) */ +#define EM_ASM_1SRC2(op, name) \ + EM_ASM_START(name) \ + case 1: __EM_ASM_1(op##b, cl); break; \ + case 2: __EM_ASM_1(op##w, cx); break; \ + case 4: __EM_ASM_1(op##l, ecx); break; \ + ON64(case 8: __EM_ASM_1(op##q, rcx); break;) \ + EM_ASM_END + +/* 1-operand, using "c" (src2) with exception */ +#define EM_ASM_1SRC2EX(op, name) \ + EM_ASM_START(name) \ + case 1: __EM_ASM_1_EX(op##b, cl); break; \ + case 2: __EM_ASM_1_EX(op##w, cx); break; \ + case 4: __EM_ASM_1_EX(op##l, ecx); break; \ + ON64(case 8: __EM_ASM_1_EX(op##q, rcx); break;) \ + EM_ASM_END + +/* 2-operand, using "a" (dst), "d" (src) */ +#define EM_ASM_2(op) \ + EM_ASM_START(op) \ + case 1: __EM_ASM_2(op##b, al, dl); break; \ + case 2: __EM_ASM_2(op##w, ax, dx); break; \ + case 4: __EM_ASM_2(op##l, eax, edx); break; \ + ON64(case 8: __EM_ASM_2(op##q, rax, rdx); break;) \ + EM_ASM_END + +/* 2-operand, reversed */ +#define EM_ASM_2R(op, name) \ + EM_ASM_START(name) \ + case 1: __EM_ASM_2(op##b, dl, al); break; \ + case 2: __EM_ASM_2(op##w, dx, ax); break; \ + case 4: __EM_ASM_2(op##l, edx, eax); break; \ + ON64(case 8: __EM_ASM_2(op##q, rdx, rax); break;) \ + EM_ASM_END + +/* 2-operand, word only (no byte op) */ +#define EM_ASM_2W(op) \ + EM_ASM_START(op) \ + case 1: break; \ + case 2: __EM_ASM_2(op##w, ax, dx); break; \ + case 4: __EM_ASM_2(op##l, eax, edx); break; \ + ON64(case 8: __EM_ASM_2(op##q, rax, rdx); break;) \ + EM_ASM_END + +/* 2-operand, using "a" (dst) and CL (src2) */ +#define EM_ASM_2CL(op) \ + EM_ASM_START(op) \ + case 1: __EM_ASM_2(op##b, al, cl); break; \ + case 2: __EM_ASM_2(op##w, ax, cl); break; \ + case 4: __EM_ASM_2(op##l, eax, cl); break; \ + ON64(case 8: __EM_ASM_2(op##q, rax, cl); break;) \ + EM_ASM_END + +/* 3-operand, using "a" (dst), "d" (src) and CL (src2) */ +#define EM_ASM_3WCL(op) \ + EM_ASM_START(op) \ + case 1: break; \ + case 2: __EM_ASM_3(op##w, ax, dx, cl); break; \ + case 4: __EM_ASM_3(op##l, eax, edx, cl); break; \ + ON64(case 8: __EM_ASM_3(op##q, rax, rdx, cl); break;) \ + EM_ASM_END + +static int em_salc(struct x86_emulate_ctxt *ctxt) +{ + /* + * Set AL 0xFF if CF is set, or 0x00 when clear. + */ + ctxt->dst.val = 0xFF * !!(ctxt->eflags & X86_EFLAGS_CF); + return X86EMUL_CONTINUE; +} /* * XXX: inoutclob user must know where the argument is being expanded. @@ -1007,56 +950,55 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt, return rc; } -FASTOP2(add); -FASTOP2(or); -FASTOP2(adc); -FASTOP2(sbb); -FASTOP2(and); -FASTOP2(sub); -FASTOP2(xor); -FASTOP2(cmp); -FASTOP2(test); - -FASTOP1SRC2(mul, mul_ex); -FASTOP1SRC2(imul, imul_ex); -FASTOP1SRC2EX(div, div_ex); -FASTOP1SRC2EX(idiv, idiv_ex); - -FASTOP3WCL(shld); -FASTOP3WCL(shrd); - -FASTOP2W(imul); - -FASTOP1(not); -FASTOP1(neg); -FASTOP1(inc); -FASTOP1(dec); - -FASTOP2CL(rol); -FASTOP2CL(ror); -FASTOP2CL(rcl); -FASTOP2CL(rcr); -FASTOP2CL(shl); -FASTOP2CL(shr); -FASTOP2CL(sar); - -FASTOP2W(bsf); -FASTOP2W(bsr); -FASTOP2W(bt); -FASTOP2W(bts); -FASTOP2W(btr); -FASTOP2W(btc); - -FASTOP2(xadd); - -FASTOP2R(cmp, cmp_r); +EM_ASM_2(add); +EM_ASM_2(or); +EM_ASM_2(adc); +EM_ASM_2(sbb); +EM_ASM_2(and); +EM_ASM_2(sub); +EM_ASM_2(xor); +EM_ASM_2(cmp); +EM_ASM_2(test); +EM_ASM_2(xadd); + +EM_ASM_1SRC2(mul, mul_ex); +EM_ASM_1SRC2(imul, imul_ex); +EM_ASM_1SRC2EX(div, div_ex); +EM_ASM_1SRC2EX(idiv, idiv_ex); + +EM_ASM_3WCL(shld); +EM_ASM_3WCL(shrd); + +EM_ASM_2W(imul); + +EM_ASM_1(not); +EM_ASM_1(neg); +EM_ASM_1(inc); +EM_ASM_1(dec); + +EM_ASM_2CL(rol); +EM_ASM_2CL(ror); +EM_ASM_2CL(rcl); +EM_ASM_2CL(rcr); +EM_ASM_2CL(shl); +EM_ASM_2CL(shr); +EM_ASM_2CL(sar); + +EM_ASM_2W(bsf); +EM_ASM_2W(bsr); +EM_ASM_2W(bt); +EM_ASM_2W(bts); +EM_ASM_2W(btr); +EM_ASM_2W(btc); + +EM_ASM_2R(cmp, cmp_r); static int em_bsf_c(struct x86_emulate_ctxt *ctxt) { /* If src is zero, do not writeback, but update flags */ if (ctxt->src.val == 0) ctxt->dst.type = OP_NONE; - return fastop(ctxt, em_bsf); + return em_bsf(ctxt); } static int em_bsr_c(struct x86_emulate_ctxt *ctxt) @@ -1064,18 +1006,12 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt) /* If src is zero, do not writeback, but update flags */ if (ctxt->src.val == 0) ctxt->dst.type = OP_NONE; - return fastop(ctxt, em_bsr); + return em_bsr(ctxt); } static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) { - u8 rc; - void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf); - - flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; - asm("push %[flags]; popf; " CALL_NOSPEC - : "=a"(rc), ASM_CALL_CONSTRAINT : [thunk_target]"r"(fop), [flags]"r"(flags)); - return rc; + return __emulate_cc(flags, condition & 0xf); } static void fetch_register_operand(struct operand *op) @@ -2325,7 +2261,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) ctxt->dst.val = reg_read(ctxt, VCPU_REGS_RAX); ctxt->src.orig_val = ctxt->src.val; ctxt->src.val = ctxt->dst.orig_val; - fastop(ctxt, em_cmp); + em_cmp(ctxt); if (ctxt->eflags & X86_EFLAGS_ZF) { /* Success: write back to memory; no update of EAX */ @@ -3090,7 +3026,7 @@ static int em_das(struct x86_emulate_ctxt *ctxt) ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; - fastop(ctxt, em_or); + em_or(ctxt); ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF); if (cf) ctxt->eflags |= X86_EFLAGS_CF; @@ -3116,7 +3052,7 @@ static int em_aam(struct x86_emulate_ctxt *ctxt) ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; - fastop(ctxt, em_or); + em_or(ctxt); return X86EMUL_CONTINUE; } @@ -3134,7 +3070,7 @@ static int em_aad(struct x86_emulate_ctxt *ctxt) ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; - fastop(ctxt, em_or); + em_or(ctxt); return X86EMUL_CONTINUE; } @@ -3225,7 +3161,7 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt) static int em_imul_3op(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = ctxt->src2.val; - return fastop(ctxt, em_imul); + return em_imul(ctxt); } static int em_cwd(struct x86_emulate_ctxt *ctxt) @@ -4004,7 +3940,6 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define MD(_f, _m) { .flags = ((_f) | ModeDual), .u.mdual = (_m) } #define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) } #define I(_f, _e) { .flags = (_f), .u.execute = (_e) } -#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) } #define II(_f, _e, _i) \ { .flags = (_f)|Intercept, .u.execute = (_e), .intercept = x86_intercept_##_i } #define IIP(_f, _e, _i, _p) \ @@ -4019,9 +3954,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define I2bvIP(_f, _e, _i, _p) \ IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p) -#define F6ALU(_f, _e) F2bv((_f) | DstMem | SrcReg | ModRM, _e), \ - F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ - F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) +#define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e), \ + I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ + I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) static const struct opcode group7_rm0[] = { N, @@ -4059,14 +3994,14 @@ static const struct opcode group7_rm7[] = { }; static const struct opcode group1[] = { - F(Lock, em_add), - F(Lock | PageTable, em_or), - F(Lock, em_adc), - F(Lock, em_sbb), - F(Lock | PageTable, em_and), - F(Lock, em_sub), - F(Lock, em_xor), - F(NoWrite, em_cmp), + I(Lock, em_add), + I(Lock | PageTable, em_or), + I(Lock, em_adc), + I(Lock, em_sbb), + I(Lock | PageTable, em_and), + I(Lock, em_sub), + I(Lock, em_xor), + I(NoWrite, em_cmp), }; static const struct opcode group1A[] = { @@ -4074,36 +4009,36 @@ static const struct opcode group1A[] = { }; static const struct opcode group2[] = { - F(DstMem | ModRM, em_rol), - F(DstMem | ModRM, em_ror), - F(DstMem | ModRM, em_rcl), - F(DstMem | ModRM, em_rcr), - F(DstMem | ModRM, em_shl), - F(DstMem | ModRM, em_shr), - F(DstMem | ModRM, em_shl), - F(DstMem | ModRM, em_sar), + I(DstMem | ModRM, em_rol), + I(DstMem | ModRM, em_ror), + I(DstMem | ModRM, em_rcl), + I(DstMem | ModRM, em_rcr), + I(DstMem | ModRM, em_shl), + I(DstMem | ModRM, em_shr), + I(DstMem | ModRM, em_shl), + I(DstMem | ModRM, em_sar), }; static const struct opcode group3[] = { - F(DstMem | SrcImm | NoWrite, em_test), - F(DstMem | SrcImm | NoWrite, em_test), - F(DstMem | SrcNone | Lock, em_not), - F(DstMem | SrcNone | Lock, em_neg), - F(DstXacc | Src2Mem, em_mul_ex), - F(DstXacc | Src2Mem, em_imul_ex), - F(DstXacc | Src2Mem, em_div_ex), - F(DstXacc | Src2Mem, em_idiv_ex), + I(DstMem | SrcImm | NoWrite, em_test), + I(DstMem | SrcImm | NoWrite, em_test), + I(DstMem | SrcNone | Lock, em_not), + I(DstMem | SrcNone | Lock, em_neg), + I(DstXacc | Src2Mem, em_mul_ex), + I(DstXacc | Src2Mem, em_imul_ex), + I(DstXacc | Src2Mem, em_div_ex), + I(DstXacc | Src2Mem, em_idiv_ex), }; static const struct opcode group4[] = { - F(ByteOp | DstMem | SrcNone | Lock, em_inc), - F(ByteOp | DstMem | SrcNone | Lock, em_dec), + I(ByteOp | DstMem | SrcNone | Lock, em_inc), + I(ByteOp | DstMem | SrcNone | Lock, em_dec), N, N, N, N, N, N, }; static const struct opcode group5[] = { - F(DstMem | SrcNone | Lock, em_inc), - F(DstMem | SrcNone | Lock, em_dec), + I(DstMem | SrcNone | Lock, em_inc), + I(DstMem | SrcNone | Lock, em_dec), I(SrcMem | NearBranch | IsBranch | ShadowStack, em_call_near_abs), I(SrcMemFAddr | ImplicitOps | IsBranch | ShadowStack, em_call_far), I(SrcMem | NearBranch | IsBranch, em_jmp_abs), @@ -4139,10 +4074,10 @@ static const struct group_dual group7 = { { static const struct opcode group8[] = { N, N, N, N, - F(DstMem | SrcImmByte | NoWrite, em_bt), - F(DstMem | SrcImmByte | Lock | PageTable, em_bts), - F(DstMem | SrcImmByte | Lock, em_btr), - F(DstMem | SrcImmByte | Lock | PageTable, em_btc), + I(DstMem | SrcImmByte | NoWrite, em_bt), + I(DstMem | SrcImmByte | Lock | PageTable, em_bts), + I(DstMem | SrcImmByte | Lock, em_btr), + I(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; /* @@ -4279,31 +4214,31 @@ static const struct instr_dual instr_dual_8d = { static const struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ - F6ALU(Lock, em_add), + I6ALU(Lock, em_add), I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ - F6ALU(Lock | PageTable, em_or), + I6ALU(Lock | PageTable, em_or), I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), N, /* 0x10 - 0x17 */ - F6ALU(Lock, em_adc), + I6ALU(Lock, em_adc), I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg), /* 0x18 - 0x1F */ - F6ALU(Lock, em_sbb), + I6ALU(Lock, em_sbb), I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ - F6ALU(Lock | PageTable, em_and), N, N, + I6ALU(Lock | PageTable, em_and), N, N, /* 0x28 - 0x2F */ - F6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), + I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), /* 0x30 - 0x37 */ - F6ALU(Lock, em_xor), N, N, + I6ALU(Lock, em_xor), N, N, /* 0x38 - 0x3F */ - F6ALU(NoWrite, em_cmp), N, N, + I6ALU(NoWrite, em_cmp), N, N, /* 0x40 - 0x4F */ - X8(F(DstReg, em_inc)), X8(F(DstReg, em_dec)), + X8(I(DstReg, em_inc)), X8(I(DstReg, em_dec)), /* 0x50 - 0x57 */ X8(I(SrcReg | Stack, em_push)), /* 0x58 - 0x5F */ @@ -4327,7 +4262,7 @@ static const struct opcode opcode_table[256] = { G(DstMem | SrcImm, group1), G(ByteOp | DstMem | SrcImm | No64, group1), G(DstMem | SrcImmByte, group1), - F2bv(DstMem | SrcReg | ModRM | NoWrite, em_test), + I2bv(DstMem | SrcReg | ModRM | NoWrite, em_test), I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg), /* 0x88 - 0x8F */ I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov), @@ -4348,12 +4283,12 @@ static const struct opcode opcode_table[256] = { I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov), - F2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r), + I2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r), /* 0xA8 - 0xAF */ - F2bv(DstAcc | SrcImm | NoWrite, em_test), + I2bv(DstAcc | SrcImm | NoWrite, em_test), I2bv(SrcAcc | DstDI | Mov | String, em_mov), I2bv(SrcSI | DstAcc | Mov | String, em_mov), - F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r), + I2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r), /* 0xB0 - 0xB7 */ X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)), /* 0xB8 - 0xBF */ @@ -4378,7 +4313,7 @@ static const struct opcode opcode_table[256] = { G(Src2CL | ByteOp, group2), G(Src2CL, group2), I(DstAcc | SrcImmUByte | No64, em_aam), I(DstAcc | SrcImmUByte | No64, em_aad), - F(DstAcc | ByteOp | No64, em_salc), + I(DstAcc | ByteOp | No64, em_salc), I(DstAcc | SrcXLat | ByteOp, em_mov), /* 0xD8 - 0xDF */ N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N, @@ -4463,32 +4398,32 @@ static const struct opcode twobyte_table[256] = { /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), II(ImplicitOps, em_cpuid, cpuid), - F(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt), - F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld), - F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, + I(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt), + I(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld), + I(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), II(EmulateOnUD | ImplicitOps, em_rsm, rsm), - F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), - F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), - F(DstMem | SrcReg | Src2CL | ModRM, em_shrd), - GD(0, &group15), F(DstReg | SrcMem | ModRM, em_imul), + I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), + I(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), + I(DstMem | SrcReg | Src2CL | ModRM, em_shrd), + GD(0, &group15), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ I2bv(DstMem | SrcReg | ModRM | Lock | PageTable | SrcWrite, em_cmpxchg), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), - F(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), + I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, G(BitOp, group8), - F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), + I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), I(DstReg | SrcMem | ModRM, em_bsf_c), I(DstReg | SrcMem | ModRM, em_bsr_c), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ - F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), + I2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), N, ID(0, &instr_dual_0f_c3), N, N, N, GD(0, &group9), /* 0xC8 - 0xCF */ @@ -5198,24 +5133,6 @@ static void fetch_possible_mmx_operand(struct operand *op) kvm_read_mmx_reg(op->addr.mm, &op->mm_val); } -static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop) -{ - ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; - - if (!(ctxt->d & ByteOp)) - fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; - - asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" - : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT - : "c"(ctxt->src2.val)); - - ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); - if (!fop) /* exception is returned in fop variable */ - return emulate_de(ctxt); - return X86EMUL_CONTINUE; -} - void init_decode_cache(struct x86_emulate_ctxt *ctxt) { /* Clear fields that are set conditionally but read without a guard. */ @@ -5379,10 +5296,7 @@ special_insn: ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { - if (ctxt->d & Fastop) - rc = fastop(ctxt, ctxt->fop); - else - rc = ctxt->execute(ctxt); + rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) goto done; goto writeback; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 0a6cf5bff2aa..bc255d709d8a 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -361,6 +361,10 @@ SYM_FUNC_END(vmread_error_trampoline) .section .text, "ax" +#ifndef CONFIG_X86_FRED + SYM_FUNC_START(vmx_do_interrupt_irqoff) VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1 SYM_FUNC_END(vmx_do_interrupt_irqoff) + +#endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7b258af63ea..f87c216d976d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7021,8 +7021,14 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; + /* + * Invoke the kernel's IRQ handler for the vector. Use the FRED path + * when it's available even if FRED isn't fully enabled, e.g. even if + * FRED isn't supported in hardware, in order to avoid the indirect + * CALL in the non-FRED path. + */ kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); - if (cpu_feature_enabled(X86_FEATURE_FRED)) + if (IS_ENABLED(CONFIG_X86_FRED)) fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); else vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S index 58891681261b..aad1e5839202 100644 --- a/arch/x86/lib/bhi.S +++ b/arch/x86/lib/bhi.S @@ -5,7 +5,7 @@ #include <asm/nospec-branch.h> /* - * Notably, the FineIBT preamble calling these will have ZF set and r10 zero. + * Notably, the FineIBT preamble calling these will have ZF set and eax zero. * * The very last element is in fact larger than 32 bytes, but since its the * last element, this does not matter, @@ -36,7 +36,7 @@ SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_1 - cmovne %r10, %rdi + cmovne %rax, %rdi ANNOTATE_UNRET_SAFE ret int3 @@ -53,8 +53,8 @@ SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_1 - cmovne %r10, %rdi - cmovne %r10, %rsi + cmovne %rax, %rdi + cmovne %rax, %rsi ANNOTATE_UNRET_SAFE ret int3 @@ -64,9 +64,9 @@ SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_1 - cmovne %r10, %rdi - cmovne %r10, %rsi - cmovne %r10, %rdx + cmovne %rax, %rdi + cmovne %rax, %rsi + cmovne %rax, %rdx ANNOTATE_UNRET_SAFE ret int3 @@ -76,10 +76,10 @@ SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_2 - cmovne %r10, %rdi - cmovne %r10, %rsi - cmovne %r10, %rdx - cmovne %r10, %rcx + cmovne %rax, %rdi + cmovne %rax, %rsi + cmovne %rax, %rdx + cmovne %rax, %rcx ANNOTATE_UNRET_SAFE ret int3 @@ -89,11 +89,11 @@ SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_2 - cmovne %r10, %rdi - cmovne %r10, %rsi - cmovne %r10, %rdx - cmovne %r10, %rcx - cmovne %r10, %r8 + cmovne %rax, %rdi + cmovne %rax, %rsi + cmovne %rax, %rdx + cmovne %rax, %rcx + cmovne %rax, %r8 ANNOTATE_UNRET_SAFE ret int3 @@ -110,12 +110,12 @@ SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_2 - cmovne %r10, %rdi - cmovne %r10, %rsi - cmovne %r10, %rdx - cmovne %r10, %rcx - cmovne %r10, %r8 - cmovne %r10, %r9 + cmovne %rax, %rdi + cmovne %rax, %rsi + cmovne %rax, %rdx + cmovne %rax, %rcx + cmovne %rax, %r8 + cmovne %rax, %r9 ANNOTATE_UNRET_SAFE ret int3 @@ -125,13 +125,13 @@ SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL) ANNOTATE_NOENDBR UNWIND_HINT_FUNC jne .Lud_2 - cmovne %r10, %rdi - cmovne %r10, %rsi - cmovne %r10, %rdx - cmovne %r10, %rcx - cmovne %r10, %r8 - cmovne %r10, %r9 - cmovne %r10, %rsp + cmovne %rax, %rdi + cmovne %rax, %rsi + cmovne %rax, %rdx + cmovne %rax, %rcx + cmovne %rax, %r8 + cmovne %rax, %r9 + cmovne %rax, %rsp ANNOTATE_UNRET_SAFE ret int3 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index f513d33b6d37..8f1fed0c3b83 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -134,10 +134,10 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) .macro ITS_THUNK reg /* - * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b) + * If CFI paranoid is used then the ITS thunk starts with opcodes (1: udb; jne 1b) * that complete the fineibt_paranoid caller sequence. */ -1: .byte 0xea +1: ASM_UDB SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index fc13306af15f..d4c93d9e73e4 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -420,12 +420,12 @@ static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity) u8 *prog = *pprog; EMIT_ENDBR(); - EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */ + EMIT1_off32(0x2d, hash); /* subl $hash, %eax */ if (cfi_bhi) { + EMIT2(0x2e, 0x2e); /* cs cs */ emit_call(&prog, __bhi_args[arity], ip + 11); } else { - EMIT2(0x75, 0xf9); /* jne.d8 .-7 */ - EMIT3(0x0f, 0x1f, 0x00); /* nop3 */ + EMIT3_off32(0x2e, 0x0f, 0x85, 3); /* jne.d32,pn 3 */ } EMIT_ENDBR_POISON(); diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 2206b8bc47b8..f0a5fba0717e 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -11,6 +11,10 @@ #include <asm/nospec-branch.h> SYM_FUNC_START(__efi_call) + /* + * The EFI code doesn't have any CFI, annotate away the CFI violation. + */ + ANNOTATE_NOCFI_SYM pushq %rbp movq %rsp, %rbp and $~0xf, %rsp diff --git a/arch/xtensa/kernel/platform.c b/arch/xtensa/kernel/platform.c index 926b8bf0f14c..f14713060fd4 100644 --- a/arch/xtensa/kernel/platform.c +++ b/arch/xtensa/kernel/platform.c @@ -14,6 +14,7 @@ #include <linux/printk.h> #include <linux/types.h> +#include <linux/units.h> #include <asm/platform.h> #include <asm/timex.h> @@ -38,7 +39,7 @@ void __weak platform_idle(void) #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT void __weak platform_calibrate_ccount(void) { - pr_err("ERROR: Cannot calibrate cpu frequency! Assuming 10MHz.\n"); - ccount_freq = 10 * 1000000UL; + pr_err("ERROR: Cannot calibrate cpu frequency! Assuming 10 MHz.\n"); + ccount_freq = 10 * HZ_PER_MHZ; } #endif diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 6ed009318d24..3cafc8feddee 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -231,10 +231,14 @@ static ssize_t proc_read_simdisk(struct file *file, char __user *buf, static ssize_t proc_write_simdisk(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - char *tmp = memdup_user_nul(buf, count); + char *tmp; struct simdisk *dev = pde_data(file_inode(file)); int err; + if (count == 0 || count > PAGE_SIZE) + return -EINVAL; + + tmp = memdup_user_nul(buf, count); if (IS_ERR(tmp)) return PTR_ERR(tmp); diff --git a/block/bio.c b/block/bio.c index 3a1a848940dd..b3a79285c278 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1316,7 +1316,7 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, } /** - * bio_iov_iter_get_pages_aligned - add user or kernel pages to a bio + * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be added * @len_align_mask: the mask to align the total size to, 0 for any length @@ -1336,7 +1336,7 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. */ -int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter, +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, unsigned len_align_mask) { int ret = 0; @@ -1360,7 +1360,6 @@ int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter, return bio_iov_iter_align_down(bio, iter, len_align_mask); return ret; } -EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages_aligned); static void submit_bio_wait_endio(struct bio *bio) { diff --git a/block/blk-map.c b/block/blk-map.c index 165f2234f00f..60faf036fb6e 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -283,7 +283,11 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); if (!bio) return -ENOMEM; - ret = bio_iov_iter_get_pages(bio, iter); + /* + * No alignment requirements on our part to support arbitrary + * passthrough commands. + */ + ret = bio_iov_iter_get_pages(bio, iter, 0); if (ret) goto out_put; ret = blk_rq_append_bio(rq, bio); diff --git a/block/fops.c b/block/fops.c index c2c0396ea9ee..5e3db9fead77 100644 --- a/block/fops.c +++ b/block/fops.c @@ -43,6 +43,13 @@ static bool blkdev_dio_invalid(struct block_device *bdev, struct kiocb *iocb, (bdev_logical_block_size(bdev) - 1); } +static inline int blkdev_iov_iter_get_pages(struct bio *bio, + struct iov_iter *iter, struct block_device *bdev) +{ + return bio_iov_iter_get_pages(bio, iter, + bdev_logical_block_size(bdev) - 1); +} + #define DIO_INLINE_BIO_VECS 4 static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, @@ -78,7 +85,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, if (iocb->ki_flags & IOCB_ATOMIC) bio.bi_opf |= REQ_ATOMIC; - ret = bio_iov_iter_get_bdev_pages(&bio, iter, bdev); + ret = blkdev_iov_iter_get_pages(&bio, iter, bdev); if (unlikely(ret)) goto out; ret = bio.bi_iter.bi_size; @@ -212,7 +219,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; - ret = bio_iov_iter_get_bdev_pages(bio, iter, bdev); + ret = blkdev_iov_iter_get_pages(bio, iter, bdev); if (unlikely(ret)) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); @@ -348,7 +355,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, */ bio_iov_bvec_set(bio, iter); } else { - ret = bio_iov_iter_get_bdev_pages(bio, iter, bdev); + ret = blkdev_iov_iter_get_pages(bio, iter, bdev); if (unlikely(ret)) goto out_bio_put; } diff --git a/crypto/essiv.c b/crypto/essiv.c index d003b78fcd85..a47a3eab6935 100644 --- a/crypto/essiv.c +++ b/crypto/essiv.c @@ -186,9 +186,14 @@ static int essiv_aead_crypt(struct aead_request *req, bool enc) const struct essiv_tfm_ctx *tctx = crypto_aead_ctx(tfm); struct essiv_aead_request_ctx *rctx = aead_request_ctx(req); struct aead_request *subreq = &rctx->aead_req; + int ivsize = crypto_aead_ivsize(tfm); + int ssize = req->assoclen - ivsize; struct scatterlist *src = req->src; int err; + if (ssize < 0) + return -EINVAL; + crypto_cipher_encrypt_one(tctx->essiv_cipher, req->iv, req->iv); /* @@ -198,19 +203,12 @@ static int essiv_aead_crypt(struct aead_request *req, bool enc) */ rctx->assoc = NULL; if (req->src == req->dst || !enc) { - scatterwalk_map_and_copy(req->iv, req->dst, - req->assoclen - crypto_aead_ivsize(tfm), - crypto_aead_ivsize(tfm), 1); + scatterwalk_map_and_copy(req->iv, req->dst, ssize, ivsize, 1); } else { u8 *iv = (u8 *)aead_request_ctx(req) + tctx->ivoffset; - int ivsize = crypto_aead_ivsize(tfm); - int ssize = req->assoclen - ivsize; struct scatterlist *sg; int nents; - if (ssize < 0) - return -EINVAL; - nents = sg_nents_for_len(req->src, ssize); if (nents < 0) return -EINVAL; diff --git a/crypto/skcipher.c b/crypto/skcipher.c index de5fc91bba26..8fa5d9686d08 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -294,6 +294,8 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm) return crypto_init_lskcipher_ops_sg(tfm); } + crypto_skcipher_set_reqsize(skcipher, crypto_tfm_alg_reqsize(tfm)); + if (alg->exit) skcipher->base.exit = crypto_skcipher_exit_tfm; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 053a086d547e..13ce229d450c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -551,8 +551,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, return -EBADF; error = loop_check_backing_file(file); - if (error) + if (error) { + fput(file); return error; + } /* suppress uevents while reconfiguring the device */ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); @@ -822,7 +824,7 @@ static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd) if (worker) goto queue_work; - worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT | __GFP_NOWARN); + worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT); /* * In the event we cannot allocate a worker, just queue on the * rootcg worker and issue the I/O as the rootcg @@ -993,8 +995,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, return -EBADF; error = loop_check_backing_file(file); - if (error) + if (error) { + fput(file); return error; + } is_loop = is_loop_device(file); diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index ba3924eb13ba..8a8f692b6088 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -29,10 +29,11 @@ if TCG_TPM config TCG_TPM2_HMAC bool "Use HMAC and encrypted transactions on the TPM bus" - default X86_64 + default n select CRYPTO_ECDH select CRYPTO_LIB_AESCFB select CRYPTO_LIB_SHA256 + select CRYPTO_LIB_UTILS help Setting this causes us to deploy a scheme which uses request and response HMACs in addition to encryption for diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index b71725827743..c9f173001d0e 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -52,7 +52,7 @@ MODULE_PARM_DESC(suspend_pcr, unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) { if (chip->flags & TPM_CHIP_FLAG_TPM2) - return tpm2_calc_ordinal_duration(chip, ordinal); + return tpm2_calc_ordinal_duration(ordinal); else return tpm1_calc_ordinal_duration(chip, ordinal); } diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 7bb87fa5f7a1..2726bd38e5ac 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -299,7 +299,7 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip); int tpm2_auto_startup(struct tpm_chip *chip); void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type); -unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); +unsigned long tpm2_calc_ordinal_duration(u32 ordinal); int tpm2_probe(struct tpm_chip *chip); int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip); int tpm2_find_cc(struct tpm_chip *chip, u32 cc); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 524d802ede26..7d77f6fbc152 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -28,120 +28,57 @@ static struct tpm2_hash tpm2_hash_map[] = { int tpm2_get_timeouts(struct tpm_chip *chip) { - /* Fixed timeouts for TPM2 */ chip->timeout_a = msecs_to_jiffies(TPM2_TIMEOUT_A); chip->timeout_b = msecs_to_jiffies(TPM2_TIMEOUT_B); chip->timeout_c = msecs_to_jiffies(TPM2_TIMEOUT_C); chip->timeout_d = msecs_to_jiffies(TPM2_TIMEOUT_D); - - /* PTP spec timeouts */ - chip->duration[TPM_SHORT] = msecs_to_jiffies(TPM2_DURATION_SHORT); - chip->duration[TPM_MEDIUM] = msecs_to_jiffies(TPM2_DURATION_MEDIUM); - chip->duration[TPM_LONG] = msecs_to_jiffies(TPM2_DURATION_LONG); - - /* Key creation commands long timeouts */ - chip->duration[TPM_LONG_LONG] = - msecs_to_jiffies(TPM2_DURATION_LONG_LONG); - chip->flags |= TPM_CHIP_FLAG_HAVE_TIMEOUTS; - return 0; } -/** - * tpm2_ordinal_duration_index() - returns an index to the chip duration table - * @ordinal: TPM command ordinal. - * - * The function returns an index to the chip duration table - * (enum tpm_duration), that describes the maximum amount of - * time the chip could take to return the result for a particular ordinal. - * - * The values of the MEDIUM, and LONG durations are taken - * from the PC Client Profile (PTP) specification (750, 2000 msec) - * - * LONG_LONG is for commands that generates keys which empirically takes - * a longer time on some systems. - * - * Return: - * * TPM_MEDIUM - * * TPM_LONG - * * TPM_LONG_LONG - * * TPM_UNDEFINED +/* + * Contains the maximum durations in milliseconds for TPM2 commands. */ -static u8 tpm2_ordinal_duration_index(u32 ordinal) -{ - switch (ordinal) { - /* Startup */ - case TPM2_CC_STARTUP: /* 144 */ - return TPM_MEDIUM; - - case TPM2_CC_SELF_TEST: /* 143 */ - return TPM_LONG; - - case TPM2_CC_GET_RANDOM: /* 17B */ - return TPM_LONG; - - case TPM2_CC_SEQUENCE_UPDATE: /* 15C */ - return TPM_MEDIUM; - case TPM2_CC_SEQUENCE_COMPLETE: /* 13E */ - return TPM_MEDIUM; - case TPM2_CC_EVENT_SEQUENCE_COMPLETE: /* 185 */ - return TPM_MEDIUM; - case TPM2_CC_HASH_SEQUENCE_START: /* 186 */ - return TPM_MEDIUM; - - case TPM2_CC_VERIFY_SIGNATURE: /* 177 */ - return TPM_LONG_LONG; - - case TPM2_CC_PCR_EXTEND: /* 182 */ - return TPM_MEDIUM; - - case TPM2_CC_HIERARCHY_CONTROL: /* 121 */ - return TPM_LONG; - case TPM2_CC_HIERARCHY_CHANGE_AUTH: /* 129 */ - return TPM_LONG; - - case TPM2_CC_GET_CAPABILITY: /* 17A */ - return TPM_MEDIUM; - - case TPM2_CC_NV_READ: /* 14E */ - return TPM_LONG; - - case TPM2_CC_CREATE_PRIMARY: /* 131 */ - return TPM_LONG_LONG; - case TPM2_CC_CREATE: /* 153 */ - return TPM_LONG_LONG; - case TPM2_CC_CREATE_LOADED: /* 191 */ - return TPM_LONG_LONG; - - default: - return TPM_UNDEFINED; - } -} +static const struct { + unsigned long ordinal; + unsigned long duration; +} tpm2_ordinal_duration_map[] = { + {TPM2_CC_STARTUP, 750}, + {TPM2_CC_SELF_TEST, 3000}, + {TPM2_CC_GET_RANDOM, 2000}, + {TPM2_CC_SEQUENCE_UPDATE, 750}, + {TPM2_CC_SEQUENCE_COMPLETE, 750}, + {TPM2_CC_EVENT_SEQUENCE_COMPLETE, 750}, + {TPM2_CC_HASH_SEQUENCE_START, 750}, + {TPM2_CC_VERIFY_SIGNATURE, 30000}, + {TPM2_CC_PCR_EXTEND, 750}, + {TPM2_CC_HIERARCHY_CONTROL, 2000}, + {TPM2_CC_HIERARCHY_CHANGE_AUTH, 2000}, + {TPM2_CC_GET_CAPABILITY, 750}, + {TPM2_CC_NV_READ, 2000}, + {TPM2_CC_CREATE_PRIMARY, 30000}, + {TPM2_CC_CREATE, 30000}, + {TPM2_CC_CREATE_LOADED, 30000}, +}; /** - * tpm2_calc_ordinal_duration() - calculate the maximum command duration - * @chip: TPM chip to use. + * tpm2_calc_ordinal_duration() - Calculate the maximum command duration * @ordinal: TPM command ordinal. * - * The function returns the maximum amount of time the chip could take - * to return the result for a particular ordinal in jiffies. - * - * Return: A maximal duration time for an ordinal in jiffies. + * Returns the maximum amount of time the chip is expected by kernel to + * take in jiffies. */ -unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) +unsigned long tpm2_calc_ordinal_duration(u32 ordinal) { - unsigned int index; + int i; - index = tpm2_ordinal_duration_index(ordinal); + for (i = 0; i < ARRAY_SIZE(tpm2_ordinal_duration_map); i++) + if (ordinal == tpm2_ordinal_duration_map[i].ordinal) + return msecs_to_jiffies(tpm2_ordinal_duration_map[i].duration); - if (index != TPM_UNDEFINED) - return chip->duration[index]; - else - return msecs_to_jiffies(TPM2_DURATION_DEFAULT); + return msecs_to_jiffies(TPM2_DURATION_DEFAULT); } - struct tpm2_pcr_read_out { __be32 update_cnt; __be32 pcr_selects_cnt; diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index bdb119453dfb..6d03c224e6b2 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -69,8 +69,8 @@ #include <linux/unaligned.h> #include <crypto/kpp.h> #include <crypto/ecdh.h> -#include <crypto/hash.h> -#include <crypto/hmac.h> +#include <crypto/sha2.h> +#include <crypto/utils.h> /* maximum number of names the TPM must remember for authorization */ #define AUTH_MAX_NAMES 3 @@ -385,51 +385,6 @@ static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, u32 *handle, u8 *name); /* - * It turns out the crypto hmac(sha256) is hard for us to consume - * because it assumes a fixed key and the TPM seems to change the key - * on every operation, so we weld the hmac init and final functions in - * here to give it the same usage characteristics as a regular hash - */ -static void tpm2_hmac_init(struct sha256_ctx *sctx, u8 *key, u32 key_len) -{ - u8 pad[SHA256_BLOCK_SIZE]; - int i; - - sha256_init(sctx); - for (i = 0; i < sizeof(pad); i++) { - if (i < key_len) - pad[i] = key[i]; - else - pad[i] = 0; - pad[i] ^= HMAC_IPAD_VALUE; - } - sha256_update(sctx, pad, sizeof(pad)); -} - -static void tpm2_hmac_final(struct sha256_ctx *sctx, u8 *key, u32 key_len, - u8 *out) -{ - u8 pad[SHA256_BLOCK_SIZE]; - int i; - - for (i = 0; i < sizeof(pad); i++) { - if (i < key_len) - pad[i] = key[i]; - else - pad[i] = 0; - pad[i] ^= HMAC_OPAD_VALUE; - } - - /* collect the final hash; use out as temporary storage */ - sha256_final(sctx, out); - - sha256_init(sctx); - sha256_update(sctx, pad, sizeof(pad)); - sha256_update(sctx, out, SHA256_DIGEST_SIZE); - sha256_final(sctx, out); -} - -/* * assume hash sha256 and nonces u, v of size SHA256_DIGEST_SIZE but * otherwise standard tpm2_KDFa. Note output is in bytes not bits. */ @@ -440,16 +395,16 @@ static void tpm2_KDFa(u8 *key, u32 key_len, const char *label, u8 *u, const __be32 bits = cpu_to_be32(bytes * 8); while (bytes > 0) { - struct sha256_ctx sctx; + struct hmac_sha256_ctx hctx; __be32 c = cpu_to_be32(counter); - tpm2_hmac_init(&sctx, key, key_len); - sha256_update(&sctx, (u8 *)&c, sizeof(c)); - sha256_update(&sctx, label, strlen(label)+1); - sha256_update(&sctx, u, SHA256_DIGEST_SIZE); - sha256_update(&sctx, v, SHA256_DIGEST_SIZE); - sha256_update(&sctx, (u8 *)&bits, sizeof(bits)); - tpm2_hmac_final(&sctx, key, key_len, out); + hmac_sha256_init_usingrawkey(&hctx, key, key_len); + hmac_sha256_update(&hctx, (u8 *)&c, sizeof(c)); + hmac_sha256_update(&hctx, label, strlen(label) + 1); + hmac_sha256_update(&hctx, u, SHA256_DIGEST_SIZE); + hmac_sha256_update(&hctx, v, SHA256_DIGEST_SIZE); + hmac_sha256_update(&hctx, (u8 *)&bits, sizeof(bits)); + hmac_sha256_final(&hctx, out); bytes -= SHA256_DIGEST_SIZE; counter++; @@ -593,6 +548,7 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) u32 attrs; u8 cphash[SHA256_DIGEST_SIZE]; struct sha256_ctx sctx; + struct hmac_sha256_ctx hctx; if (!auth) return; @@ -704,14 +660,14 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) sha256_final(&sctx, cphash); /* now calculate the hmac */ - tpm2_hmac_init(&sctx, auth->session_key, sizeof(auth->session_key) - + auth->passphrase_len); - sha256_update(&sctx, cphash, sizeof(cphash)); - sha256_update(&sctx, auth->our_nonce, sizeof(auth->our_nonce)); - sha256_update(&sctx, auth->tpm_nonce, sizeof(auth->tpm_nonce)); - sha256_update(&sctx, &auth->attrs, 1); - tpm2_hmac_final(&sctx, auth->session_key, sizeof(auth->session_key) - + auth->passphrase_len, hmac); + hmac_sha256_init_usingrawkey(&hctx, auth->session_key, + sizeof(auth->session_key) + + auth->passphrase_len); + hmac_sha256_update(&hctx, cphash, sizeof(cphash)); + hmac_sha256_update(&hctx, auth->our_nonce, sizeof(auth->our_nonce)); + hmac_sha256_update(&hctx, auth->tpm_nonce, sizeof(auth->tpm_nonce)); + hmac_sha256_update(&hctx, &auth->attrs, 1); + hmac_sha256_final(&hctx, hmac); } EXPORT_SYMBOL(tpm_buf_fill_hmac_session); @@ -751,6 +707,7 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, u8 rphash[SHA256_DIGEST_SIZE]; u32 attrs, cc; struct sha256_ctx sctx; + struct hmac_sha256_ctx hctx; u16 tag = be16_to_cpu(head->tag); int parm_len, len, i, handles; @@ -820,21 +777,20 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, sha256_final(&sctx, rphash); /* now calculate the hmac */ - tpm2_hmac_init(&sctx, auth->session_key, sizeof(auth->session_key) - + auth->passphrase_len); - sha256_update(&sctx, rphash, sizeof(rphash)); - sha256_update(&sctx, auth->tpm_nonce, sizeof(auth->tpm_nonce)); - sha256_update(&sctx, auth->our_nonce, sizeof(auth->our_nonce)); - sha256_update(&sctx, &auth->attrs, 1); + hmac_sha256_init_usingrawkey(&hctx, auth->session_key, + sizeof(auth->session_key) + + auth->passphrase_len); + hmac_sha256_update(&hctx, rphash, sizeof(rphash)); + hmac_sha256_update(&hctx, auth->tpm_nonce, sizeof(auth->tpm_nonce)); + hmac_sha256_update(&hctx, auth->our_nonce, sizeof(auth->our_nonce)); + hmac_sha256_update(&hctx, &auth->attrs, 1); /* we're done with the rphash, so put our idea of the hmac there */ - tpm2_hmac_final(&sctx, auth->session_key, sizeof(auth->session_key) - + auth->passphrase_len, rphash); - if (memcmp(rphash, &buf->data[offset_s], SHA256_DIGEST_SIZE) == 0) { - rc = 0; - } else { + hmac_sha256_final(&hctx, rphash); + if (crypto_memneq(rphash, &buf->data[offset_s], SHA256_DIGEST_SIZE)) { dev_err(&chip->dev, "TPM: HMAC check failed\n"); goto out; } + rc = 0; /* now do response decryption */ if (auth->attrs & TPM2_SA_ENCRYPT) { diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c index d53fce1c9d6f..c9793a3d986d 100644 --- a/drivers/char/tpm/tpm_ppi.c +++ b/drivers/char/tpm/tpm_ppi.c @@ -33,6 +33,20 @@ static const guid_t tpm_ppi_guid = GUID_INIT(0x3DDDFAA6, 0x361B, 0x4EB4, 0xA4, 0x24, 0x8D, 0x10, 0x08, 0x9D, 0x16, 0x53); +static const char * const tpm_ppi_info[] = { + "Not implemented", + "BIOS only", + "Blocked for OS by system firmware", + "User required", + "User not required", +}; + +/* A spinlock to protect access to the cache from concurrent reads */ +static DEFINE_MUTEX(tpm_ppi_lock); + +static u32 ppi_operations_cache[PPI_VS_REQ_END + 1]; +static bool ppi_cache_populated; + static bool tpm_ppi_req_has_parameter(u64 req) { return req == 23; @@ -277,8 +291,7 @@ cleanup: return status; } -static ssize_t show_ppi_operations(acpi_handle dev_handle, char *buf, u32 start, - u32 end) +static ssize_t cache_ppi_operations(acpi_handle dev_handle, char *buf) { int i; u32 ret; @@ -286,34 +299,22 @@ static ssize_t show_ppi_operations(acpi_handle dev_handle, char *buf, u32 start, union acpi_object *obj, tmp; union acpi_object argv = ACPI_INIT_DSM_ARGV4(1, &tmp); - static char *info[] = { - "Not implemented", - "BIOS only", - "Blocked for OS by BIOS", - "User required", - "User not required", - }; - if (!acpi_check_dsm(dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID_1, 1 << TPM_PPI_FN_GETOPR)) return -EPERM; tmp.integer.type = ACPI_TYPE_INTEGER; - for (i = start; i <= end; i++) { + for (i = 0; i <= PPI_VS_REQ_END; i++) { tmp.integer.value = i; obj = tpm_eval_dsm(dev_handle, TPM_PPI_FN_GETOPR, ACPI_TYPE_INTEGER, &argv, TPM_PPI_REVISION_ID_1); - if (!obj) { + if (!obj) return -ENOMEM; - } else { - ret = obj->integer.value; - ACPI_FREE(obj); - } - if (ret > 0 && ret < ARRAY_SIZE(info)) - len += sysfs_emit_at(buf, len, "%d %d: %s\n", - i, ret, info[ret]); + ret = obj->integer.value; + ppi_operations_cache[i] = ret; + ACPI_FREE(obj); } return len; @@ -324,9 +325,30 @@ static ssize_t tpm_show_ppi_tcg_operations(struct device *dev, char *buf) { struct tpm_chip *chip = to_tpm_chip(dev); + ssize_t len = 0; + u32 ret; + int i; + + mutex_lock(&tpm_ppi_lock); + if (!ppi_cache_populated) { + len = cache_ppi_operations(chip->acpi_dev_handle, buf); + if (len < 0) { + mutex_unlock(&tpm_ppi_lock); + return len; + } - return show_ppi_operations(chip->acpi_dev_handle, buf, 0, - PPI_TPM_REQ_MAX); + ppi_cache_populated = true; + } + + for (i = 0; i <= PPI_TPM_REQ_MAX; i++) { + ret = ppi_operations_cache[i]; + if (ret >= 0 && ret < ARRAY_SIZE(tpm_ppi_info)) + len += sysfs_emit_at(buf, len, "%d %d: %s\n", + i, ret, tpm_ppi_info[ret]); + } + mutex_unlock(&tpm_ppi_lock); + + return len; } static ssize_t tpm_show_ppi_vs_operations(struct device *dev, @@ -334,9 +356,30 @@ static ssize_t tpm_show_ppi_vs_operations(struct device *dev, char *buf) { struct tpm_chip *chip = to_tpm_chip(dev); + ssize_t len = 0; + u32 ret; + int i; - return show_ppi_operations(chip->acpi_dev_handle, buf, PPI_VS_REQ_START, - PPI_VS_REQ_END); + mutex_lock(&tpm_ppi_lock); + if (!ppi_cache_populated) { + len = cache_ppi_operations(chip->acpi_dev_handle, buf); + if (len < 0) { + mutex_unlock(&tpm_ppi_lock); + return len; + } + + ppi_cache_populated = true; + } + + for (i = PPI_VS_REQ_START; i <= PPI_VS_REQ_END; i++) { + ret = ppi_operations_cache[i]; + if (ret >= 0 && ret < ARRAY_SIZE(tpm_ppi_info)) + len += sysfs_emit_at(buf, len, "%d %d: %s\n", + i, ret, tpm_ppi_info[ret]); + } + mutex_unlock(&tpm_ppi_lock); + + return len; } static DEVICE_ATTR(version, S_IRUGO, tpm_show_ppi_version, NULL); diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 4b12c4b9da8b..8954a8660ffc 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -978,8 +978,8 @@ restore_irqs: * will call disable_irq which undoes all of the above. */ if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { - tpm_tis_write8(priv, original_int_vec, - TPM_INT_VECTOR(priv->locality)); + tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), + original_int_vec); rc = -1; } diff --git a/drivers/gpio/gpio-usbio.c b/drivers/gpio/gpio-usbio.c index e13c120824e3..34d42c743d5b 100644 --- a/drivers/gpio/gpio-usbio.c +++ b/drivers/gpio/gpio-usbio.c @@ -29,6 +29,7 @@ static const struct acpi_device_id usbio_gpio_acpi_hids[] = { { "INTC1007" }, /* MTL */ { "INTC10B2" }, /* ARL */ { "INTC10B5" }, /* LNL */ + { "INTC10D1" }, /* MTL-CVF */ { "INTC10E2" }, /* PTL */ { } }; diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c index 4af504c23e6f..572b85e77370 100644 --- a/drivers/gpio/gpio-wcd934x.c +++ b/drivers/gpio/gpio-wcd934x.c @@ -103,7 +103,7 @@ static int wcd_gpio_probe(struct platform_device *pdev) chip->base = -1; chip->ngpio = WCD934X_NPINS; chip->label = dev_name(dev); - chip->can_sleep = false; + chip->can_sleep = true; return devm_gpiochip_add_data(dev, chip, data); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 7c54fe6b0f5d..83020963dfde 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2586,12 +2586,17 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, * from the KFD, trigger a segmentation fault in VM debug mode. */ if (amdgpu_ttm_adev(bo->tbo.bdev)->debug_vm_userptr) { + struct kfd_process *p; + pr_err("Pid %d unmapped memory before destroying userptr at GPU addr 0x%llx\n", pid_nr(process_info->pid), mem->va); // Send GPU VM fault to user space - kfd_signal_vm_fault_event_with_userptr(kfd_lookup_process_by_pid(process_info->pid), - mem->va); + p = kfd_lookup_process_by_pid(process_info->pid); + if (p) { + kfd_signal_vm_fault_event_with_userptr(p, mem->va); + kfd_unref_process(p); + } } ret = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index a77000c2e0bb..7a899fb4de29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -6389,23 +6389,28 @@ static int amdgpu_device_sched_resume(struct list_head *device_list, if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) drm_helper_resume_force_mode(adev_to_drm(tmp_adev)); - if (tmp_adev->asic_reset_res) - r = tmp_adev->asic_reset_res; - - tmp_adev->asic_reset_res = 0; - - if (r) { + if (tmp_adev->asic_reset_res) { /* bad news, how to tell it to userspace ? * for ras error, we should report GPU bad status instead of * reset failure */ if (reset_context->src != AMDGPU_RESET_SRC_RAS || !amdgpu_ras_eeprom_check_err_threshold(tmp_adev)) - dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", - atomic_read(&tmp_adev->gpu_reset_counter)); - amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r); + dev_info( + tmp_adev->dev, + "GPU reset(%d) failed with error %d \n", + atomic_read( + &tmp_adev->gpu_reset_counter), + tmp_adev->asic_reset_res); + amdgpu_vf_error_put(tmp_adev, + AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, + tmp_adev->asic_reset_res); + if (!r) + r = tmp_adev->asic_reset_res; + tmp_adev->asic_reset_res = 0; } else { - dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter)); + dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", + atomic_read(&tmp_adev->gpu_reset_counter)); if (amdgpu_acpi_smart_shift_update(tmp_adev, AMDGPU_SS_DEV_D0)) dev_warn(tmp_adev->dev, @@ -7157,28 +7162,35 @@ void amdgpu_pci_resume(struct pci_dev *pdev) static void amdgpu_device_cache_switch_state(struct amdgpu_device *adev) { - struct pci_dev *parent = pci_upstream_bridge(adev->pdev); + struct pci_dev *swus, *swds; int r; - if (!parent || parent->vendor != PCI_VENDOR_ID_ATI) + swds = pci_upstream_bridge(adev->pdev); + if (!swds || swds->vendor != PCI_VENDOR_ID_ATI || + pci_pcie_type(swds) != PCI_EXP_TYPE_DOWNSTREAM) + return; + swus = pci_upstream_bridge(swds); + if (!swus || + (swus->vendor != PCI_VENDOR_ID_ATI && + swus->vendor != PCI_VENDOR_ID_AMD) || + pci_pcie_type(swus) != PCI_EXP_TYPE_UPSTREAM) return; /* If already saved, return */ if (adev->pcie_reset_ctx.swus) return; /* Upstream bridge is ATI, assume it's SWUS/DS architecture */ - r = pci_save_state(parent); + r = pci_save_state(swds); if (r) return; - adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(parent); + adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(swds); - parent = pci_upstream_bridge(parent); - r = pci_save_state(parent); + r = pci_save_state(swus); if (r) return; - adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(parent); + adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(swus); - adev->pcie_reset_ctx.swus = parent; + adev->pcie_reset_ctx.swus = swus; } static void amdgpu_device_load_switch_state(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index a09ccf7d8aa2..ebe2b4c68b0f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -1102,6 +1102,9 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_ might_sleep(); while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) { + if (amdgpu_in_reset(adev)) + goto failed_kiq_read; + msleep(MAX_KIQ_REG_BAILOUT_INTERVAL); r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT); } @@ -1171,6 +1174,8 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint3 might_sleep(); while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) { + if (amdgpu_in_reset(adev)) + goto failed_kiq_write; msleep(MAX_KIQ_REG_BAILOUT_INTERVAL); r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 8676400834fc..a9327472c651 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1421,14 +1421,10 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) amdgpu_debugfs_vm_init(file_priv); - r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id); + r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id, pasid); if (r) goto error_pasid; - r = amdgpu_vm_set_pasid(adev, &fpriv->vm, pasid); - if (r) - goto error_vm; - fpriv->prt_va = amdgpu_vm_bo_add(adev, &fpriv->vm, NULL); if (!fpriv->prt_va) { r = -ENOMEM; @@ -1468,10 +1464,8 @@ error_vm: amdgpu_vm_fini(adev, &fpriv->vm); error_pasid: - if (pasid) { + if (pasid) amdgpu_pasid_free(pasid); - amdgpu_vm_set_pasid(adev, &fpriv->vm, 0); - } kfree(fpriv); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 1578e4e2bf84..8c0e5d03de50 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2352,7 +2352,7 @@ static int psp_securedisplay_initialize(struct psp_context *psp) } ret = psp_ta_load(psp, &psp->securedisplay_context.context); - if (!ret) { + if (!ret && !psp->securedisplay_context.context.resp_status) { psp->securedisplay_context.context.initialized = true; mutex_init(&psp->securedisplay_context.mutex); } else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 48e0932f5b62..1add21160d21 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -726,12 +726,12 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec, struct amdgpu_bo *bo; int ret; - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); while (!list_empty(&vm->invalidated)) { bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va, base.vm_status); - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); bo = bo_va->base.bo; ret = drm_exec_prepare_obj(exec, &bo->tbo.base, 2); @@ -748,9 +748,9 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec, if (ret) return ret; - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); } - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8c28e8923f02..c1a801203949 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -139,48 +139,6 @@ static void amdgpu_vm_assert_locked(struct amdgpu_vm *vm) } /** - * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping - * - * @adev: amdgpu_device pointer - * @vm: amdgpu_vm pointer - * @pasid: the pasid the VM is using on this GPU - * - * Set the pasid this VM is using on this GPU, can also be used to remove the - * pasid by passing in zero. - * - */ -int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm, - u32 pasid) -{ - int r; - - amdgpu_vm_assert_locked(vm); - - if (vm->pasid == pasid) - return 0; - - if (vm->pasid) { - r = xa_err(xa_erase_irq(&adev->vm_manager.pasids, vm->pasid)); - if (r < 0) - return r; - - vm->pasid = 0; - } - - if (pasid) { - r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm, - GFP_KERNEL)); - if (r < 0) - return r; - - vm->pasid = pasid; - } - - - return 0; -} - -/** * amdgpu_vm_bo_evicted - vm_bo is evicted * * @vm_bo: vm_bo which is evicted @@ -195,10 +153,12 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo) vm_bo->moved = true; amdgpu_vm_assert_locked(vm); + spin_lock(&vm_bo->vm->status_lock); if (bo->tbo.type == ttm_bo_type_kernel) list_move(&vm_bo->vm_status, &vm->evicted); else list_move_tail(&vm_bo->vm_status, &vm->evicted); + spin_unlock(&vm_bo->vm->status_lock); } /** * amdgpu_vm_bo_moved - vm_bo is moved @@ -211,7 +171,9 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo) static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo) { amdgpu_vm_assert_locked(vm_bo->vm); + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->moved); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -225,7 +187,9 @@ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo) static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo) { amdgpu_vm_assert_locked(vm_bo->vm); + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->idle); + spin_unlock(&vm_bo->vm->status_lock); vm_bo->moved = false; } @@ -239,9 +203,9 @@ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->invalidated_lock); + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated); - spin_unlock(&vm_bo->vm->invalidated_lock); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -254,9 +218,10 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo) { - amdgpu_vm_assert_locked(vm_bo->vm); vm_bo->moved = true; + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->evicted_user); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -270,10 +235,13 @@ static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo) static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo) { amdgpu_vm_assert_locked(vm_bo->vm); - if (vm_bo->bo->parent) + if (vm_bo->bo->parent) { + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->relocated); - else + spin_unlock(&vm_bo->vm->status_lock); + } else { amdgpu_vm_bo_idle(vm_bo); + } } /** @@ -287,7 +255,9 @@ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo) static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo) { amdgpu_vm_assert_locked(vm_bo->vm); + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->done); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -301,13 +271,13 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) { struct amdgpu_vm_bo_base *vm_bo, *tmp; - spin_lock(&vm->invalidated_lock); + amdgpu_vm_assert_locked(vm); + + spin_lock(&vm->status_lock); list_splice_init(&vm->done, &vm->invalidated); list_for_each_entry(vm_bo, &vm->invalidated, vm_status) vm_bo->moved = true; - spin_unlock(&vm->invalidated_lock); - amdgpu_vm_assert_locked(vm_bo->vm); list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) { struct amdgpu_bo *bo = vm_bo->bo; @@ -317,13 +287,14 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) else if (bo->parent) list_move(&vm_bo->vm_status, &vm_bo->vm->relocated); } + spin_unlock(&vm->status_lock); } /** * amdgpu_vm_update_shared - helper to update shared memory stat * @base: base structure for tracking BO usage in a VM * - * Takes the vm stats_lock and updates the shared memory stat. If the basic + * Takes the vm status_lock and updates the shared memory stat. If the basic * stat changed (e.g. buffer was moved) amdgpu_vm_update_stats need to be called * as well. */ @@ -336,7 +307,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base) bool shared; dma_resv_assert_held(bo->tbo.base.resv); - spin_lock(&vm->stats_lock); + spin_lock(&vm->status_lock); shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base); if (base->shared != shared) { base->shared = shared; @@ -348,7 +319,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base) vm->stats[bo_memtype].drm.private += size; } } - spin_unlock(&vm->stats_lock); + spin_unlock(&vm->status_lock); } /** @@ -373,11 +344,11 @@ void amdgpu_vm_bo_update_shared(struct amdgpu_bo *bo) * be bo->tbo.resource * @sign: if we should add (+1) or subtract (-1) from the stat * - * Caller need to have the vm stats_lock held. Useful for when multiple update + * Caller need to have the vm status_lock held. Useful for when multiple update * need to happen at the same time. */ static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base, - struct ttm_resource *res, int sign) + struct ttm_resource *res, int sign) { struct amdgpu_vm *vm = base->vm; struct amdgpu_bo *bo = base->bo; @@ -401,8 +372,7 @@ static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base, */ if (bo->flags & AMDGPU_GEM_CREATE_DISCARDABLE) vm->stats[res_memtype].drm.purgeable += size; - if (!(bo->preferred_domains & - amdgpu_mem_type_to_domain(res_memtype))) + if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(res_memtype))) vm->stats[bo_memtype].evicted += size; } } @@ -421,9 +391,9 @@ void amdgpu_vm_update_stats(struct amdgpu_vm_bo_base *base, { struct amdgpu_vm *vm = base->vm; - spin_lock(&vm->stats_lock); + spin_lock(&vm->status_lock); amdgpu_vm_update_stats_locked(base, res, sign); - spin_unlock(&vm->stats_lock); + spin_unlock(&vm->status_lock); } /** @@ -449,10 +419,10 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, base->next = bo->vm_bo; bo->vm_bo = base; - spin_lock(&vm->stats_lock); + spin_lock(&vm->status_lock); base->shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base); amdgpu_vm_update_stats_locked(base, bo->tbo.resource, +1); - spin_unlock(&vm->stats_lock); + spin_unlock(&vm->status_lock); if (!amdgpu_vm_is_bo_always_valid(vm, bo)) return; @@ -511,10 +481,10 @@ int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec, int ret; /* We can only trust prev->next while holding the lock */ - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); while (!list_is_head(prev->next, &vm->done)) { bo_va = list_entry(prev->next, typeof(*bo_va), base.vm_status); - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); bo = bo_va->base.bo; if (bo) { @@ -522,10 +492,10 @@ int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec, if (unlikely(ret)) return ret; } - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); prev = prev->next; } - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); return 0; } @@ -621,7 +591,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, void *param) { uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); - struct amdgpu_vm_bo_base *bo_base, *tmp; + struct amdgpu_vm_bo_base *bo_base; struct amdgpu_bo *bo; int r; @@ -634,7 +604,13 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, return r; } - list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) { + spin_lock(&vm->status_lock); + while (!list_empty(&vm->evicted)) { + bo_base = list_first_entry(&vm->evicted, + struct amdgpu_vm_bo_base, + vm_status); + spin_unlock(&vm->status_lock); + bo = bo_base->bo; r = validate(param, bo); @@ -647,21 +623,26 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, vm->update_funcs->map_table(to_amdgpu_bo_vm(bo)); amdgpu_vm_bo_relocated(bo_base); } + spin_lock(&vm->status_lock); } + while (ticket && !list_empty(&vm->evicted_user)) { + bo_base = list_first_entry(&vm->evicted_user, + struct amdgpu_vm_bo_base, + vm_status); + spin_unlock(&vm->status_lock); + + bo = bo_base->bo; + dma_resv_assert_held(bo->tbo.base.resv); - if (ticket) { - list_for_each_entry_safe(bo_base, tmp, &vm->evicted_user, - vm_status) { - bo = bo_base->bo; - dma_resv_assert_held(bo->tbo.base.resv); + r = validate(param, bo); + if (r) + return r; - r = validate(param, bo); - if (r) - return r; + amdgpu_vm_bo_invalidated(bo_base); - amdgpu_vm_bo_invalidated(bo_base); - } + spin_lock(&vm->status_lock); } + spin_unlock(&vm->status_lock); amdgpu_vm_eviction_lock(vm); vm->evicting = false; @@ -690,7 +671,9 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm) ret = !vm->evicting; amdgpu_vm_eviction_unlock(vm); + spin_lock(&vm->status_lock); ret &= list_empty(&vm->evicted); + spin_unlock(&vm->status_lock); spin_lock(&vm->immediate.lock); ret &= !vm->immediate.stopped; @@ -981,13 +964,18 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, struct amdgpu_vm *vm, bool immediate) { struct amdgpu_vm_update_params params; - struct amdgpu_vm_bo_base *entry, *tmp; + struct amdgpu_vm_bo_base *entry; bool flush_tlb_needed = false; + LIST_HEAD(relocated); int r, idx; amdgpu_vm_assert_locked(vm); - if (list_empty(&vm->relocated)) + spin_lock(&vm->status_lock); + list_splice_init(&vm->relocated, &relocated); + spin_unlock(&vm->status_lock); + + if (list_empty(&relocated)) return 0; if (!drm_dev_enter(adev_to_drm(adev), &idx)) @@ -1003,7 +991,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, if (r) goto error; - list_for_each_entry(entry, &vm->relocated, vm_status) { + list_for_each_entry(entry, &relocated, vm_status) { /* vm_flush_needed after updating moved PDEs */ flush_tlb_needed |= entry->moved; @@ -1019,7 +1007,9 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, if (flush_tlb_needed) atomic64_inc(&vm->tlb_seq); - list_for_each_entry_safe(entry, tmp, &vm->relocated, vm_status) { + while (!list_empty(&relocated)) { + entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base, + vm_status); amdgpu_vm_bo_idle(entry); } @@ -1246,9 +1236,9 @@ error_free: void amdgpu_vm_get_memory(struct amdgpu_vm *vm, struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]) { - spin_lock(&vm->stats_lock); + spin_lock(&vm->status_lock); memcpy(stats, vm->stats, sizeof(*stats) * __AMDGPU_PL_NUM); - spin_unlock(&vm->stats_lock); + spin_unlock(&vm->status_lock); } /** @@ -1615,24 +1605,29 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket) { - struct amdgpu_bo_va *bo_va, *tmp; + struct amdgpu_bo_va *bo_va; struct dma_resv *resv; bool clear, unlock; int r; - list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) { + spin_lock(&vm->status_lock); + while (!list_empty(&vm->moved)) { + bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va, + base.vm_status); + spin_unlock(&vm->status_lock); + /* Per VM BOs never need to bo cleared in the page tables */ r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; + spin_lock(&vm->status_lock); } - spin_lock(&vm->invalidated_lock); while (!list_empty(&vm->invalidated)) { bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va, base.vm_status); resv = bo_va->base.bo->tbo.base.resv; - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); /* Try to reserve the BO to avoid clearing its ptes */ if (!adev->debug_vm && dma_resv_trylock(resv)) { @@ -1664,9 +1659,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, bo_va->base.bo->tbo.resource->mem_type == TTM_PL_SYSTEM)) amdgpu_vm_bo_evicted_user(&bo_va->base); - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); } - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); return 0; } @@ -2195,9 +2190,9 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev, } } - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); list_del(&bo_va->base.vm_status); - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); list_for_each_entry_safe(mapping, next, &bo_va->valids, list) { list_del(&mapping->list); @@ -2305,10 +2300,10 @@ void amdgpu_vm_bo_move(struct amdgpu_bo *bo, struct ttm_resource *new_mem, for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; - spin_lock(&vm->stats_lock); + spin_lock(&vm->status_lock); amdgpu_vm_update_stats_locked(bo_base, bo->tbo.resource, -1); amdgpu_vm_update_stats_locked(bo_base, new_mem, +1); - spin_unlock(&vm->stats_lock); + spin_unlock(&vm->status_lock); } amdgpu_vm_bo_invalidate(bo, evicted); @@ -2554,6 +2549,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) * @adev: amdgpu_device pointer * @vm: requested vm * @xcp_id: GPU partition selection id + * @pasid: the pasid the VM is using on this GPU * * Init @vm fields. * @@ -2561,7 +2557,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) * 0 for success, error for failure. */ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, - int32_t xcp_id) + int32_t xcp_id, uint32_t pasid) { struct amdgpu_bo *root_bo; struct amdgpu_bo_vm *root; @@ -2575,12 +2571,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, INIT_LIST_HEAD(&vm->relocated); INIT_LIST_HEAD(&vm->moved); INIT_LIST_HEAD(&vm->idle); - spin_lock_init(&vm->invalidated_lock); INIT_LIST_HEAD(&vm->invalidated); + spin_lock_init(&vm->status_lock); INIT_LIST_HEAD(&vm->freed); INIT_LIST_HEAD(&vm->done); INIT_KFIFO(vm->faults); - spin_lock_init(&vm->stats_lock); r = amdgpu_vm_init_entities(adev, vm); if (r) @@ -2638,12 +2633,26 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) dev_dbg(adev->dev, "Failed to create task info for VM\n"); + /* Store new PASID in XArray (if non-zero) */ + if (pasid != 0) { + r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm, GFP_KERNEL)); + if (r < 0) + goto error_free_root; + + vm->pasid = pasid; + } + amdgpu_bo_unreserve(vm->root.bo); amdgpu_bo_unref(&root_bo); return 0; error_free_root: + /* If PASID was partially set, erase it from XArray before failing */ + if (vm->pasid != 0) { + xa_erase_irq(&adev->vm_manager.pasids, vm->pasid); + vm->pasid = 0; + } amdgpu_vm_pt_free_root(adev, vm); amdgpu_bo_unreserve(vm->root.bo); amdgpu_bo_unref(&root_bo); @@ -2749,7 +2758,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) root = amdgpu_bo_ref(vm->root.bo); amdgpu_bo_reserve(root, true); - amdgpu_vm_set_pasid(adev, vm, 0); + /* Remove PASID mapping before destroying VM */ + if (vm->pasid != 0) { + xa_erase_irq(&adev->vm_manager.pasids, vm->pasid); + vm->pasid = 0; + } dma_fence_wait(vm->last_unlocked, false); dma_fence_put(vm->last_unlocked); dma_fence_wait(vm->last_tlb_flush, false); @@ -3038,6 +3051,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) amdgpu_vm_assert_locked(vm); + spin_lock(&vm->status_lock); seq_puts(m, "\tIdle BOs:\n"); list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) { if (!bo_va->base.bo) @@ -3075,13 +3089,11 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) id = 0; seq_puts(m, "\tInvalidated BOs:\n"); - spin_lock(&vm->invalidated_lock); list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) { if (!bo_va->base.bo) continue; total_invalidated += amdgpu_bo_print_info(id++, bo_va->base.bo, m); } - spin_unlock(&vm->invalidated_lock); total_invalidated_objs = id; id = 0; @@ -3091,6 +3103,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) continue; total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m); } + spin_unlock(&vm->status_lock); total_done_objs = id; seq_printf(m, "\tTotal idle size: %12lld\tobjs:\t%d\n", total_idle, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index adc5c9161fa8..cf0ec94e8a07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -203,11 +203,11 @@ struct amdgpu_vm_bo_base { /* protected by bo being reserved */ struct amdgpu_vm_bo_base *next; - /* protected by vm reservation and invalidated_lock */ + /* protected by vm status_lock */ struct list_head vm_status; /* if the bo is counted as shared in mem stats - * protected by vm BO being reserved */ + * protected by vm status_lock */ bool shared; /* protected by the BO being reserved */ @@ -343,8 +343,10 @@ struct amdgpu_vm { bool evicting; unsigned int saved_flags; - /* Memory statistics for this vm, protected by stats_lock */ - spinlock_t stats_lock; + /* Lock to protect vm_bo add/del/move on all lists of vm */ + spinlock_t status_lock; + + /* Memory statistics for this vm, protected by status_lock */ struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]; /* @@ -352,8 +354,6 @@ struct amdgpu_vm { * PDs, PTs or per VM BOs. The state transits are: * * evicted -> relocated (PDs, PTs) or moved (per VM BOs) -> idle - * - * Lists are protected by the root PD dma_resv lock. */ /* Per-VM and PT BOs who needs a validation */ @@ -374,10 +374,7 @@ struct amdgpu_vm { * state transits are: * * evicted_user or invalidated -> done - * - * Lists are protected by the invalidated_lock. */ - spinlock_t invalidated_lock; /* BOs for user mode queues that need a validation */ struct list_head evicted_user; @@ -503,11 +500,8 @@ extern const struct amdgpu_vm_update_funcs amdgpu_vm_sdma_funcs; void amdgpu_vm_manager_init(struct amdgpu_device *adev); void amdgpu_vm_manager_fini(struct amdgpu_device *adev); -int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm, - u32 pasid); - long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout); -int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id); +int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id, uint32_t pasid); int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 7a4c12ff9b18..f794fb1cc06e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -543,7 +543,9 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) entry->bo->vm_bo = NULL; ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); + spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); + spin_unlock(&entry->vm->status_lock); amdgpu_bo_unref(&entry->bo); } @@ -587,6 +589,7 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params, struct amdgpu_vm_pt_cursor seek; struct amdgpu_vm_bo_base *entry; + spin_lock(¶ms->vm->status_lock); for_each_amdgpu_vm_pt_dfs_safe(params->adev, params->vm, cursor, seek, entry) { if (entry && entry->bo) list_move(&entry->vm_status, ¶ms->tlb_flush_waitlist); @@ -594,6 +597,7 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params, /* enter start node now */ list_move(&cursor->entry->vm_status, ¶ms->tlb_flush_waitlist); + spin_unlock(¶ms->vm->status_lock); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index 404cc8c2ff2c..f4a19357ccbc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -337,7 +337,7 @@ static void gmc_v12_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev, int vmid, i; if (adev->enable_uni_mes && adev->mes.ring[AMDGPU_MES_SCHED_PIPE].sched.ready && - (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x83) { + (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x84) { struct mes_inv_tlbs_pasid_input input = {0}; input.pasid = pasid; input.flush_type = flush_type; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 273f42e3afdd..9d72411c3379 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3045,6 +3045,8 @@ retry_write_locked: if (svms->checkpoint_ts[gpuidx] != 0) { if (amdgpu_ih_ts_after_or_equal(ts, svms->checkpoint_ts[gpuidx])) { pr_debug("draining retry fault, drop fault 0x%llx\n", addr); + if (write_locked) + mmap_write_downgrade(mm); r = -EAGAIN; goto out_unlock_svms; } else { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 8e1622bf7a42..0d03e324d5b9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2000,6 +2000,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.flags.disable_ips_in_vpb = 0; + /* DCN35 and above supports dynamic DTBCLK switch */ + if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 5, 0)) + init_data.flags.allow_0_dtb_clk = true; + /* Enable DWB for tested platforms only */ if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0)) init_data.num_virtual_links = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c index 2b1673d69ea8..1ab5ae9b5ea5 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c @@ -154,10 +154,13 @@ static bool dce60_setup_scaling_configuration( REG_SET(SCL_BYPASS_CONTROL, 0, SCL_BYPASS_MODE, 0); if (data->taps.h_taps + data->taps.v_taps <= 2) { - /* Set bypass */ - - /* DCE6 has no SCL_MODE register, skip scale mode programming */ + /* Disable scaler functionality */ + REG_WRITE(SCL_SCALER_ENABLE, 0); + /* Clear registers that can cause glitches even when the scaler is off */ + REG_WRITE(SCL_TAP_CONTROL, 0); + REG_WRITE(SCL_AUTOMATIC_MODE_CONTROL, 0); + REG_WRITE(SCL_F_SHARP_CONTROL, 0); return false; } @@ -165,7 +168,7 @@ static bool dce60_setup_scaling_configuration( SCL_H_NUM_OF_TAPS, data->taps.h_taps - 1, SCL_V_NUM_OF_TAPS, data->taps.v_taps - 1); - /* DCE6 has no SCL_MODE register, skip scale mode programming */ + REG_WRITE(SCL_SCALER_ENABLE, 1); /* DCE6 has no SCL_BOUNDARY_MODE bit, skip replace out of bound pixels */ @@ -502,6 +505,8 @@ static void dce60_transform_set_scaler( REG_SET(DC_LB_MEM_SIZE, 0, DC_LB_MEM_SIZE, xfm_dce->lb_memory_size); + REG_WRITE(SCL_UPDATE, 0x00010000); + /* Clear SCL_F_SHARP_CONTROL value to 0 */ REG_WRITE(SCL_F_SHARP_CONTROL, 0); @@ -527,8 +532,7 @@ static void dce60_transform_set_scaler( if (coeffs_v != xfm_dce->filter_v || coeffs_h != xfm_dce->filter_h) { /* 4. Program vertical filters */ if (xfm_dce->filter_v == NULL) - REG_SET(SCL_VERT_FILTER_CONTROL, 0, - SCL_V_2TAP_HARDCODE_COEF_EN, 0); + REG_WRITE(SCL_VERT_FILTER_CONTROL, 0); program_multi_taps_filter( xfm_dce, data->taps.v_taps, @@ -542,8 +546,7 @@ static void dce60_transform_set_scaler( /* 5. Program horizontal filters */ if (xfm_dce->filter_h == NULL) - REG_SET(SCL_HORZ_FILTER_CONTROL, 0, - SCL_H_2TAP_HARDCODE_COEF_EN, 0); + REG_WRITE(SCL_HORZ_FILTER_CONTROL, 0); program_multi_taps_filter( xfm_dce, data->taps.h_taps, @@ -566,6 +569,8 @@ static void dce60_transform_set_scaler( /* DCE6 has no SCL_COEF_UPDATE_COMPLETE bit to flip to new coefficient memory */ /* DCE6 DATA_FORMAT register does not support ALPHA_EN */ + + REG_WRITE(SCL_UPDATE, 0); } #endif diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h index cbce194ec7b8..eb716e8337e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h @@ -155,6 +155,9 @@ SRI(SCL_COEF_RAM_TAP_DATA, SCL, id), \ SRI(VIEWPORT_START, SCL, id), \ SRI(VIEWPORT_SIZE, SCL, id), \ + SRI(SCL_SCALER_ENABLE, SCL, id), \ + SRI(SCL_HORZ_FILTER_INIT_RGB_LUMA, SCL, id), \ + SRI(SCL_HORZ_FILTER_INIT_CHROMA, SCL, id), \ SRI(SCL_HORZ_FILTER_SCALE_RATIO, SCL, id), \ SRI(SCL_VERT_FILTER_SCALE_RATIO, SCL, id), \ SRI(SCL_VERT_FILTER_INIT, SCL, id), \ @@ -590,6 +593,7 @@ struct dce_transform_registers { uint32_t SCL_VERT_FILTER_SCALE_RATIO; uint32_t SCL_HORZ_FILTER_INIT; #if defined(CONFIG_DRM_AMD_DC_SI) + uint32_t SCL_SCALER_ENABLE; uint32_t SCL_HORZ_FILTER_INIT_RGB_LUMA; uint32_t SCL_HORZ_FILTER_INIT_CHROMA; #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index 17a21bcbde17..1a28061bb9ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -808,6 +808,8 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc) { + dc_assert_fp_enabled(); + return soc->clock_limits[0].dispclk_mhz * 10000.0 / (1.0 + soc->dcn_downspread_percent / 100.0); } @@ -815,6 +817,8 @@ int dcn_get_approx_det_segs_required_for_pstate( struct _vcs_dpi_soc_bounding_box_st *soc, int pix_clk_100hz, int bpp, int seg_size_kb) { + dc_assert_fp_enabled(); + /* Roughly calculate required crb to hide latency. In practice there is slightly * more buffer available for latency hiding */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index c9dd920744c9..817a370e80a7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -445,6 +445,8 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc, bool upscaled = false; const unsigned int max_allowed_vblank_nom = 1023; + dc_assert_fp_enabled(); + dcn31_populate_dml_pipes_from_context(dc, context, pipes, validate_mode); @@ -498,9 +500,7 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc, pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; - DC_FP_START(); dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt); - DC_FP_END(); pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; pipes[pipe_cnt].pipe.src.dcc_rate = 3; @@ -581,6 +581,8 @@ void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context) unsigned int i, plane_count = 0; DC_LOGGER_INIT(dc->ctx->logger); + dc_assert_fp_enabled(); + for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c index 8cda18ce1a76..77023b619f1e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c @@ -478,6 +478,8 @@ int dcn351_populate_dml_pipes_from_context_fpu(struct dc *dc, bool upscaled = false; const unsigned int max_allowed_vblank_nom = 1023; + dc_assert_fp_enabled(); + dcn31_populate_dml_pipes_from_context(dc, context, pipes, validate_mode); @@ -531,9 +533,7 @@ int dcn351_populate_dml_pipes_from_context_fpu(struct dc *dc, pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; - DC_FP_START(); dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt); - DC_FP_END(); pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; pipes[pipe_cnt].pipe.src.dcc_rate = 3; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c index 53c67ebe779f..b75be6ad64f6 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c @@ -404,13 +404,13 @@ static const struct dc_plane_cap plane_cap = { }, .max_upscale_factor = { - .argb8888 = 16000, + .argb8888 = 1, .nv12 = 1, .fp16 = 1 }, .max_downscale_factor = { - .argb8888 = 250, + .argb8888 = 1, .nv12 = 1, .fp16 = 1 } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 07552445e424..fff57f23f4f7 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -1760,6 +1760,20 @@ enum dc_status dcn35_patch_unknown_plane_state(struct dc_plane_state *plane_stat } +static int populate_dml_pipes_from_context_fpu(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + enum dc_validate_mode validate_mode) +{ + int ret; + + DC_FP_START(); + ret = dcn35_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode); + DC_FP_END(); + + return ret; +} + static struct resource_funcs dcn35_res_pool_funcs = { .destroy = dcn35_destroy_resource_pool, .link_enc_create = dcn35_link_encoder_create, @@ -1770,7 +1784,7 @@ static struct resource_funcs dcn35_res_pool_funcs = { .validate_bandwidth = dcn35_validate_bandwidth, .calculate_wm_and_dlg = NULL, .update_soc_for_wm_a = dcn31_update_soc_for_wm_a, - .populate_dml_pipes = dcn35_populate_dml_pipes_from_context_fpu, + .populate_dml_pipes = populate_dml_pipes_from_context_fpu, .acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer, .release_pipe = dcn20_release_pipe, .add_stream_to_ctx = dcn30_add_stream_to_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index cb0478a9a34d..0abd163b425e 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -1732,6 +1732,21 @@ static enum dc_status dcn351_validate_bandwidth(struct dc *dc, return out ? DC_OK : DC_FAIL_BANDWIDTH_VALIDATE; } +static int populate_dml_pipes_from_context_fpu(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + enum dc_validate_mode validate_mode) +{ + int ret; + + DC_FP_START(); + ret = dcn351_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode); + DC_FP_END(); + + return ret; + +} + static struct resource_funcs dcn351_res_pool_funcs = { .destroy = dcn351_destroy_resource_pool, .link_enc_create = dcn35_link_encoder_create, @@ -1742,7 +1757,7 @@ static struct resource_funcs dcn351_res_pool_funcs = { .validate_bandwidth = dcn351_validate_bandwidth, .calculate_wm_and_dlg = NULL, .update_soc_for_wm_a = dcn31_update_soc_for_wm_a, - .populate_dml_pipes = dcn351_populate_dml_pipes_from_context_fpu, + .populate_dml_pipes = populate_dml_pipes_from_context_fpu, .acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer, .release_pipe = dcn20_release_pipe, .add_stream_to_ctx = dcn30_add_stream_to_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c index 126090c9bb8a..ca125ee6c2fb 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c @@ -1734,6 +1734,20 @@ static enum dc_status dcn35_validate_bandwidth(struct dc *dc, } +static int populate_dml_pipes_from_context_fpu(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + enum dc_validate_mode validate_mode) +{ + int ret; + + DC_FP_START(); + ret = dcn35_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode); + DC_FP_END(); + + return ret; +} + static struct resource_funcs dcn36_res_pool_funcs = { .destroy = dcn36_destroy_resource_pool, .link_enc_create = dcn35_link_encoder_create, @@ -1744,7 +1758,7 @@ static struct resource_funcs dcn36_res_pool_funcs = { .validate_bandwidth = dcn35_validate_bandwidth, .calculate_wm_and_dlg = NULL, .update_soc_for_wm_a = dcn31_update_soc_for_wm_a, - .populate_dml_pipes = dcn35_populate_dml_pipes_from_context_fpu, + .populate_dml_pipes = populate_dml_pipes_from_context_fpu, .acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer, .release_pipe = dcn20_release_pipe, .add_stream_to_ctx = dcn30_add_stream_to_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c index 55b929ca7982..b1fb0f8a253a 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c @@ -641,16 +641,16 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in, /* this gives the direction of the cositing (negative will move * left, right otherwise) */ - int sign = 1; + int h_sign = flip_horz_scan_dir ? -1 : 1; + int v_sign = flip_vert_scan_dir ? -1 : 1; switch (spl_in->basic_in.cositing) { - case CHROMA_COSITING_TOPLEFT: - init_adj_h = spl_fixpt_from_fraction(sign, 4); - init_adj_v = spl_fixpt_from_fraction(sign, 4); + init_adj_h = spl_fixpt_from_fraction(h_sign, 4); + init_adj_v = spl_fixpt_from_fraction(v_sign, 4); break; case CHROMA_COSITING_LEFT: - init_adj_h = spl_fixpt_from_fraction(sign, 4); + init_adj_h = spl_fixpt_from_fraction(h_sign, 4); init_adj_v = spl_fixpt_zero; break; case CHROMA_COSITING_NONE: diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h index 9de01ae574c0..067eddd9c62d 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h @@ -4115,6 +4115,7 @@ #define mmSCL0_SCL_COEF_RAM_CONFLICT_STATUS 0x1B55 #define mmSCL0_SCL_COEF_RAM_SELECT 0x1B40 #define mmSCL0_SCL_COEF_RAM_TAP_DATA 0x1B41 +#define mmSCL0_SCL_SCALER_ENABLE 0x1B42 #define mmSCL0_SCL_CONTROL 0x1B44 #define mmSCL0_SCL_DEBUG 0x1B6A #define mmSCL0_SCL_DEBUG2 0x1B69 @@ -4144,6 +4145,7 @@ #define mmSCL1_SCL_COEF_RAM_CONFLICT_STATUS 0x1E55 #define mmSCL1_SCL_COEF_RAM_SELECT 0x1E40 #define mmSCL1_SCL_COEF_RAM_TAP_DATA 0x1E41 +#define mmSCL1_SCL_SCALER_ENABLE 0x1E42 #define mmSCL1_SCL_CONTROL 0x1E44 #define mmSCL1_SCL_DEBUG 0x1E6A #define mmSCL1_SCL_DEBUG2 0x1E69 @@ -4173,6 +4175,7 @@ #define mmSCL2_SCL_COEF_RAM_CONFLICT_STATUS 0x4155 #define mmSCL2_SCL_COEF_RAM_SELECT 0x4140 #define mmSCL2_SCL_COEF_RAM_TAP_DATA 0x4141 +#define mmSCL2_SCL_SCALER_ENABLE 0x4142 #define mmSCL2_SCL_CONTROL 0x4144 #define mmSCL2_SCL_DEBUG 0x416A #define mmSCL2_SCL_DEBUG2 0x4169 @@ -4202,6 +4205,7 @@ #define mmSCL3_SCL_COEF_RAM_CONFLICT_STATUS 0x4455 #define mmSCL3_SCL_COEF_RAM_SELECT 0x4440 #define mmSCL3_SCL_COEF_RAM_TAP_DATA 0x4441 +#define mmSCL3_SCL_SCALER_ENABLE 0x4442 #define mmSCL3_SCL_CONTROL 0x4444 #define mmSCL3_SCL_DEBUG 0x446A #define mmSCL3_SCL_DEBUG2 0x4469 @@ -4231,6 +4235,7 @@ #define mmSCL4_SCL_COEF_RAM_CONFLICT_STATUS 0x4755 #define mmSCL4_SCL_COEF_RAM_SELECT 0x4740 #define mmSCL4_SCL_COEF_RAM_TAP_DATA 0x4741 +#define mmSCL4_SCL_SCALER_ENABLE 0x4742 #define mmSCL4_SCL_CONTROL 0x4744 #define mmSCL4_SCL_DEBUG 0x476A #define mmSCL4_SCL_DEBUG2 0x4769 @@ -4260,6 +4265,7 @@ #define mmSCL5_SCL_COEF_RAM_CONFLICT_STATUS 0x4A55 #define mmSCL5_SCL_COEF_RAM_SELECT 0x4A40 #define mmSCL5_SCL_COEF_RAM_TAP_DATA 0x4A41 +#define mmSCL5_SCL_SCALER_ENABLE 0x4A42 #define mmSCL5_SCL_CONTROL 0x4A44 #define mmSCL5_SCL_DEBUG 0x4A6A #define mmSCL5_SCL_DEBUG2 0x4A69 @@ -4287,6 +4293,7 @@ #define mmSCL_COEF_RAM_CONFLICT_STATUS 0x1B55 #define mmSCL_COEF_RAM_SELECT 0x1B40 #define mmSCL_COEF_RAM_TAP_DATA 0x1B41 +#define mmSCL_SCALER_ENABLE 0x1B42 #define mmSCL_CONTROL 0x1B44 #define mmSCL_DEBUG 0x1B6A #define mmSCL_DEBUG2 0x1B69 diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h index 2d6a598a6c25..9317a7afa621 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h @@ -8650,6 +8650,8 @@ #define REGAMMA_LUT_INDEX__REGAMMA_LUT_INDEX__SHIFT 0x00000000 #define REGAMMA_LUT_WRITE_EN_MASK__REGAMMA_LUT_WRITE_EN_MASK_MASK 0x00000007L #define REGAMMA_LUT_WRITE_EN_MASK__REGAMMA_LUT_WRITE_EN_MASK__SHIFT 0x00000000 +#define SCL_SCALER_ENABLE__SCL_SCALE_EN_MASK 0x00000001L +#define SCL_SCALER_ENABLE__SCL_SCALE_EN__SHIFT 0x00000000 #define SCL_ALU_CONTROL__SCL_ALU_DISABLE_MASK 0x00000001L #define SCL_ALU_CONTROL__SCL_ALU_DISABLE__SHIFT 0x00000000 #define SCL_BYPASS_CONTROL__SCL_BYPASS_MODE_MASK 0x00000003L diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 1a1f2a6b2e52..a89075e25717 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -288,7 +288,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) * Considering above, we just leave user a verbal message instead * of halt driver loading. */ - if (if_version != smu->smc_driver_if_version) { + if (smu->smc_driver_if_version != SMU_IGNORE_IF_VERSION && + if_version != smu->smc_driver_if_version) { dev_info(adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, " "smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n", smu->smc_driver_if_version, if_version, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index cbe5b06438c1..285cf7979693 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -450,8 +450,7 @@ static void smu_v13_0_6_init_caps(struct smu_context *smu) ((pgm == 4) && (fw_ver >= 0x4557000))) smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET)); - if (((pgm == 0) && (fw_ver >= 0x00558200)) || - ((pgm == 4) && (fw_ver >= 0x04557100))) + if ((pgm == 0) && (fw_ver >= 0x00558200)) smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET)); } @@ -3933,7 +3932,7 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) smu->feature_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ? smu_v13_0_12_feature_mask_map : smu_v13_0_6_feature_mask_map; smu->table_map = smu_v13_0_6_table_map; - smu->smc_driver_if_version = SMU13_0_6_DRIVER_IF_VERSION; + smu->smc_driver_if_version = SMU_IGNORE_IF_VERSION; smu->smc_fw_caps |= SMU_FW_CAP_RAS_PRI; smu_v13_0_set_smu_mailbox_registers(smu); smu_v13_0_6_set_temp_funcs(smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index d588f74b98de..0ae91c8b6d72 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -40,6 +40,8 @@ #define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8 #define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9 +#define SMU_IGNORE_IF_VERSION 0xFFFFFFFF + #define smu_cmn_init_soft_gpu_metrics(ptr, frev, crev) \ do { \ typecheck(struct gpu_metrics_v##frev##_##crev *, (ptr)); \ diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index eeeeb99cfdf6..cb906765897e 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -361,7 +361,6 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = { * @name: Name of the GPU SVM. * @drm: Pointer to the DRM device structure. * @mm: Pointer to the mm_struct for the address space. - * @device_private_page_owner: Device private pages owner. * @mm_start: Start address of GPU SVM. * @mm_range: Range of the GPU SVM. * @notifier_size: Size of individual notifiers. @@ -383,7 +382,7 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = { */ int drm_gpusvm_init(struct drm_gpusvm *gpusvm, const char *name, struct drm_device *drm, - struct mm_struct *mm, void *device_private_page_owner, + struct mm_struct *mm, unsigned long mm_start, unsigned long mm_range, unsigned long notifier_size, const struct drm_gpusvm_ops *ops, @@ -395,15 +394,13 @@ int drm_gpusvm_init(struct drm_gpusvm *gpusvm, mmgrab(mm); } else { /* No full SVM mode, only core drm_gpusvm_pages API. */ - if (ops || num_chunks || mm_range || notifier_size || - device_private_page_owner) + if (ops || num_chunks || mm_range || notifier_size) return -EINVAL; } gpusvm->name = name; gpusvm->drm = drm; gpusvm->mm = mm; - gpusvm->device_private_page_owner = device_private_page_owner; gpusvm->mm_start = mm_start; gpusvm->mm_range = mm_range; gpusvm->notifier_size = notifier_size; @@ -684,6 +681,7 @@ static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn, * @notifier: Pointer to the GPU SVM notifier structure * @start: Start address * @end: End address + * @dev_private_owner: The device private page owner * * Check if pages between start and end have been faulted in on the CPU. Use to * prevent migration of pages without CPU backing store. @@ -692,14 +690,15 @@ static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn, */ static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm, struct drm_gpusvm_notifier *notifier, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, + void *dev_private_owner) { struct hmm_range hmm_range = { .default_flags = 0, .notifier = ¬ifier->notifier, .start = start, .end = end, - .dev_private_owner = gpusvm->device_private_page_owner, + .dev_private_owner = dev_private_owner, }; unsigned long timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); @@ -753,6 +752,7 @@ err_free: * @gpuva_start: Start address of GPUVA which mirrors CPU * @gpuva_end: End address of GPUVA which mirrors CPU * @check_pages_threshold: Check CPU pages for present threshold + * @dev_private_owner: The device private page owner * * This function determines the chunk size for the GPU SVM range based on the * fault address, GPU SVM chunk sizes, existing GPU SVM ranges, and the virtual @@ -767,7 +767,8 @@ drm_gpusvm_range_chunk_size(struct drm_gpusvm *gpusvm, unsigned long fault_addr, unsigned long gpuva_start, unsigned long gpuva_end, - unsigned long check_pages_threshold) + unsigned long check_pages_threshold, + void *dev_private_owner) { unsigned long start, end; int i = 0; @@ -814,7 +815,7 @@ retry: * process-many-malloc' mallocs at least 64k at a time. */ if (end - start <= check_pages_threshold && - !drm_gpusvm_check_pages(gpusvm, notifier, start, end)) { + !drm_gpusvm_check_pages(gpusvm, notifier, start, end, dev_private_owner)) { ++i; goto retry; } @@ -957,7 +958,8 @@ drm_gpusvm_range_find_or_insert(struct drm_gpusvm *gpusvm, chunk_size = drm_gpusvm_range_chunk_size(gpusvm, notifier, vas, fault_addr, gpuva_start, gpuva_end, - ctx->check_pages_threshold); + ctx->check_pages_threshold, + ctx->device_private_page_owner); if (chunk_size == LONG_MAX) { err = -EINVAL; goto err_notifier_remove; @@ -1268,7 +1270,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, .notifier = notifier, .start = pages_start, .end = pages_end, - .dev_private_owner = gpusvm->device_private_page_owner, + .dev_private_owner = ctx->device_private_page_owner, }; void *zdd; unsigned long timeout = diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index b96f0555ca14..f26562eafffc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -929,7 +929,7 @@ done: nvif_vmm_put(vmm, &old_mem->vma[1]); nvif_vmm_put(vmm, &old_mem->vma[0]); } - return 0; + return ret; } static int diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 0317f3d7452a..1884686985b8 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -62,6 +62,8 @@ struct v3d_queue_state { /* Currently active job for this queue */ struct v3d_job *active_job; spinlock_t queue_lock; + /* Protect dma fence for signalling job completion */ + spinlock_t fence_lock; }; /* Performance monitor object. The perform lifetime is controlled by userspace diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c index 8f8471adae34..c82500a1df73 100644 --- a/drivers/gpu/drm/v3d/v3d_fence.c +++ b/drivers/gpu/drm/v3d/v3d_fence.c @@ -15,7 +15,7 @@ struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q) fence->dev = &v3d->drm; fence->queue = q; fence->seqno = ++queue->emit_seqno; - dma_fence_init(&fence->base, &v3d_fence_ops, &queue->queue_lock, + dma_fence_init(&fence->base, &v3d_fence_ops, &queue->fence_lock, queue->fence_context, fence->seqno); return &fence->base; diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index c77d90aa9b82..bb110d35f749 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -273,6 +273,7 @@ v3d_gem_init(struct drm_device *dev) seqcount_init(&queue->stats.lock); spin_lock_init(&queue->queue_lock); + spin_lock_init(&queue->fence_lock); } spin_lock_init(&v3d->mm_lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 819704ac675d..d539f25b5fbe 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1497,6 +1497,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { struct vmw_bo *vmw_bo = NULL; + struct vmw_resource *res; struct vmw_surface *srf = NULL; VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdSurfaceDMA); int ret; @@ -1532,18 +1533,24 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, dirty = (cmd->body.transfer == SVGA3D_WRITE_HOST_VRAM) ? VMW_RES_DIRTY_SET : 0; - ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, - dirty, user_surface_converter, - &cmd->body.host.sid, NULL); + ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, dirty, + user_surface_converter, &cmd->body.host.sid, + NULL); if (unlikely(ret != 0)) { if (unlikely(ret != -ERESTARTSYS)) VMW_DEBUG_USER("could not find surface for DMA.\n"); return ret; } - srf = vmw_res_to_srf(sw_context->res_cache[vmw_res_surface].res); + res = sw_context->res_cache[vmw_res_surface].res; + if (!res) { + VMW_DEBUG_USER("Invalid DMA surface.\n"); + return -EINVAL; + } - vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->tbo, header); + srf = vmw_res_to_srf(res); + vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->tbo, + header); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index 7ee93e7191c7..35dc94c3db39 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -308,8 +308,10 @@ int vmw_validation_add_resource(struct vmw_validation_context *ctx, hash_add_rcu(ctx->sw_context->res_ht, &node->hash.head, node->hash.key); } node->res = vmw_resource_reference_unless_doomed(res); - if (!node->res) + if (!node->res) { + hash_del_rcu(&node->hash.head); return -ESRCH; + } node->first_usage = 1; if (!res->dev_priv->has_mob) { @@ -636,7 +638,7 @@ void vmw_validation_drop_ht(struct vmw_validation_context *ctx) hash_del_rcu(&val->hash.head); list_for_each_entry(val, &ctx->resource_ctx_list, head) - hash_del_rcu(&entry->hash.head); + hash_del_rcu(&val->hash.head); ctx->sw_context = NULL; } diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c index 49b37dfd4e58..69e2840c7ef0 100644 --- a/drivers/gpu/drm/xe/tests/xe_pci.c +++ b/drivers/gpu/drm/xe/tests/xe_pci.c @@ -211,15 +211,15 @@ static void xe_ip_kunit_desc(const struct xe_ip *param, char *desc) * param generator can be used for both */ static const struct xe_ip pre_gmdid_graphics_ips[] = { - graphics_ip_xelp, - graphics_ip_xelpp, - graphics_ip_xehpg, - graphics_ip_xehpc, + { 1200, "Xe_LP", &graphics_xelp }, + { 1210, "Xe_LP+", &graphics_xelp }, + { 1255, "Xe_HPG", &graphics_xehpg }, + { 1260, "Xe_HPC", &graphics_xehpc }, }; static const struct xe_ip pre_gmdid_media_ips[] = { - media_ip_xem, - media_ip_xehpm, + { 1200, "Xe_M", &media_xem }, + { 1255, "Xe_HPM", &media_xem }, }; KUNIT_ARRAY_PARAM(pre_gmdid_graphics_ip, pre_gmdid_graphics_ips, xe_ip_kunit_desc); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 8422f3cab113..4410e28dee54 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1737,6 +1737,24 @@ static bool should_migrate_to_smem(struct xe_bo *bo) bo->attr.atomic_access == DRM_XE_ATOMIC_CPU; } +static int xe_bo_wait_usage_kernel(struct xe_bo *bo, struct ttm_operation_ctx *ctx) +{ + long lerr; + + if (ctx->no_wait_gpu) + return dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL) ? + 0 : -EBUSY; + + lerr = dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + ctx->interruptible, MAX_SCHEDULE_TIMEOUT); + if (lerr < 0) + return lerr; + if (lerr == 0) + return -EBUSY; + + return 0; +} + /* Populate the bo if swapped out, or migrate if the access mode requires that. */ static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx, struct drm_exec *exec) @@ -1745,10 +1763,9 @@ static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx, int err = 0; if (ttm_manager_type(tbo->bdev, tbo->resource->mem_type)->use_tt) { - xe_assert(xe_bo_device(bo), - dma_resv_test_signaled(tbo->base.resv, DMA_RESV_USAGE_KERNEL) || - (tbo->ttm && ttm_tt_is_populated(tbo->ttm))); - err = ttm_bo_populate(&bo->ttm, ctx); + err = xe_bo_wait_usage_kernel(bo, ctx); + if (!err) + err = ttm_bo_populate(&bo->ttm, ctx); } else if (should_migrate_to_smem(bo)) { xe_assert(xe_bo_device(bo), bo->flags & XE_BO_FLAG_SYSTEM); err = xe_bo_migrate(bo, XE_PL_TT, ctx, exec); @@ -1922,7 +1939,6 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf) .no_wait_gpu = false, .gfp_retry_mayfail = retry_after_wait, }; - long lerr; err = drm_exec_lock_obj(&exec, &tbo->base); drm_exec_retry_on_contention(&exec); @@ -1942,13 +1958,9 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf) break; } - lerr = dma_resv_wait_timeout(tbo->base.resv, - DMA_RESV_USAGE_KERNEL, true, - MAX_SCHEDULE_TIMEOUT); - if (lerr < 0) { - err = lerr; + err = xe_bo_wait_usage_kernel(bo, &tctx); + if (err) break; - } if (!retry_after_wait) ret = __xe_bo_cpu_fault(vmf, xe, bo); diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c index 8a9b950e7a6d..139663423185 100644 --- a/drivers/gpu/drm/xe/xe_configfs.c +++ b/drivers/gpu/drm/xe/xe_configfs.c @@ -126,8 +126,20 @@ * not intended for normal execution and will taint the kernel with TAINT_TEST * when used. * - * Currently this is implemented only for post and mid context restore. - * Examples: + * The syntax allows to pass straight instructions to be executed by the engine + * in a batch buffer or set specific registers. + * + * #. Generic instruction:: + * + * <engine-class> cmd <instr> [[dword0] [dword1] [...]] + * + * #. Simple register setting:: + * + * <engine-class> reg <address> <value> + * + * Commands are saved per engine class: all instances of that class will execute + * those commands during context switch. The instruction, dword arguments, + * addresses and values are in hex format like in the examples below. * * #. Execute a LRI command to write 0xDEADBEEF to register 0x4f10 after the * normal context restore:: @@ -154,7 +166,8 @@ * When using multiple lines, make sure to use a command that is * implemented with a single write syscall, like HEREDOC. * - * These attributes can only be set before binding to the device. + * Currently this is implemented only for post and mid context restore and + * these attributes can only be set before binding to the device. * * Remove devices * ============== @@ -324,8 +337,8 @@ static const struct engine_info *lookup_engine_info(const char *pattern, u64 *ma continue; pattern += strlen(engine_info[i].cls); - if (!mask && !*pattern) - return &engine_info[i]; + if (!mask) + return *pattern ? NULL : &engine_info[i]; if (!strcmp(pattern, "*")) { *mask = engine_info[i].mask; diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index fdb7b7498920..2883b39c9b37 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -685,16 +685,16 @@ static int wait_for_lmem_ready(struct xe_device *xe) } ALLOW_ERROR_INJECTION(wait_for_lmem_ready, ERRNO); /* See xe_pci_probe() */ -static void sriov_update_device_info(struct xe_device *xe) +static void vf_update_device_info(struct xe_device *xe) { + xe_assert(xe, IS_SRIOV_VF(xe)); /* disable features that are not available/applicable to VFs */ - if (IS_SRIOV_VF(xe)) { - xe->info.probe_display = 0; - xe->info.has_heci_cscfi = 0; - xe->info.has_heci_gscfi = 0; - xe->info.skip_guc_pc = 1; - xe->info.skip_pcode = 1; - } + xe->info.probe_display = 0; + xe->info.has_heci_cscfi = 0; + xe->info.has_heci_gscfi = 0; + xe->info.has_late_bind = 0; + xe->info.skip_guc_pc = 1; + xe->info.skip_pcode = 1; } static int xe_device_vram_alloc(struct xe_device *xe) @@ -735,7 +735,8 @@ int xe_device_probe_early(struct xe_device *xe) xe_sriov_probe_early(xe); - sriov_update_device_info(xe); + if (IS_SRIOV_VF(xe)) + vf_update_device_info(xe); err = xe_pcode_probe_early(xe); if (err || xe_survivability_mode_is_requested(xe)) { diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c index 58bee3ffe881..fa4db5f23342 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine_group.c +++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c @@ -213,17 +213,13 @@ static int xe_hw_engine_group_suspend_faulting_lr_jobs(struct xe_hw_engine_group err = q->ops->suspend_wait(q); if (err) - goto err_suspend; + return err; } if (need_resume) xe_hw_engine_group_resume_faulting_lr_jobs(group); return 0; - -err_suspend: - up_write(&group->mode_sem); - return err; } /** diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw.c b/drivers/gpu/drm/xe/xe_late_bind_fw.c index 38f3feb2aecd..768442ca7da6 100644 --- a/drivers/gpu/drm/xe/xe_late_bind_fw.c +++ b/drivers/gpu/drm/xe/xe_late_bind_fw.c @@ -60,7 +60,7 @@ static int parse_cpd_header(struct xe_late_bind_fw *lb_fw, const struct gsc_manifest_header *manifest; const struct gsc_cpd_entry *entry; size_t min_size = sizeof(*header); - u32 offset; + u32 offset = 0; int i; /* manifest_entry is mandatory */ @@ -116,7 +116,7 @@ static int parse_lb_layout(struct xe_late_bind_fw *lb_fw, const struct csc_fpt_header *header = data; const struct csc_fpt_entry *entry; size_t min_size = sizeof(*header); - u32 offset; + u32 offset = 0; int i; /* fpt_entry is mandatory */ @@ -184,17 +184,13 @@ static const char *xe_late_bind_parse_status(uint32_t status) } } -static int xe_late_bind_fw_num_fans(struct xe_late_bind *late_bind) +static int xe_late_bind_fw_num_fans(struct xe_late_bind *late_bind, u32 *num_fans) { struct xe_device *xe = late_bind_to_xe(late_bind); struct xe_tile *root_tile = xe_device_get_root_tile(xe); - u32 uval; - if (!xe_pcode_read(root_tile, - PCODE_MBOX(FAN_SPEED_CONTROL, FSC_READ_NUM_FANS, 0), &uval, NULL)) - return uval; - else - return 0; + return xe_pcode_read(root_tile, + PCODE_MBOX(FAN_SPEED_CONTROL, FSC_READ_NUM_FANS, 0), num_fans, NULL); } void xe_late_bind_wait_for_worker_completion(struct xe_late_bind *late_bind) @@ -314,7 +310,11 @@ static int __xe_late_bind_fw_init(struct xe_late_bind *late_bind, u32 fw_id) lb_fw->flags &= ~INTEL_LB_FLAG_IS_PERSISTENT; if (lb_fw->type == INTEL_LB_TYPE_FAN_CONTROL) { - num_fans = xe_late_bind_fw_num_fans(late_bind); + ret = xe_late_bind_fw_num_fans(late_bind, &num_fans); + if (ret) { + drm_dbg(&xe->drm, "Failed to read number of fans: %d\n", ret); + return 0; /* Not a fatal error, continue without fan control */ + } drm_dbg(&xe->drm, "Number of Fans: %d\n", num_fans); if (!num_fans) return 0; diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index d6625c71115b..2c5a44377994 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -201,7 +201,7 @@ int xe_pm_resume(struct xe_device *xe) if (err) goto err; - xe_i2c_pm_resume(xe, xe->d3cold.allowed); + xe_i2c_pm_resume(xe, true); xe_irq_resume(xe); diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index e1b603aba61b..2e9ff33ed2fe 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -276,8 +276,7 @@ static int query_mem_regions(struct xe_device *xe, mem_regions->mem_regions[0].instance = 0; mem_regions->mem_regions[0].min_page_size = PAGE_SIZE; mem_regions->mem_regions[0].total_size = man->size << PAGE_SHIFT; - if (perfmon_capable()) - mem_regions->mem_regions[0].used = ttm_resource_manager_usage(man); + mem_regions->mem_regions[0].used = ttm_resource_manager_usage(man); mem_regions->num_mem_regions = 1; for (i = XE_PL_VRAM0; i <= XE_PL_VRAM1; ++i) { @@ -293,13 +292,11 @@ static int query_mem_regions(struct xe_device *xe, mem_regions->mem_regions[mem_regions->num_mem_regions].total_size = man->size; - if (perfmon_capable()) { - xe_ttm_vram_get_used(man, - &mem_regions->mem_regions - [mem_regions->num_mem_regions].used, - &mem_regions->mem_regions - [mem_regions->num_mem_regions].cpu_visible_used); - } + xe_ttm_vram_get_used(man, + &mem_regions->mem_regions + [mem_regions->num_mem_regions].used, + &mem_regions->mem_regions + [mem_regions->num_mem_regions].cpu_visible_used); mem_regions->mem_regions[mem_regions->num_mem_regions].cpu_visible_size = xe_ttm_vram_get_cpu_visible_size(man); diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 7f2f1f041f1d..7e2db71ff34e 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -67,11 +67,6 @@ void xe_svm_range_debug(struct xe_svm_range *range, const char *operation) range_debug(range, operation); } -static void *xe_svm_devm_owner(struct xe_device *xe) -{ - return xe; -} - static struct drm_gpusvm_range * xe_svm_range_alloc(struct drm_gpusvm *gpusvm) { @@ -744,15 +739,14 @@ int xe_svm_init(struct xe_vm *vm) xe_svm_garbage_collector_work_func); err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm, - current->mm, xe_svm_devm_owner(vm->xe), 0, - vm->size, + current->mm, 0, vm->size, xe_modparam.svm_notifier_size * SZ_1M, &gpusvm_ops, fault_chunk_sizes, ARRAY_SIZE(fault_chunk_sizes)); drm_gpusvm_driver_set_lock(&vm->svm.gpusvm, &vm->lock); } else { err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)", - &vm->xe->drm, NULL, NULL, 0, 0, 0, NULL, + &vm->xe->drm, NULL, 0, 0, 0, NULL, NULL, 0); } @@ -1017,6 +1011,7 @@ static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, .devmem_only = need_vram && devmem_possible, .timeslice_ms = need_vram && devmem_possible ? vm->xe->atomic_svm_timeslice_ms : 0, + .device_private_page_owner = xe_svm_devm_owner(vm->xe), }; struct xe_validation_ctx vctx; struct drm_exec exec; diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h index cef6ee7d6fe3..0955d2ac8d74 100644 --- a/drivers/gpu/drm/xe/xe_svm.h +++ b/drivers/gpu/drm/xe/xe_svm.h @@ -6,6 +6,20 @@ #ifndef _XE_SVM_H_ #define _XE_SVM_H_ +struct xe_device; + +/** + * xe_svm_devm_owner() - Return the owner of device private memory + * @xe: The xe device. + * + * Return: The owner of this device's device private memory to use in + * hmm_range_fault()- + */ +static inline void *xe_svm_devm_owner(struct xe_device *xe) +{ + return xe; +} + #if IS_ENABLED(CONFIG_DRM_XE_GPUSVM) #include <drm/drm_pagemap.h> diff --git a/drivers/gpu/drm/xe/xe_userptr.c b/drivers/gpu/drm/xe/xe_userptr.c index 91d09af71ced..f16e92cd8090 100644 --- a/drivers/gpu/drm/xe/xe_userptr.c +++ b/drivers/gpu/drm/xe/xe_userptr.c @@ -54,6 +54,7 @@ int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma) struct xe_device *xe = vm->xe; struct drm_gpusvm_ctx ctx = { .read_only = xe_vma_read_only(vma), + .device_private_page_owner = NULL, }; lockdep_assert_held(&vm->lock); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 0cacab20ff85..027e6ce648c5 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2881,6 +2881,7 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_op *op) ctx.read_only = xe_vma_read_only(vma); ctx.devmem_possible = devmem_possible; ctx.check_pages_threshold = devmem_possible ? SZ_64K : 0; + ctx.device_private_page_owner = xe_svm_devm_owner(vm->xe); /* TODO: Threading the migration */ xa_for_each(&op->prefetch_range.range, i, svm_range) { diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c index 74b66aec33d4..ee86df4cff4b 100644 --- a/drivers/i2c/algos/i2c-algo-pca.c +++ b/drivers/i2c/algos/i2c-algo-pca.c @@ -30,7 +30,7 @@ static int i2c_debug; #define pca_clock(adap) adap->i2c_clock #define pca_set_con(adap, val) pca_outw(adap, I2C_PCA_CON, val) #define pca_get_con(adap) pca_inw(adap, I2C_PCA_CON) -#define pca_wait(adap) adap->wait_for_completion(adap->data) +#define pca_wait(adap) adap->wait_for_completion_cb(adap->data) static void pca_reset(struct i2c_algo_pca_data *adap) { diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index dee40704825c..aefdbee1f03c 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -868,7 +868,7 @@ static int mtk_i2c_calculate_speed(struct mtk_i2c *i2c, unsigned int clk_src, return 0; } -static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk) +static void mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk) { unsigned int clk_src; unsigned int step_cnt; @@ -938,9 +938,6 @@ static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk) break; } - - - return 0; } static void i2c_dump_register(struct mtk_i2c *i2c) @@ -1460,11 +1457,7 @@ static int mtk_i2c_probe(struct platform_device *pdev) strscpy(i2c->adap.name, I2C_DRV_NAME, sizeof(i2c->adap.name)); - ret = mtk_i2c_set_speed(i2c, clk_get_rate(i2c->clocks[speed_clk].clk)); - if (ret) { - dev_err(&pdev->dev, "Failed to set the speed.\n"); - return -EINVAL; - } + mtk_i2c_set_speed(i2c, clk_get_rate(i2c->clocks[speed_clk].clk)); if (i2c->dev_comp->max_dma_support > 32) { ret = dma_set_mask(&pdev->dev, diff --git a/drivers/i2c/busses/i2c-pca-isa.c b/drivers/i2c/busses/i2c-pca-isa.c index 85e8cf58e8bf..0cbf2f509527 100644 --- a/drivers/i2c/busses/i2c-pca-isa.c +++ b/drivers/i2c/busses/i2c-pca-isa.c @@ -95,7 +95,7 @@ static struct i2c_algo_pca_data pca_isa_data = { /* .data intentionally left NULL, not needed with ISA */ .write_byte = pca_isa_writebyte, .read_byte = pca_isa_readbyte, - .wait_for_completion = pca_isa_waitforcompletion, + .wait_for_completion_cb = pca_isa_waitforcompletion, .reset_chip = pca_isa_resetchip, }; diff --git a/drivers/i2c/busses/i2c-pca-platform.c b/drivers/i2c/busses/i2c-pca-platform.c index 87da8241b927..c0f35ebbe37d 100644 --- a/drivers/i2c/busses/i2c-pca-platform.c +++ b/drivers/i2c/busses/i2c-pca-platform.c @@ -180,7 +180,7 @@ static int i2c_pca_pf_probe(struct platform_device *pdev) } i2c->algo_data.data = i2c; - i2c->algo_data.wait_for_completion = i2c_pca_pf_waitforcompletion; + i2c->algo_data.wait_for_completion_cb = i2c_pca_pf_waitforcompletion; if (i2c->gpio) i2c->algo_data.reset_chip = i2c_pca_pf_resetchip; else diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c index af991b28e4f8..4723e48cfe18 100644 --- a/drivers/i2c/busses/i2c-rtl9300.c +++ b/drivers/i2c/busses/i2c-rtl9300.c @@ -8,6 +8,7 @@ #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/regmap.h> +#include <linux/unaligned.h> enum rtl9300_bus_freq { RTL9300_I2C_STD_FREQ, @@ -20,103 +21,143 @@ struct rtl9300_i2c_chan { struct i2c_adapter adap; struct rtl9300_i2c *i2c; enum rtl9300_bus_freq bus_freq; - u8 sda_pin; + u8 sda_num; +}; + +enum rtl9300_i2c_reg_scope { + REG_SCOPE_GLOBAL, + REG_SCOPE_MASTER, +}; + +struct rtl9300_i2c_reg_field { + struct reg_field field; + enum rtl9300_i2c_reg_scope scope; +}; + +enum rtl9300_i2c_reg_fields { + F_DATA_WIDTH = 0, + F_DEV_ADDR, + F_I2C_FAIL, + F_I2C_TRIG, + F_MEM_ADDR, + F_MEM_ADDR_WIDTH, + F_RD_MODE, + F_RWOP, + F_SCL_FREQ, + F_SCL_SEL, + F_SDA_OUT_SEL, + F_SDA_SEL, + + /* keep last */ + F_NUM_FIELDS +}; + +struct rtl9300_i2c_drv_data { + struct rtl9300_i2c_reg_field field_desc[F_NUM_FIELDS]; + int (*select_scl)(struct rtl9300_i2c *i2c, u8 scl); + u32 data_reg; + u8 max_nchan; }; #define RTL9300_I2C_MUX_NCHAN 8 +#define RTL9310_I2C_MUX_NCHAN 12 struct rtl9300_i2c { struct regmap *regmap; struct device *dev; - struct rtl9300_i2c_chan chans[RTL9300_I2C_MUX_NCHAN]; + struct rtl9300_i2c_chan chans[RTL9310_I2C_MUX_NCHAN]; + struct regmap_field *fields[F_NUM_FIELDS]; u32 reg_base; - u8 sda_pin; + u32 data_reg; + u8 scl_num; + u8 sda_num; struct mutex lock; }; +DEFINE_GUARD(rtl9300_i2c, struct rtl9300_i2c *, mutex_lock(&_T->lock), mutex_unlock(&_T->lock)) + +enum rtl9300_i2c_xfer_type { + RTL9300_I2C_XFER_BYTE, + RTL9300_I2C_XFER_WORD, + RTL9300_I2C_XFER_BLOCK, +}; + +struct rtl9300_i2c_xfer { + enum rtl9300_i2c_xfer_type type; + u16 dev_addr; + u8 reg_addr; + u8 reg_addr_len; + u8 *data; + u8 data_len; + bool write; +}; + #define RTL9300_I2C_MST_CTRL1 0x0 -#define RTL9300_I2C_MST_CTRL1_MEM_ADDR_OFS 8 -#define RTL9300_I2C_MST_CTRL1_MEM_ADDR_MASK GENMASK(31, 8) -#define RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_OFS 4 -#define RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_MASK GENMASK(6, 4) -#define RTL9300_I2C_MST_CTRL1_GPIO_SCL_SEL BIT(3) -#define RTL9300_I2C_MST_CTRL1_RWOP BIT(2) -#define RTL9300_I2C_MST_CTRL1_I2C_FAIL BIT(1) -#define RTL9300_I2C_MST_CTRL1_I2C_TRIG BIT(0) #define RTL9300_I2C_MST_CTRL2 0x4 -#define RTL9300_I2C_MST_CTRL2_RD_MODE BIT(15) -#define RTL9300_I2C_MST_CTRL2_DEV_ADDR_OFS 8 -#define RTL9300_I2C_MST_CTRL2_DEV_ADDR_MASK GENMASK(14, 8) -#define RTL9300_I2C_MST_CTRL2_DATA_WIDTH_OFS 4 -#define RTL9300_I2C_MST_CTRL2_DATA_WIDTH_MASK GENMASK(7, 4) -#define RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_OFS 2 -#define RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_MASK GENMASK(3, 2) -#define RTL9300_I2C_MST_CTRL2_SCL_FREQ_OFS 0 -#define RTL9300_I2C_MST_CTRL2_SCL_FREQ_MASK GENMASK(1, 0) #define RTL9300_I2C_MST_DATA_WORD0 0x8 #define RTL9300_I2C_MST_DATA_WORD1 0xc #define RTL9300_I2C_MST_DATA_WORD2 0x10 #define RTL9300_I2C_MST_DATA_WORD3 0x14 - #define RTL9300_I2C_MST_GLB_CTRL 0x384 +#define RTL9310_I2C_MST_IF_CTRL 0x1004 +#define RTL9310_I2C_MST_IF_SEL 0x1008 +#define RTL9310_I2C_MST_CTRL 0x0 +#define RTL9310_I2C_MST_MEMADDR_CTRL 0x4 +#define RTL9310_I2C_MST_DATA_CTRL 0x8 + static int rtl9300_i2c_reg_addr_set(struct rtl9300_i2c *i2c, u32 reg, u16 len) { - u32 val, mask; int ret; - val = len << RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_OFS; - mask = RTL9300_I2C_MST_CTRL2_MEM_ADDR_WIDTH_MASK; - - ret = regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL2, mask, val); + ret = regmap_field_write(i2c->fields[F_MEM_ADDR_WIDTH], len); if (ret) return ret; - val = reg << RTL9300_I2C_MST_CTRL1_MEM_ADDR_OFS; - mask = RTL9300_I2C_MST_CTRL1_MEM_ADDR_MASK; - - return regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, mask, val); + return regmap_field_write(i2c->fields[F_MEM_ADDR], reg); } -static int rtl9300_i2c_config_io(struct rtl9300_i2c *i2c, u8 sda_pin) +static int rtl9300_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl) { - int ret; - u32 val, mask; - - ret = regmap_update_bits(i2c->regmap, RTL9300_I2C_MST_GLB_CTRL, BIT(sda_pin), BIT(sda_pin)); - if (ret) - return ret; - - val = (sda_pin << RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_OFS) | - RTL9300_I2C_MST_CTRL1_GPIO_SCL_SEL; - mask = RTL9300_I2C_MST_CTRL1_SDA_OUT_SEL_MASK | RTL9300_I2C_MST_CTRL1_GPIO_SCL_SEL; + return regmap_field_write(i2c->fields[F_SCL_SEL], 1); +} - return regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, mask, val); +static int rtl9310_i2c_select_scl(struct rtl9300_i2c *i2c, u8 scl) +{ + return regmap_field_update_bits(i2c->fields[F_SCL_SEL], BIT(scl), BIT(scl)); } -static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan, - u16 addr, u16 len) +static int rtl9300_i2c_config_chan(struct rtl9300_i2c *i2c, struct rtl9300_i2c_chan *chan) { - u32 val, mask; + struct rtl9300_i2c_drv_data *drv_data; + int ret; - if (len < 1 || len > 16) - return -EINVAL; + if (i2c->sda_num == chan->sda_num) + return 0; - val = chan->bus_freq << RTL9300_I2C_MST_CTRL2_SCL_FREQ_OFS; - mask = RTL9300_I2C_MST_CTRL2_SCL_FREQ_MASK; + ret = regmap_field_write(i2c->fields[F_SCL_FREQ], chan->bus_freq); + if (ret) + return ret; - val |= addr << RTL9300_I2C_MST_CTRL2_DEV_ADDR_OFS; - mask |= RTL9300_I2C_MST_CTRL2_DEV_ADDR_MASK; + drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev); + ret = drv_data->select_scl(i2c, i2c->scl_num); + if (ret) + return ret; - val |= ((len - 1) & 0xf) << RTL9300_I2C_MST_CTRL2_DATA_WIDTH_OFS; - mask |= RTL9300_I2C_MST_CTRL2_DATA_WIDTH_MASK; + ret = regmap_field_update_bits(i2c->fields[F_SDA_SEL], BIT(chan->sda_num), + BIT(chan->sda_num)); + if (ret) + return ret; - mask |= RTL9300_I2C_MST_CTRL2_RD_MODE; + ret = regmap_field_write(i2c->fields[F_SDA_OUT_SEL], chan->sda_num); + if (ret) + return ret; - return regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL2, mask, val); + i2c->sda_num = chan->sda_num; + return 0; } -static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len) +static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, u8 len) { u32 vals[4] = {}; int i, ret; @@ -124,8 +165,7 @@ static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len) if (len > 16) return -EIO; - ret = regmap_bulk_read(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, - vals, ARRAY_SIZE(vals)); + ret = regmap_bulk_read(i2c->regmap, i2c->data_reg, vals, ARRAY_SIZE(vals)); if (ret) return ret; @@ -137,7 +177,7 @@ static int rtl9300_i2c_read(struct rtl9300_i2c *i2c, u8 *buf, int len) return 0; } -static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, int len) +static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, u8 len) { u32 vals[4] = {}; int i; @@ -152,56 +192,94 @@ static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, int len) vals[reg] |= buf[i] << shift; } - return regmap_bulk_write(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, - vals, ARRAY_SIZE(vals)); + return regmap_bulk_write(i2c->regmap, i2c->data_reg, vals, ARRAY_SIZE(vals)); } static int rtl9300_i2c_writel(struct rtl9300_i2c *i2c, u32 data) { - return regmap_write(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, data); + return regmap_write(i2c->regmap, i2c->data_reg, data); } -static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write, - int size, union i2c_smbus_data *data, int len) +static int rtl9300_i2c_prepare_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_xfer *xfer) { - u32 val, mask; int ret; - val = read_write == I2C_SMBUS_WRITE ? RTL9300_I2C_MST_CTRL1_RWOP : 0; - mask = RTL9300_I2C_MST_CTRL1_RWOP; + if (xfer->data_len < 1 || xfer->data_len > 16) + return -EINVAL; + + ret = regmap_field_write(i2c->fields[F_DEV_ADDR], xfer->dev_addr); + if (ret) + return ret; + + ret = rtl9300_i2c_reg_addr_set(i2c, xfer->reg_addr, xfer->reg_addr_len); + if (ret) + return ret; + + ret = regmap_field_write(i2c->fields[F_RWOP], xfer->write); + if (ret) + return ret; + + ret = regmap_field_write(i2c->fields[F_DATA_WIDTH], (xfer->data_len - 1) & 0xf); + if (ret) + return ret; - val |= RTL9300_I2C_MST_CTRL1_I2C_TRIG; - mask |= RTL9300_I2C_MST_CTRL1_I2C_TRIG; + if (xfer->write) { + switch (xfer->type) { + case RTL9300_I2C_XFER_BYTE: + ret = rtl9300_i2c_writel(i2c, *xfer->data); + break; + case RTL9300_I2C_XFER_WORD: + ret = rtl9300_i2c_writel(i2c, get_unaligned((const u16 *)xfer->data)); + break; + default: + ret = rtl9300_i2c_write(i2c, xfer->data, xfer->data_len); + break; + } + } - ret = regmap_update_bits(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, mask, val); + return ret; +} + +static int rtl9300_i2c_do_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_xfer *xfer) +{ + u32 val; + int ret; + + ret = regmap_field_write(i2c->fields[F_I2C_TRIG], 1); if (ret) return ret; - ret = regmap_read_poll_timeout(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1, - val, !(val & RTL9300_I2C_MST_CTRL1_I2C_TRIG), 100, 100000); + ret = regmap_field_read_poll_timeout(i2c->fields[F_I2C_TRIG], val, !val, 100, 100000); if (ret) return ret; - if (val & RTL9300_I2C_MST_CTRL1_I2C_FAIL) + ret = regmap_field_read(i2c->fields[F_I2C_FAIL], &val); + if (ret) + return ret; + if (val) return -EIO; - if (read_write == I2C_SMBUS_READ) { - if (size == I2C_SMBUS_BYTE || size == I2C_SMBUS_BYTE_DATA) { - ret = regmap_read(i2c->regmap, - i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, &val); + if (!xfer->write) { + switch (xfer->type) { + case RTL9300_I2C_XFER_BYTE: + ret = regmap_read(i2c->regmap, i2c->data_reg, &val); if (ret) return ret; - data->byte = val & 0xff; - } else if (size == I2C_SMBUS_WORD_DATA) { - ret = regmap_read(i2c->regmap, - i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0, &val); + + *xfer->data = val & 0xff; + break; + case RTL9300_I2C_XFER_WORD: + ret = regmap_read(i2c->regmap, i2c->data_reg, &val); if (ret) return ret; - data->word = val & 0xffff; - } else { - ret = rtl9300_i2c_read(i2c, &data->block[0], len); + + put_unaligned(val & 0xffff, (u16*)xfer->data); + break; + default: + ret = rtl9300_i2c_read(i2c, xfer->data, xfer->data_len); if (ret) return ret; + break; } } @@ -214,100 +292,68 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s { struct rtl9300_i2c_chan *chan = i2c_get_adapdata(adap); struct rtl9300_i2c *i2c = chan->i2c; - int len = 0, ret; + struct rtl9300_i2c_xfer xfer = {0}; + int ret; - mutex_lock(&i2c->lock); - if (chan->sda_pin != i2c->sda_pin) { - ret = rtl9300_i2c_config_io(i2c, chan->sda_pin); - if (ret) - goto out_unlock; - i2c->sda_pin = chan->sda_pin; - } + if (addr > 0x7f) + return -EINVAL; + + guard(rtl9300_i2c)(i2c); + + ret = rtl9300_i2c_config_chan(i2c, chan); + if (ret) + return ret; + + xfer.dev_addr = addr & 0x7f; + xfer.write = (read_write == I2C_SMBUS_WRITE); + xfer.reg_addr = command; + xfer.reg_addr_len = 1; switch (size) { case I2C_SMBUS_BYTE: - if (read_write == I2C_SMBUS_WRITE) { - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0); - if (ret) - goto out_unlock; - ret = rtl9300_i2c_reg_addr_set(i2c, command, 1); - if (ret) - goto out_unlock; - } else { - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 1); - if (ret) - goto out_unlock; - ret = rtl9300_i2c_reg_addr_set(i2c, 0, 0); - if (ret) - goto out_unlock; - } + xfer.data = (read_write == I2C_SMBUS_READ) ? &data->byte : &command; + xfer.data_len = 1; + xfer.reg_addr = 0; + xfer.reg_addr_len = 0; + xfer.type = RTL9300_I2C_XFER_BYTE; break; - case I2C_SMBUS_BYTE_DATA: - ret = rtl9300_i2c_reg_addr_set(i2c, command, 1); - if (ret) - goto out_unlock; - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 1); - if (ret) - goto out_unlock; - if (read_write == I2C_SMBUS_WRITE) { - ret = rtl9300_i2c_writel(i2c, data->byte); - if (ret) - goto out_unlock; - } + xfer.data = &data->byte; + xfer.data_len = 1; + xfer.type = RTL9300_I2C_XFER_BYTE; break; - case I2C_SMBUS_WORD_DATA: - ret = rtl9300_i2c_reg_addr_set(i2c, command, 1); - if (ret) - goto out_unlock; - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 2); - if (ret) - goto out_unlock; - if (read_write == I2C_SMBUS_WRITE) { - ret = rtl9300_i2c_writel(i2c, data->word); - if (ret) - goto out_unlock; - } + xfer.data = (u8 *)&data->word; + xfer.data_len = 2; + xfer.type = RTL9300_I2C_XFER_WORD; break; - case I2C_SMBUS_BLOCK_DATA: - ret = rtl9300_i2c_reg_addr_set(i2c, command, 1); - if (ret) - goto out_unlock; - if (data->block[0] < 1 || data->block[0] > I2C_SMBUS_BLOCK_MAX) { - ret = -EINVAL; - goto out_unlock; - } - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, data->block[0] + 1); - if (ret) - goto out_unlock; - if (read_write == I2C_SMBUS_WRITE) { - ret = rtl9300_i2c_write(i2c, &data->block[0], data->block[0] + 1); - if (ret) - goto out_unlock; - } - len = data->block[0] + 1; + xfer.data = &data->block[0]; + xfer.data_len = data->block[0] + 1; + xfer.type = RTL9300_I2C_XFER_BLOCK; + break; + case I2C_SMBUS_I2C_BLOCK_DATA: + xfer.data = &data->block[1]; + xfer.data_len = data->block[0]; + xfer.type = RTL9300_I2C_XFER_BLOCK; break; - default: dev_err(&adap->dev, "Unsupported transaction %d\n", size); - ret = -EOPNOTSUPP; - goto out_unlock; + return -EOPNOTSUPP; } - ret = rtl9300_i2c_execute_xfer(i2c, read_write, size, data, len); - -out_unlock: - mutex_unlock(&i2c->lock); + ret = rtl9300_i2c_prepare_xfer(i2c, &xfer); + if (ret) + return ret; - return ret; + return rtl9300_i2c_do_xfer(i2c, &xfer); } static u32 rtl9300_i2c_func(struct i2c_adapter *a) { return I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_BYTE_DATA | - I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BLOCK_DATA; + I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BLOCK_DATA | + I2C_FUNC_SMBUS_I2C_BLOCK; } static const struct i2c_algorithm rtl9300_i2c_algo = { @@ -325,9 +371,11 @@ static int rtl9300_i2c_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct rtl9300_i2c *i2c; - u32 clock_freq, sda_pin; - int ret, i = 0; struct fwnode_handle *child; + struct rtl9300_i2c_drv_data *drv_data; + struct reg_field fields[F_NUM_FIELDS]; + u32 clock_freq, scl_num, sda_num; + int ret, i = 0; i2c = devm_kzalloc(dev, sizeof(*i2c), GFP_KERNEL); if (!i2c) @@ -344,16 +392,34 @@ static int rtl9300_i2c_probe(struct platform_device *pdev) if (ret) return ret; + ret = device_property_read_u32(dev, "realtek,scl", &scl_num); + if (ret || scl_num != 1) + scl_num = 0; + i2c->scl_num = (u8)scl_num; + platform_set_drvdata(pdev, i2c); - if (device_get_child_node_count(dev) > RTL9300_I2C_MUX_NCHAN) + drv_data = (struct rtl9300_i2c_drv_data *)device_get_match_data(i2c->dev); + if (device_get_child_node_count(dev) > drv_data->max_nchan) return dev_err_probe(dev, -EINVAL, "Too many channels\n"); + i2c->data_reg = i2c->reg_base + drv_data->data_reg; + for (i = 0; i < F_NUM_FIELDS; i++) { + fields[i] = drv_data->field_desc[i].field; + if (drv_data->field_desc[i].scope == REG_SCOPE_MASTER) + fields[i].reg += i2c->reg_base; + } + ret = devm_regmap_field_bulk_alloc(dev, i2c->regmap, i2c->fields, + fields, F_NUM_FIELDS); + if (ret) + return ret; + + i = 0; device_for_each_child_node(dev, child) { struct rtl9300_i2c_chan *chan = &i2c->chans[i]; struct i2c_adapter *adap = &chan->adap; - ret = fwnode_property_read_u32(child, "reg", &sda_pin); + ret = fwnode_property_read_u32(child, "reg", &sda_num); if (ret) return ret; @@ -365,17 +431,16 @@ static int rtl9300_i2c_probe(struct platform_device *pdev) case I2C_MAX_STANDARD_MODE_FREQ: chan->bus_freq = RTL9300_I2C_STD_FREQ; break; - case I2C_MAX_FAST_MODE_FREQ: chan->bus_freq = RTL9300_I2C_FAST_FREQ; break; default: dev_warn(i2c->dev, "SDA%d clock-frequency %d not supported using default\n", - sda_pin, clock_freq); + sda_num, clock_freq); break; } - chan->sda_pin = sda_pin; + chan->sda_num = sda_num; chan->i2c = i2c; adap = &i2c->chans[i].adap; adap->owner = THIS_MODULE; @@ -385,23 +450,77 @@ static int rtl9300_i2c_probe(struct platform_device *pdev) adap->dev.parent = dev; i2c_set_adapdata(adap, chan); adap->dev.of_node = to_of_node(child); - snprintf(adap->name, sizeof(adap->name), "%s SDA%d\n", dev_name(dev), sda_pin); + snprintf(adap->name, sizeof(adap->name), "%s SDA%d\n", dev_name(dev), sda_num); i++; ret = devm_i2c_add_adapter(dev, adap); if (ret) return ret; } - i2c->sda_pin = 0xff; + i2c->sda_num = 0xff; + + /* only use standard read format */ + ret = regmap_field_write(i2c->fields[F_RD_MODE], 0); + if (ret) + return ret; return 0; } +#define GLB_REG_FIELD(reg, msb, lsb) \ + { .field = REG_FIELD(reg, msb, lsb), .scope = REG_SCOPE_GLOBAL } +#define MST_REG_FIELD(reg, msb, lsb) \ + { .field = REG_FIELD(reg, msb, lsb), .scope = REG_SCOPE_MASTER } + +static const struct rtl9300_i2c_drv_data rtl9300_i2c_drv_data = { + .field_desc = { + [F_MEM_ADDR] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 8, 31), + [F_SDA_OUT_SEL] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 4, 6), + [F_SCL_SEL] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 3, 3), + [F_RWOP] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 2, 2), + [F_I2C_FAIL] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 1, 1), + [F_I2C_TRIG] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL1, 0, 0), + [F_RD_MODE] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 15, 15), + [F_DEV_ADDR] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 8, 14), + [F_DATA_WIDTH] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 4, 7), + [F_MEM_ADDR_WIDTH] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 2, 3), + [F_SCL_FREQ] = MST_REG_FIELD(RTL9300_I2C_MST_CTRL2, 0, 1), + [F_SDA_SEL] = GLB_REG_FIELD(RTL9300_I2C_MST_GLB_CTRL, 0, 7), + }, + .select_scl = rtl9300_i2c_select_scl, + .data_reg = RTL9300_I2C_MST_DATA_WORD0, + .max_nchan = RTL9300_I2C_MUX_NCHAN, +}; + +static const struct rtl9300_i2c_drv_data rtl9310_i2c_drv_data = { + .field_desc = { + [F_SCL_SEL] = GLB_REG_FIELD(RTL9310_I2C_MST_IF_SEL, 12, 13), + [F_SDA_SEL] = GLB_REG_FIELD(RTL9310_I2C_MST_IF_SEL, 0, 11), + [F_SCL_FREQ] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 30, 31), + [F_DEV_ADDR] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 11, 17), + [F_SDA_OUT_SEL] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 18, 21), + [F_MEM_ADDR_WIDTH] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 9, 10), + [F_DATA_WIDTH] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 5, 8), + [F_RD_MODE] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 4, 4), + [F_RWOP] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 2, 2), + [F_I2C_FAIL] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 1, 1), + [F_I2C_TRIG] = MST_REG_FIELD(RTL9310_I2C_MST_CTRL, 0, 0), + [F_MEM_ADDR] = MST_REG_FIELD(RTL9310_I2C_MST_MEMADDR_CTRL, 0, 23), + }, + .select_scl = rtl9310_i2c_select_scl, + .data_reg = RTL9310_I2C_MST_DATA_CTRL, + .max_nchan = RTL9310_I2C_MUX_NCHAN, +}; + static const struct of_device_id i2c_rtl9300_dt_ids[] = { - { .compatible = "realtek,rtl9301-i2c" }, - { .compatible = "realtek,rtl9302b-i2c" }, - { .compatible = "realtek,rtl9302c-i2c" }, - { .compatible = "realtek,rtl9303-i2c" }, + { .compatible = "realtek,rtl9301-i2c", .data = (void *) &rtl9300_i2c_drv_data }, + { .compatible = "realtek,rtl9302b-i2c", .data = (void *) &rtl9300_i2c_drv_data }, + { .compatible = "realtek,rtl9302c-i2c", .data = (void *) &rtl9300_i2c_drv_data }, + { .compatible = "realtek,rtl9303-i2c", .data = (void *) &rtl9300_i2c_drv_data }, + { .compatible = "realtek,rtl9310-i2c", .data = (void *) &rtl9310_i2c_drv_data }, + { .compatible = "realtek,rtl9311-i2c", .data = (void *) &rtl9310_i2c_drv_data }, + { .compatible = "realtek,rtl9312-i2c", .data = (void *) &rtl9310_i2c_drv_data }, + { .compatible = "realtek,rtl9313-i2c", .data = (void *) &rtl9310_i2c_drv_data }, {} }; MODULE_DEVICE_TABLE(of, i2c_rtl9300_dt_ids); diff --git a/drivers/misc/lkdtm/perms.c b/drivers/misc/lkdtm/perms.c index 6c24426104ba..e1f5e9abb301 100644 --- a/drivers/misc/lkdtm/perms.c +++ b/drivers/misc/lkdtm/perms.c @@ -9,6 +9,7 @@ #include <linux/vmalloc.h> #include <linux/mman.h> #include <linux/uaccess.h> +#include <linux/objtool.h> #include <asm/cacheflush.h> #include <asm/sections.h> @@ -86,6 +87,10 @@ static noinline __nocfi void execute_location(void *dst, bool write) func(); pr_err("FAIL: func returned\n"); } +/* + * Explicitly doing the wrong thing for testing. + */ +ANNOTATE_NOCFI_SYM(execute_location); static void execute_user_location(void *dst) { diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 63ceed89b62e..1a163596ddf5 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -197,13 +197,22 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, static int amd_ntb_get_link_status(struct amd_ntb_dev *ndev) { - struct pci_dev *pdev = NULL; + struct pci_dev *pdev = ndev->ntb.pdev; struct pci_dev *pci_swds = NULL; struct pci_dev *pci_swus = NULL; u32 stat; int rc; if (ndev->ntb.topo == NTB_TOPO_SEC) { + if (ndev->dev_data->is_endpoint) { + rc = pcie_capability_read_dword(pdev, PCI_EXP_LNKCTL, &stat); + if (rc) + return rc; + + ndev->lnk_sta = stat; + return 0; + } + /* Locate the pointer to Downstream Switch for this device */ pci_swds = pci_upstream_bridge(ndev->ntb.pdev); if (pci_swds) { @@ -1311,6 +1320,11 @@ static const struct ntb_dev_data dev_data[] = { .mw_count = 2, .mw_idx = 2, }, + { /* for device 0x17d7 */ + .mw_count = 2, + .mw_idx = 2, + .is_endpoint = true, + }, }; static const struct pci_device_id amd_ntb_pci_tbl[] = { @@ -1319,6 +1333,8 @@ static const struct pci_device_id amd_ntb_pci_tbl[] = { { PCI_VDEVICE(AMD, 0x14c0), (kernel_ulong_t)&dev_data[1] }, { PCI_VDEVICE(AMD, 0x14c3), (kernel_ulong_t)&dev_data[1] }, { PCI_VDEVICE(AMD, 0x155a), (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x17d4), (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x17d7), (kernel_ulong_t)&dev_data[2] }, { PCI_VDEVICE(HYGON, 0x145b), (kernel_ulong_t)&dev_data[0] }, { 0, } }; diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.h b/drivers/ntb/hw/amd/ntb_hw_amd.h index 5f337b1572a0..e8c3165fa38b 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.h +++ b/drivers/ntb/hw/amd/ntb_hw_amd.h @@ -168,6 +168,7 @@ enum { struct ntb_dev_data { const unsigned char mw_count; const unsigned int mw_idx; + const bool is_endpoint; }; struct amd_ntb_dev; diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c index 00f0e78f685b..d3ecf25a5162 100644 --- a/drivers/ntb/hw/epf/ntb_hw_epf.c +++ b/drivers/ntb/hw/epf/ntb_hw_epf.c @@ -49,6 +49,7 @@ #define NTB_EPF_COMMAND_TIMEOUT 1000 /* 1 Sec */ enum pci_barno { + NO_BAR = -1, BAR_0, BAR_1, BAR_2, @@ -57,16 +58,26 @@ enum pci_barno { BAR_5, }; +enum epf_ntb_bar { + BAR_CONFIG, + BAR_PEER_SPAD, + BAR_DB, + BAR_MW1, + BAR_MW2, + BAR_MW3, + BAR_MW4, + NTB_BAR_NUM, +}; + +#define NTB_EPF_MAX_MW_COUNT (NTB_BAR_NUM - BAR_MW1) + struct ntb_epf_dev { struct ntb_dev ntb; struct device *dev; /* Mutex to protect providing commands to NTB EPF */ struct mutex cmd_lock; - enum pci_barno ctrl_reg_bar; - enum pci_barno peer_spad_reg_bar; - enum pci_barno db_reg_bar; - enum pci_barno mw_bar; + const enum pci_barno *barno_map; unsigned int mw_count; unsigned int spad_count; @@ -85,17 +96,6 @@ struct ntb_epf_dev { #define ntb_ndev(__ntb) container_of(__ntb, struct ntb_epf_dev, ntb) -struct ntb_epf_data { - /* BAR that contains both control region and self spad region */ - enum pci_barno ctrl_reg_bar; - /* BAR that contains peer spad region */ - enum pci_barno peer_spad_reg_bar; - /* BAR that contains Doorbell region and Memory window '1' */ - enum pci_barno db_reg_bar; - /* BAR that contains memory windows*/ - enum pci_barno mw_bar; -}; - static int ntb_epf_send_command(struct ntb_epf_dev *ndev, u32 command, u32 argument) { @@ -144,7 +144,7 @@ static int ntb_epf_mw_to_bar(struct ntb_epf_dev *ndev, int idx) return -EINVAL; } - return idx + 2; + return ndev->barno_map[BAR_MW1 + idx]; } static int ntb_epf_mw_count(struct ntb_dev *ntb, int pidx) @@ -413,7 +413,9 @@ static int ntb_epf_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, return -EINVAL; } - bar = idx + ndev->mw_bar; + bar = ntb_epf_mw_to_bar(ndev, idx); + if (bar < 0) + return bar; mw_size = pci_resource_len(ntb->pdev, bar); @@ -455,7 +457,9 @@ static int ntb_epf_peer_mw_get_addr(struct ntb_dev *ntb, int idx, if (idx == 0) offset = readl(ndev->ctrl_reg + NTB_EPF_MW1_OFFSET); - bar = idx + ndev->mw_bar; + bar = ntb_epf_mw_to_bar(ndev, idx); + if (bar < 0) + return bar; if (base) *base = pci_resource_start(ndev->ntb.pdev, bar) + offset; @@ -560,6 +564,11 @@ static int ntb_epf_init_dev(struct ntb_epf_dev *ndev) ndev->mw_count = readl(ndev->ctrl_reg + NTB_EPF_MW_COUNT); ndev->spad_count = readl(ndev->ctrl_reg + NTB_EPF_SPAD_COUNT); + if (ndev->mw_count > NTB_EPF_MAX_MW_COUNT) { + dev_err(dev, "Unsupported MW count: %u\n", ndev->mw_count); + return -EINVAL; + } + return 0; } @@ -596,14 +605,15 @@ static int ntb_epf_init_pci(struct ntb_epf_dev *ndev, dev_warn(&pdev->dev, "Cannot DMA highmem\n"); } - ndev->ctrl_reg = pci_iomap(pdev, ndev->ctrl_reg_bar, 0); + ndev->ctrl_reg = pci_iomap(pdev, ndev->barno_map[BAR_CONFIG], 0); if (!ndev->ctrl_reg) { ret = -EIO; goto err_pci_regions; } - if (ndev->peer_spad_reg_bar) { - ndev->peer_spad_reg = pci_iomap(pdev, ndev->peer_spad_reg_bar, 0); + if (ndev->barno_map[BAR_PEER_SPAD] != ndev->barno_map[BAR_CONFIG]) { + ndev->peer_spad_reg = pci_iomap(pdev, + ndev->barno_map[BAR_PEER_SPAD], 0); if (!ndev->peer_spad_reg) { ret = -EIO; goto err_pci_regions; @@ -614,7 +624,7 @@ static int ntb_epf_init_pci(struct ntb_epf_dev *ndev, ndev->peer_spad_reg = ndev->ctrl_reg + spad_off + spad_sz; } - ndev->db_reg = pci_iomap(pdev, ndev->db_reg_bar, 0); + ndev->db_reg = pci_iomap(pdev, ndev->barno_map[BAR_DB], 0); if (!ndev->db_reg) { ret = -EIO; goto err_pci_regions; @@ -659,12 +669,7 @@ static void ntb_epf_cleanup_isr(struct ntb_epf_dev *ndev) static int ntb_epf_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - enum pci_barno peer_spad_reg_bar = BAR_1; - enum pci_barno ctrl_reg_bar = BAR_0; - enum pci_barno db_reg_bar = BAR_2; - enum pci_barno mw_bar = BAR_2; struct device *dev = &pdev->dev; - struct ntb_epf_data *data; struct ntb_epf_dev *ndev; int ret; @@ -675,18 +680,10 @@ static int ntb_epf_pci_probe(struct pci_dev *pdev, if (!ndev) return -ENOMEM; - data = (struct ntb_epf_data *)id->driver_data; - if (data) { - peer_spad_reg_bar = data->peer_spad_reg_bar; - ctrl_reg_bar = data->ctrl_reg_bar; - db_reg_bar = data->db_reg_bar; - mw_bar = data->mw_bar; - } + ndev->barno_map = (const enum pci_barno *)id->driver_data; + if (!ndev->barno_map) + return -EINVAL; - ndev->peer_spad_reg_bar = peer_spad_reg_bar; - ndev->ctrl_reg_bar = ctrl_reg_bar; - ndev->db_reg_bar = db_reg_bar; - ndev->mw_bar = mw_bar; ndev->dev = dev; ntb_epf_init_struct(ndev, pdev); @@ -730,30 +727,51 @@ static void ntb_epf_pci_remove(struct pci_dev *pdev) ntb_epf_deinit_pci(ndev); } -static const struct ntb_epf_data j721e_data = { - .ctrl_reg_bar = BAR_0, - .peer_spad_reg_bar = BAR_1, - .db_reg_bar = BAR_2, - .mw_bar = BAR_2, +static const enum pci_barno j721e_map[NTB_BAR_NUM] = { + [BAR_CONFIG] = BAR_0, + [BAR_PEER_SPAD] = BAR_1, + [BAR_DB] = BAR_2, + [BAR_MW1] = BAR_2, + [BAR_MW2] = BAR_3, + [BAR_MW3] = BAR_4, + [BAR_MW4] = BAR_5 }; -static const struct ntb_epf_data mx8_data = { - .ctrl_reg_bar = BAR_0, - .peer_spad_reg_bar = BAR_0, - .db_reg_bar = BAR_2, - .mw_bar = BAR_4, +static const enum pci_barno mx8_map[NTB_BAR_NUM] = { + [BAR_CONFIG] = BAR_0, + [BAR_PEER_SPAD] = BAR_0, + [BAR_DB] = BAR_2, + [BAR_MW1] = BAR_4, + [BAR_MW2] = BAR_5, + [BAR_MW3] = NO_BAR, + [BAR_MW4] = NO_BAR +}; + +static const enum pci_barno rcar_barno[NTB_BAR_NUM] = { + [BAR_CONFIG] = BAR_0, + [BAR_PEER_SPAD] = BAR_0, + [BAR_DB] = BAR_4, + [BAR_MW1] = BAR_2, + [BAR_MW2] = NO_BAR, + [BAR_MW3] = NO_BAR, + [BAR_MW4] = NO_BAR, }; static const struct pci_device_id ntb_epf_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_J721E), .class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00, - .driver_data = (kernel_ulong_t)&j721e_data, + .driver_data = (kernel_ulong_t)j721e_map, }, { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, 0x0809), .class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00, - .driver_data = (kernel_ulong_t)&mx8_data, + .driver_data = (kernel_ulong_t)mx8_map, + }, + { + PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0030), + .class = PCI_CLASS_MEMORY_RAM << 8, .class_mask = 0xffff00, + .driver_data = (kernel_ulong_t)rcar_barno, }, { }, }; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 4f775c3e218f..eb875e3db2e3 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -59,6 +59,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/uaccess.h> +#include <linux/mutex.h> #include "linux/ntb.h" #include "linux/ntb_transport.h" @@ -241,6 +242,9 @@ struct ntb_transport_ctx { struct work_struct link_cleanup; struct dentry *debugfs_node_dir; + + /* Make sure workq of link event be executed serially */ + struct mutex link_event_lock; }; enum { @@ -1024,6 +1028,7 @@ static void ntb_transport_link_cleanup_work(struct work_struct *work) struct ntb_transport_ctx *nt = container_of(work, struct ntb_transport_ctx, link_cleanup); + guard(mutex)(&nt->link_event_lock); ntb_transport_link_cleanup(nt); } @@ -1047,6 +1052,8 @@ static void ntb_transport_link_work(struct work_struct *work) u32 val; int rc = 0, i, spad; + guard(mutex)(&nt->link_event_lock); + /* send the local info, in the opposite order of the way we read it */ if (nt->use_msi) { diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 788ccb6ab287..65c3c23255b7 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -163,7 +163,7 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph * @out_irq: structure of_phandle_args updated by this function * * This function is a low-level interrupt tree walking function. It - * can be used to do a partial walk with synthetized reg and interrupts + * can be used to do a partial walk with synthesized reg and interrupts * properties, for example when resolving PCI interrupts when no device * node exist for the parent. It takes an interrupt specifier structure as * input, walks the tree looking for any interrupt-map properties, translates diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 1af6f52d0708..255e8362f600 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -135,7 +135,7 @@ static BLOCKING_NOTIFIER_HEAD(overlay_notify_chain); * @nb: Notifier block to register * * Register for notification on overlay operations on device tree nodes. The - * reported actions definied by @of_reconfig_change. The notifier callback + * reported actions defined by @of_reconfig_change. The notifier callback * furthermore receives a pointer to the affected device tree node. * * Note that a notifier callback is not supposed to store pointers to a device diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index e3503ec20f6c..388e9ec2cccf 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -4300,6 +4300,7 @@ static int of_unittest_pci_node_verify(struct pci_dev *pdev, bool add) unittest(!np, "Child device tree node is not removed\n"); child_dev = device_find_any_child(&pdev->dev); unittest(!child_dev, "Child device is not removed\n"); + put_device(child_dev); } failed: diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 4a8dc8d0a4b7..2933c41c77c8 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -406,6 +406,16 @@ config RTC_DRV_MAX77686 This driver can also be built as a module. If so, the module will be called rtc-max77686. +config RTC_DRV_SPACEMIT_P1 + tristate "SpacemiT P1 RTC" + depends on ARCH_SPACEMIT || COMPILE_TEST + select MFD_SPACEMIT_P1 + default ARCH_SPACEMIT + help + Enable support for the RTC function in the SpacemiT P1 PMIC. + This driver can also be built as a module, which will be called + "spacemit-p1-rtc". + config RTC_DRV_NCT3018Y tristate "Nuvoton NCT3018Y" depends on OF @@ -2044,20 +2054,6 @@ config RTC_DRV_RENESAS_RTCA3 This driver can also be built as a module, if so, the module will be called "rtc-rtca3". -comment "HID Sensor RTC drivers" - -config RTC_DRV_HID_SENSOR_TIME - tristate "HID Sensor Time" - depends on USB_HID - depends on HID_SENSOR_HUB && IIO - select HID_SENSOR_IIO_COMMON - help - Say yes here to build support for the HID Sensors of type Time. - This drivers makes such sensors available as RTCs. - - If this driver is compiled as a module, it will be named - rtc-hid-sensor-time. - config RTC_DRV_GOLDFISH tristate "Goldfish Real Time Clock" depends on HAS_IOMEM @@ -2132,4 +2128,18 @@ config RTC_DRV_S32G This RTC module can be used as a wakeup source. Please note that it is not battery-powered. +comment "HID Sensor RTC drivers" + +config RTC_DRV_HID_SENSOR_TIME + tristate "HID Sensor Time" + depends on USB_HID + depends on HID_SENSOR_HUB && IIO + select HID_SENSOR_IIO_COMMON + help + Say yes here to build support for the HID Sensors of type Time. + This drivers makes such sensors available as RTCs. + + If this driver is compiled as a module, it will be named + rtc-hid-sensor-time. + endif # RTC_CLASS diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 610a9ee5fd33..8221bda6e6dc 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -172,6 +172,7 @@ obj-$(CONFIG_RTC_DRV_SD2405AL) += rtc-sd2405al.o obj-$(CONFIG_RTC_DRV_SD3078) += rtc-sd3078.o obj-$(CONFIG_RTC_DRV_SH) += rtc-sh.o obj-$(CONFIG_RTC_DRV_SNVS) += rtc-snvs.o +obj-$(CONFIG_RTC_DRV_SPACEMIT_P1) += rtc-spacemit-p1.o obj-$(CONFIG_RTC_DRV_SPEAR) += rtc-spear.o obj-$(CONFIG_RTC_DRV_STARFIRE) += rtc-starfire.o obj-$(CONFIG_RTC_DRV_STK17TA8) += rtc-stk17ta8.o diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index dc741ba29fa3..b8b298efd9a9 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -443,6 +443,29 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) else err = rtc->ops->set_alarm(rtc->dev.parent, alarm); + /* + * Check for potential race described above. If the waiting for next + * second, and the second just ticked since the check above, either + * + * 1) It ticked after the alarm was set, and an alarm irq should be + * generated. + * + * 2) It ticked before the alarm was set, and alarm irq most likely will + * not be generated. + * + * While we cannot easily check for which of these two scenarios we + * are in, we can return -ETIME to signal that the timer has already + * expired, which is true in both cases. + */ + if ((scheduled - now) <= 1) { + err = __rtc_read_time(rtc, &tm); + if (err) + return err; + now = rtc_tm_to_time64(&tm); + if (scheduled <= now) + return -ETIME; + } + trace_rtc_set_alarm(rtc_tm_to_time64(&alarm->time), err); return err; } @@ -594,6 +617,10 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled) rtc->uie_rtctimer.node.expires = ktime_add(now, onesec); rtc->uie_rtctimer.period = ktime_set(1, 0); err = rtc_timer_enqueue(rtc, &rtc->uie_rtctimer); + if (!err && rtc->ops && rtc->ops->alarm_irq_enable) + err = rtc->ops->alarm_irq_enable(rtc->dev.parent, 1); + if (err) + goto out; } else { rtc_timer_remove(rtc, &rtc->uie_rtctimer); } diff --git a/drivers/rtc/rtc-amlogic-a4.c b/drivers/rtc/rtc-amlogic-a4.c index 09d78c2cc691..1928b29c1045 100644 --- a/drivers/rtc/rtc-amlogic-a4.c +++ b/drivers/rtc/rtc-amlogic-a4.c @@ -72,13 +72,6 @@ struct aml_rtc_data { const struct aml_rtc_config *config; }; -static const struct regmap_config aml_rtc_regmap_config = { - .reg_bits = 32, - .val_bits = 32, - .reg_stride = 4, - .max_register = RTC_REAL_TIME, -}; - static inline u32 gray_to_binary(u32 gray) { u32 bcd = gray; @@ -328,6 +321,13 @@ static int aml_rtc_probe(struct platform_device *pdev) void __iomem *base; int ret = 0; + const struct regmap_config aml_rtc_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .max_register = RTC_REAL_TIME, + }; + rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL); if (!rtc) return -ENOMEM; diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c index c170345ac076..8b6b35716f53 100644 --- a/drivers/rtc/rtc-cpcap.c +++ b/drivers/rtc/rtc-cpcap.c @@ -268,6 +268,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev) return err; rtc->alarm_irq = platform_get_irq(pdev, 0); + rtc->alarm_enabled = true; err = devm_request_threaded_irq(dev, rtc->alarm_irq, NULL, cpcap_rtc_alarm_irq, IRQF_TRIGGER_NONE | IRQF_ONESHOT, diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c index fa8bf82df948..b4f44999ef0f 100644 --- a/drivers/rtc/rtc-efi.c +++ b/drivers/rtc/rtc-efi.c @@ -112,48 +112,6 @@ convert_from_efi_time(efi_time_t *eft, struct rtc_time *wtime) return true; } -static int efi_read_alarm(struct device *dev, struct rtc_wkalrm *wkalrm) -{ - efi_time_t eft; - efi_status_t status; - - /* - * As of EFI v1.10, this call always returns an unsupported status - */ - status = efi.get_wakeup_time((efi_bool_t *)&wkalrm->enabled, - (efi_bool_t *)&wkalrm->pending, &eft); - - if (status != EFI_SUCCESS) - return -EINVAL; - - if (!convert_from_efi_time(&eft, &wkalrm->time)) - return -EIO; - - return rtc_valid_tm(&wkalrm->time); -} - -static int efi_set_alarm(struct device *dev, struct rtc_wkalrm *wkalrm) -{ - efi_time_t eft; - efi_status_t status; - - convert_to_efi_time(&wkalrm->time, &eft); - - /* - * XXX Fixme: - * As of EFI 0.92 with the firmware I have on my - * machine this call does not seem to work quite - * right - * - * As of v1.10, this call always returns an unsupported status - */ - status = efi.set_wakeup_time((efi_bool_t)wkalrm->enabled, &eft); - - dev_warn(dev, "write status is %d\n", (int)status); - - return status == EFI_SUCCESS ? 0 : -EINVAL; -} - static int efi_read_time(struct device *dev, struct rtc_time *tm) { efi_status_t status; @@ -188,17 +146,13 @@ static int efi_set_time(struct device *dev, struct rtc_time *tm) static int efi_procfs(struct device *dev, struct seq_file *seq) { - efi_time_t eft, alm; + efi_time_t eft; efi_time_cap_t cap; - efi_bool_t enabled, pending; - struct rtc_device *rtc = dev_get_drvdata(dev); memset(&eft, 0, sizeof(eft)); - memset(&alm, 0, sizeof(alm)); memset(&cap, 0, sizeof(cap)); efi.get_time(&eft, &cap); - efi.get_wakeup_time(&enabled, &pending, &alm); seq_printf(seq, "Time\t\t: %u:%u:%u.%09u\n" @@ -214,26 +168,6 @@ static int efi_procfs(struct device *dev, struct seq_file *seq) /* XXX fixme: convert to string? */ seq_printf(seq, "Timezone\t: %u\n", eft.timezone); - if (test_bit(RTC_FEATURE_ALARM, rtc->features)) { - seq_printf(seq, - "Alarm Time\t: %u:%u:%u.%09u\n" - "Alarm Date\t: %u-%u-%u\n" - "Alarm Daylight\t: %u\n" - "Enabled\t\t: %s\n" - "Pending\t\t: %s\n", - alm.hour, alm.minute, alm.second, alm.nanosecond, - alm.year, alm.month, alm.day, - alm.daylight, - enabled == 1 ? "yes" : "no", - pending == 1 ? "yes" : "no"); - - if (alm.timezone == EFI_UNSPECIFIED_TIMEZONE) - seq_puts(seq, "Timezone\t: unspecified\n"); - else - /* XXX fixme: convert to string? */ - seq_printf(seq, "Timezone\t: %u\n", alm.timezone); - } - /* * now prints the capabilities */ @@ -249,8 +183,6 @@ static int efi_procfs(struct device *dev, struct seq_file *seq) static const struct rtc_class_ops efi_rtc_ops = { .read_time = efi_read_time, .set_time = efi_set_time, - .read_alarm = efi_read_alarm, - .set_alarm = efi_set_alarm, .proc = efi_procfs, }; @@ -271,11 +203,7 @@ static int __init efi_rtc_probe(struct platform_device *dev) platform_set_drvdata(dev, rtc); rtc->ops = &efi_rtc_ops; - clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); - if (efi_rt_services_supported(EFI_RT_SUPPORTED_WAKEUP_SERVICES)) - set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); - else - clear_bit(RTC_FEATURE_ALARM, rtc->features); + clear_bit(RTC_FEATURE_ALARM, rtc->features); device_init_wakeup(&dev->dev, true); diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 9b44839a7402..5fc52dc64213 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -413,6 +413,7 @@ static int isl12022_setup_irq(struct device *dev, int irq) if (ret) return ret; + isl12022->irq_enabled = true; ret = devm_request_threaded_irq(dev, irq, NULL, isl12022_rtc_interrupt, IRQF_SHARED | IRQF_ONESHOT, diff --git a/drivers/rtc/rtc-meson.c b/drivers/rtc/rtc-meson.c index 47e9ebf58ffc..21eceb9e2e13 100644 --- a/drivers/rtc/rtc-meson.c +++ b/drivers/rtc/rtc-meson.c @@ -72,7 +72,6 @@ static const struct regmap_config meson_rtc_peripheral_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = RTC_REG4, - .fast_io = true, }; /* RTC front-end serialiser controls */ diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c index 9f8b5d4a8f6b..184c6d142801 100644 --- a/drivers/rtc/rtc-optee.c +++ b/drivers/rtc/rtc-optee.c @@ -5,19 +5,104 @@ #include <linux/device.h> #include <linux/kernel.h> +#include <linux/kthread.h> #include <linux/module.h> #include <linux/rtc.h> #include <linux/tee_drv.h> -#define RTC_INFO_VERSION 0x1 +#define RTC_INFO_VERSION 0x1 -#define TA_CMD_RTC_GET_INFO 0x0 -#define TA_CMD_RTC_GET_TIME 0x1 -#define TA_CMD_RTC_SET_TIME 0x2 -#define TA_CMD_RTC_GET_OFFSET 0x3 -#define TA_CMD_RTC_SET_OFFSET 0x4 +#define TA_RTC_FEATURE_CORRECTION BIT(0) +#define TA_RTC_FEATURE_ALARM BIT(1) +#define TA_RTC_FEATURE_WAKEUP_ALARM BIT(2) -#define TA_RTC_FEATURE_CORRECTION BIT(0) +enum rtc_optee_pta_cmd { + /* PTA_CMD_RTC_GET_INFO - Get RTC information + * + * [out] memref[0] RTC buffer memory reference containing a struct pta_rtc_info + */ + PTA_CMD_RTC_GET_INF = 0x0, + + /* + * PTA_CMD_RTC_GET_TIME - Get time from RTC + * + * [out] memref[0] RTC buffer memory reference containing a struct pta_rtc_time + */ + PTA_CMD_RTC_GET_TIME = 0x1, + + /* + * PTA_CMD_RTC_SET_TIME - Set time from RTC + * + * [in] memref[0] RTC buffer memory reference containing a struct pta_rtc_time to be + * used as RTC time + */ + PTA_CMD_RTC_SET_TIME = 0x2, + + /* + * PTA_CMD_RTC_GET_OFFSET - Get RTC offset + * + * [out] value[0].a RTC offset (signed 32bit value) + */ + PTA_CMD_RTC_GET_OFFSET = 0x3, + + /* + * PTA_CMD_RTC_SET_OFFSET - Set RTC offset + * + * [in] value[0].a RTC offset to be set (signed 32bit value) + */ + PTA_CMD_RTC_SET_OFFSET = 0x4, + + /* + * PTA_CMD_RTC_READ_ALARM - Read RTC alarm + * + * [out] memref[0] RTC buffer memory reference containing a struct pta_rtc_alarm + */ + PTA_CMD_RTC_READ_ALARM = 0x5, + + /* + * PTA_CMD_RTC_SET_ALARM - Set RTC alarm + * + * [in] memref[0] RTC buffer memory reference containing a struct pta_rtc_alarm to be + * used as RTC alarm + */ + PTA_CMD_RTC_SET_ALARM = 0x6, + + /* + * PTA_CMD_RTC_ENABLE_ALARM - Enable Alarm + * + * [in] value[0].a RTC IRQ flag (uint32_t), 0 to disable the alarm, 1 to enable + */ + PTA_CMD_RTC_ENABLE_ALARM = 0x7, + + /* + * PTA_CMD_RTC_WAIT_ALARM - Get alarm event + * + * [out] value[0].a RTC wait alarm return status (uint32_t): + * - 0: No alarm event + * - 1: Alarm event occurred + * - 2: Alarm event canceled + */ + PTA_CMD_RTC_WAIT_ALARM = 0x8, + + /* + * PTA_CMD_RTC_CANCEL_WAIT - Cancel wait for alarm event + */ + PTA_CMD_RTC_CANCEL_WAIT = 0x9, + + /* + * PTA_CMD_RTC_SET_WAKE_ALARM_STATUS - Set RTC wake alarm status flag + * + * [in] value[0].a RTC IRQ wake alarm flag (uint32_t), 0 to disable the wake up + * capability, 1 to enable. + */ + PTA_CMD_RTC_SET_WAKE_ALARM_STATUS = 0xA, +}; + +enum rtc_wait_alarm_status { + WAIT_ALARM_RESET = 0x0, + WAIT_ALARM_ALARM_OCCURRED = 0x1, + WAIT_ALARM_CANCELED = 0x2, +}; struct optee_rtc_time { u32 tm_sec; @@ -29,6 +114,12 @@ struct optee_rtc_time { u32 tm_wday; }; +struct optee_rtc_alarm { + u8 enabled; + u8 pending; + struct optee_rtc_time time; +}; + struct optee_rtc_info { u64 version; u64 features; @@ -41,15 +132,21 @@ struct optee_rtc_info { * @dev: OP-TEE based RTC device. * @ctx: OP-TEE context handler. * @session_id: RTC TA session identifier. + * @session2_id: RTC wait alarm session identifier. * @shm: Memory pool shared with RTC device. * @features: Bitfield of RTC features + * @alarm_task: RTC wait alamr task. + * @rtc: RTC device. */ struct optee_rtc { struct device *dev; struct tee_context *ctx; u32 session_id; + u32 session2_id; struct tee_shm *shm; u64 features; + struct task_struct *alarm_task; + struct rtc_device *rtc; }; static int optee_rtc_readtime(struct device *dev, struct rtc_time *tm) @@ -60,7 +157,7 @@ static int optee_rtc_readtime(struct device *dev, struct rtc_time *tm) struct tee_param param[4] = {0}; int ret; - inv_arg.func = TA_CMD_RTC_GET_TIME; + inv_arg.func = PTA_CMD_RTC_GET_TIME; inv_arg.session = priv->session_id; inv_arg.num_params = 4; @@ -97,19 +194,10 @@ static int optee_rtc_settime(struct device *dev, struct rtc_time *tm) struct optee_rtc *priv = dev_get_drvdata(dev); struct tee_ioctl_invoke_arg inv_arg = {0}; struct tee_param param[4] = {0}; - struct optee_rtc_time optee_tm; - void *rtc_data; + struct optee_rtc_time *optee_tm; int ret; - optee_tm.tm_sec = tm->tm_sec; - optee_tm.tm_min = tm->tm_min; - optee_tm.tm_hour = tm->tm_hour; - optee_tm.tm_mday = tm->tm_mday; - optee_tm.tm_mon = tm->tm_mon; - optee_tm.tm_year = tm->tm_year + 1900; - optee_tm.tm_wday = tm->tm_wday; - - inv_arg.func = TA_CMD_RTC_SET_TIME; + inv_arg.func = PTA_CMD_RTC_SET_TIME; inv_arg.session = priv->session_id; inv_arg.num_params = 4; @@ -117,11 +205,17 @@ static int optee_rtc_settime(struct device *dev, struct rtc_time *tm) param[0].u.memref.shm = priv->shm; param[0].u.memref.size = sizeof(struct optee_rtc_time); - rtc_data = tee_shm_get_va(priv->shm, 0); - if (IS_ERR(rtc_data)) - return PTR_ERR(rtc_data); + optee_tm = tee_shm_get_va(priv->shm, 0); + if (IS_ERR(optee_tm)) + return PTR_ERR(optee_tm); - memcpy(rtc_data, &optee_tm, sizeof(struct optee_rtc_time)); + optee_tm->tm_min = tm->tm_min; + optee_tm->tm_sec = tm->tm_sec; + optee_tm->tm_hour = tm->tm_hour; + optee_tm->tm_mday = tm->tm_mday; + optee_tm->tm_mon = tm->tm_mon; + optee_tm->tm_year = tm->tm_year + 1900; + optee_tm->tm_wday = tm->tm_wday; ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); if (ret < 0 || inv_arg.ret != 0) @@ -140,7 +234,7 @@ static int optee_rtc_readoffset(struct device *dev, long *offset) if (!(priv->features & TA_RTC_FEATURE_CORRECTION)) return -EOPNOTSUPP; - inv_arg.func = TA_CMD_RTC_GET_OFFSET; + inv_arg.func = PTA_CMD_RTC_GET_OFFSET; inv_arg.session = priv->session_id; inv_arg.num_params = 4; @@ -165,7 +259,7 @@ static int optee_rtc_setoffset(struct device *dev, long offset) if (!(priv->features & TA_RTC_FEATURE_CORRECTION)) return -EOPNOTSUPP; - inv_arg.func = TA_CMD_RTC_SET_OFFSET; + inv_arg.func = PTA_CMD_RTC_SET_OFFSET; inv_arg.session = priv->session_id; inv_arg.num_params = 4; @@ -179,13 +273,228 @@ static int optee_rtc_setoffset(struct device *dev, long offset) return 0; } +static int optee_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct optee_rtc_alarm *optee_alarm; + struct tee_param param[1] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + return -EOPNOTSUPP; + + inv_arg.func = PTA_CMD_RTC_READ_ALARM; + inv_arg.session = priv->session_id; + inv_arg.num_params = 1; + + /* Fill invoke cmd params */ + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; + param[0].u.memref.shm = priv->shm; + param[0].u.memref.size = sizeof(struct optee_rtc_alarm); + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + optee_alarm = tee_shm_get_va(priv->shm, 0); + if (IS_ERR(optee_alarm)) + return PTR_ERR(optee_alarm); + + if (param[0].u.memref.size != sizeof(*optee_alarm)) + return -EPROTO; + + alarm->enabled = optee_alarm->enabled; + alarm->pending = optee_alarm->pending; + alarm->time.tm_sec = optee_alarm->time.tm_sec; + alarm->time.tm_min = optee_alarm->time.tm_min; + alarm->time.tm_hour = optee_alarm->time.tm_hour; + alarm->time.tm_mday = optee_alarm->time.tm_mday; + alarm->time.tm_mon = optee_alarm->time.tm_mon; + alarm->time.tm_year = optee_alarm->time.tm_year - 1900; + alarm->time.tm_wday = optee_alarm->time.tm_wday; + alarm->time.tm_yday = rtc_year_days(alarm->time.tm_mday, + alarm->time.tm_mon, + alarm->time.tm_year); + + return 0; +} + +static int optee_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct optee_rtc_alarm *optee_alarm; + struct tee_param param[1] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + return -EOPNOTSUPP; + + inv_arg.func = PTA_CMD_RTC_SET_ALARM; + inv_arg.session = priv->session_id; + inv_arg.num_params = 1; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT; + param[0].u.memref.shm = priv->shm; + param[0].u.memref.size = sizeof(struct optee_rtc_alarm); + + optee_alarm = tee_shm_get_va(priv->shm, 0); + if (IS_ERR(optee_alarm)) + return PTR_ERR(optee_alarm); + + optee_alarm->enabled = alarm->enabled; + optee_alarm->pending = alarm->pending; + optee_alarm->time.tm_sec = alarm->time.tm_sec; + optee_alarm->time.tm_min = alarm->time.tm_min; + optee_alarm->time.tm_hour = alarm->time.tm_hour; + optee_alarm->time.tm_mday = alarm->time.tm_mday; + optee_alarm->time.tm_mon = alarm->time.tm_mon; + optee_alarm->time.tm_year = alarm->time.tm_year + 1900; + optee_alarm->time.tm_wday = alarm->time.tm_wday; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + return 0; +} + +static int optee_rtc_enable_alarm(struct device *dev, unsigned int enabled) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[1] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + return -EOPNOTSUPP; + + inv_arg.func = PTA_CMD_RTC_ENABLE_ALARM; + inv_arg.session = priv->session_id; + inv_arg.num_params = 1; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT; + param[0].u.value.a = (bool)enabled; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + return 0; +} + static const struct rtc_class_ops optee_rtc_ops = { - .read_time = optee_rtc_readtime, - .set_time = optee_rtc_settime, - .set_offset = optee_rtc_setoffset, - .read_offset = optee_rtc_readoffset, + .read_time = optee_rtc_readtime, + .set_time = optee_rtc_settime, + .set_offset = optee_rtc_setoffset, + .read_offset = optee_rtc_readoffset, + .read_alarm = optee_rtc_read_alarm, + .set_alarm = optee_rtc_set_alarm, + .alarm_irq_enable = optee_rtc_enable_alarm, }; +static int optee_rtc_wait_alarm(struct device *dev, int *return_status) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[1] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + return -EOPNOTSUPP; + + inv_arg.func = PTA_CMD_RTC_WAIT_ALARM; + inv_arg.session = priv->session2_id; + inv_arg.num_params = 1; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + *return_status = param[0].u.value.a; + + return 0; +} + +static int optee_rtc_cancel_wait_alarm(struct device *dev) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[1] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + return -EOPNOTSUPP; + + inv_arg.func = PTA_CMD_RTC_CANCEL_WAIT; + inv_arg.session = priv->session_id; + inv_arg.num_params = 0; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + return 0; +} + +static int optee_rtc_set_alarm_wake_status(struct device *dev, bool status) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[1] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + return -EOPNOTSUPP; + + inv_arg.func = PTA_CMD_RTC_SET_WAKE_ALARM_STATUS; + inv_arg.session = priv->session_id; + inv_arg.num_params = 1; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT; + param[0].u.value.a = status; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + return 0; +} + +static int optee_rtc_handle_alarm_event(void *data) +{ + struct optee_rtc *priv = (struct optee_rtc *)data; + int wait_alarm_return_status = 0; + int ret; + + while (!kthread_should_stop()) { + ret = optee_rtc_wait_alarm(priv->dev, &wait_alarm_return_status); + if (ret) { + dev_err(priv->dev, "Failed to wait for alarm: %d\n", ret); + return ret; + } + switch (wait_alarm_return_status) { + case WAIT_ALARM_ALARM_OCCURRED: + dev_dbg(priv->dev, "Alarm occurred\n"); + rtc_update_irq(priv->rtc, 1, RTC_IRQF | RTC_AF); + break; + case WAIT_ALARM_CANCELED: + dev_dbg(priv->dev, "Alarm canceled\n"); + break; + default: + dev_warn(priv->dev, "Unknown return status: %d\n", + wait_alarm_return_status); + break; + } + } + + return 0; +} + static int optee_rtc_read_info(struct device *dev, struct rtc_device *rtc, u64 *features) { @@ -196,7 +505,7 @@ static int optee_rtc_read_info(struct device *dev, struct rtc_device *rtc, struct optee_rtc_time *tm; int ret; - inv_arg.func = TA_CMD_RTC_GET_INFO; + inv_arg.func = PTA_CMD_RTC_GET_INF; inv_arg.session = priv->session_id; inv_arg.num_params = 4; @@ -241,14 +550,13 @@ static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data) static int optee_rtc_probe(struct device *dev) { struct tee_client_device *rtc_device = to_tee_client_device(dev); - struct tee_ioctl_open_session_arg sess_arg; + struct tee_ioctl_open_session_arg sess2_arg = {0}; + struct tee_ioctl_open_session_arg sess_arg = {0}; struct optee_rtc *priv; struct rtc_device *rtc; struct tee_shm *shm; int ret, err; - memset(&sess_arg, 0, sizeof(sess_arg)); - priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -257,12 +565,14 @@ static int optee_rtc_probe(struct device *dev) if (IS_ERR(rtc)) return PTR_ERR(rtc); + priv->rtc = rtc; + /* Open context with TEE driver */ priv->ctx = tee_client_open_context(NULL, optee_ctx_match, NULL, NULL); if (IS_ERR(priv->ctx)) return -ENODEV; - /* Open session with rtc Trusted App */ + /* Open first session with rtc Pseudo Trusted App */ export_uuid(sess_arg.uuid, &rtc_device->id.uuid); sess_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL; @@ -274,6 +584,11 @@ static int optee_rtc_probe(struct device *dev) } priv->session_id = sess_arg.session; + /* + * Shared memory is used for passing an instance of either struct optee_rtc_info, + * struct optee_rtc_time or struct optee_rtc_alarm to OP-TEE service. + * The former is by definition large enough to cover both parameter cases. + */ shm = tee_shm_alloc_kernel_buf(priv->ctx, sizeof(struct optee_rtc_info)); if (IS_ERR(shm)) { dev_err(priv->dev, "tee_shm_alloc_kernel_buf failed\n"); @@ -293,19 +608,70 @@ static int optee_rtc_probe(struct device *dev) goto out_shm; } + /* Handle feature's related setup before registering to rtc framework */ + if (priv->features & TA_RTC_FEATURE_ALARM) { + priv->alarm_task = kthread_create(optee_rtc_handle_alarm_event, + priv, "rtc_alarm_evt"); + if (IS_ERR(priv->alarm_task)) { + dev_err(dev, "Failed to create alarm thread\n"); + err = PTR_ERR(priv->alarm_task); + goto out_shm; + } + + /* + * In case of supported alarm feature on optee side, we create a kthread + * that will, in a new optee session, call a PTA interface "rtc_wait_alarm". + * This call return in case of alarm and in case of canceled alarm. + * The new optee session is therefore only needed in this case as we cannot + * use the same session for parallel calls to optee PTA. + * Hence one session is reserved to wait for alarms and the other to make + * standard calls to RTC PTA. + */ + + /* Open second session with rtc Trusted App */ + export_uuid(sess2_arg.uuid, &rtc_device->id.uuid); + sess2_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL; + + ret = tee_client_open_session(priv->ctx, &sess2_arg, NULL); + if (ret < 0 || sess2_arg.ret != 0) { + dev_err(dev, "tee_client_open_session failed, err: %x\n", sess2_arg.ret); + err = -EINVAL; + goto out_thrd; + } + priv->session2_id = sess2_arg.session; + + if (priv->features & TA_RTC_FEATURE_WAKEUP_ALARM) + device_init_wakeup(dev, true); + } + err = devm_rtc_register_device(rtc); if (err) - goto out_shm; + goto out_wk; /* - * We must clear this bit after registering because rtc_register_device - * will set it if it sees that .set_offset is provided. + * We must clear those bits after registering because registering a rtc_device + * will set them if it sees that .set_offset and .set_alarm are provided. */ if (!(priv->features & TA_RTC_FEATURE_CORRECTION)) clear_bit(RTC_FEATURE_CORRECTION, rtc->features); + if (!(priv->features & TA_RTC_FEATURE_ALARM)) + clear_bit(RTC_FEATURE_ALARM, rtc->features); - return 0; + /* Start the thread after the rtc is setup */ + if (priv->alarm_task) { + wake_up_process(priv->alarm_task); + dev_dbg(dev, "Wait alarm thread successfully started\n"); + } + return 0; +out_wk: + if (priv->features & TA_RTC_FEATURE_ALARM) { + device_init_wakeup(dev, false); + tee_client_close_session(priv->ctx, priv->session2_id); + } +out_thrd: + if (priv->features & TA_RTC_FEATURE_ALARM) + kthread_stop(priv->alarm_task); out_shm: tee_shm_free(priv->shm); out_sess: @@ -320,12 +686,34 @@ static int optee_rtc_remove(struct device *dev) { struct optee_rtc *priv = dev_get_drvdata(dev); + if (priv->features & TA_RTC_FEATURE_ALARM) { + optee_rtc_cancel_wait_alarm(dev); + kthread_stop(priv->alarm_task); + device_init_wakeup(dev, false); + tee_client_close_session(priv->ctx, priv->session2_id); + } + + tee_shm_free(priv->shm); tee_client_close_session(priv->ctx, priv->session_id); tee_client_close_context(priv->ctx); return 0; } +static int optee_rtc_suspend(struct device *dev) +{ + int res = optee_rtc_set_alarm_wake_status(dev, device_may_wakeup(dev)); + + if (res) { + dev_err(dev, "Unable to transmit wakeup information to optee rtc\n"); + return res; + } + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(optee_rtc_pm_ops, optee_rtc_suspend, NULL); + static const struct tee_client_device_id optee_rtc_id_table[] = { {UUID_INIT(0xf389f8c8, 0x845f, 0x496c, 0x8b, 0xbe, 0xd6, 0x4b, 0xd2, 0x4c, 0x92, 0xfd)}, @@ -341,6 +729,7 @@ static struct tee_client_driver optee_rtc_driver = { .bus = &tee_bus_type, .probe = optee_rtc_probe, .remove = optee_rtc_remove, + .pm = pm_sleep_ptr(&optee_rtc_pm_ops), }, }; diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 2e1ac0c42e93..bb4fe81d3d62 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -42,6 +42,7 @@ #define PCF2127_BIT_CTRL2_AF BIT(4) #define PCF2127_BIT_CTRL2_TSF2 BIT(5) #define PCF2127_BIT_CTRL2_WDTF BIT(6) +#define PCF2127_BIT_CTRL2_MSF BIT(7) /* Control register 3 */ #define PCF2127_REG_CTRL3 0x02 #define PCF2127_BIT_CTRL3_BLIE BIT(0) @@ -96,7 +97,8 @@ #define PCF2127_CTRL2_IRQ_MASK ( \ PCF2127_BIT_CTRL2_AF | \ PCF2127_BIT_CTRL2_WDTF | \ - PCF2127_BIT_CTRL2_TSF2) + PCF2127_BIT_CTRL2_TSF2 | \ + PCF2127_BIT_CTRL2_MSF) #define PCF2127_MAX_TS_SUPPORTED 4 @@ -606,6 +608,21 @@ static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127) set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status); } + /* + * When using interrupt pin (INT A) as watchdog output, only allow + * watchdog interrupt (PCF2131_BIT_INT_WD_CD) and disable (mask) all + * other interrupts. + */ + if (pcf2127->cfg->type == PCF2131) { + ret = regmap_write(pcf2127->regmap, + PCF2131_REG_INT_A_MASK1, + PCF2131_BIT_INT_BLIE | + PCF2131_BIT_INT_BIE | + PCF2131_BIT_INT_AIE | + PCF2131_BIT_INT_SI | + PCF2131_BIT_INT_MI); + } + return devm_watchdog_register_device(dev, &pcf2127->wdd); } diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 79b2a16f15ad..291c0ccb0acd 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -331,7 +331,7 @@ static const struct rtc_class_ops s3c_rtcops = { .alarm_irq_enable = s3c_rtc_setaie, }; -static void s3c24xx_rtc_enable(struct s3c_rtc *info) +static void s3c6410_rtc_enable(struct s3c_rtc *info) { unsigned int con, tmp; @@ -361,19 +361,6 @@ static void s3c24xx_rtc_enable(struct s3c_rtc *info) } } -static void s3c24xx_rtc_disable(struct s3c_rtc *info) -{ - unsigned int con; - - con = readw(info->base + S3C2410_RTCCON); - con &= ~S3C2410_RTCCON_RTCEN; - writew(con, info->base + S3C2410_RTCCON); - - con = readb(info->base + S3C2410_TICNT); - con &= ~S3C2410_TICNT_ENABLE; - writeb(con, info->base + S3C2410_TICNT); -} - static void s3c6410_rtc_disable(struct s3c_rtc *info) { unsigned int con; @@ -538,53 +525,21 @@ static int s3c_rtc_resume(struct device *dev) #endif static SIMPLE_DEV_PM_OPS(s3c_rtc_pm_ops, s3c_rtc_suspend, s3c_rtc_resume); -static void s3c24xx_rtc_irq(struct s3c_rtc *info, int mask) -{ - rtc_update_irq(info->rtc, 1, RTC_AF | RTC_IRQF); -} - static void s3c6410_rtc_irq(struct s3c_rtc *info, int mask) { rtc_update_irq(info->rtc, 1, RTC_AF | RTC_IRQF); writeb(mask, info->base + S3C2410_INTP); } -static const struct s3c_rtc_data s3c2410_rtc_data = { - .irq_handler = s3c24xx_rtc_irq, - .enable = s3c24xx_rtc_enable, - .disable = s3c24xx_rtc_disable, -}; - -static const struct s3c_rtc_data s3c2416_rtc_data = { - .irq_handler = s3c24xx_rtc_irq, - .enable = s3c24xx_rtc_enable, - .disable = s3c24xx_rtc_disable, -}; - -static const struct s3c_rtc_data s3c2443_rtc_data = { - .irq_handler = s3c24xx_rtc_irq, - .enable = s3c24xx_rtc_enable, - .disable = s3c24xx_rtc_disable, -}; - static const struct s3c_rtc_data s3c6410_rtc_data = { .needs_src_clk = true, .irq_handler = s3c6410_rtc_irq, - .enable = s3c24xx_rtc_enable, + .enable = s3c6410_rtc_enable, .disable = s3c6410_rtc_disable, }; static const __maybe_unused struct of_device_id s3c_rtc_dt_match[] = { { - .compatible = "samsung,s3c2410-rtc", - .data = &s3c2410_rtc_data, - }, { - .compatible = "samsung,s3c2416-rtc", - .data = &s3c2416_rtc_data, - }, { - .compatible = "samsung,s3c2443-rtc", - .data = &s3c2443_rtc_data, - }, { .compatible = "samsung,s3c6410-rtc", .data = &s3c6410_rtc_data, }, { diff --git a/drivers/rtc/rtc-s3c.h b/drivers/rtc/rtc-s3c.h index 3552914aa611..11d7a1255ce4 100644 --- a/drivers/rtc/rtc-s3c.h +++ b/drivers/rtc/rtc-s3c.h @@ -21,25 +21,6 @@ #define S3C2443_RTCCON_TICSEL (1 << 4) #define S3C64XX_RTCCON_TICEN (1 << 8) -#define S3C2410_TICNT S3C2410_RTCREG(0x44) -#define S3C2410_TICNT_ENABLE (1 << 7) - -/* S3C2443: tick count is 15 bit wide - * TICNT[6:0] contains upper 7 bits - * TICNT1[7:0] contains lower 8 bits - */ -#define S3C2443_TICNT_PART(x) ((x & 0x7f00) >> 8) -#define S3C2443_TICNT1 S3C2410_RTCREG(0x4C) -#define S3C2443_TICNT1_PART(x) (x & 0xff) - -/* S3C2416: tick count is 32 bit wide - * TICNT[6:0] contains bits [14:8] - * TICNT1[7:0] contains lower 8 bits - * TICNT2[16:0] contains upper 17 bits - */ -#define S3C2416_TICNT2 S3C2410_RTCREG(0x48) -#define S3C2416_TICNT2_PART(x) ((x & 0xffff8000) >> 15) - #define S3C2410_RTCALM S3C2410_RTCREG(0x50) #define S3C2410_RTCALM_ALMEN (1 << 6) #define S3C2410_RTCALM_YEAREN (1 << 5) diff --git a/drivers/rtc/rtc-sd2405al.c b/drivers/rtc/rtc-sd2405al.c index 00c3033e8079..708ea5d964de 100644 --- a/drivers/rtc/rtc-sd2405al.c +++ b/drivers/rtc/rtc-sd2405al.c @@ -5,7 +5,9 @@ * Datasheet: * https://image.dfrobot.com/image/data/TOY0021/SD2405AL%20datasheet%20(Angelo%20v0.1).pdf * - * Copyright (C) 2024 Tóth János <gomba007@gmail.com> + * I2C slave address: 0x32 + * + * Copyright (C) 2024-2025 Tóth János <gomba007@gmail.com> */ #include <linux/bcd.h> diff --git a/drivers/rtc/rtc-spacemit-p1.c b/drivers/rtc/rtc-spacemit-p1.c new file mode 100644 index 000000000000..43ab62494bb4 --- /dev/null +++ b/drivers/rtc/rtc-spacemit-p1.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for the RTC found in the SpacemiT P1 PMIC + * + * Copyright (C) 2025 by RISCstar Solutions Corporation. All rights reserved. + */ + +#include <linux/bits.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/rtc.h> + +#define MOD_NAME "spacemit-p1-rtc" + +/* + * Six consecutive 1-byte registers hold the seconds, minutes, hours, + * day-of-month, month, and year (respectively). + * + * The range of values in these registers is: + * seconds 0-59 + * minutes 0-59 + * hours 0-59 + * day 0-30 (struct tm is 1-31) + * month 0-11 + * year years since 2000 (struct tm is since 1900) + * + * Note that the day and month must be converted after reading and + * before writing. + */ +#define RTC_TIME 0x0d /* Offset of the seconds register */ + +#define RTC_CTRL 0x1d +#define RTC_EN BIT(2) + +/* Number of attempts to read a consistent time stamp before giving up */ +#define RTC_READ_TRIES 20 /* At least 1 */ + +struct p1_rtc { + struct regmap *regmap; + struct rtc_device *rtc; +}; + +/* + * The P1 hardware documentation states that the register values are + * latched to ensure a consistent time snapshot within the registers, + * but these are in fact unstable due to a bug in the hardware design. + * So we loop until we get two identical readings. + */ +static int p1_rtc_read_time(struct device *dev, struct rtc_time *t) +{ + struct p1_rtc *p1 = dev_get_drvdata(dev); + struct regmap *regmap = p1->regmap; + u32 count = RTC_READ_TRIES; + u8 seconds; + u8 time[6]; + int ret; + + if (!regmap_test_bits(regmap, RTC_CTRL, RTC_EN)) + return -EINVAL; /* RTC is disabled */ + + ret = regmap_bulk_read(regmap, RTC_TIME, time, sizeof(time)); + if (ret) + return ret; + + do { + seconds = time[0]; + ret = regmap_bulk_read(regmap, RTC_TIME, time, sizeof(time)); + if (ret) + return ret; + } while (time[0] != seconds && --count); + + if (!count) + return -EIO; /* Unable to get a consistent result */ + + t->tm_sec = time[0] & GENMASK(5, 0); + t->tm_min = time[1] & GENMASK(5, 0); + t->tm_hour = time[2] & GENMASK(4, 0); + t->tm_mday = (time[3] & GENMASK(4, 0)) + 1; + t->tm_mon = time[4] & GENMASK(3, 0); + t->tm_year = (time[5] & GENMASK(5, 0)) + 100; + + return 0; +} + +/* + * The P1 hardware documentation states that values in the registers are + * latched so when written they represent a consistent time snapshot. + * Nevertheless, this is not guaranteed by the implementation, so we must + * disable the RTC while updating it. + */ +static int p1_rtc_set_time(struct device *dev, struct rtc_time *t) +{ + struct p1_rtc *p1 = dev_get_drvdata(dev); + struct regmap *regmap = p1->regmap; + u8 time[6]; + int ret; + + time[0] = t->tm_sec; + time[1] = t->tm_min; + time[2] = t->tm_hour; + time[3] = t->tm_mday - 1; + time[4] = t->tm_mon; + time[5] = t->tm_year - 100; + + /* Disable the RTC to update; re-enable again when done */ + ret = regmap_clear_bits(regmap, RTC_CTRL, RTC_EN); + if (ret) + return ret; + + /* If something goes wrong, leave the RTC disabled */ + ret = regmap_bulk_write(regmap, RTC_TIME, time, sizeof(time)); + if (ret) + return ret; + + return regmap_set_bits(regmap, RTC_CTRL, RTC_EN); +} + +static const struct rtc_class_ops p1_rtc_class_ops = { + .read_time = p1_rtc_read_time, + .set_time = p1_rtc_set_time, +}; + +static int p1_rtc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rtc_device *rtc; + struct p1_rtc *p1; + + p1 = devm_kzalloc(dev, sizeof(*p1), GFP_KERNEL); + if (!p1) + return -ENOMEM; + dev_set_drvdata(dev, p1); + + p1->regmap = dev_get_regmap(dev->parent, NULL); + if (!p1->regmap) + return dev_err_probe(dev, -ENODEV, "failed to get regmap\n"); + + rtc = devm_rtc_allocate_device(dev); + if (IS_ERR(rtc)) + return dev_err_probe(dev, PTR_ERR(rtc), + "error allocating device\n"); + p1->rtc = rtc; + + rtc->ops = &p1_rtc_class_ops; + rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + rtc->range_max = RTC_TIMESTAMP_END_2063; + + clear_bit(RTC_FEATURE_ALARM, rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); + + return devm_rtc_register_device(rtc); +} + +static struct platform_driver p1_rtc_driver = { + .probe = p1_rtc_probe, + .driver = { + .name = MOD_NAME, + }, +}; + +module_platform_driver(p1_rtc_driver); + +MODULE_DESCRIPTION("SpacemiT P1 RTC driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" MOD_NAME); diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c index 54c8429b16bf..76ecf7b798f0 100644 --- a/drivers/rtc/rtc-tps6586x.c +++ b/drivers/rtc/rtc-tps6586x.c @@ -258,6 +258,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev) irq_set_status_flags(rtc->irq, IRQ_NOAUTOEN); + rtc->irq_en = true; ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL, tps6586x_rtc_irq, IRQF_ONESHOT, diff --git a/drivers/rtc/rtc-x1205.c b/drivers/rtc/rtc-x1205.c index 4bcd7ca32f27..b8a0fccef14e 100644 --- a/drivers/rtc/rtc-x1205.c +++ b/drivers/rtc/rtc-x1205.c @@ -669,7 +669,7 @@ static const struct i2c_device_id x1205_id[] = { MODULE_DEVICE_TABLE(i2c, x1205_id); static const struct of_device_id x1205_dt_ids[] = { - { .compatible = "xircom,x1205", }, + { .compatible = "xicor,x1205", }, {}, }; MODULE_DEVICE_TABLE(of, x1205_dt_ids); diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c index f39102b66eac..3baa2b481d9f 100644 --- a/drivers/rtc/rtc-zynqmp.c +++ b/drivers/rtc/rtc-zynqmp.c @@ -277,6 +277,10 @@ static irqreturn_t xlnx_rtc_interrupt(int irq, void *id) static int xlnx_rtc_probe(struct platform_device *pdev) { struct xlnx_rtc_dev *xrtcdev; + bool is_alarm_set = false; + u32 pending_alrm_irq; + u32 current_time; + u32 alarm_time; int ret; xrtcdev = devm_kzalloc(&pdev->dev, sizeof(*xrtcdev), GFP_KERNEL); @@ -296,6 +300,17 @@ static int xlnx_rtc_probe(struct platform_device *pdev) if (IS_ERR(xrtcdev->reg_base)) return PTR_ERR(xrtcdev->reg_base); + /* Clear any pending alarm interrupts from previous kernel/boot */ + pending_alrm_irq = readl(xrtcdev->reg_base + RTC_INT_STS) & RTC_INT_ALRM; + if (pending_alrm_irq) + writel(pending_alrm_irq, xrtcdev->reg_base + RTC_INT_STS); + + /* Check if a valid alarm is already set from previous kernel/boot */ + alarm_time = readl(xrtcdev->reg_base + RTC_ALRM); + current_time = readl(xrtcdev->reg_base + RTC_CUR_TM); + if (alarm_time > current_time && alarm_time != 0) + is_alarm_set = true; + xrtcdev->alarm_irq = platform_get_irq_byname(pdev, "alarm"); if (xrtcdev->alarm_irq < 0) return xrtcdev->alarm_irq; @@ -337,6 +352,10 @@ static int xlnx_rtc_probe(struct platform_device *pdev) xlnx_init_rtc(xrtcdev); + /* Re-enable alarm interrupt if a valid alarm was found */ + if (is_alarm_set) + writel(RTC_INT_ALRM, xrtcdev->reg_base + RTC_INT_EN); + device_init_wakeup(&pdev->dev, true); return devm_rtc_register_device(xrtcdev->rtc); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 2c72da6b8cf0..7f1ad305eee6 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -124,7 +124,7 @@ static void mvs_free(struct mvs_info *mvi) if (mvi->shost) scsi_host_put(mvi->shost); list_for_each_entry(mwq, &mvi->wq_list, entry) - cancel_delayed_work(&mwq->work_q); + cancel_delayed_work_sync(&mwq->work_q); kfree(mvi->rsvd_tags); kfree(mvi); } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 604e66bead1e..cb95b7b12051 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -4890,7 +4890,9 @@ struct purex_item { struct purex_item *pkt); atomic_t in_use; uint16_t size; - uint8_t iocb[] __counted_by(size); + struct { + uint8_t iocb[64]; + } iocb; }; #include "qla_edif.h" @@ -5099,6 +5101,7 @@ typedef struct scsi_qla_host { struct list_head head; spinlock_t lock; } purex_list; + struct purex_item default_item; struct name_list_extended gnl; /* Count of active session/fcport */ @@ -5127,11 +5130,6 @@ typedef struct scsi_qla_host { #define DPORT_DIAG_IN_PROGRESS BIT_0 #define DPORT_DIAG_CHIP_RESET_IN_PROGRESS BIT_1 uint16_t dport_status; - - /* Must be last --ends in a flexible-array member. */ - TRAILING_OVERLAP(struct purex_item, default_item, iocb, - uint8_t __default_item_iocb[QLA_DEFAULT_PAYLOAD_SIZE]; - ); } scsi_qla_host_t; struct qla27xx_image_status { diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 4559b490614d..c4c6b5c6658c 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1077,17 +1077,17 @@ static struct purex_item * qla24xx_alloc_purex_item(scsi_qla_host_t *vha, uint16_t size) { struct purex_item *item = NULL; + uint8_t item_hdr_size = sizeof(*item); if (size > QLA_DEFAULT_PAYLOAD_SIZE) { - item = kzalloc(struct_size(item, iocb, size), GFP_ATOMIC); + item = kzalloc(item_hdr_size + + (size - QLA_DEFAULT_PAYLOAD_SIZE), GFP_ATOMIC); } else { if (atomic_inc_return(&vha->default_item.in_use) == 1) { item = &vha->default_item; goto initialize_purex_header; } else { - item = kzalloc( - struct_size(item, iocb, QLA_DEFAULT_PAYLOAD_SIZE), - GFP_ATOMIC); + item = kzalloc(item_hdr_size, GFP_ATOMIC); } } if (!item) { @@ -1127,16 +1127,17 @@ qla24xx_queue_purex_item(scsi_qla_host_t *vha, struct purex_item *pkt, * @vha: SCSI driver HA context * @pkt: ELS packet */ -static struct purex_item * -qla24xx_copy_std_pkt(struct scsi_qla_host *vha, void *pkt) +static struct purex_item +*qla24xx_copy_std_pkt(struct scsi_qla_host *vha, void *pkt) { struct purex_item *item; - item = qla24xx_alloc_purex_item(vha, QLA_DEFAULT_PAYLOAD_SIZE); + item = qla24xx_alloc_purex_item(vha, + QLA_DEFAULT_PAYLOAD_SIZE); if (!item) return item; - memcpy(&item->iocb, pkt, QLA_DEFAULT_PAYLOAD_SIZE); + memcpy(&item->iocb, pkt, sizeof(item->iocb)); return item; } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 065f9bcca26f..316594aa40cc 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -1308,7 +1308,7 @@ void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp) ql_dbg(ql_dbg_unsol, vha, 0x2121, "PURLS OP[%01x] size %d xchg addr 0x%x portid %06x\n", - item->iocb[3], item->size, uctx->exchange_address, + item->iocb.iocb[3], item->size, uctx->exchange_address, fcport->d_id.b24); /* +48 0 1 2 3 4 5 6 7 8 9 A B C D E F * ----- ----------------------------------------------- diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index cb56d2af6cfa..5ffd94586652 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -6459,10 +6459,9 @@ dealloc: void qla24xx_free_purex_item(struct purex_item *item) { - if (item == &item->vha->default_item) { + if (item == &item->vha->default_item) memset(&item->vha->default_item, 0, sizeof(struct purex_item)); - memset(&item->vha->__default_item_iocb, 0, QLA_DEFAULT_PAYLOAD_SIZE); - } else + else kfree(item); } diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 0904ecae253a..b19acd662726 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2774,7 +2774,7 @@ static ssize_t target_lu_gp_members_show(struct config_item *item, char *page) config_item_name(&dev->dev_group.cg_item)); cur_len++; /* Extra byte for NULL terminator */ - if ((cur_len + len) > PAGE_SIZE) { + if ((cur_len + len) > PAGE_SIZE || cur_len > LU_GROUP_NAME_BUF) { pr_warn("Ran out of lu_gp_show_attr" "_members buffer\n"); break; diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c index 0086816b27cd..c040afc6668e 100644 --- a/drivers/ufs/core/ufs-sysfs.c +++ b/drivers/ufs/core/ufs-sysfs.c @@ -1949,7 +1949,7 @@ static umode_t ufs_sysfs_hid_is_visible(struct kobject *kobj, return hba->dev_info.hid_sup ? attr->mode : 0; } -static const struct attribute_group ufs_sysfs_hid_group = { +const struct attribute_group ufs_sysfs_hid_group = { .name = "hid", .attrs = ufs_sysfs_hid, .is_visible = ufs_sysfs_hid_is_visible, diff --git a/drivers/ufs/core/ufs-sysfs.h b/drivers/ufs/core/ufs-sysfs.h index 8d94af3b8077..6efb82a082fd 100644 --- a/drivers/ufs/core/ufs-sysfs.h +++ b/drivers/ufs/core/ufs-sysfs.h @@ -14,5 +14,6 @@ void ufs_sysfs_remove_nodes(struct device *dev); extern const struct attribute_group ufs_sysfs_unit_descriptor_group; extern const struct attribute_group ufs_sysfs_lun_attributes_group; +extern const struct attribute_group ufs_sysfs_hid_group; #endif diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index d9632d7c5f01..8339fec975b9 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6684,6 +6684,14 @@ static void ufshcd_err_handler(struct work_struct *work) } spin_unlock_irqrestore(hba->host->host_lock, flags); + ufshcd_rpm_get_noresume(hba); + if (hba->pm_op_in_progress) { + ufshcd_link_recovery(hba); + ufshcd_rpm_put(hba); + return; + } + ufshcd_rpm_put(hba); + ufshcd_err_handling_prepare(hba); spin_lock_irqsave(hba->host->host_lock, flags); @@ -8489,6 +8497,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba) DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP) & UFS_DEV_HID_SUPPORT; + sysfs_update_group(&hba->dev->kobj, &ufs_sysfs_hid_group); + model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME]; err = ufshcd_read_string_desc(hba, model_index, @@ -10677,6 +10687,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) */ spin_lock_init(&hba->clk_gating.lock); + /* Initialize mutex for PM QoS request synchronization */ + mutex_init(&hba->pm_qos_mutex); + /* * Set the default power management level for runtime and system PM. * Host controller drivers can override them in their @@ -10765,9 +10778,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) mutex_init(&hba->wb_mutex); - /* Initialize mutex for PM QoS request synchronization */ - mutex_init(&hba->pm_qos_mutex); - init_rwsem(&hba->clk_scaling_lock); ufshcd_init_clk_gating(hba); diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index c3b9954df804..a257b739188d 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -126,9 +126,9 @@ config FB_ACORN config FB_CLPS711X tristate "CLPS711X LCD support" depends on FB && (ARCH_CLPS711X || COMPILE_TEST) + depends on LCD_CLASS_DEVICE select FB_IOMEM_HELPERS select FB_MODE_HELPERS - select LCD_CLASS_DEVICE select VIDEOMODE_HELPERS help Say Y to enable the Framebuffer driver for the Cirrus Logic @@ -150,7 +150,7 @@ config FB_IMX tristate "Freescale i.MX1/21/25/27 LCD support" depends on FB && HAVE_CLK && HAS_IOMEM depends on ARCH_MXC || COMPILE_TEST - select LCD_CLASS_DEVICE + depends on LCD_CLASS_DEVICE select FB_IOMEM_HELPERS select FB_MODE_HELPERS select VIDEOMODE_HELPERS @@ -948,9 +948,6 @@ config FB_RADEON a framebuffer device. There are both PCI and AGP versions. You don't need to choose this to run the Radeon in plain VGA mode. - There is a product page at - https://products.amd.com/en-us/GraphicCardResult.aspx - config FB_RADEON_I2C bool "DDC/I2C for ATI Radeon support" depends on FB_RADEON @@ -1060,6 +1057,7 @@ config FB_S3 select FB_TILEBLITTING select FB_SVGALIB select VGASTATE + select FB_CFB_REV_PIXELS_IN_BYTE select FONT_8x16 if FRAMEBUFFER_CONSOLE help Driver for graphics boards with S3 Trio / S3 Virge chip. diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index f9475c14f733..a9ec7f488522 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -160,6 +160,11 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info, image.height = vc->vc_font.height; image.depth = 1; + if (image.dy >= info->var.yres) + return; + + image.height = min(image.height, info->var.yres - image.dy); + if (attribute) { buf = kmalloc(cellsize, GFP_ATOMIC); if (!buf) @@ -173,6 +178,18 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info, cnt = count; image.width = vc->vc_font.width * cnt; + + if (image.dx >= info->var.xres) + break; + + if (image.dx + image.width > info->var.xres) { + image.width = info->var.xres - image.dx; + cnt = image.width / vc->vc_font.width; + if (cnt == 0) + break; + image.width = cnt * vc->vc_font.width; + } + pitch = DIV_ROUND_UP(image.width, 8) + scan_align; pitch &= ~scan_align; size = pitch * image.height + buf_align; diff --git a/drivers/video/fbdev/core/fb_cmdline.c b/drivers/video/fbdev/core/fb_cmdline.c index 4d1634c492ec..594b60424d1c 100644 --- a/drivers/video/fbdev/core/fb_cmdline.c +++ b/drivers/video/fbdev/core/fb_cmdline.c @@ -40,7 +40,7 @@ int fb_get_options(const char *name, char **option) bool enabled; if (name) - is_of = strncmp(name, "offb", 4); + is_of = !strncmp(name, "offb", 4); enabled = __video_get_options(name, &options, is_of); diff --git a/drivers/video/fbdev/core/fb_fillrect.h b/drivers/video/fbdev/core/fb_fillrect.h index 66042e534de7..f366670a53af 100644 --- a/drivers/video/fbdev/core/fb_fillrect.h +++ b/drivers/video/fbdev/core/fb_fillrect.h @@ -92,8 +92,7 @@ static unsigned long pixel_to_pat(int bpp, u32 color) pattern = pattern | pattern << bpp; break; default: - pattern = color; - break; + return color; } #ifndef __LITTLE_ENDIAN pattern <<= (BITS_PER_LONG % bpp); diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index 3b779c27c271..0a65bef01e3c 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -36,6 +36,7 @@ #include <video/of_videomode.h> #include <video/videomode.h> #include "../edid.h" +#include <linux/string_choices.h> /* * EDID parser @@ -320,9 +321,9 @@ static void get_dpms_capabilities(unsigned char flags, if (flags & DPMS_STANDBY) specs->dpms |= FB_DPMS_STANDBY; DPRINTK(" DPMS: Active %s, Suspend %s, Standby %s\n", - (flags & DPMS_ACTIVE_OFF) ? "yes" : "no", - (flags & DPMS_SUSPEND) ? "yes" : "no", - (flags & DPMS_STANDBY) ? "yes" : "no"); + str_yes_no(flags & DPMS_ACTIVE_OFF), + str_yes_no(flags & DPMS_SUSPEND), + str_yes_no(flags & DPMS_STANDBY)); } static void get_chroma(unsigned char *block, struct fb_monspecs *specs) diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c index ade88e7bc760..676c6d3ccc12 100644 --- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c +++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c @@ -674,7 +674,7 @@ static int of_platform_mb862xx_probe(struct platform_device *ofdev) struct fb_info *info; struct resource res; resource_size_t res_size; - unsigned long ret = -ENODEV; + int ret = -ENODEV; if (of_address_to_resource(np, 0, &res)) { dev_err(dev, "Invalid address\n"); diff --git a/drivers/video/fbdev/nvidia/nvidia.c b/drivers/video/fbdev/nvidia/nvidia.c index cfaf9454014d..72b85f475605 100644 --- a/drivers/video/fbdev/nvidia/nvidia.c +++ b/drivers/video/fbdev/nvidia/nvidia.c @@ -22,6 +22,7 @@ #include <linux/pci.h> #include <linux/console.h> #include <linux/backlight.h> +#include <linux/string_choices.h> #ifdef CONFIG_BOOTX_TEXT #include <asm/btext.h> #endif @@ -622,7 +623,7 @@ static int nvidiafb_set_par(struct fb_info *info) else par->FPDither = !!(NV_RD32(par->PRAMDAC, 0x083C) & 1); printk(KERN_INFO PFX "Flat panel dithering %s\n", - par->FPDither ? "enabled" : "disabled"); + str_enabled_disabled(par->FPDither)); } info->fix.visual = (info->var.bits_per_pixel == 8) ? diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index baf87f34cc24..b96a8a96bce8 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -60,6 +60,7 @@ #include <linux/soc/pxa/cpu.h> #include <video/of_display_timing.h> #include <video/videomode.h> +#include <linux/string_choices.h> #include <asm/io.h> #include <asm/irq.h> @@ -1419,7 +1420,7 @@ static inline void __pxafb_lcd_power(struct pxafb_info *fbi, int on) if (ret < 0) pr_warn("Unable to %s LCD supply regulator: %d\n", - on ? "enable" : "disable", ret); + str_enable_disable(on), ret); else fbi->lcd_supply_enabled = on; } diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c index ff84106ecf1c..ba30e5568cab 100644 --- a/drivers/video/fbdev/s3fb.c +++ b/drivers/video/fbdev/s3fb.c @@ -50,10 +50,14 @@ struct s3fb_info { static const struct svga_fb_format s3fb_formats[] = { { 0, {0, 6, 0}, {0, 6, 0}, {0, 6, 0}, {0, 0, 0}, 0, FB_TYPE_TEXT, FB_AUX_TEXT_SVGA_STEP4, FB_VISUAL_PSEUDOCOLOR, 8, 16}, - { 4, {0, 4, 0}, {0, 4, 0}, {0, 4, 0}, {0, 0, 0}, 0, - FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 8, 16}, + { 1, {0, 1, 0}, {0, 1, 0}, {0, 1, 0}, {0, 0, 0}, 2, + FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 32, 64}, + { 2, {0, 2, 0}, {0, 2, 0}, {0, 2, 0}, {0, 0, 0}, 2, + FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 16, 32}, { 4, {0, 4, 0}, {0, 4, 0}, {0, 4, 0}, {0, 0, 0}, 1, FB_TYPE_INTERLEAVED_PLANES, 1, FB_VISUAL_PSEUDOCOLOR, 8, 16}, + { 4, {0, 4, 0}, {0, 4, 0}, {0, 4, 0}, {0, 0, 0}, 2, + FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 8, 16}, { 8, {0, 8, 0}, {0, 8, 0}, {0, 8, 0}, {0, 0, 0}, 0, FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 4, 8}, {16, {10, 5, 0}, {5, 5, 0}, {0, 5, 0}, {0, 0, 0}, 0, @@ -557,7 +561,7 @@ static int s3fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) /* 32bpp mode is not supported on VIRGE VX, 24bpp is not supported on others */ - if ((par->chip == CHIP_988_VIRGE_VX) ? (rv == 7) : (rv == 6)) + if ((par->chip == CHIP_988_VIRGE_VX) ? (rv == 9) : (rv == 8)) rv = -EINVAL; if (rv < 0) { @@ -607,7 +611,7 @@ static int s3fb_set_par(struct fb_info *info) struct s3fb_info *par = info->par; u32 value, mode, hmul, offset_value, screen_size, multiplex, dbytes; u32 bpp = info->var.bits_per_pixel; - u32 htotal, hsstart; + u32 htotal, hsstart, pel_msk; if (bpp != 0) { info->fix.ypanstep = 1; @@ -617,9 +621,11 @@ static int s3fb_set_par(struct fb_info *info) info->tileops = NULL; /* in 4bpp supports 8p wide tiles only, any tiles otherwise */ - if (bpp == 4) { + if (bpp == 4 && (info->var.nonstd & 1) != 0) { + int i; bitmap_zero(info->pixmap.blit_x, FB_MAX_BLIT_WIDTH); - set_bit(8 - 1, info->pixmap.blit_x); + for (i = 8; i <= FB_MAX_BLIT_WIDTH; i += 8) + set_bit(i - 1, info->pixmap.blit_x); } else { bitmap_fill(info->pixmap.blit_x, FB_MAX_BLIT_WIDTH); } @@ -730,7 +736,7 @@ static int s3fb_set_par(struct fb_info *info) vga_wcrt(par->state.vgabase, 0x50, 0x00); vga_wcrt(par->state.vgabase, 0x67, 0x50); msleep(10); /* screen remains blank sometimes without this */ - vga_wcrt(par->state.vgabase, 0x63, (mode <= 2) ? 0x90 : 0x09); + vga_wcrt(par->state.vgabase, 0x63, (mode <= 4) ? 0x90 : 0x09); vga_wcrt(par->state.vgabase, 0x66, 0x90); } @@ -763,12 +769,17 @@ static int s3fb_set_par(struct fb_info *info) svga_wcrt_mask(par->state.vgabase, 0x31, 0x00, 0x40); multiplex = 0; hmul = 1; + pel_msk = 0xff; + + svga_wcrt_mask(par->state.vgabase, 0x08, 0x00, 0x60); + svga_wcrt_mask(par->state.vgabase, 0x05, 0x00, 0x60); /* Set mode-specific register values */ switch (mode) { case 0: fb_dbg(info, "text mode\n"); svga_set_textmode_vga_regs(par->state.vgabase); + pel_msk = 0x0f; /* Set additional registers like in 8-bit mode */ svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30); @@ -783,8 +794,11 @@ static int s3fb_set_par(struct fb_info *info) } break; case 1: - fb_dbg(info, "4 bit pseudocolor\n"); - vga_wgfx(par->state.vgabase, VGA_GFX_MODE, 0x40); + fb_dbg(info, "1 bit pseudocolor\n"); + svga_wseq_mask(par->state.vgabase, 0x01, 0x10, 0x14); + svga_wcrt_mask(par->state.vgabase, 0x08, 0x60, 0x60); + svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60); + pel_msk = 0x01; /* Set additional registers like in 8-bit mode */ svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30); @@ -794,7 +808,13 @@ static int s3fb_set_par(struct fb_info *info) svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30); break; case 2: - fb_dbg(info, "4 bit pseudocolor, planar\n"); + fb_dbg(info, "2 bit pseudocolor\n"); + svga_wseq_mask(par->state.vgabase, 0x01, 0x04, 0x14); + svga_wseq_mask(par->state.vgabase, 0x04, 0x08, 0x08); + vga_wgfx(par->state.vgabase, VGA_GFX_MODE, 0x20); + svga_wcrt_mask(par->state.vgabase, 0x08, 0x20, 0x60); + svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60); + pel_msk = 0x03; /* Set additional registers like in 8-bit mode */ svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30); @@ -804,8 +824,35 @@ static int s3fb_set_par(struct fb_info *info) svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30); break; case 3: + fb_dbg(info, "4 bit pseudocolor, planar\n"); + pel_msk = 0x0f; + + /* Set additional registers like in 8-bit mode */ + svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30); + svga_wcrt_mask(par->state.vgabase, 0x67, 0x00, 0xF0); + svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60); + + /* disable enhanced mode */ + svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30); + break; + case 4: + fb_dbg(info, "4 bit pseudocolor\n"); + vga_wgfx(par->state.vgabase, VGA_GFX_MODE, 0x40); + svga_wattr(par->state.vgabase, 0x33, 0x01); + svga_wcrt_mask(par->state.vgabase, 0x05, 0x40, 0x60); + pel_msk = 0xf0; + + /* Set additional registers like in 8-bit mode */ + svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30); + svga_wcrt_mask(par->state.vgabase, 0x67, 0x00, 0xF0); + + /* disable enhanced mode */ + svga_wcrt_mask(par->state.vgabase, 0x3A, 0x00, 0x30); + break; + case 5: fb_dbg(info, "8 bit pseudocolor\n"); svga_wcrt_mask(par->state.vgabase, 0x50, 0x00, 0x30); + svga_wcrt_mask(par->state.vgabase, 0x05, 0x20, 0x60); if (info->var.pixclock > 20000 || par->chip == CHIP_357_VIRGE_GX2 || par->chip == CHIP_359_VIRGE_GX2P || @@ -819,7 +866,7 @@ static int s3fb_set_par(struct fb_info *info) multiplex = 1; } break; - case 4: + case 6: fb_dbg(info, "5/5/5 truecolor\n"); if (par->chip == CHIP_988_VIRGE_VX) { if (info->var.pixclock > 20000) @@ -847,7 +894,7 @@ static int s3fb_set_par(struct fb_info *info) hmul = 2; } break; - case 5: + case 7: fb_dbg(info, "5/6/5 truecolor\n"); if (par->chip == CHIP_988_VIRGE_VX) { if (info->var.pixclock > 20000) @@ -875,12 +922,12 @@ static int s3fb_set_par(struct fb_info *info) hmul = 2; } break; - case 6: + case 8: /* VIRGE VX case */ fb_dbg(info, "8/8/8 truecolor\n"); svga_wcrt_mask(par->state.vgabase, 0x67, 0xD0, 0xF0); break; - case 7: + case 9: fb_dbg(info, "8/8/8/8 truecolor\n"); svga_wcrt_mask(par->state.vgabase, 0x50, 0x30, 0x30); svga_wcrt_mask(par->state.vgabase, 0x67, 0xD0, 0xF0); @@ -889,6 +936,7 @@ static int s3fb_set_par(struct fb_info *info) fb_err(info, "unsupported mode - bug\n"); return -EINVAL; } + vga_w(par->state.vgabase, VGA_PEL_MSK, pel_msk); if (par->chip != CHIP_988_VIRGE_VX) { svga_wseq_mask(par->state.vgabase, 0x15, multiplex ? 0x10 : 0x00, 0x10); @@ -927,33 +975,26 @@ static int s3fb_set_par(struct fb_info *info) static int s3fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, u_int transp, struct fb_info *fb) { + struct s3fb_info *par = fb->par; + int cols; + switch (fb->var.bits_per_pixel) { case 0: + case 1: + case 2: case 4: - if (regno >= 16) - return -EINVAL; - - if ((fb->var.bits_per_pixel == 4) && - (fb->var.nonstd == 0)) { - outb(0xF0, VGA_PEL_MSK); - outb(regno*16, VGA_PEL_IW); - } else { - outb(0x0F, VGA_PEL_MSK); - outb(regno, VGA_PEL_IW); - } - outb(red >> 10, VGA_PEL_D); - outb(green >> 10, VGA_PEL_D); - outb(blue >> 10, VGA_PEL_D); - break; case 8: - if (regno >= 256) + cols = 1 << (fb->var.bits_per_pixel ? fb->var.bits_per_pixel : 4); + if (regno >= cols) return -EINVAL; - outb(0xFF, VGA_PEL_MSK); - outb(regno, VGA_PEL_IW); - outb(red >> 10, VGA_PEL_D); - outb(green >> 10, VGA_PEL_D); - outb(blue >> 10, VGA_PEL_D); + if ((fb->var.bits_per_pixel == 4) && ((fb->var.nonstd & 1) == 0)) + regno <<= 4; + + vga_w(par->state.vgabase, VGA_PEL_IW, regno); + vga_w(par->state.vgabase, VGA_PEL_D, red >> 10); + vga_w(par->state.vgabase, VGA_PEL_D, green >> 10); + vga_w(par->state.vgabase, VGA_PEL_D, blue >> 10); break; case 16: if (regno >= 16) @@ -988,34 +1029,30 @@ static int s3fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, static int s3fb_blank(int blank_mode, struct fb_info *info) { struct s3fb_info *par = info->par; + u8 data; + + data = (blank_mode == FB_BLANK_UNBLANK) ? 0x00 : 0x20; + svga_wseq_mask(par->state.vgabase, 0x01, data, 0x20); + svga_wseq_mask(par->state.vgabase, 0x18, data, 0x20); switch (blank_mode) { - case FB_BLANK_UNBLANK: - fb_dbg(info, "unblank\n"); - svga_wcrt_mask(par->state.vgabase, 0x56, 0x00, 0x06); - svga_wseq_mask(par->state.vgabase, 0x01, 0x00, 0x20); - break; - case FB_BLANK_NORMAL: - fb_dbg(info, "blank\n"); - svga_wcrt_mask(par->state.vgabase, 0x56, 0x00, 0x06); - svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20); + default: + data = 0x00; break; case FB_BLANK_HSYNC_SUSPEND: - fb_dbg(info, "hsync\n"); - svga_wcrt_mask(par->state.vgabase, 0x56, 0x02, 0x06); - svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20); + data = 0x02; break; case FB_BLANK_VSYNC_SUSPEND: - fb_dbg(info, "vsync\n"); - svga_wcrt_mask(par->state.vgabase, 0x56, 0x04, 0x06); - svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20); + data = 0x04; break; case FB_BLANK_POWERDOWN: - fb_dbg(info, "sync down\n"); - svga_wcrt_mask(par->state.vgabase, 0x56, 0x06, 0x06); - svga_wseq_mask(par->state.vgabase, 0x01, 0x20, 0x20); + data = 0x06; break; } + svga_wcrt_mask(par->state.vgabase, 0x56, data, 0x06); + + data = (blank_mode == FB_BLANK_POWERDOWN) ? 0x01 : 0x00; + svga_wseq_mask(par->state.vgabase, 0x14, data, 0x01); return 0; } @@ -1045,6 +1082,33 @@ static int s3fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) return 0; } +/* Get capabilities of accelerator based on the mode */ + +static void s3fb_get_caps(struct fb_info *info, struct fb_blit_caps *caps, + struct fb_var_screeninfo *var) +{ + int i; + + if (var->bits_per_pixel == 0) { + /* can only support 256 8x16 bitmap */ + bitmap_zero(caps->x, FB_MAX_BLIT_WIDTH); + set_bit(8 - 1, caps->x); + bitmap_zero(caps->y, FB_MAX_BLIT_HEIGHT); + set_bit(16 - 1, caps->y); + caps->len = 256; + } else { + if (var->bits_per_pixel == 4 && (var->nonstd & 1) != 0) { + bitmap_zero(caps->x, FB_MAX_BLIT_WIDTH); + for (i = 8; i <= FB_MAX_BLIT_WIDTH; i += 8) + set_bit(i - 1, caps->x); + } else { + bitmap_fill(caps->x, FB_MAX_BLIT_WIDTH); + } + bitmap_fill(caps->y, FB_MAX_BLIT_HEIGHT); + caps->len = ~(u32)0; + } +} + /* ------------------------------------------------------------------------- */ /* Frame buffer operations */ @@ -1063,7 +1127,7 @@ static const struct fb_ops s3fb_ops = { .fb_copyarea = cfb_copyarea, .fb_imageblit = s3fb_imageblit, __FB_DEFAULT_IOMEM_OPS_MMAP, - .fb_get_caps = svga_get_caps, + .fb_get_caps = s3fb_get_caps, }; /* ------------------------------------------------------------------------- */ @@ -1445,6 +1509,8 @@ static int __maybe_unused s3_pci_suspend(struct device *dev) } fb_set_suspend(info, 1); + svga_wseq_mask(par->state.vgabase, 0x18, 0x20, 0x20); + svga_wseq_mask(par->state.vgabase, 0x14, 0x01, 0x01); mutex_unlock(&(par->open_lock)); console_unlock(); @@ -1471,6 +1537,9 @@ static int __maybe_unused s3_pci_resume(struct device *dev) return 0; } + vga_wseq(par->state.vgabase, 0x08, 0x06); + svga_wseq_mask(par->state.vgabase, 0x18, 0x00, 0x20); + svga_wseq_mask(par->state.vgabase, 0x14, 0x00, 0x01); s3fb_set_par(info); fb_set_suspend(info, 0); diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c index 1893815dc67f..6acf5a00c2ba 100644 --- a/drivers/video/fbdev/simplefb.c +++ b/drivers/video/fbdev/simplefb.c @@ -93,6 +93,7 @@ struct simplefb_par { static void simplefb_clocks_destroy(struct simplefb_par *par); static void simplefb_regulators_destroy(struct simplefb_par *par); +static void simplefb_detach_genpds(void *res); /* * fb_ops.fb_destroy is called by the last put_fb_info() call at the end @@ -105,6 +106,7 @@ static void simplefb_destroy(struct fb_info *info) simplefb_regulators_destroy(info->par); simplefb_clocks_destroy(info->par); + simplefb_detach_genpds(info->par); if (info->screen_base) iounmap(info->screen_base); @@ -445,13 +447,14 @@ static void simplefb_detach_genpds(void *res) if (!IS_ERR_OR_NULL(par->genpds[i])) dev_pm_domain_detach(par->genpds[i], true); } + par->num_genpds = 0; } static int simplefb_attach_genpds(struct simplefb_par *par, struct platform_device *pdev) { struct device *dev = &pdev->dev; - unsigned int i; + unsigned int i, num_genpds; int err; err = of_count_phandle_with_args(dev->of_node, "power-domains", @@ -465,26 +468,35 @@ static int simplefb_attach_genpds(struct simplefb_par *par, return err; } - par->num_genpds = err; + num_genpds = err; /* * Single power-domain devices are handled by the driver core, so * nothing to do here. */ - if (par->num_genpds <= 1) + if (num_genpds <= 1) { + par->num_genpds = num_genpds; return 0; + } - par->genpds = devm_kcalloc(dev, par->num_genpds, sizeof(*par->genpds), + par->genpds = devm_kcalloc(dev, num_genpds, sizeof(*par->genpds), GFP_KERNEL); if (!par->genpds) return -ENOMEM; - par->genpd_links = devm_kcalloc(dev, par->num_genpds, + par->genpd_links = devm_kcalloc(dev, num_genpds, sizeof(*par->genpd_links), GFP_KERNEL); if (!par->genpd_links) return -ENOMEM; + /* + * Set par->num_genpds only after genpds and genpd_links are allocated + * to exit early from simplefb_detach_genpds() without full + * initialisation. + */ + par->num_genpds = num_genpds; + for (i = 0; i < par->num_genpds; i++) { par->genpds[i] = dev_pm_domain_attach_by_id(dev, i); if (IS_ERR(par->genpds[i])) { @@ -506,9 +518,10 @@ static int simplefb_attach_genpds(struct simplefb_par *par, dev_warn(dev, "failed to link power-domain %u\n", i); } - return devm_add_action_or_reset(dev, simplefb_detach_genpds, par); + return 0; } #else +static void simplefb_detach_genpds(void *res) { } static int simplefb_attach_genpds(struct simplefb_par *par, struct platform_device *pdev) { @@ -622,18 +635,20 @@ static int simplefb_probe(struct platform_device *pdev) ret = devm_aperture_acquire_for_platform_device(pdev, par->base, par->size); if (ret) { dev_err(&pdev->dev, "Unable to acquire aperture: %d\n", ret); - goto error_regulators; + goto error_genpds; } ret = register_framebuffer(info); if (ret < 0) { dev_err(&pdev->dev, "Unable to register simplefb: %d\n", ret); - goto error_regulators; + goto error_genpds; } dev_info(&pdev->dev, "fb%d: simplefb registered!\n", info->node); return 0; +error_genpds: + simplefb_detach_genpds(par); error_regulators: simplefb_regulators_destroy(par); error_clocks: diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index c90f48ebb15e..d8f3bfb2dd6c 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -390,7 +390,7 @@ static int xenfb_probe(struct xenbus_device *dev, info->nr_pages = (fb_size + PAGE_SIZE - 1) >> PAGE_SHIFT; - info->gfns = vmalloc(array_size(sizeof(unsigned long), info->nr_pages)); + info->gfns = vmalloc_array(info->nr_pages, sizeof(unsigned long)); if (!info->gfns) goto error_nomem; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 32973c62c1a2..d18c0eaef9b7 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1260,8 +1260,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, spin_unlock(&fsc->async_unlink_conflict_lock); spin_lock(&dentry->d_lock); - di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK; - wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT); + clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags); spin_unlock(&dentry->d_lock); synchronize_rcu(); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 978acd3d4b32..99b30f784ee2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -579,8 +579,7 @@ static void wake_async_create_waiters(struct inode *inode, spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { - ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE; - wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT); + clear_and_wake_up_bit(CEPH_ASYNC_CREATE_BIT, &ci->i_ceph_flags); if (ci->i_ceph_flags & CEPH_I_ASYNC_CHECK_CAPS) { ci->i_ceph_flags &= ~CEPH_I_ASYNC_CHECK_CAPS; @@ -762,8 +761,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode, } spin_lock(&dentry->d_lock); - di->flags &= ~CEPH_DENTRY_ASYNC_CREATE; - wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT); + clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_CREATE_BIT, &di->flags); spin_unlock(&dentry->d_lock); return ret; @@ -2121,10 +2119,10 @@ again: if (ceph_inode_is_shutdown(inode)) return -ESTALE; - if (direct_lock) - ceph_start_io_direct(inode); - else - ceph_start_io_read(inode); + ret = direct_lock ? ceph_start_io_direct(inode) : + ceph_start_io_read(inode); + if (ret) + return ret; if (!(fi->flags & CEPH_F_SYNC) && !direct_lock) want |= CEPH_CAP_FILE_CACHE; @@ -2277,7 +2275,9 @@ static ssize_t ceph_splice_read(struct file *in, loff_t *ppos, (fi->flags & CEPH_F_SYNC)) return copy_splice_read(in, ppos, pipe, len, flags); - ceph_start_io_read(inode); + ret = ceph_start_io_read(inode); + if (ret) + return ret; want = CEPH_CAP_FILE_CACHE; if (fi->fmode & CEPH_FILE_MODE_LAZY) @@ -2356,10 +2356,10 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) direct_lock = true; retry_snap: - if (direct_lock) - ceph_start_io_direct(inode); - else - ceph_start_io_write(inode); + err = direct_lock ? ceph_start_io_direct(inode) : + ceph_start_io_write(inode); + if (err) + goto out_unlocked; if (iocb->ki_flags & IOCB_APPEND) { err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false); @@ -2878,7 +2878,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off struct ceph_object_id src_oid, dst_oid; struct ceph_osd_client *osdc; struct ceph_osd_request *req; - size_t bytes = 0; + ssize_t bytes = 0; u64 src_objnum, src_objoff, dst_objnum, dst_objoff; u32 src_objlen, dst_objlen; u32 object_size = src_ci->i_layout.object_size; @@ -2928,7 +2928,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off "OSDs don't support copy-from2; disabling copy offload\n"); } doutc(cl, "returned %d\n", ret); - if (!bytes) + if (bytes <= 0) bytes = ret; goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 949f0badc944..a6e260d9e420 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1794,6 +1794,11 @@ retry_lookup: goto done; } + if (unlikely(!in)) { + err = -EINVAL; + goto done; + } + /* attach proper inode */ if (d_really_is_negative(dn)) { ceph_dir_clear_ordered(dir); @@ -1829,6 +1834,12 @@ retry_lookup: doutc(cl, " linking snapped dir %p to dn %p\n", in, req->r_dentry); ceph_dir_clear_ordered(dir); + + if (unlikely(!in)) { + err = -EINVAL; + goto done; + } + ihold(in); err = splice_dentry(&req->r_dentry, in); if (err < 0) diff --git a/fs/ceph/io.c b/fs/ceph/io.c index c456509b31c3..2d10f49c93a9 100644 --- a/fs/ceph/io.c +++ b/fs/ceph/io.c @@ -21,14 +21,23 @@ /* Call with exclusively locked inode->i_rwsem */ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode) { + bool is_odirect; + lockdep_assert_held_write(&inode->i_rwsem); - if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) { - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags &= ~CEPH_I_ODIRECT; - spin_unlock(&ci->i_ceph_lock); - inode_dio_wait(inode); + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + if (is_odirect) { + clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags); + /* ensure modified bit is visible */ + smp_mb__after_atomic(); } + spin_unlock(&ci->i_ceph_lock); + + if (is_odirect) + inode_dio_wait(inode); } /** @@ -47,20 +56,35 @@ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode) * Note that buffered writes and truncates both take a write lock on * inode->i_rwsem, meaning that those are serialised w.r.t. the reads. */ -void -ceph_start_io_read(struct inode *inode) +int ceph_start_io_read(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); + bool is_odirect; + int err; /* Be an optimist! */ - down_read(&inode->i_rwsem); - if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) - return; + err = down_read_killable(&inode->i_rwsem); + if (err) + return err; + + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + spin_unlock(&ci->i_ceph_lock); + if (!is_odirect) + return 0; up_read(&inode->i_rwsem); + /* Slow path.... */ - down_write(&inode->i_rwsem); + err = down_write_killable(&inode->i_rwsem); + if (err) + return err; + ceph_block_o_direct(ci, inode); downgrade_write(&inode->i_rwsem); + + return 0; } /** @@ -83,11 +107,12 @@ ceph_end_io_read(struct inode *inode) * Declare that a buffered write operation is about to start, and ensure * that we block all direct I/O. */ -void -ceph_start_io_write(struct inode *inode) +int ceph_start_io_write(struct inode *inode) { - down_write(&inode->i_rwsem); - ceph_block_o_direct(ceph_inode(inode), inode); + int err = down_write_killable(&inode->i_rwsem); + if (!err) + ceph_block_o_direct(ceph_inode(inode), inode); + return err; } /** @@ -106,12 +131,22 @@ ceph_end_io_write(struct inode *inode) /* Call with exclusively locked inode->i_rwsem */ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode) { + bool is_odirect; + lockdep_assert_held_write(&inode->i_rwsem); - if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) { - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags |= CEPH_I_ODIRECT; - spin_unlock(&ci->i_ceph_lock); + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + if (!is_odirect) { + set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags); + /* ensure modified bit is visible */ + smp_mb__after_atomic(); + } + spin_unlock(&ci->i_ceph_lock); + + if (!is_odirect) { /* FIXME: unmap_mapping_range? */ filemap_write_and_wait(inode->i_mapping); } @@ -133,20 +168,35 @@ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode) * Note that buffered writes and truncates both take a write lock on * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT. */ -void -ceph_start_io_direct(struct inode *inode) +int ceph_start_io_direct(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); + bool is_odirect; + int err; /* Be an optimist! */ - down_read(&inode->i_rwsem); - if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) - return; + err = down_read_killable(&inode->i_rwsem); + if (err) + return err; + + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + spin_unlock(&ci->i_ceph_lock); + if (is_odirect) + return 0; up_read(&inode->i_rwsem); + /* Slow path.... */ - down_write(&inode->i_rwsem); + err = down_write_killable(&inode->i_rwsem); + if (err) + return err; + ceph_block_buffered(ci, inode); downgrade_write(&inode->i_rwsem); + + return 0; } /** diff --git a/fs/ceph/io.h b/fs/ceph/io.h index fa594cd77348..79029825e8b8 100644 --- a/fs/ceph/io.h +++ b/fs/ceph/io.h @@ -2,11 +2,13 @@ #ifndef _FS_CEPH_IO_H #define _FS_CEPH_IO_H -void ceph_start_io_read(struct inode *inode); +#include <linux/compiler_attributes.h> + +int __must_check ceph_start_io_read(struct inode *inode); void ceph_end_io_read(struct inode *inode); -void ceph_start_io_write(struct inode *inode); +int __must_check ceph_start_io_write(struct inode *inode); void ceph_end_io_write(struct inode *inode); -void ceph_start_io_direct(struct inode *inode); +int __must_check ceph_start_io_direct(struct inode *inode); void ceph_end_io_direct(struct inode *inode); #endif /* FS_CEPH_IO_H */ diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index e861de3c79b9..15cde055f3da 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -246,21 +246,28 @@ static long ceph_ioctl_lazyio(struct file *file) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc; struct ceph_client *cl = mdsc->fsc->client; + bool is_file_already_lazy = false; + spin_lock(&ci->i_ceph_lock); if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) { - spin_lock(&ci->i_ceph_lock); fi->fmode |= CEPH_FILE_MODE_LAZY; ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++; __ceph_touch_fmode(ci, mdsc, fi->fmode); - spin_unlock(&ci->i_ceph_lock); + } else { + is_file_already_lazy = true; + } + spin_unlock(&ci->i_ceph_lock); + + if (is_file_already_lazy) { + doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode, + ceph_vinop(inode)); + } else { doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode, ceph_vinop(inode)); ceph_check_caps(ci, 0); - } else { - doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode, - ceph_vinop(inode)); } + return 0; } diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index ebf4ac0055dd..dd764f9c64b9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -221,7 +221,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, if (err && err != -ERESTARTSYS) return err; - wait_for_completion_killable(&req->r_safe_completion); + err = wait_for_completion_killable(&req->r_safe_completion); + if (err) + return err; + return 0; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 73da2648fa0f..1740047aef0f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -979,14 +979,15 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, if (mds >= mdsc->max_sessions) { int newmax = 1 << get_count_order(mds + 1); struct ceph_mds_session **sa; + size_t ptr_size = sizeof(struct ceph_mds_session *); doutc(cl, "realloc to %d\n", newmax); - sa = kcalloc(newmax, sizeof(void *), GFP_NOFS); + sa = kcalloc(newmax, ptr_size, GFP_NOFS); if (!sa) goto fail_realloc; if (mdsc->sessions) { memcpy(sa, mdsc->sessions, - mdsc->max_sessions * sizeof(void *)); + mdsc->max_sessions * ptr_size); kfree(mdsc->sessions); } mdsc->sessions = sa; @@ -2532,6 +2533,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options; size_t size = sizeof(struct ceph_mds_reply_dir_entry); unsigned int num_entries; + u64 bytes_count; int order; spin_lock(&ci->i_ceph_lock); @@ -2540,7 +2542,11 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, num_entries = max(num_entries, 1U); num_entries = min(num_entries, opt->max_readdir); - order = get_order(size * num_entries); + bytes_count = (u64)size * num_entries; + if (unlikely(bytes_count > ULONG_MAX)) + bytes_count = ULONG_MAX; + + order = get_order((unsigned long)bytes_count); while (order >= 0) { rinfo->dir_entries = (void*)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | @@ -2550,7 +2556,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, break; order--; } - if (!rinfo->dir_entries) + if (!rinfo->dir_entries || unlikely(order < 0)) return -ENOMEM; num_entries = (PAGE_SIZE << order) / size; @@ -5649,11 +5655,19 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); struct ceph_client *cl = mdsc->fsc->client; + const char *fs_name = mdsc->fsc->mount_options->mds_namespace; const char *spath = mdsc->fsc->mount_options->server_path; bool gid_matched = false; u32 gid, tlen, len; int i, j; + doutc(cl, "fsname check fs_name=%s match.fs_name=%s\n", + fs_name, auth->match.fs_name ? auth->match.fs_name : ""); + if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) { + /* fsname mismatch, try next one */ + return 0; + } + doutc(cl, "match.uid %lld\n", auth->match.uid); if (auth->match.uid != MDS_AUTH_UID_ANY) { if (auth->match.uid != caller_uid) diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 8109aba66e02..2c7b151a7c95 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -353,10 +353,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { + u32 fsname_len; /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); /* fs_name */ - ceph_decode_skip_string(p, end, bad_ext); + ceph_decode_32_safe(p, end, fsname_len, bad_ext); + + /* validate fsname against mds_namespace */ + if (!namespace_equals(mdsc->fsc->mount_options, *p, + fsname_len)) { + pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n", + (int)fsname_len, (char *)*p, + mdsc->fsc->mount_options->mds_namespace); + goto bad; + } + /* skip fsname after validation */ + ceph_decode_skip_n(p, end, fsname_len, bad); } /* damaged */ if (mdsmap_ev >= 9) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index db6c2db68f96..ad0cf177e75a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -246,20 +246,6 @@ static void canonicalize_path(char *path) path[j] = '\0'; } -/* - * Check if the mds namespace in ceph_mount_options matches - * the passed in namespace string. First time match (when - * ->mds_namespace is NULL) is treated specially, since - * ->mds_namespace needs to be initialized by the caller. - */ -static int namespace_equals(struct ceph_mount_options *fsopt, - const char *namespace, size_t len) -{ - return !(fsopt->mds_namespace && - (strlen(fsopt->mds_namespace) != len || - strncmp(fsopt->mds_namespace, namespace, len))); -} - static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 25d8bacbcf44..a1f781c46b41 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -104,6 +104,20 @@ struct ceph_mount_options { struct fscrypt_dummy_policy dummy_enc_policy; }; +/* + * Check if the mds namespace in ceph_mount_options matches + * the passed in namespace string. First time match (when + * ->mds_namespace is NULL) is treated specially, since + * ->mds_namespace needs to be initialized by the caller. + */ +static inline int namespace_equals(struct ceph_mount_options *fsopt, + const char *namespace, size_t len) +{ + return !(fsopt->mds_namespace && + (strlen(fsopt->mds_namespace) != len || + strncmp(fsopt->mds_namespace, namespace, len))); +} + /* mount state */ enum { CEPH_MOUNT_MOUNTING, @@ -639,7 +653,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */ #define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */ #define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */ -#define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ +#define CEPH_I_ODIRECT_BIT (11) /* inode in direct I/O mode */ +#define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) #define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) #define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ diff --git a/fs/hpfs/anode.c b/fs/hpfs/anode.c index c14c9a035ee0..a4f5321eafae 100644 --- a/fs/hpfs/anode.c +++ b/fs/hpfs/anode.c @@ -27,7 +27,7 @@ secno hpfs_bplus_lookup(struct super_block *s, struct inode *inode, a = le32_to_cpu(btree->u.internal[i].down); brelse(bh); if (!(anode = hpfs_map_anode(s, a, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); goto go_down; } hpfs_error(s, "sector %08x not found in internal anode %08x", sec, a); @@ -69,12 +69,13 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi int n; unsigned fs; int c1, c2 = 0; + if (fnod) { if (!(fnode = hpfs_map_fnode(s, node, &bh))) return -1; - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } else { if (!(anode = hpfs_map_anode(s, node, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } a = node; go_down: @@ -91,7 +92,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi if (hpfs_sb(s)->sb_chk) if (hpfs_stop_cycles(s, a, &c1, &c2, "hpfs_add_sector_to_btree #1")) return -1; if (!(anode = hpfs_map_anode(s, a, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); goto go_down; } if (n >= 0) { @@ -151,7 +152,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi } brelse(bh); bh = bh1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } btree->n_free_nodes--; n = btree->n_used_nodes++; le16_add_cpu(&btree->first_free, 12); @@ -168,10 +169,10 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi if (hpfs_stop_cycles(s, up, &c1, &c2, "hpfs_add_sector_to_btree #2")) return -1; if (up != node || !fnod) { if (!(anode = hpfs_map_anode(s, up, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } else { if (!(fnode = hpfs_map_fnode(s, up, &bh))) return -1; - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } if (btree->n_free_nodes) { btree->n_free_nodes--; n = btree->n_used_nodes++; @@ -206,8 +207,8 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi anode->btree.n_used_nodes = 1; anode->btree.n_free_nodes = 59; anode->btree.first_free = cpu_to_le16(16); - anode->btree.u.internal[0].down = cpu_to_le32(a); - anode->btree.u.internal[0].file_secno = cpu_to_le32(-1); + GET_BTREE_PTR(&anode->btree)->u.internal[0].down = cpu_to_le32(a); + GET_BTREE_PTR(&anode->btree)->u.internal[0].file_secno = cpu_to_le32(-1); mark_buffer_dirty(bh); brelse(bh); if ((anode = hpfs_map_anode(s, a, &bh))) { @@ -229,20 +230,20 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi brelse(bh2); return -1; } - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } else { if (!(fnode = hpfs_map_fnode(s, node, &bh))) { brelse(bh2); return -1; } - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } ranode->up = cpu_to_le32(node); memcpy(&ranode->btree, btree, le16_to_cpu(btree->first_free)); if (fnod) ranode->btree.flags |= BP_fnode_parent; - ranode->btree.n_free_nodes = (bp_internal(&ranode->btree) ? 60 : 40) - ranode->btree.n_used_nodes; - if (bp_internal(&ranode->btree)) for (n = 0; n < ranode->btree.n_used_nodes; n++) { + GET_BTREE_PTR(&ranode->btree)->n_free_nodes = (bp_internal(GET_BTREE_PTR(&ranode->btree)) ? 60 : 40) - GET_BTREE_PTR(&ranode->btree)->n_used_nodes; + if (bp_internal(GET_BTREE_PTR(&ranode->btree))) for (n = 0; n < GET_BTREE_PTR(&ranode->btree)->n_used_nodes; n++) { struct anode *unode; if ((unode = hpfs_map_anode(s, le32_to_cpu(ranode->u.internal[n].down), &bh1))) { unode->up = cpu_to_le32(ra); @@ -291,7 +292,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree) if (hpfs_stop_cycles(s, ano, &d1, &d2, "hpfs_remove_btree #1")) return; if (!(anode = hpfs_map_anode(s, ano, &bh))) return; - btree1 = &anode->btree; + btree1 = GET_BTREE_PTR(&anode->btree); level++; pos = 0; } @@ -307,7 +308,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree) ano = le32_to_cpu(anode->up); if (--level) { if (!(anode = hpfs_map_anode(s, ano, &bh))) return; - btree1 = &anode->btree; + btree1 = GET_BTREE_PTR(&anode->btree); } else btree1 = btree; for (i = 0; i < btree1->n_used_nodes; i++) { if (le32_to_cpu(btree1->u.internal[i].down) == oano) { @@ -332,7 +333,7 @@ static secno anode_lookup(struct super_block *s, anode_secno a, unsigned sec) struct anode *anode; struct buffer_head *bh; if (!(anode = hpfs_map_anode(s, a, &bh))) return -1; - return hpfs_bplus_lookup(s, NULL, &anode->btree, sec, bh); + return hpfs_bplus_lookup(s, NULL, GET_BTREE_PTR(&anode->btree), sec, bh); } int hpfs_ea_read(struct super_block *s, secno a, int ano, unsigned pos, @@ -388,7 +389,7 @@ void hpfs_ea_remove(struct super_block *s, secno a, int ano, unsigned len) struct buffer_head *bh; if (ano) { if (!(anode = hpfs_map_anode(s, a, &bh))) return; - hpfs_remove_btree(s, &anode->btree); + hpfs_remove_btree(s, GET_BTREE_PTR(&anode->btree)); brelse(bh); hpfs_free_sectors(s, a, 1); } else hpfs_free_sectors(s, a, (len + 511) >> 9); @@ -407,10 +408,10 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs) int c1, c2 = 0; if (fno) { if (!(fnode = hpfs_map_fnode(s, f, &bh))) return; - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } else { if (!(anode = hpfs_map_anode(s, f, &bh))) return; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } if (!secs) { hpfs_remove_btree(s, btree); @@ -448,7 +449,7 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs) if (hpfs_stop_cycles(s, node, &c1, &c2, "hpfs_truncate_btree")) return; if (!(anode = hpfs_map_anode(s, node, &bh))) return; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } nodes = btree->n_used_nodes + btree->n_free_nodes; for (i = 0; i < btree->n_used_nodes; i++) @@ -485,7 +486,7 @@ void hpfs_remove_fnode(struct super_block *s, fnode_secno fno) struct extended_attribute *ea; struct extended_attribute *ea_end; if (!(fnode = hpfs_map_fnode(s, fno, &bh))) return; - if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, &fnode->btree); + if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, GET_BTREE_PTR(&fnode->btree)); else hpfs_remove_dtree(s, le32_to_cpu(fnode->u.external[0].disk_secno)); ea_end = fnode_end_ea(fnode); for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea)) diff --git a/fs/hpfs/ea.c b/fs/hpfs/ea.c index 102ba18e561f..2149d3ca530b 100644 --- a/fs/hpfs/ea.c +++ b/fs/hpfs/ea.c @@ -41,7 +41,7 @@ void hpfs_ea_ext_remove(struct super_block *s, secno a, int ano, unsigned len) struct buffer_head *bh; struct anode *anode; if ((anode = hpfs_map_anode(s, a, &bh))) { - hpfs_remove_btree(s, &anode->btree); + hpfs_remove_btree(s, GET_BTREE_PTR(&anode->btree)); brelse(bh); hpfs_free_sectors(s, a, 1); } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 263b5bbe1849..29e876705369 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -51,7 +51,9 @@ static secno hpfs_bmap(struct inode *inode, unsigned file_secno, unsigned *n_sec return hpfs_inode->i_disk_sec + n; } if (!(fnode = hpfs_map_fnode(inode->i_sb, inode->i_ino, &bh))) return 0; - disk_secno = hpfs_bplus_lookup(inode->i_sb, inode, &fnode->btree, file_secno, bh); + disk_secno = hpfs_bplus_lookup(inode->i_sb, inode, + GET_BTREE_PTR(&fnode->btree), + file_secno, bh); if (disk_secno == -1) return 0; if (hpfs_chk_sectors(inode->i_sb, disk_secno, 1, "bmap")) return 0; n = file_secno - hpfs_inode->i_file_sec; diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h index 281dec8f636b..353f73c914d9 100644 --- a/fs/hpfs/hpfs.h +++ b/fs/hpfs/hpfs.h @@ -394,27 +394,45 @@ enum { BP_binary_search = 0x40, BP_internal = 0x80 }; + +/** + * GET_BTREE_PTR() - Get a pointer to struct bplus_header + * + * Wrapper around container_of() to retrieve a pointer to struct + * bplus_header from a pointer to struct bplus_header_fixed. + * + * @ptr: Pointer to struct bplus_header_fixed. + * + */ +#define GET_BTREE_PTR(ptr) \ + container_of(ptr, struct bplus_header, __hdr) + struct bplus_header { - u8 flags; /* bit 0 - high bit of first free entry offset + /* New members MUST be added within the struct_group() macro below. */ + struct_group_tagged(bplus_header_fixed, __hdr, + u8 flags; /* bit 0 - high bit of first free entry offset bit 5 - we're pointed to by an fnode, the data btree or some ea or the main ea bootage pointer ea_secno bit 6 - suggest binary search (unused) bit 7 - 1 -> (internal) tree of anodes 0 -> (leaf) list of extents */ - u8 fill[3]; - u8 n_free_nodes; /* free nodes in following array */ - u8 n_used_nodes; /* used nodes in following array */ - __le16 first_free; /* offset from start of header to + u8 fill[3]; + u8 n_free_nodes; /* free nodes in following array */ + u8 n_used_nodes; /* used nodes in following array */ + __le16 first_free; /* offset from start of header to first free node in array */ - union { - /* (internal) 2-word entries giving subtree pointers */ - DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal); - /* (external) 3-word entries giving sector runs */ - DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external); - } u; + ); + union { + /* (internal) 2-word entries giving subtree pointers */ + DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal); + /* (external) 3-word entries giving sector runs */ + DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external); + } u; }; +static_assert(offsetof(struct bplus_header, u.internal) == sizeof(struct bplus_header_fixed), + "struct member likely outside of struct_group_tagged()"); static inline bool bp_internal(struct bplus_header *bp) { @@ -453,7 +471,7 @@ struct fnode __le16 flags; /* bit 1 set -> ea_secno is an anode */ /* bit 8 set -> directory. first & only extent points to dnode. */ - struct bplus_header btree; /* b+ tree, 8 extents or 12 subtrees */ + struct bplus_header_fixed btree; /* b+ tree, 8 extents or 12 subtrees */ union { struct bplus_leaf_node external[8]; struct bplus_internal_node internal[12]; @@ -495,7 +513,7 @@ struct anode __le32 self; /* pointer to this anode */ __le32 up; /* parent anode or fnode */ - struct bplus_header btree; /* b+tree, 40 extents or 60 subtrees */ + struct bplus_header_fixed btree; /* b+tree, 40 extents or 60 subtrees */ union { struct bplus_leaf_node external[40]; struct bplus_internal_node internal[60]; diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index ecd9fccd1663..be73233502f8 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -178,14 +178,14 @@ struct fnode *hpfs_map_fnode(struct super_block *s, ino_t ino, struct buffer_hea } if (!fnode_is_dir(fnode)) { if ((unsigned)fnode->btree.n_used_nodes + (unsigned)fnode->btree.n_free_nodes != - (bp_internal(&fnode->btree) ? 12 : 8)) { + (bp_internal(GET_BTREE_PTR(&fnode->btree)) ? 12 : 8)) { hpfs_error(s, "bad number of nodes in fnode %08lx", (unsigned long)ino); goto bail; } if (le16_to_cpu(fnode->btree.first_free) != - 8 + fnode->btree.n_used_nodes * (bp_internal(&fnode->btree) ? 8 : 12)) { + 8 + fnode->btree.n_used_nodes * (bp_internal(GET_BTREE_PTR(&fnode->btree)) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in fnode %08lx", (unsigned long)ino); @@ -233,12 +233,12 @@ struct anode *hpfs_map_anode(struct super_block *s, anode_secno ano, struct buff goto bail; } if ((unsigned)anode->btree.n_used_nodes + (unsigned)anode->btree.n_free_nodes != - (bp_internal(&anode->btree) ? 60 : 40)) { + (bp_internal(GET_BTREE_PTR(&anode->btree)) ? 60 : 40)) { hpfs_error(s, "bad number of nodes in anode %08x", ano); goto bail; } if (le16_to_cpu(anode->btree.first_free) != - 8 + anode->btree.n_used_nodes * (bp_internal(&anode->btree) ? 8 : 12)) { + 8 + anode->btree.n_used_nodes * (bp_internal(GET_BTREE_PTR(&anode->btree)) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in anode %08x", ano); goto bail; } diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index e3cdc421dfba..353e13a615f5 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -52,8 +52,10 @@ static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, dee.fnode = cpu_to_le32(fno); dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail2; + } hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; @@ -153,9 +155,10 @@ static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; - + } hpfs_init_inode(result); result->i_ino = fno; result->i_mode |= S_IFREG; @@ -239,9 +242,10 @@ static int hpfs_mknod(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; - + } hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; @@ -314,8 +318,10 @@ static int hpfs_symlink(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; + } result->i_ino = fno; hpfs_init_inode(result); hpfs_i(result)->i_parent_dir = dir->i_ino; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 42b779b4d87f..8ab85e7ac91e 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -404,15 +404,11 @@ static int hpfs_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_timeshift: { - int m = 1; char *rhs = param->string; int timeshift; - if (*rhs == '-') m = -1; - if (*rhs == '+' || *rhs == '-') rhs++; - timeshift = simple_strtoul(rhs, &rhs, 0) * m; - if (*rhs) - return -EINVAL; + if (kstrtoint(rhs, 0, ×hift)) + return -EINVAL; ctx->timeshift = timeshift; break; } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 9802b2cc29bb..5d5d63efbd57 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -433,7 +433,8 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; - ret = bio_iov_iter_get_bdev_pages(bio, dio->submit.iter, iomap->bdev); + ret = bio_iov_iter_get_pages(bio, dio->submit.iter, + bdev_logical_block_size(iomap->bdev) - 1); if (unlikely(ret)) { /* * We have to stop part way through an IO. We must fall diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index b36f9f9340f0..b8ac7b7faf61 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -562,8 +562,8 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) /* * Mark all the cfids as closed, and move them to the cfids->dying list. - * They'll be cleaned up later by cfids_invalidation_worker. Take - * a reference to each cfid during this process. + * They'll be cleaned up by laundromat. Take a reference to each cfid + * during this process. */ spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { @@ -580,12 +580,11 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) } else kref_get(&cfid->refcount); } - /* - * Queue dropping of the dentries once locks have been dropped - */ - if (!list_empty(&cfids->dying)) - queue_work(cfid_put_wq, &cfids->invalidation_work); spin_unlock(&cfids->cfid_list_lock); + + /* run laundromat unconditionally now as there might have been previously queued work */ + mod_delayed_work(cfid_put_wq, &cfids->laundromat_work, 0); + flush_delayed_work(&cfids->laundromat_work); } static void @@ -715,25 +714,6 @@ static void free_cached_dir(struct cached_fid *cfid) kfree(cfid); } -static void cfids_invalidation_worker(struct work_struct *work) -{ - struct cached_fids *cfids = container_of(work, struct cached_fids, - invalidation_work); - struct cached_fid *cfid, *q; - LIST_HEAD(entry); - - spin_lock(&cfids->cfid_list_lock); - /* move cfids->dying to the local list */ - list_cut_before(&entry, &cfids->dying, &cfids->dying); - spin_unlock(&cfids->cfid_list_lock); - - list_for_each_entry_safe(cfid, q, &entry, entry) { - list_del(&cfid->entry); - /* Drop the ref-count acquired in invalidate_all_cached_dirs */ - kref_put(&cfid->refcount, smb2_close_cached_fid); - } -} - static void cfids_laundromat_worker(struct work_struct *work) { struct cached_fids *cfids; @@ -743,6 +723,9 @@ static void cfids_laundromat_worker(struct work_struct *work) cfids = container_of(work, struct cached_fids, laundromat_work.work); spin_lock(&cfids->cfid_list_lock); + /* move cfids->dying to the local list */ + list_cut_before(&entry, &cfids->dying, &cfids->dying); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { if (cfid->last_access_time && time_after(jiffies, cfid->last_access_time + HZ * dir_cache_timeout)) { @@ -796,7 +779,6 @@ struct cached_fids *init_cached_dirs(void) INIT_LIST_HEAD(&cfids->entries); INIT_LIST_HEAD(&cfids->dying); - INIT_WORK(&cfids->invalidation_work, cfids_invalidation_worker); INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker); queue_delayed_work(cfid_put_wq, &cfids->laundromat_work, dir_cache_timeout * HZ); @@ -820,7 +802,6 @@ void free_cached_dirs(struct cached_fids *cfids) return; cancel_delayed_work_sync(&cfids->laundromat_work); - cancel_work_sync(&cfids->invalidation_work); spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h index 31339dc32719..1e383db7c337 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -62,7 +62,6 @@ struct cached_fids { int num_entries; struct list_head entries; struct list_head dying; - struct work_struct invalidation_work; struct delayed_work laundromat_work; /* aggregate accounting for all cached dirents under this tcon */ atomic_long_t total_dirents_entries; diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 43b86fa4d695..9891f55bac1e 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -24,20 +24,14 @@ static const struct cred *spnego_cred; static int cifs_spnego_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { - char *payload; - int ret; + char *payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL); - ret = -ENOMEM; - payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL); if (!payload) - goto error; + return -ENOMEM; /* attach the data */ key->payload.data[0] = payload; - ret = 0; - -error: - return ret; + return 0; } static void diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c index 7233c6a7e6d7..68a1f87c446d 100644 --- a/fs/smb/client/cifs_swn.c +++ b/fs/smb/client/cifs_swn.c @@ -82,10 +82,8 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg) int ret; skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb == NULL) { - ret = -ENOMEM; - goto fail; - } + if (!skb) + return -ENOMEM; hdr = genlmsg_put(skb, 0, 0, &cifs_genl_family, 0, CIFS_GENL_CMD_SWN_REGISTER); if (hdr == NULL) { @@ -172,7 +170,6 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg) nlmsg_fail: genlmsg_cancel(skb, hdr); nlmsg_free(skb); -fail: return ret; } @@ -313,17 +310,15 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) reg = cifs_find_swn_reg(tcon); if (!IS_ERR(reg)) { kref_get(®->ref_count); - mutex_unlock(&cifs_swnreg_idr_mutex); - return reg; + goto unlock; } else if (PTR_ERR(reg) != -EEXIST) { - mutex_unlock(&cifs_swnreg_idr_mutex); - return reg; + goto unlock; } reg = kmalloc(sizeof(struct cifs_swn_reg), GFP_ATOMIC); if (reg == NULL) { - mutex_unlock(&cifs_swnreg_idr_mutex); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto fail_unlock; } kref_init(®->ref_count); @@ -354,7 +349,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT); reg->tcon = tcon; - +unlock: mutex_unlock(&cifs_swnreg_idr_mutex); return reg; @@ -365,6 +360,7 @@ fail_idr: idr_remove(&cifs_swnreg_idr, reg->id); fail: kfree(reg); +fail_unlock: mutex_unlock(&cifs_swnreg_idr_mutex); return ERR_PTR(ret); } diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 1775c2b7528f..05b1fa76e8cc 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -392,11 +392,27 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct TCP_Server_Info *server = tcon->ses->server; + struct inode *inode = file_inode(file); + int rc; + + if (!server->ops->fallocate) + return -EOPNOTSUPP; + + rc = inode_lock_killable(inode); + if (rc) + return rc; + + netfs_wait_for_outstanding_io(inode); - if (server->ops->fallocate) - return server->ops->fallocate(file, tcon, mode, off, len); + rc = file_modified(file); + if (rc) + goto out_unlock; + + rc = server->ops->fallocate(file, tcon, mode, off, len); - return -EOPNOTSUPP; +out_unlock: + inode_unlock(inode); + return rc; } static int cifs_permission(struct mnt_idmap *idmap, diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 3ce7c614ccc0..e9534258d1ef 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -145,6 +145,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 56 -#define CIFS_VERSION "2.56" +#define SMB3_PRODUCT_BUILD 57 +#define CIFS_VERSION "2.57" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 3ac254e123dc..8f6f567d7474 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1566,6 +1566,11 @@ struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr, bool offload); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); +int cifs_file_flush(const unsigned int xid, struct inode *inode, + struct cifsFileInfo *cfile); +int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, + const char *full_path, struct cifsFileInfo *open_file, + loff_t size); #define CIFS_CACHE_READ_FLG 1 #define CIFS_CACHE_HANDLE_FLG 2 diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index d20766f664c4..2881efcbe09a 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1163,7 +1163,7 @@ OldOpenRetry: cpu_to_le64(le32_to_cpu(pSMBr->EndOfFile)); pfile_info->EndOfFile = pfile_info->AllocationSize; pfile_info->NumberOfLinks = cpu_to_le32(1); - pfile_info->DeletePending = 0; + pfile_info->DeletePending = 0; /* successful open = not delete pending */ } } @@ -1288,7 +1288,7 @@ openRetry: buf->AllocationSize = rsp->AllocationSize; buf->EndOfFile = rsp->EndOfFile; buf->NumberOfLinks = cpu_to_le32(1); - buf->DeletePending = 0; + buf->DeletePending = 0; /* successful open = not delete pending */ } cifs_buf_release(req); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index fc67a6441c96..da5597dbf5b9 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -200,8 +200,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { - free_dentry_path(page); - return PTR_ERR(full_path); + rc = PTR_ERR(full_path); + goto out; } /* If we're caching, we need to be able to fill in around partial writes. */ @@ -678,7 +678,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, const char *full_path; void *page; int retry_count = 0; - struct cached_fid *cfid = NULL; + struct dentry *de; xid = get_xid(); @@ -690,16 +690,15 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, cifs_sb = CIFS_SB(parent_dir_inode->i_sb); tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { - free_xid(xid); - return ERR_CAST(tlink); + de = ERR_CAST(tlink); + goto free_xid; } pTcon = tlink_tcon(tlink); rc = check_name(direntry, pTcon); if (unlikely(rc)) { - cifs_put_tlink(tlink); - free_xid(xid); - return ERR_PTR(rc); + de = ERR_PTR(rc); + goto put_tlink; } /* can not grab the rename sem here since it would @@ -708,15 +707,15 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, page = alloc_dentry_path(); full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { - cifs_put_tlink(tlink); - free_xid(xid); - free_dentry_path(page); - return ERR_CAST(full_path); + de = ERR_CAST(full_path); + goto free_dentry_path; } if (d_really_is_positive(direntry)) { cifs_dbg(FYI, "non-NULL inode in lookup\n"); } else { + struct cached_fid *cfid = NULL; + cifs_dbg(FYI, "NULL inode in lookup\n"); /* @@ -775,25 +774,27 @@ again: } out: + de = d_splice_alias(newInode, direntry); +free_dentry_path: free_dentry_path(page); +put_tlink: cifs_put_tlink(tlink); +free_xid: free_xid(xid); - return d_splice_alias(newInode, direntry); + return de; } static int cifs_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *direntry, unsigned int flags) { - struct inode *inode = NULL; - struct cached_fid *cfid; - int rc; - if (flags & LOOKUP_RCU) return -ECHILD; if (d_really_is_positive(direntry)) { - inode = d_inode(direntry); + int rc; + struct inode *inode = d_inode(direntry); + if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) CIFS_I(inode)->time = 0; /* force reval */ @@ -836,6 +837,7 @@ cifs_d_revalidate(struct inode *dir, const struct qstr *name, } else { struct cifs_sb_info *cifs_sb = CIFS_SB(dir->i_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + struct cached_fid *cfid; if (!open_cached_dir_by_dentry(tcon, direntry->d_parent, &cfid)) { /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a5ed742afa00..474dadeb1593 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -952,6 +952,66 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, } } +int cifs_file_flush(const unsigned int xid, struct inode *inode, + struct cifsFileInfo *cfile) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_tcon *tcon; + int rc; + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC) + return 0; + + if (cfile && (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE)) { + tcon = tlink_tcon(cfile->tlink); + return tcon->ses->server->ops->flush(xid, tcon, + &cfile->fid); + } + rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); + if (!rc) { + tcon = tlink_tcon(cfile->tlink); + rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid); + cifsFileInfo_put(cfile); + } else if (rc == -EBADF) { + rc = 0; + } + return rc; +} + +static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) +{ + struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry)); + struct inode *inode = d_inode(dentry); + struct cifsFileInfo *cfile = NULL; + struct TCP_Server_Info *server; + struct cifs_tcon *tcon; + int rc; + + rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) + return -ERESTARTSYS; + mapping_set_error(inode->i_mapping, rc); + + cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY); + rc = cifs_file_flush(xid, inode, cfile); + if (!rc) { + if (cfile) { + tcon = tlink_tcon(cfile->tlink); + server = tcon->ses->server; + rc = server->ops->set_file_size(xid, tcon, + cfile, 0, false); + } + if (!rc) { + netfs_resize_file(&cinode->netfs, 0, true); + cifs_setsize(inode, 0); + inode->i_blocks = 0; + } + } + if (cfile) + cifsFileInfo_put(cfile); + return rc; +} + int cifs_open(struct inode *inode, struct file *file) { @@ -1004,6 +1064,12 @@ int cifs_open(struct inode *inode, struct file *file) file->f_op = &cifs_file_direct_ops; } + if (file->f_flags & O_TRUNC) { + rc = cifs_do_truncate(xid, file_dentry(file)); + if (rc) + goto out; + } + /* Get the cached handle as SMB2 close is deferred */ if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { rc = cifs_get_writable_path(tcon, full_path, @@ -2685,13 +2751,10 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - unsigned int xid; - int rc = 0; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; struct inode *inode = file_inode(file); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + unsigned int xid; + int rc; rc = file_write_and_wait_range(file, start, end); if (rc) { @@ -2699,39 +2762,15 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, return rc; } - xid = get_xid(); - - cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n", - file, datasync); + cifs_dbg(FYI, "%s: name=%pD datasync=0x%x\n", __func__, file, datasync); if (!CIFS_CACHE_READ(CIFS_I(inode))) { rc = cifs_zap_mapping(inode); - if (rc) { - cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc); - rc = 0; /* don't care about it in fsync */ - } + cifs_dbg(FYI, "%s: invalidate mapping: rc = %d\n", __func__, rc); } - tcon = tlink_tcon(smbfile->tlink); - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { - server = tcon->ses->server; - if (server->ops->flush == NULL) { - rc = -ENOSYS; - goto strict_fsync_exit; - } - - if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { - smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); - if (smbfile) { - rc = server->ops->flush(xid, tcon, &smbfile->fid); - cifsFileInfo_put(smbfile); - } else - cifs_dbg(FYI, "ignore fsync for file not open for write\n"); - } else - rc = server->ops->flush(xid, tcon, &smbfile->fid); - } - -strict_fsync_exit: + xid = get_xid(); + rc = cifs_file_flush(xid, inode, smbfile); free_xid(xid); return rc; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 8bb544be401e..239dd84a336f 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3007,28 +3007,25 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, void cifs_setsize(struct inode *inode, loff_t offset) { - struct cifsInodeInfo *cifs_i = CIFS_I(inode); - spin_lock(&inode->i_lock); i_size_write(inode, offset); spin_unlock(&inode->i_lock); - - /* Cached inode must be refreshed on truncate */ - cifs_i->time = 0; + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); truncate_pagecache(inode, offset); + netfs_wait_for_outstanding_io(inode); } -static int -cifs_set_file_size(struct inode *inode, struct iattr *attrs, - unsigned int xid, const char *full_path, struct dentry *dentry) +int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, + const char *full_path, struct cifsFileInfo *open_file, + loff_t size) { - int rc; - struct cifsFileInfo *open_file; - struct cifsInodeInfo *cifsInode = CIFS_I(inode); + struct inode *inode = d_inode(dentry); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct tcon_link *tlink = NULL; struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; + int rc = -EINVAL; /* * To avoid spurious oplock breaks from server, in the case of @@ -3039,19 +3036,25 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, * writebehind data than the SMB timeout for the SetPathInfo * request would allow */ - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); - if (open_file) { + if (open_file && (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE)) { tcon = tlink_tcon(open_file->tlink); server = tcon->ses->server; - if (server->ops->set_file_size) - rc = server->ops->set_file_size(xid, tcon, open_file, - attrs->ia_size, false); - else - rc = -ENOSYS; - cifsFileInfo_put(open_file); - cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc); - } else - rc = -EINVAL; + rc = server->ops->set_file_size(xid, tcon, + open_file, + size, false); + cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); + } else { + open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + if (open_file) { + tcon = tlink_tcon(open_file->tlink); + server = tcon->ses->server; + rc = server->ops->set_file_size(xid, tcon, + open_file, + size, false); + cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); + cifsFileInfo_put(open_file); + } + } if (!rc) goto set_size_out; @@ -3069,20 +3072,15 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, * valid, writeable file handle for it was found or because there was * an error setting it by handle. */ - if (server->ops->set_path_size) - rc = server->ops->set_path_size(xid, tcon, full_path, - attrs->ia_size, cifs_sb, false, dentry); - else - rc = -ENOSYS; - cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); - - if (tlink) - cifs_put_tlink(tlink); + rc = server->ops->set_path_size(xid, tcon, full_path, size, + cifs_sb, false, dentry); + cifs_dbg(FYI, "%s: SetEOF by path (setattrs) rc = %d\n", __func__, rc); + cifs_put_tlink(tlink); set_size_out: if (rc == 0) { - netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true); - cifs_setsize(inode, attrs->ia_size); + netfs_resize_file(&cifsInode->netfs, size, true); + cifs_setsize(inode, size); /* * i_blocks is not related to (i_size / i_blksize), but instead * 512 byte (2**9) size is required for calculating num blocks. @@ -3090,15 +3088,7 @@ set_size_out: * this is best estimate we have for blocks allocated for a file * Number of blocks must be rounded up so size 1 is not 0 blocks */ - inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9; - - /* - * The man page of truncate says if the size changed, - * then the st_ctime and st_mtime fields for the file - * are updated. - */ - attrs->ia_ctime = attrs->ia_mtime = current_time(inode); - attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME; + inode->i_blocks = (512 - 1 + size) >> 9; } return rc; @@ -3118,7 +3108,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) struct tcon_link *tlink; struct cifs_tcon *pTcon; struct cifs_unix_set_info_args *args = NULL; - struct cifsFileInfo *open_file; + struct cifsFileInfo *open_file = NULL; cifs_dbg(FYI, "setattr_unix on file %pd attrs->ia_valid=0x%x\n", direntry, attrs->ia_valid); @@ -3132,6 +3122,9 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if (rc < 0) goto out; + if (attrs->ia_valid & ATTR_FILE) + open_file = attrs->ia_file->private_data; + full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { rc = PTR_ERR(full_path); @@ -3159,9 +3152,16 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) rc = 0; if (attrs->ia_valid & ATTR_SIZE) { - rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry); + rc = cifs_file_set_size(xid, direntry, full_path, + open_file, attrs->ia_size); if (rc != 0) goto out; + /* + * Avoid setting timestamps on the server for ftruncate(2) to + * prevent it from disabling automatic timestamp updates as per + * MS-FSA 2.1.4.17. + */ + attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME); } /* skip mode change if it's just for clearing setuid/setgid */ @@ -3206,14 +3206,24 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) args->ctime = NO_CHANGE_64; args->device = 0; - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); - if (open_file) { - u16 nfid = open_file->fid.netfid; - u32 npid = open_file->pid; + rc = -EINVAL; + if (open_file && (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE)) { pTcon = tlink_tcon(open_file->tlink); - rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, nfid, npid); - cifsFileInfo_put(open_file); + rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, + open_file->fid.netfid, + open_file->pid); } else { + open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + if (open_file) { + pTcon = tlink_tcon(open_file->tlink); + rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, + open_file->fid.netfid, + open_file->pid); + cifsFileInfo_put(open_file); + } + } + + if (rc) { tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { rc = PTR_ERR(tlink); @@ -3221,8 +3231,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) } pTcon = tlink_tcon(tlink); rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); + cifs_sb->local_nls, + cifs_remap(cifs_sb)); cifs_put_tlink(tlink); } @@ -3264,8 +3274,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) struct inode *inode = d_inode(direntry); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cifsInode = CIFS_I(inode); - struct cifsFileInfo *wfile; - struct cifs_tcon *tcon; + struct cifsFileInfo *cfile = NULL; const char *full_path; void *page = alloc_dentry_path(); int rc = -EACCES; @@ -3285,6 +3294,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (rc < 0) goto cifs_setattr_exit; + if (attrs->ia_valid & ATTR_FILE) + cfile = attrs->ia_file->private_data; + full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { rc = PTR_ERR(full_path); @@ -3311,25 +3323,23 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) rc = 0; - if ((attrs->ia_valid & ATTR_MTIME) && - !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { - rc = cifs_get_writable_file(cifsInode, FIND_WR_ANY, &wfile); - if (!rc) { - tcon = tlink_tcon(wfile->tlink); - rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); - cifsFileInfo_put(wfile); - if (rc) - goto cifs_setattr_exit; - } else if (rc != -EBADF) + if (attrs->ia_valid & ATTR_MTIME) { + rc = cifs_file_flush(xid, inode, cfile); + if (rc) goto cifs_setattr_exit; - else - rc = 0; } if (attrs->ia_valid & ATTR_SIZE) { - rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry); + rc = cifs_file_set_size(xid, direntry, full_path, + cfile, attrs->ia_size); if (rc != 0) goto cifs_setattr_exit; + /* + * Avoid setting timestamps on the server for ftruncate(2) to + * prevent it from disabling automatic timestamp updates as per + * MS-FSA 2.1.4.17. + */ + attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME); } if (attrs->ia_valid & ATTR_UID) @@ -3459,6 +3469,13 @@ cifs_setattr(struct mnt_idmap *idmap, struct dentry *direntry, if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; + /* + * Avoid setting [cm]time with O_TRUNC to prevent the server from + * disabling automatic timestamp updates as specified in + * MS-FSA 2.1.4.17. + */ + if (attrs->ia_valid & ATTR_OPEN) + return 0; do { #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index a02d41d1ce4a..ca8f3dd7ff63 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -652,13 +652,71 @@ static int cifs_query_path_info(const unsigned int xid, #ifdef CONFIG_CIFS_XATTR /* + * For non-symlink WSL reparse points it is required to fetch + * EA $LXMOD which contains in its S_DT part the mandatory file type. + */ + if (!rc && data->reparse_point) { + struct smb2_file_full_ea_info *ea; + u32 next = 0; + + ea = (struct smb2_file_full_ea_info *)data->wsl.eas; + do { + ea = (void *)((u8 *)ea + next); + next = le32_to_cpu(ea->next_entry_offset); + } while (next); + if (le16_to_cpu(ea->ea_value_length)) { + ea->next_entry_offset = cpu_to_le32(ALIGN(sizeof(*ea) + + ea->ea_name_length + 1 + + le16_to_cpu(ea->ea_value_length), 4)); + ea = (void *)((u8 *)ea + le32_to_cpu(ea->next_entry_offset)); + } + + rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_MODE, + &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1], + SMB2_WSL_XATTR_MODE_SIZE, cifs_sb); + if (rc == SMB2_WSL_XATTR_MODE_SIZE) { + ea->next_entry_offset = cpu_to_le32(0); + ea->flags = 0; + ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN; + ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_MODE_SIZE); + memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_MODE, SMB2_WSL_XATTR_NAME_LEN + 1); + data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + + SMB2_WSL_XATTR_MODE_SIZE, 4); + rc = 0; + } else if (rc >= 0) { + /* It is an error if EA $LXMOD has wrong size. */ + rc = -EINVAL; + } else { + /* + * In all other cases ignore error if fetching + * of EA $LXMOD failed. It is needed only for + * non-symlink WSL reparse points and wsl_to_fattr() + * handle the case when EA is missing. + */ + rc = 0; + } + } + + /* * For WSL CHR and BLK reparse points it is required to fetch * EA $LXDEV which contains major and minor device numbers. */ if (!rc && data->reparse_point) { struct smb2_file_full_ea_info *ea; + u32 next = 0; ea = (struct smb2_file_full_ea_info *)data->wsl.eas; + do { + ea = (void *)((u8 *)ea + next); + next = le32_to_cpu(ea->next_entry_offset); + } while (next); + if (le16_to_cpu(ea->ea_value_length)) { + ea->next_entry_offset = cpu_to_le32(ALIGN(sizeof(*ea) + + ea->ea_name_length + 1 + + le16_to_cpu(ea->ea_value_length), 4)); + ea = (void *)((u8 *)ea + le32_to_cpu(ea->next_entry_offset)); + } + rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_DEV, &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1], SMB2_WSL_XATTR_DEV_SIZE, cifs_sb); @@ -668,8 +726,8 @@ static int cifs_query_path_info(const unsigned int xid, ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN; ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE); memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1); - data->wsl.eas_len = sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + - SMB2_WSL_XATTR_DEV_SIZE; + data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + + SMB2_WSL_XATTR_MODE_SIZE, 4); rc = 0; } else if (rc >= 0) { /* It is an error if EA $LXDEV has wrong size. */ @@ -818,6 +876,11 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path, info.Attributes = cpu_to_le32(dosattrs); rc = CIFSSMBSetPathInfo(xid, tcon, full_path, &info, cifs_sb->local_nls, cifs_sb); + if (rc == -EOPNOTSUPP || rc == -EINVAL) + rc = SMBSetInformation(xid, tcon, full_path, + info.Attributes, + 0 /* do not change write time */, + cifs_sb->local_nls, cifs_sb); if (rc == 0) cifsInode->cifsAttrs = dosattrs; } @@ -974,7 +1037,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, .tcon = tcon, .cifs_sb = cifs_sb, .desired_access = SYNCHRONIZE | FILE_WRITE_ATTRIBUTES, - .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR), + .create_options = cifs_create_options(cifs_sb, 0), .disposition = FILE_OPEN, .path = full_path, .fid = &fid, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 0985db9f86e5..09e3fc81d7cb 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -676,7 +676,7 @@ finished: idata->fi.EndOfFile = create_rsp->EndofFile; if (le32_to_cpu(idata->fi.NumberOfLinks) == 0) idata->fi.NumberOfLinks = cpu_to_le32(1); /* dummy value */ - idata->fi.DeletePending = 0; + idata->fi.DeletePending = 0; /* successful open = not delete pending */ idata->fi.Directory = !!(le32_to_cpu(create_rsp->FileAttributes) & ATTR_DIRECTORY); /* smb2_parse_contexts() fills idata->fi.IndexNumber */ @@ -1382,31 +1382,33 @@ int smb2_set_file_info(struct inode *inode, const char *full_path, FILE_BASIC_INFO *buf, const unsigned int xid) { - struct cifs_open_parms oparms; + struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), }; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsFileInfo *cfile = NULL; + struct cifs_open_parms oparms; struct tcon_link *tlink; struct cifs_tcon *tcon; - struct cifsFileInfo *cfile; - struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), }; - int rc; - - if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && - (buf->LastWriteTime == 0) && (buf->ChangeTime == 0) && - (buf->Attributes == 0)) - return 0; /* would be a no op, no sense sending this */ + int rc = 0; tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && + (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) { + if (buf->Attributes == 0) + goto out; /* would be a no op, no sense sending this */ + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + } + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, ACL_NO_MODE); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, &in_iov, &(int){SMB2_OP_SET_INFO}, 1, cfile, NULL, NULL, NULL); +out: cifs_put_tlink(tlink); return rc; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 058050f744c0..7c392cf5940b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1803,140 +1803,226 @@ free_vars: return rc; } +/** + * calc_chunk_count - calculates the number chunks to be filled in the Chunks[] + * array of struct copychunk_ioctl + * + * @tcon: destination file tcon + * @bytes_left: how many bytes are left to copy + * + * Return: maximum number of chunks with which Chunks[] can be filled. + */ +static inline u32 +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +{ + u32 max_chunks = READ_ONCE(tcon->max_chunks); + u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy); + u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk); + u64 need; + u32 allowed; + + if (!max_bytes_chunk || !max_bytes_copy || !max_chunks) + return 0; + + /* chunks needed for the remaining bytes */ + need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + /* chunks allowed per cc request */ + allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + + return (u32)umin(need, umin(max_chunks, allowed)); +} + +/** + * smb2_copychunk_range - server-side copy of data range + * + * @xid: transaction id + * @src_file: source file + * @dst_file: destination file + * @src_off: source file byte offset + * @len: number of bytes to copy + * @dst_off: destination file byte offset + * + * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE + * IOCTLs, splitting the request into chunks limited by tcon->max_*. + * + * Return: @len on success; negative errno on failure. + */ static ssize_t smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *srcfile, - struct cifsFileInfo *trgtfile, u64 src_off, - u64 len, u64 dest_off) + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { - int rc; - unsigned int ret_data_len; - struct copychunk_ioctl *pcchunk; - struct copychunk_ioctl_rsp *retbuf = NULL; + int rc = 0; + unsigned int ret_data_len = 0; + struct copychunk_ioctl *cc_req = NULL; + struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; - int chunks_copied = 0; - bool chunk_sizes_updated = false; - ssize_t bytes_written, total_bytes_written = 0; + struct copychunk *chunk; + u32 chunks, chunk_count, chunk_bytes; + u32 copy_bytes, copy_bytes_left; + u32 chunks_written, bytes_written; + u64 total_bytes_left = len; + u64 src_off_prev, dst_off_prev; + u32 retries = 0; + + tcon = tlink_tcon(dst_file->tlink); + + trace_smb3_copychunk_enter(xid, src_file->fid.volatile_fid, + dst_file->fid.volatile_fid, tcon->tid, + tcon->ses->Suid, src_off, dst_off, len); + +retry: + chunk_count = calc_chunk_count(tcon, total_bytes_left); + if (!chunk_count) { + rc = -EOPNOTSUPP; + goto out; + } - pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); - if (pcchunk == NULL) - return -ENOMEM; + cc_req = kzalloc(struct_size(cc_req, Chunks, chunk_count), GFP_KERNEL); + if (!cc_req) { + rc = -ENOMEM; + goto out; + } - cifs_dbg(FYI, "%s: about to call request res key\n", __func__); /* Request a key from the server to identify the source of the copy */ - rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink), - srcfile->fid.persistent_fid, - srcfile->fid.volatile_fid, pcchunk); + rc = SMB2_request_res_key(xid, + tlink_tcon(src_file->tlink), + src_file->fid.persistent_fid, + src_file->fid.volatile_fid, + cc_req); - /* Note: request_res_key sets res_key null only if rc !=0 */ + /* Note: request_res_key sets res_key null only if rc != 0 */ if (rc) - goto cchunk_out; + goto out; + + while (total_bytes_left > 0) { + + /* Store previous offsets to allow rewind */ + src_off_prev = src_off; + dst_off_prev = dst_off; - /* For now array only one chunk long, will make more flexible later */ - pcchunk->ChunkCount = cpu_to_le32(1); - pcchunk->Reserved = 0; - pcchunk->Reserved2 = 0; + chunks = 0; + copy_bytes = 0; + copy_bytes_left = umin(total_bytes_left, tcon->max_bytes_copy); + while (copy_bytes_left > 0 && chunks < chunk_count) { + chunk = &cc_req->Chunks[chunks++]; - tcon = tlink_tcon(trgtfile->tlink); + chunk->SourceOffset = cpu_to_le64(src_off); + chunk->TargetOffset = cpu_to_le64(dst_off); - trace_smb3_copychunk_enter(xid, srcfile->fid.volatile_fid, - trgtfile->fid.volatile_fid, tcon->tid, - tcon->ses->Suid, src_off, dest_off, len); + chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk); - while (len > 0) { - pcchunk->SourceOffset = cpu_to_le64(src_off); - pcchunk->TargetOffset = cpu_to_le64(dest_off); - pcchunk->Length = - cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); + chunk->Length = cpu_to_le32(chunk_bytes); + /* Buffer is zeroed, no need to set chunk->Reserved = 0 */ + + src_off += chunk_bytes; + dst_off += chunk_bytes; + + copy_bytes_left -= chunk_bytes; + copy_bytes += chunk_bytes; + } + + cc_req->ChunkCount = cpu_to_le32(chunks); + /* Buffer is zeroed, no need to set cc_req->Reserved = 0 */ /* Request server copy to target from src identified by key */ - kfree(retbuf); - retbuf = NULL; - rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, - trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, - (char *)pcchunk, sizeof(struct copychunk_ioctl), - CIFSMaxBufSize, (char **)&retbuf, &ret_data_len); + kfree(cc_rsp); + cc_rsp = NULL; + rc = SMB2_ioctl(xid, tcon, dst_file->fid.persistent_fid, + dst_file->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, + (char *)cc_req, struct_size(cc_req, Chunks, chunks), + CIFSMaxBufSize, (char **)&cc_rsp, &ret_data_len); + + if (rc && rc != -EINVAL) + goto out; + + if (unlikely(ret_data_len != sizeof(*cc_rsp))) { + cifs_tcon_dbg(VFS, "Copychunk invalid response: size %u/%zu\n", + ret_data_len, sizeof(*cc_rsp)); + rc = -EIO; + goto out; + } + + bytes_written = le32_to_cpu(cc_rsp->TotalBytesWritten); + chunks_written = le32_to_cpu(cc_rsp->ChunksWritten); + chunk_bytes = le32_to_cpu(cc_rsp->ChunkBytesWritten); + if (rc == 0) { - if (ret_data_len != - sizeof(struct copychunk_ioctl_rsp)) { - cifs_tcon_dbg(VFS, "Invalid cchunk response size\n"); - rc = -EIO; - goto cchunk_out; - } - if (retbuf->TotalBytesWritten == 0) { - cifs_dbg(FYI, "no bytes copied\n"); + /* Check if server claimed to write more than we asked */ + if (unlikely(!bytes_written || bytes_written > copy_bytes || + !chunks_written || chunks_written > chunks)) { + cifs_tcon_dbg(VFS, "Copychunk invalid response: bytes written %u/%u, chunks written %u/%u\n", + bytes_written, copy_bytes, chunks_written, chunks); rc = -EIO; - goto cchunk_out; - } - /* - * Check if server claimed to write more than we asked - */ - if (le32_to_cpu(retbuf->TotalBytesWritten) > - le32_to_cpu(pcchunk->Length)) { - cifs_tcon_dbg(VFS, "Invalid copy chunk response\n"); - rc = -EIO; - goto cchunk_out; + goto out; } - if (le32_to_cpu(retbuf->ChunksWritten) != 1) { - cifs_tcon_dbg(VFS, "Invalid num chunks written\n"); - rc = -EIO; - goto cchunk_out; + + /* Partial write: rewind */ + if (bytes_written < copy_bytes) { + u32 delta = copy_bytes - bytes_written; + + src_off -= delta; + dst_off -= delta; } - chunks_copied++; - - bytes_written = le32_to_cpu(retbuf->TotalBytesWritten); - src_off += bytes_written; - dest_off += bytes_written; - len -= bytes_written; - total_bytes_written += bytes_written; - - cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n", - le32_to_cpu(retbuf->ChunksWritten), - le32_to_cpu(retbuf->ChunkBytesWritten), - bytes_written); - trace_smb3_copychunk_done(xid, srcfile->fid.volatile_fid, - trgtfile->fid.volatile_fid, tcon->tid, - tcon->ses->Suid, src_off, dest_off, len); - } else if (rc == -EINVAL) { - if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) - goto cchunk_out; - - cifs_dbg(FYI, "MaxChunks %d BytesChunk %d MaxCopy %d\n", - le32_to_cpu(retbuf->ChunksWritten), - le32_to_cpu(retbuf->ChunkBytesWritten), - le32_to_cpu(retbuf->TotalBytesWritten)); - /* - * Check if this is the first request using these sizes, - * (ie check if copy succeed once with original sizes - * and check if the server gave us different sizes after - * we already updated max sizes on previous request). - * if not then why is the server returning an error now - */ - if ((chunks_copied != 0) || chunk_sizes_updated) - goto cchunk_out; - - /* Check that server is not asking us to grow size */ - if (le32_to_cpu(retbuf->ChunkBytesWritten) < - tcon->max_bytes_chunk) - tcon->max_bytes_chunk = - le32_to_cpu(retbuf->ChunkBytesWritten); - else - goto cchunk_out; /* server gave us bogus size */ + total_bytes_left -= bytes_written; + continue; + } - /* No need to change MaxChunks since already set to 1 */ - chunk_sizes_updated = true; - } else - goto cchunk_out; + /* + * Check if server is not asking us to reduce size. + * + * Note: As per MS-SMB2 2.2.32.1, the values returned + * in cc_rsp are not strictly lower than what existed + * before. + */ + if (bytes_written < tcon->max_bytes_copy) { + cifs_tcon_dbg(FYI, "Copychunk MaxBytesCopy updated: %u -> %u\n", + tcon->max_bytes_copy, bytes_written); + tcon->max_bytes_copy = bytes_written; + } + + if (chunks_written < tcon->max_chunks) { + cifs_tcon_dbg(FYI, "Copychunk MaxChunks updated: %u -> %u\n", + tcon->max_chunks, chunks_written); + tcon->max_chunks = chunks_written; + } + + if (chunk_bytes < tcon->max_bytes_chunk) { + cifs_tcon_dbg(FYI, "Copychunk MaxBytesChunk updated: %u -> %u\n", + tcon->max_bytes_chunk, chunk_bytes); + tcon->max_bytes_chunk = chunk_bytes; + } + + /* reset to last offsets */ + if (retries++ < 2) { + src_off = src_off_prev; + dst_off = dst_off_prev; + kfree(cc_req); + cc_req = NULL; + goto retry; + } + + break; } -cchunk_out: - kfree(pcchunk); - kfree(retbuf); - if (rc) +out: + kfree(cc_req); + kfree(cc_rsp); + if (rc) { + trace_smb3_copychunk_err(xid, src_file->fid.volatile_fid, + dst_file->fid.volatile_fid, tcon->tid, + tcon->ses->Suid, src_off, dst_off, len, rc); return rc; - else - return total_bytes_written; + } else { + trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid, + dst_file->fid.volatile_fid, tcon->tid, + tcon->ses->Suid, src_off, dst_off, len); + return len; + } } static int @@ -3281,7 +3367,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); - inode_lock(inode); filemap_invalidate_lock(inode->i_mapping); i_size = i_size_read(inode); @@ -3299,6 +3384,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, * first, otherwise the data may be inconsistent with the server. */ truncate_pagecache_range(inode, offset, offset + len - 1); + netfs_wait_for_outstanding_io(inode); /* if file not oplocked can't be sure whether asking to extend size */ rc = -EOPNOTSUPP; @@ -3327,7 +3413,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); - inode_unlock(inode); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3351,7 +3436,6 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode_lock(inode); /* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) { @@ -3365,6 +3449,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, * caches first, otherwise the data may be inconsistent with the server. */ truncate_pagecache_range(inode, offset, offset + len - 1); + netfs_wait_for_outstanding_io(inode); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -3399,7 +3484,6 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, unlock: filemap_invalidate_unlock(inode->i_mapping); out: - inode_unlock(inode); free_xid(xid); return rc; } @@ -3663,8 +3747,6 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode_lock(inode); - old_eof = i_size_read(inode); if ((off >= old_eof) || off + len >= old_eof) { @@ -3679,6 +3761,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, truncate_pagecache_range(inode, off, old_eof); ictx->zero_point = old_eof; + netfs_wait_for_outstanding_io(inode); rc = smb2_copychunk_range(xid, cfile, cfile, off + len, old_eof - off - len, off); @@ -3699,8 +3782,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, fscache_resize_cookie(cifs_inode_cookie(inode), new_eof); out_2: filemap_invalidate_unlock(inode->i_mapping); - out: - inode_unlock(inode); +out: free_xid(xid); return rc; } @@ -3717,8 +3799,6 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode_lock(inode); - old_eof = i_size_read(inode); if (off >= old_eof) { rc = -EINVAL; @@ -3733,6 +3813,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, if (rc < 0) goto out_2; truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); @@ -3755,8 +3836,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, rc = 0; out_2: filemap_invalidate_unlock(inode->i_mapping); - out: - inode_unlock(inode); +out: free_xid(xid); return rc; } @@ -4650,7 +4730,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, unsigned int pad_len; struct cifs_io_subrequest *rdata = mid->callback_data; struct smb2_hdr *shdr = (struct smb2_hdr *)buf; - int length; + size_t copied; bool use_rdma_mr = false; if (shdr->Command != SMB2_READ) { @@ -4763,10 +4843,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ WARN_ONCE(buffer, "read data can be either in buf or in buffer"); - length = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); - if (length < 0) - return length; - rdata->got_bytes = data_len; + copied = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); + if (copied == 0) + return -EIO; + rdata->got_bytes = copied; } else { /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 42e2d4ea344d..b0739a2661bf 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3277,7 +3277,7 @@ replay_again: buf->EndOfFile = rsp->EndofFile; buf->Attributes = rsp->FileAttributes; buf->NumberOfLinks = cpu_to_le32(1); - buf->DeletePending = 0; + buf->DeletePending = 0; /* successful open = not delete pending */ } diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 3c09a58dfd07..101024f8f725 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -201,16 +201,20 @@ struct resume_key_req { char Context[]; /* ignored, Windows sets to 4 bytes of zero */ } __packed; + +struct copychunk { + __le64 SourceOffset; + __le64 TargetOffset; + __le32 Length; + __le32 Reserved; +} __packed; + /* this goes in the ioctl buffer when doing a copychunk request */ struct copychunk_ioctl { char SourceKey[COPY_CHUNK_RES_KEY_SIZE]; - __le32 ChunkCount; /* we are only sending 1 */ + __le32 ChunkCount; __le32 Reserved; - /* array will only be one chunk long for us */ - __le64 SourceOffset; - __le64 TargetOffset; - __le32 Length; /* how many bytes to copy */ - __u32 Reserved2; + struct copychunk Chunks[]; } __packed; struct copychunk_ioctl_rsp { diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index bc0e92eb2b64..33f33013b392 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -240,11 +240,6 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) return NULL; } tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); - if (!tcon) { - spin_unlock(&cifs_tcp_ses_lock); - cifs_put_smb_ses(ses); - return NULL; - } spin_unlock(&cifs_tcp_ses_lock); /* tcon already has a ref to ses, so we don't need ses anymore */ cifs_put_smb_ses(ses); diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index fd650e2afc76..28e00c34df1c 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -266,7 +266,7 @@ DEFINE_EVENT(smb3_copy_range_err_class, smb3_##name, \ TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len, rc)) DEFINE_SMB3_COPY_RANGE_ERR_EVENT(clone_err); -/* TODO: Add SMB3_COPY_RANGE_ERR_EVENT(copychunk_err) */ +DEFINE_SMB3_COPY_RANGE_ERR_EVENT(copychunk_err); DECLARE_EVENT_CLASS(smb3_copy_range_done_class, TP_PROTO(unsigned int xid, diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h index 5434048a2ca4..b92faa9a26b2 100644 --- a/include/drm/drm_gpusvm.h +++ b/include/drm/drm_gpusvm.h @@ -179,7 +179,6 @@ struct drm_gpusvm_range { * @name: Name of the GPU SVM * @drm: Pointer to the DRM device structure * @mm: Pointer to the mm_struct for the address space - * @device_private_page_owner: Device private pages owner * @mm_start: Start address of GPU SVM * @mm_range: Range of the GPU SVM * @notifier_size: Size of individual notifiers @@ -204,7 +203,6 @@ struct drm_gpusvm { const char *name; struct drm_device *drm; struct mm_struct *mm; - void *device_private_page_owner; unsigned long mm_start; unsigned long mm_range; unsigned long notifier_size; @@ -226,6 +224,8 @@ struct drm_gpusvm { /** * struct drm_gpusvm_ctx - DRM GPU SVM context * + * @device_private_page_owner: The device-private page owner to use for + * this operation * @check_pages_threshold: Check CPU pages for present if chunk is less than or * equal to threshold. If not present, reduce chunk * size. @@ -239,6 +239,7 @@ struct drm_gpusvm { * Context that is DRM GPUSVM is operating in (i.e. user arguments). */ struct drm_gpusvm_ctx { + void *device_private_page_owner; unsigned long check_pages_threshold; unsigned long timeslice_ms; unsigned int in_notifier :1; @@ -249,7 +250,7 @@ struct drm_gpusvm_ctx { int drm_gpusvm_init(struct drm_gpusvm *gpusvm, const char *name, struct drm_device *drm, - struct mm_struct *mm, void *device_private_page_owner, + struct mm_struct *mm, unsigned long mm_start, unsigned long mm_range, unsigned long notifier_size, const struct drm_gpusvm_ops *ops, diff --git a/include/linux/bio.h b/include/linux/bio.h index a64a30131031..16c1c85613b7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -446,14 +446,9 @@ int submit_bio_wait(struct bio *bio); int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data, size_t len, enum req_op op); -int bio_iov_iter_get_pages_aligned(struct bio *bio, struct iov_iter *iter, +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, unsigned len_align_mask); -static inline int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) -{ - return bio_iov_iter_get_pages_aligned(bio, iter, 0); -} - void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dad5cb5b3812..70b671a9a7f7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1873,13 +1873,6 @@ static inline int bio_split_rw_at(struct bio *bio, return bio_split_io_at(bio, lim, segs, max_bytes, lim->dma_alignment); } -static inline int bio_iov_iter_get_bdev_pages(struct bio *bio, - struct iov_iter *iter, struct block_device *bdev) -{ - return bio_iov_iter_get_pages_aligned(bio, iter, - bdev_logical_block_size(bdev) - 1); -} - #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 1717cc57cdac..6aa4c6478c9f 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -2,6 +2,7 @@ #ifndef __FS_CEPH_MESSENGER_H #define __FS_CEPH_MESSENGER_H +#include <crypto/sha2.h> #include <linux/bvec.h> #include <linux/crypto.h> #include <linux/kref.h> @@ -412,7 +413,8 @@ struct ceph_connection_v2_info { struct ceph_msg_data_cursor in_cursor; struct ceph_msg_data_cursor out_cursor; - struct crypto_shash *hmac_tfm; /* post-auth signature */ + struct hmac_sha256_key hmac_key; /* post-auth signature */ + bool hmac_key_set; struct crypto_aead *gcm_tfm; /* on-wire encryption */ struct aead_request *gcm_req; struct crypto_wait gcm_wait; @@ -548,12 +550,12 @@ void ceph_addr_set_port(struct ceph_entity_addr *addr, int p); void ceph_con_process_message(struct ceph_connection *con); int ceph_con_in_msg_alloc(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip); -void ceph_con_get_out_msg(struct ceph_connection *con); +struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con); /* messenger_v1.c */ int ceph_con_v1_try_read(struct ceph_connection *con); int ceph_con_v1_try_write(struct ceph_connection *con); -void ceph_con_v1_revoke(struct ceph_connection *con); +void ceph_con_v1_revoke(struct ceph_connection *con, struct ceph_msg *msg); void ceph_con_v1_revoke_incoming(struct ceph_connection *con); bool ceph_con_v1_opened(struct ceph_connection *con); void ceph_con_v1_reset_session(struct ceph_connection *con); @@ -562,7 +564,7 @@ void ceph_con_v1_reset_protocol(struct ceph_connection *con); /* messenger_v2.c */ int ceph_con_v2_try_read(struct ceph_connection *con); int ceph_con_v2_try_write(struct ceph_connection *con); -void ceph_con_v2_revoke(struct ceph_connection *con); +void ceph_con_v2_revoke(struct ceph_connection *con, struct ceph_msg *msg); void ceph_con_v2_revoke_incoming(struct ceph_connection *con); bool ceph_con_v2_opened(struct ceph_connection *con); void ceph_con_v2_reset_session(struct ceph_connection *con); diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 8720a0705900..107ce05bd16e 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -115,11 +115,6 @@ # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif -#if __has_feature(kcfi) -/* Disable CFI checking inside a function. */ -#define __nocfi __attribute__((__no_sanitize__("kcfi"))) -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5d07c469b571..5de824a0b3d7 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -35,10 +35,6 @@ (typeof(ptr)) (__ptr + (off)); \ }) -#ifdef CONFIG_MITIGATION_RETPOLINE -#define __noretpoline __attribute__((__indirect_branch__("keep"))) -#endif - #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2f3e80bf9f35..59288a2c1ad2 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -455,7 +455,9 @@ struct ftrace_likely_data { # define __noscs #endif -#ifndef __nocfi +#if defined(CONFIG_CFI) +# define __nocfi __attribute__((__no_sanitize__("kcfi"))) +#else # define __nocfi #endif diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h index 7c522fdd9ea7..e305bf32e40a 100644 --- a/include/linux/i2c-algo-pca.h +++ b/include/linux/i2c-algo-pca.h @@ -71,7 +71,7 @@ struct i2c_algo_pca_data { void *data; /* private low level data */ void (*write_byte) (void *data, int reg, int val); int (*read_byte) (void *data, int reg); - int (*wait_for_completion) (void *data); + int (*wait_for_completion_cb) (void *data); void (*reset_chip) (void *data); /* For PCA9564, use one of the predefined frequencies: * 330000, 288000, 217000, 146000, 88000, 59000, 44000, 36000 diff --git a/include/linux/init.h b/include/linux/init.h index a60d32d227ee..17c1bc712e23 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -7,13 +7,6 @@ #include <linux/stringify.h> #include <linux/types.h> -/* Built-in __init functions needn't be compiled with retpoline */ -#if defined(__noretpoline) && !defined(MODULE) -#define __noinitretpoline __noretpoline -#else -#define __noinitretpoline -#endif - /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) * as `initialization' functions. The kernel can take this @@ -50,7 +43,6 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ #define __init __section(".init.text") __cold __latent_entropy \ - __noinitretpoline \ __no_kstack_erase #define __initdata __section(".init.data") #define __initconst __section(".init.rodata") diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h index 559d13a3bc44..25042c1d8d54 100644 --- a/include/linux/kexec_handover.h +++ b/include/linux/kexec_handover.h @@ -18,6 +18,7 @@ enum kho_event { struct folio; struct notifier_block; +struct page; #define DECLARE_KHOSER_PTR(name, type) \ union { \ @@ -38,13 +39,24 @@ struct notifier_block; struct kho_serialization; +struct kho_vmalloc_chunk; +struct kho_vmalloc { + DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *); + unsigned int total_pages; + unsigned short flags; + unsigned short order; +}; + #ifdef CONFIG_KEXEC_HANDOVER bool kho_is_enabled(void); bool is_kho_boot(void); int kho_preserve_folio(struct folio *folio); -int kho_preserve_phys(phys_addr_t phys, size_t size); +int kho_preserve_pages(struct page *page, unsigned int nr_pages); +int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation); struct folio *kho_restore_folio(phys_addr_t phys); +struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages); +void *kho_restore_vmalloc(const struct kho_vmalloc *preservation); int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt); int kho_retrieve_subtree(const char *name, phys_addr_t *phys); @@ -71,7 +83,13 @@ static inline int kho_preserve_folio(struct folio *folio) return -EOPNOTSUPP; } -static inline int kho_preserve_phys(phys_addr_t phys, size_t size) +static inline int kho_preserve_pages(struct page *page, unsigned int nr_pages) +{ + return -EOPNOTSUPP; +} + +static inline int kho_preserve_vmalloc(void *ptr, + struct kho_vmalloc *preservation) { return -EOPNOTSUPP; } @@ -81,6 +99,17 @@ static inline struct folio *kho_restore_folio(phys_addr_t phys) return NULL; } +static inline struct page *kho_restore_pages(phys_addr_t phys, + unsigned int nr_pages) +{ + return NULL; +} + +static inline void *kho_restore_vmalloc(const struct kho_vmalloc *preservation) +{ + return NULL; +} + static inline int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt) { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 16fe0306e50e..873e510d6f8d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1001,22 +1001,28 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, count_memcg_events_mm(mm, idx, 1); } -static inline void memcg_memory_event(struct mem_cgroup *memcg, - enum memcg_memory_event event) +static inline void __memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event, + bool allow_spinning) { bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || event == MEMCG_SWAP_FAIL; + /* For now only MEMCG_MAX can happen with !allow_spinning context. */ + VM_WARN_ON_ONCE(!allow_spinning && event != MEMCG_MAX); + atomic_long_inc(&memcg->memory_events_local[event]); - if (!swap_event) + if (!swap_event && allow_spinning) cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); - if (swap_event) - cgroup_file_notify(&memcg->swap_events_file); - else - cgroup_file_notify(&memcg->events_file); + if (allow_spinning) { + if (swap_event) + cgroup_file_notify(&memcg->swap_events_file); + else + cgroup_file_notify(&memcg->events_file); + } if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; @@ -1026,6 +1032,12 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, !mem_cgroup_is_root(memcg)); } +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) +{ + __memcg_memory_event(memcg, event, true); +} + static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { diff --git a/include/linux/mm.h b/include/linux/mm.h index a3f97c551ad8..d16b33bacc32 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -323,7 +323,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ -#define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ +#define VM_MERGEABLE BIT(31) /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 366ad004d794..46ebaa46e6c5 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -184,6 +184,15 @@ * WARN using UD2. */ #define ANNOTATE_REACHABLE(label) __ASM_ANNOTATE(label, ANNOTYPE_REACHABLE) +/* + * This should not be used; it annotates away CFI violations. There are a few + * valid use cases like kexec handover to the next kernel image, and there is + * no security concern there. + * + * There are also a few real issues annotated away, like EFI because we can't + * control the EFI code. + */ +#define ANNOTATE_NOCFI_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOCFI)) #else #define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR @@ -194,6 +203,7 @@ #define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL #define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN #define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE +#define ANNOTATE_NOCFI_SYM ANNOTATE type=ANNOTYPE_NOCFI #endif #if defined(CONFIG_NOINSTR_VALIDATION) && \ diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index df5d9fa84dba..aceac94632c8 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -65,5 +65,6 @@ struct unwind_hint { #define ANNOTYPE_IGNORE_ALTS 6 #define ANNOTYPE_INTRA_FUNCTION_CALL 7 #define ANNOTYPE_REACHABLE 8 +#define ANNOTYPE_NOCFI 9 #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/of.h b/include/linux/of.h index 5e2c6ed9370a..121a288ca92d 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1134,7 +1134,7 @@ static inline bool of_phandle_args_equal(const struct of_phandle_args *a1, * Search for a property in a device node and count the number of u8 elements * in it. * - * Return: The number of elements on sucess, -EINVAL if the property does + * Return: The number of elements on success, -EINVAL if the property does * not exist or its length does not match a multiple of u8 and -ENODATA if the * property does not have a value. */ @@ -1153,7 +1153,7 @@ static inline int of_property_count_u8_elems(const struct device_node *np, * Search for a property in a device node and count the number of u16 elements * in it. * - * Return: The number of elements on sucess, -EINVAL if the property does + * Return: The number of elements on success, -EINVAL if the property does * not exist or its length does not match a multiple of u16 and -ENODATA if the * property does not have a value. */ @@ -1172,7 +1172,7 @@ static inline int of_property_count_u16_elems(const struct device_node *np, * Search for a property in a device node and count the number of u32 elements * in it. * - * Return: The number of elements on sucess, -EINVAL if the property does + * Return: The number of elements on success, -EINVAL if the property does * not exist or its length does not match a multiple of u32 and -ENODATA if the * property does not have a value. */ @@ -1191,7 +1191,7 @@ static inline int of_property_count_u32_elems(const struct device_node *np, * Search for a property in a device node and count the number of u64 elements * in it. * - * Return: The number of elements on sucess, -EINVAL if the property does + * Return: The number of elements on success, -EINVAL if the property does * not exist or its length does not match a multiple of u64 and -ENODATA if the * property does not have a value. */ diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index eeeff2a04529..729415e91215 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -17,8 +17,8 @@ struct disk_stats { /* * Macros to operate on percpu disk statistics: * - * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters and should - * be called between disk_stat_lock() and disk_stat_unlock(). + * part_stat_{add|sub|inc|dec}() modify the stat counters and should + * be called between part_stat_lock() and part_stat_unlock(). * * part_stat_read() can be called at any time. */ diff --git a/include/linux/tpm.h b/include/linux/tpm.h index b0e9eb5ef022..dc0338a783f3 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -228,10 +228,11 @@ enum tpm2_timeouts { TPM2_TIMEOUT_B = 4000, TPM2_TIMEOUT_C = 200, TPM2_TIMEOUT_D = 30, +}; + +enum tpm2_durations { TPM2_DURATION_SHORT = 20, - TPM2_DURATION_MEDIUM = 750, TPM2_DURATION_LONG = 2000, - TPM2_DURATION_LONG_LONG = 300000, TPM2_DURATION_DEFAULT = 120000, }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ae83d8649ef1..6829936d33f5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4891,7 +4891,7 @@ union bpf_attr { * * **-ENOENT** if the bpf_local_storage cannot be found. * - * long bpf_d_path(struct path *path, char *buf, u32 sz) + * long bpf_d_path(const struct path *path, char *buf, u32 sz) * Description * Return full path for given **struct path** object, which * needs to be the kernel BTF *path* object. The path is diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a0cc1cc0dd01..263bed13473e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -404,7 +404,7 @@ enum io_uring_op { * will be contiguous from the starting buffer ID. * * IORING_SEND_VECTORIZED If set, SEND[_ZC] will take a pointer to a io_vec - * to allow vectorized send operations. + * to allow vectorized send operations. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 04c7d283dc7d..5d1727a6d040 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -67,8 +67,8 @@ struct kfd_ioctl_get_version_args { struct kfd_ioctl_create_queue_args { __u64 ring_base_address; /* to KFD */ - __u64 write_pointer_address; /* from KFD */ - __u64 read_pointer_address; /* from KFD */ + __u64 write_pointer_address; /* to KFD */ + __u64 read_pointer_address; /* to KFD */ __u64 doorbell_offset; /* from KFD */ __u32 ring_size; /* to KFD */ diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index 612500a7088f..e64b70132101 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -180,6 +180,7 @@ static inline u32 ufshci_version(u32 major, u32 minor) #define UTP_TASK_REQ_COMPL 0x200 #define UIC_COMMAND_COMPL 0x400 #define DEVICE_FATAL_ERROR 0x800 +#define UTP_ERROR 0x1000 #define CONTROLLER_FATAL_ERROR 0x10000 #define SYSTEM_BUS_FATAL_ERROR 0x20000 #define CRYPTO_ENGINE_FATAL_ERROR 0x40000 @@ -199,7 +200,8 @@ static inline u32 ufshci_version(u32 major, u32 minor) CONTROLLER_FATAL_ERROR |\ SYSTEM_BUS_FATAL_ERROR |\ CRYPTO_ENGINE_FATAL_ERROR |\ - UIC_LINK_LOST) + UIC_LINK_LOST |\ + UTP_ERROR) /* HCS - Host Controller Status 30h */ #define DEVICE_PRESENT 0x1 diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 49ebdeb5b2d9..820ef0527666 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -29,7 +29,7 @@ * * Also see the examples in the liburing library: * - * git://git.kernel.dk/liburing + * git://git.kernel.org/pub/scm/linux/kernel/git/axboe/liburing.git * * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens * from data shared between the kernel and application. This is done both diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 26c118f3918d..f25110fb1b12 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -230,13 +230,14 @@ static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, if (!pid_child_should_wake(wo, p)) return 0; + list_del_init(&wait->entry); + /* cancel is in progress */ if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) return 1; req->io_task_work.func = io_waitid_cb; io_req_task_work_add(req); - list_del_init(&wait->entry); return 1; } diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 723e4266b91f..a816f5902091 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -1079,6 +1079,7 @@ static ssize_t io_copy_page(struct io_copy_cache *cc, struct page *src_page, cc->size -= n; cc->offset += n; + src_offset += n; len -= n; copied += n; } @@ -1236,12 +1237,16 @@ io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb, end = start + frag_iter->len; if (offset < end) { + size_t count; + copy = end - offset; if (copy > len) copy = len; off = offset - start; + count = desc->count; ret = io_zcrx_recv_skb(desc, frag_iter, off, copy); + desc->count = count; if (ret < 0) goto out; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index f90bdcc0a047..81780bcf8d25 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -775,7 +775,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void bpf_free_inode(struct inode *inode) +static void bpf_destroy_inode(struct inode *inode) { enum bpf_type type; @@ -790,7 +790,7 @@ const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = inode_just_drop, .show_options = bpf_show_options, - .free_inode = bpf_free_inode, + .destroy_inode = bpf_destroy_inode, }; enum { diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 5083c68c3a4e..76f0940fb485 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -18,6 +18,7 @@ #include <linux/memblock.h> #include <linux/notifier.h> #include <linux/page-isolation.h> +#include <linux/vmalloc.h> #include <asm/early_ioremap.h> @@ -107,6 +108,29 @@ struct kho_serialization { struct khoser_mem_chunk *preserved_mem_map; }; +struct kho_out { + struct blocking_notifier_head chain_head; + + struct dentry *dir; + + struct mutex lock; /* protects KHO FDT finalization */ + + struct kho_serialization ser; + bool finalized; +}; + +static struct kho_out kho_out = { + .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head), + .lock = __MUTEX_INITIALIZER(kho_out.lock), + .ser = { + .fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list), + .track = { + .orders = XARRAY_INIT(kho_out.ser.track.orders, 0), + }, + }, + .finalized = false, +}; + static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz) { void *elm, *res; @@ -165,6 +189,9 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, might_sleep(); + if (kho_out.finalized) + return -EBUSY; + physxa = xa_load(&track->orders, order); if (!physxa) { int err; @@ -248,6 +275,37 @@ struct folio *kho_restore_folio(phys_addr_t phys) } EXPORT_SYMBOL_GPL(kho_restore_folio); +/** + * kho_restore_pages - restore list of contiguous order 0 pages. + * @phys: physical address of the first page. + * @nr_pages: number of pages. + * + * Restore a contiguous list of order 0 pages that was preserved with + * kho_preserve_pages(). + * + * Return: 0 on success, error code on failure + */ +struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages) +{ + const unsigned long start_pfn = PHYS_PFN(phys); + const unsigned long end_pfn = start_pfn + nr_pages; + unsigned long pfn = start_pfn; + + while (pfn < end_pfn) { + const unsigned int order = + min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); + struct page *page = kho_restore_page(PFN_PHYS(pfn)); + + if (!page) + return NULL; + split_page(page, order); + pfn += 1 << order; + } + + return pfn_to_page(start_pfn); +} +EXPORT_SYMBOL_GPL(kho_restore_pages); + /* Serialize and deserialize struct kho_mem_phys across kexec * * Record all the bitmaps in a linked list of pages for the next kernel to @@ -667,29 +725,6 @@ int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt) } EXPORT_SYMBOL_GPL(kho_add_subtree); -struct kho_out { - struct blocking_notifier_head chain_head; - - struct dentry *dir; - - struct mutex lock; /* protects KHO FDT finalization */ - - struct kho_serialization ser; - bool finalized; -}; - -static struct kho_out kho_out = { - .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head), - .lock = __MUTEX_INITIALIZER(kho_out.lock), - .ser = { - .fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list), - .track = { - .orders = XARRAY_INIT(kho_out.ser.track.orders, 0), - }, - }, - .finalized = false, -}; - int register_kho_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&kho_out.chain_head, nb); @@ -717,37 +752,28 @@ int kho_preserve_folio(struct folio *folio) const unsigned int order = folio_order(folio); struct kho_mem_track *track = &kho_out.ser.track; - if (kho_out.finalized) - return -EBUSY; - return __kho_preserve_order(track, pfn, order); } EXPORT_SYMBOL_GPL(kho_preserve_folio); /** - * kho_preserve_phys - preserve a physically contiguous range across kexec. - * @phys: physical address of the range. - * @size: size of the range. + * kho_preserve_pages - preserve contiguous pages across kexec + * @page: first page in the list. + * @nr_pages: number of pages. * - * Instructs KHO to preserve the memory range from @phys to @phys + @size - * across kexec. + * Preserve a contiguous list of order 0 pages. Must be restored using + * kho_restore_pages() to ensure the pages are restored properly as order 0. * * Return: 0 on success, error code on failure */ -int kho_preserve_phys(phys_addr_t phys, size_t size) +int kho_preserve_pages(struct page *page, unsigned int nr_pages) { - unsigned long pfn = PHYS_PFN(phys); + struct kho_mem_track *track = &kho_out.ser.track; + const unsigned long start_pfn = page_to_pfn(page); + const unsigned long end_pfn = start_pfn + nr_pages; + unsigned long pfn = start_pfn; unsigned long failed_pfn = 0; - const unsigned long start_pfn = pfn; - const unsigned long end_pfn = PHYS_PFN(phys + size); int err = 0; - struct kho_mem_track *track = &kho_out.ser.track; - - if (kho_out.finalized) - return -EBUSY; - - if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size)) - return -EINVAL; while (pfn < end_pfn) { const unsigned int order = @@ -767,7 +793,256 @@ int kho_preserve_phys(phys_addr_t phys, size_t size) return err; } -EXPORT_SYMBOL_GPL(kho_preserve_phys); +EXPORT_SYMBOL_GPL(kho_preserve_pages); + +struct kho_vmalloc_hdr { + DECLARE_KHOSER_PTR(next, struct kho_vmalloc_chunk *); +}; + +#define KHO_VMALLOC_SIZE \ + ((PAGE_SIZE - sizeof(struct kho_vmalloc_hdr)) / \ + sizeof(phys_addr_t)) + +struct kho_vmalloc_chunk { + struct kho_vmalloc_hdr hdr; + phys_addr_t phys[KHO_VMALLOC_SIZE]; +}; + +static_assert(sizeof(struct kho_vmalloc_chunk) == PAGE_SIZE); + +/* vmalloc flags KHO supports */ +#define KHO_VMALLOC_SUPPORTED_FLAGS (VM_ALLOC | VM_ALLOW_HUGE_VMAP) + +/* KHO internal flags for vmalloc preservations */ +#define KHO_VMALLOC_ALLOC 0x0001 +#define KHO_VMALLOC_HUGE_VMAP 0x0002 + +static unsigned short vmalloc_flags_to_kho(unsigned int vm_flags) +{ + unsigned short kho_flags = 0; + + if (vm_flags & VM_ALLOC) + kho_flags |= KHO_VMALLOC_ALLOC; + if (vm_flags & VM_ALLOW_HUGE_VMAP) + kho_flags |= KHO_VMALLOC_HUGE_VMAP; + + return kho_flags; +} + +static unsigned int kho_flags_to_vmalloc(unsigned short kho_flags) +{ + unsigned int vm_flags = 0; + + if (kho_flags & KHO_VMALLOC_ALLOC) + vm_flags |= VM_ALLOC; + if (kho_flags & KHO_VMALLOC_HUGE_VMAP) + vm_flags |= VM_ALLOW_HUGE_VMAP; + + return vm_flags; +} + +static struct kho_vmalloc_chunk *new_vmalloc_chunk(struct kho_vmalloc_chunk *cur) +{ + struct kho_vmalloc_chunk *chunk; + int err; + + chunk = (struct kho_vmalloc_chunk *)get_zeroed_page(GFP_KERNEL); + if (!chunk) + return NULL; + + err = kho_preserve_pages(virt_to_page(chunk), 1); + if (err) + goto err_free; + if (cur) + KHOSER_STORE_PTR(cur->hdr.next, chunk); + return chunk; + +err_free: + free_page((unsigned long)chunk); + return NULL; +} + +static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk) +{ + struct kho_mem_track *track = &kho_out.ser.track; + unsigned long pfn = PHYS_PFN(virt_to_phys(chunk)); + + __kho_unpreserve(track, pfn, pfn + 1); + + for (int i = 0; chunk->phys[i]; i++) { + pfn = PHYS_PFN(chunk->phys[i]); + __kho_unpreserve(track, pfn, pfn + 1); + } +} + +static void kho_vmalloc_free_chunks(struct kho_vmalloc *kho_vmalloc) +{ + struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(kho_vmalloc->first); + + while (chunk) { + struct kho_vmalloc_chunk *tmp = chunk; + + kho_vmalloc_unpreserve_chunk(chunk); + + chunk = KHOSER_LOAD_PTR(chunk->hdr.next); + free_page((unsigned long)tmp); + } +} + +/** + * kho_preserve_vmalloc - preserve memory allocated with vmalloc() across kexec + * @ptr: pointer to the area in vmalloc address space + * @preservation: placeholder for preservation metadata + * + * Instructs KHO to preserve the area in vmalloc address space at @ptr. The + * physical pages mapped at @ptr will be preserved and on successful return + * @preservation will hold the physical address of a structure that describes + * the preservation. + * + * NOTE: The memory allocated with vmalloc_node() variants cannot be reliably + * restored on the same node + * + * Return: 0 on success, error code on failure + */ +int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation) +{ + struct kho_vmalloc_chunk *chunk; + struct vm_struct *vm = find_vm_area(ptr); + unsigned int order, flags, nr_contig_pages; + unsigned int idx = 0; + int err; + + if (!vm) + return -EINVAL; + + if (vm->flags & ~KHO_VMALLOC_SUPPORTED_FLAGS) + return -EOPNOTSUPP; + + flags = vmalloc_flags_to_kho(vm->flags); + order = get_vm_area_page_order(vm); + + chunk = new_vmalloc_chunk(NULL); + if (!chunk) + return -ENOMEM; + KHOSER_STORE_PTR(preservation->first, chunk); + + nr_contig_pages = (1 << order); + for (int i = 0; i < vm->nr_pages; i += nr_contig_pages) { + phys_addr_t phys = page_to_phys(vm->pages[i]); + + err = kho_preserve_pages(vm->pages[i], nr_contig_pages); + if (err) + goto err_free; + + chunk->phys[idx++] = phys; + if (idx == ARRAY_SIZE(chunk->phys)) { + chunk = new_vmalloc_chunk(chunk); + if (!chunk) + goto err_free; + idx = 0; + } + } + + preservation->total_pages = vm->nr_pages; + preservation->flags = flags; + preservation->order = order; + + return 0; + +err_free: + kho_vmalloc_free_chunks(preservation); + return err; +} +EXPORT_SYMBOL_GPL(kho_preserve_vmalloc); + +/** + * kho_restore_vmalloc - recreates and populates an area in vmalloc address + * space from the preserved memory. + * @preservation: preservation metadata. + * + * Recreates an area in vmalloc address space and populates it with memory that + * was preserved using kho_preserve_vmalloc(). + * + * Return: pointer to the area in the vmalloc address space, NULL on failure. + */ +void *kho_restore_vmalloc(const struct kho_vmalloc *preservation) +{ + struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(preservation->first); + unsigned int align, order, shift, vm_flags; + unsigned long total_pages, contig_pages; + unsigned long addr, size; + struct vm_struct *area; + struct page **pages; + unsigned int idx = 0; + int err; + + vm_flags = kho_flags_to_vmalloc(preservation->flags); + if (vm_flags & ~KHO_VMALLOC_SUPPORTED_FLAGS) + return NULL; + + total_pages = preservation->total_pages; + pages = kvmalloc_array(total_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return NULL; + order = preservation->order; + contig_pages = (1 << order); + shift = PAGE_SHIFT + order; + align = 1 << shift; + + while (chunk) { + struct page *page; + + for (int i = 0; chunk->phys[i]; i++) { + phys_addr_t phys = chunk->phys[i]; + + if (idx + contig_pages > total_pages) + goto err_free_pages_array; + + page = kho_restore_pages(phys, contig_pages); + if (!page) + goto err_free_pages_array; + + for (int j = 0; j < contig_pages; j++) + pages[idx++] = page; + + phys += contig_pages * PAGE_SIZE; + } + + page = kho_restore_pages(virt_to_phys(chunk), 1); + if (!page) + goto err_free_pages_array; + chunk = KHOSER_LOAD_PTR(chunk->hdr.next); + __free_page(page); + } + + if (idx != total_pages) + goto err_free_pages_array; + + area = __get_vm_area_node(total_pages * PAGE_SIZE, align, shift, + vm_flags, VMALLOC_START, VMALLOC_END, + NUMA_NO_NODE, GFP_KERNEL, + __builtin_return_address(0)); + if (!area) + goto err_free_pages_array; + + addr = (unsigned long)area->addr; + size = get_vm_area_size(area); + err = vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, shift); + if (err) + goto err_free_vm_area; + + area->nr_pages = total_pages; + area->pages = pages; + + return area->addr; + +err_free_vm_area: + free_vm_area(area); +err_free_pages_array: + kvfree(pages); + return NULL; +} +EXPORT_SYMBOL_GPL(kho_restore_vmalloc); /* Handling for debug/kho/out */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 43460949ad3f..1244d2c5c384 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7273,7 +7273,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, atomic_dec(&cpu_buffer->resize_disabled); } - return 0; + return err; } int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 156e7e0bf559..d1e527cf2aae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4791,12 +4791,6 @@ int tracing_single_release_file_tr(struct inode *inode, struct file *filp) return single_release(inode, filp); } -static int tracing_mark_open(struct inode *inode, struct file *filp) -{ - stream_open(inode, filp); - return tracing_open_generic_tr(inode, filp); -} - static int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -7163,7 +7157,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) #define TRACE_MARKER_MAX_SIZE 4096 -static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user *ubuf, +static ssize_t write_marker_to_buffer(struct trace_array *tr, const char *buf, size_t cnt, unsigned long ip) { struct ring_buffer_event *event; @@ -7173,20 +7167,11 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user int meta_size; ssize_t written; size_t size; - int len; - -/* Used in tracing_mark_raw_write() as well */ -#define FAULTED_STR "<faulted>" -#define FAULTED_SIZE (sizeof(FAULTED_STR) - 1) /* '\0' is already accounted for */ meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ again: size = cnt + meta_size; - /* If less than "<faulted>", then make sure we can still add that */ - if (cnt < FAULTED_SIZE) - size += FAULTED_SIZE - cnt; - buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, tracing_gen_ctx()); @@ -7196,9 +7181,6 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user * make it smaller and try again. */ if (size > ring_buffer_max_event_size(buffer)) { - /* cnt < FAULTED size should never be bigger than max */ - if (WARN_ON_ONCE(cnt < FAULTED_SIZE)) - return -EBADF; cnt = ring_buffer_max_event_size(buffer) - meta_size; /* The above should only happen once */ if (WARN_ON_ONCE(cnt + meta_size == size)) @@ -7212,14 +7194,8 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user entry = ring_buffer_event_data(event); entry->ip = ip; - - len = copy_from_user_nofault(&entry->buf, ubuf, cnt); - if (len) { - memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); - cnt = FAULTED_SIZE; - written = -EFAULT; - } else - written = cnt; + memcpy(&entry->buf, buf, cnt); + written = cnt; if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { /* do not add \n before testing triggers, but add \0 */ @@ -7243,6 +7219,169 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user return written; } +struct trace_user_buf { + char *buf; +}; + +struct trace_user_buf_info { + struct trace_user_buf __percpu *tbuf; + int ref; +}; + + +static DEFINE_MUTEX(trace_user_buffer_mutex); +static struct trace_user_buf_info *trace_user_buffer; + +static void trace_user_fault_buffer_free(struct trace_user_buf_info *tinfo) +{ + char *buf; + int cpu; + + for_each_possible_cpu(cpu) { + buf = per_cpu_ptr(tinfo->tbuf, cpu)->buf; + kfree(buf); + } + free_percpu(tinfo->tbuf); + kfree(tinfo); +} + +static int trace_user_fault_buffer_enable(void) +{ + struct trace_user_buf_info *tinfo; + char *buf; + int cpu; + + guard(mutex)(&trace_user_buffer_mutex); + + if (trace_user_buffer) { + trace_user_buffer->ref++; + return 0; + } + + tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); + if (!tinfo) + return -ENOMEM; + + tinfo->tbuf = alloc_percpu(struct trace_user_buf); + if (!tinfo->tbuf) { + kfree(tinfo); + return -ENOMEM; + } + + tinfo->ref = 1; + + /* Clear each buffer in case of error */ + for_each_possible_cpu(cpu) { + per_cpu_ptr(tinfo->tbuf, cpu)->buf = NULL; + } + + for_each_possible_cpu(cpu) { + buf = kmalloc_node(TRACE_MARKER_MAX_SIZE, GFP_KERNEL, + cpu_to_node(cpu)); + if (!buf) { + trace_user_fault_buffer_free(tinfo); + return -ENOMEM; + } + per_cpu_ptr(tinfo->tbuf, cpu)->buf = buf; + } + + trace_user_buffer = tinfo; + + return 0; +} + +static void trace_user_fault_buffer_disable(void) +{ + struct trace_user_buf_info *tinfo; + + guard(mutex)(&trace_user_buffer_mutex); + + tinfo = trace_user_buffer; + + if (WARN_ON_ONCE(!tinfo)) + return; + + if (--tinfo->ref) + return; + + trace_user_fault_buffer_free(tinfo); + trace_user_buffer = NULL; +} + +/* Must be called with preemption disabled */ +static char *trace_user_fault_read(struct trace_user_buf_info *tinfo, + const char __user *ptr, size_t size, + size_t *read_size) +{ + int cpu = smp_processor_id(); + char *buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf; + unsigned int cnt; + int trys = 0; + int ret; + + if (size > TRACE_MARKER_MAX_SIZE) + size = TRACE_MARKER_MAX_SIZE; + *read_size = 0; + + /* + * This acts similar to a seqcount. The per CPU context switches are + * recorded, migration is disabled and preemption is enabled. The + * read of the user space memory is copied into the per CPU buffer. + * Preemption is disabled again, and if the per CPU context switches count + * is still the same, it means the buffer has not been corrupted. + * If the count is different, it is assumed the buffer is corrupted + * and reading must be tried again. + */ + + do { + /* + * If for some reason, copy_from_user() always causes a context + * switch, this would then cause an infinite loop. + * If this task is preempted by another user space task, it + * will cause this task to try again. But just in case something + * changes where the copying from user space causes another task + * to run, prevent this from going into an infinite loop. + * 100 tries should be plenty. + */ + if (WARN_ONCE(trys++ > 100, "Error: Too many tries to read user space")) + return NULL; + + /* Read the current CPU context switch counter */ + cnt = nr_context_switches_cpu(cpu); + + /* + * Preemption is going to be enabled, but this task must + * remain on this CPU. + */ + migrate_disable(); + + /* + * Now preemption is being enabed and another task can come in + * and use the same buffer and corrupt our data. + */ + preempt_enable_notrace(); + + ret = __copy_from_user(buffer, ptr, size); + + preempt_disable_notrace(); + migrate_enable(); + + /* if it faulted, no need to test if the buffer was corrupted */ + if (ret) + return NULL; + + /* + * Preemption is disabled again, now check the per CPU context + * switch counter. If it doesn't match, then another user space + * process may have schedule in and corrupted our buffer. In that + * case the copying must be retried. + */ + } while (nr_context_switches_cpu(cpu) != cnt); + + *read_size = size; + return buffer; +} + static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) @@ -7250,6 +7389,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, struct trace_array *tr = filp->private_data; ssize_t written = -ENODEV; unsigned long ip; + size_t size; + char *buf; if (tracing_disabled) return -EINVAL; @@ -7263,6 +7404,16 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (cnt > TRACE_MARKER_MAX_SIZE) cnt = TRACE_MARKER_MAX_SIZE; + /* Must have preemption disabled while having access to the buffer */ + guard(preempt_notrace)(); + + buf = trace_user_fault_read(trace_user_buffer, ubuf, cnt, &size); + if (!buf) + return -EFAULT; + + if (cnt > size) + cnt = size; + /* The selftests expect this function to be the IP address */ ip = _THIS_IP_; @@ -7270,32 +7421,28 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tr == &global_trace) { guard(rcu)(); list_for_each_entry_rcu(tr, &marker_copies, marker_list) { - written = write_marker_to_buffer(tr, ubuf, cnt, ip); + written = write_marker_to_buffer(tr, buf, cnt, ip); if (written < 0) break; } } else { - written = write_marker_to_buffer(tr, ubuf, cnt, ip); + written = write_marker_to_buffer(tr, buf, cnt, ip); } return written; } static ssize_t write_raw_marker_to_buffer(struct trace_array *tr, - const char __user *ubuf, size_t cnt) + const char *buf, size_t cnt) { struct ring_buffer_event *event; struct trace_buffer *buffer; struct raw_data_entry *entry; ssize_t written; - int size; - int len; - -#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int)) + size_t size; - size = sizeof(*entry) + cnt; - if (cnt < FAULT_SIZE_ID) - size += FAULT_SIZE_ID - cnt; + /* cnt includes both the entry->id and the data behind it. */ + size = struct_size(entry, buf, cnt - sizeof(entry->id)); buffer = tr->array_buffer.buffer; @@ -7309,14 +7456,11 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr, return -EBADF; entry = ring_buffer_event_data(event); - - len = copy_from_user_nofault(&entry->id, ubuf, cnt); - if (len) { - entry->id = -1; - memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); - written = -EFAULT; - } else - written = cnt; + unsafe_memcpy(&entry->id, buf, cnt, + "id and content already reserved on ring buffer" + "'buf' includes the 'id' and the data." + "'entry' was allocated with cnt from 'id'."); + written = cnt; __buffer_unlock_commit(buffer, event); @@ -7329,8 +7473,8 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; ssize_t written = -ENODEV; - -#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int)) + size_t size; + char *buf; if (tracing_disabled) return -EINVAL; @@ -7342,21 +7486,53 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, if (cnt < sizeof(unsigned int)) return -EINVAL; + /* Must have preemption disabled while having access to the buffer */ + guard(preempt_notrace)(); + + buf = trace_user_fault_read(trace_user_buffer, ubuf, cnt, &size); + if (!buf) + return -EFAULT; + + /* raw write is all or nothing */ + if (cnt > size) + return -EINVAL; + /* The global trace_marker_raw can go to multiple instances */ if (tr == &global_trace) { guard(rcu)(); list_for_each_entry_rcu(tr, &marker_copies, marker_list) { - written = write_raw_marker_to_buffer(tr, ubuf, cnt); + written = write_raw_marker_to_buffer(tr, buf, cnt); if (written < 0) break; } } else { - written = write_raw_marker_to_buffer(tr, ubuf, cnt); + written = write_raw_marker_to_buffer(tr, buf, cnt); } return written; } +static int tracing_mark_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = trace_user_fault_buffer_enable(); + if (ret < 0) + return ret; + + stream_open(inode, filp); + ret = tracing_open_generic_tr(inode, filp); + if (ret < 0) + trace_user_fault_buffer_disable(); + return ret; +} + +static int tracing_mark_release(struct inode *inode, struct file *file) +{ + trace_user_fault_buffer_disable(); + return tracing_release_generic_tr(inode, file); +} + static int tracing_clock_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; @@ -7764,13 +7940,13 @@ static const struct file_operations tracing_free_buffer_fops = { static const struct file_operations tracing_mark_fops = { .open = tracing_mark_open, .write = tracing_mark_write, - .release = tracing_release_generic_tr, + .release = tracing_mark_release, }; static const struct file_operations tracing_mark_raw_fops = { .open = tracing_mark_open, .write = tracing_mark_raw_write, - .release = tracing_release_generic_tr, + .release = tracing_mark_release, }; static const struct file_operations trace_clock_fops = { diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 5496758b6c76..4c45c49b06c8 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -184,7 +184,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, unsigned long flags; unsigned int trace_ctx; u64 *calltime; - int ret; + int ret = 0; if (ftrace_graph_ignore_func(gops, trace)) return 0; @@ -202,13 +202,11 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, return 0; calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime)); - if (!calltime) - return 0; - - *calltime = trace_clock_local(); - - trace_ctx = tracing_gen_ctx_flags(flags); - ret = __trace_graph_entry(tr, trace, trace_ctx); + if (calltime) { + *calltime = trace_clock_local(); + trace_ctx = tracing_gen_ctx_flags(flags); + ret = __trace_graph_entry(tr, trace, trace_ctx); + } local_dec(&data->disabled); return ret; @@ -233,11 +231,10 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace, rettime = trace_clock_local(); calltime = fgraph_retrieve_data(gops->idx, &size); - if (!calltime) - return; - - trace_ctx = tracing_gen_ctx_flags(flags); - __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); + if (calltime) { + trace_ctx = tracing_gen_ctx_flags(flags); + __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); + } local_dec(&data->disabled); } diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 12ee346820da..a9962d4497e8 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -24,6 +24,7 @@ #include <linux/sched/clock.h> #include <uapi/linux/sched/types.h> #include <linux/sched.h> +#include <linux/string.h> #include "trace.h" #ifdef CONFIG_X86_LOCAL_APIC @@ -2325,13 +2326,9 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count, if (count < 1) return 0; - buf = kmalloc(count + 1, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (copy_from_user(buf, ubuf, count)) - return -EFAULT; - buf[count] = '\0'; + buf = memdup_user_nul(ubuf, count); + if (IS_ERR(buf)) + return PTR_ERR(buf); if (!zalloc_cpumask_var(&osnoise_cpumask_new, GFP_KERNEL)) return -ENOMEM; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index bf1cb80742ae..e3f2e4f56faa 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -138,12 +138,10 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, return 0; calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime)); - if (!calltime) - return 0; - - *calltime = trace_clock_local(); - - ret = __trace_graph_entry(tr, trace, trace_ctx); + if (calltime) { + *calltime = trace_clock_local(); + ret = __trace_graph_entry(tr, trace, trace_ctx); + } local_dec(&data->disabled); preempt_enable_notrace(); @@ -169,12 +167,10 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace, rettime = trace_clock_local(); calltime = fgraph_retrieve_data(gops->idx, &size); - if (!calltime) - return; + if (calltime) + __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); - __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); local_dec(&data->disabled); - preempt_enable_notrace(); return; } diff --git a/lib/test_kho.c b/lib/test_kho.c index fe8504e3407b..60cd899ea745 100644 --- a/lib/test_kho.c +++ b/lib/test_kho.c @@ -32,6 +32,7 @@ module_param(max_mem, long, 0644); struct kho_test_state { unsigned int nr_folios; struct folio **folios; + phys_addr_t *folios_info; struct folio *fdt; __wsum csum; }; @@ -67,18 +68,15 @@ static struct notifier_block kho_test_nb = { static int kho_test_save_data(struct kho_test_state *state, void *fdt) { - phys_addr_t *folios_info; + phys_addr_t *folios_info __free(kvfree) = NULL; + struct kho_vmalloc folios_info_phys; int err = 0; - err |= fdt_begin_node(fdt, "data"); - err |= fdt_property(fdt, "nr_folios", &state->nr_folios, - sizeof(state->nr_folios)); - err |= fdt_property_placeholder(fdt, "folios_info", - state->nr_folios * sizeof(*folios_info), - (void **)&folios_info); - err |= fdt_property(fdt, "csum", &state->csum, sizeof(state->csum)); - err |= fdt_end_node(fdt); + folios_info = vmalloc_array(state->nr_folios, sizeof(*folios_info)); + if (!folios_info) + return -ENOMEM; + err = kho_preserve_vmalloc(folios_info, &folios_info_phys); if (err) return err; @@ -93,6 +91,17 @@ static int kho_test_save_data(struct kho_test_state *state, void *fdt) break; } + err |= fdt_begin_node(fdt, "data"); + err |= fdt_property(fdt, "nr_folios", &state->nr_folios, + sizeof(state->nr_folios)); + err |= fdt_property(fdt, "folios_info", &folios_info_phys, + sizeof(folios_info_phys)); + err |= fdt_property(fdt, "csum", &state->csum, sizeof(state->csum)); + err |= fdt_end_node(fdt); + + if (!err) + state->folios_info = no_free_ptr(folios_info); + return err; } @@ -209,8 +218,9 @@ err_free_folios: static int kho_test_restore_data(const void *fdt, int node) { + const struct kho_vmalloc *folios_info_phys; const unsigned int *nr_folios; - const phys_addr_t *folios_info; + phys_addr_t *folios_info; const __wsum *old_csum; __wsum csum = 0; int len; @@ -225,8 +235,12 @@ static int kho_test_restore_data(const void *fdt, int node) if (!old_csum || len != sizeof(*old_csum)) return -EINVAL; - folios_info = fdt_getprop(fdt, node, "folios_info", &len); - if (!folios_info || len != sizeof(*folios_info) * *nr_folios) + folios_info_phys = fdt_getprop(fdt, node, "folios_info", &len); + if (!folios_info_phys || len != sizeof(*folios_info_phys)) + return -EINVAL; + + folios_info = kho_restore_vmalloc(folios_info_phys); + if (!folios_info) return -EINVAL; for (int i = 0; i < *nr_folios; i++) { @@ -246,6 +260,8 @@ static int kho_test_restore_data(const void *fdt, int node) folio_put(folio); } + vfree(folios_info); + if (csum != *old_csum) return -EINVAL; @@ -304,6 +320,7 @@ static void kho_test_cleanup(void) folio_put(kho_test_state.folios[i]); kvfree(kho_test_state.folios); + vfree(kho_test_state.folios_info); folio_put(kho_test_state.fdt); } diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 8c048f9b129e..7e834467b2d8 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -328,10 +328,8 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr, } pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - if (!pte) { - walk->action = ACTION_AGAIN; + if (!pte) return 0; - } if (!pte_present(ptep_get(pte))) goto out; damon_ptep_mkold(pte, walk->vma, addr); @@ -481,10 +479,8 @@ regular_page: #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - if (!pte) { - walk->action = ACTION_AGAIN; + if (!pte) return 0; - } ptent = ptep_get(pte); if (!pte_present(ptent)) goto out; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5acca24bbabb..1b81680b4225 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4104,32 +4104,23 @@ static unsigned long deferred_split_count(struct shrinker *shrink, static bool thp_underused(struct folio *folio) { int num_zero_pages = 0, num_filled_pages = 0; - void *kaddr; int i; if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1) return false; for (i = 0; i < folio_nr_pages(folio); i++) { - kaddr = kmap_local_folio(folio, i * PAGE_SIZE); - if (!memchr_inv(kaddr, 0, PAGE_SIZE)) { - num_zero_pages++; - if (num_zero_pages > khugepaged_max_ptes_none) { - kunmap_local(kaddr); + if (pages_identical(folio_page(folio, i), ZERO_PAGE(0))) { + if (++num_zero_pages > khugepaged_max_ptes_none) return true; - } } else { /* * Another path for early exit once the number * of non-zero filled pages exceeds threshold. */ - num_filled_pages++; - if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) { - kunmap_local(kaddr); + if (++num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) return false; - } } - kunmap_local(kaddr); } return false; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6cac826cb61f..795ee393eac0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7222,6 +7222,8 @@ long hugetlb_change_protection(struct vm_area_struct *vma, psize); } spin_unlock(ptl); + + cond_resched(); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare diff --git a/mm/memblock.c b/mm/memblock.c index 120a501a887a..e23e16618e9b 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2452,8 +2452,10 @@ static int reserve_mem_kho_finalize(struct kho_serialization *ser) for (i = 0; i < reserved_mem_count; i++) { struct reserve_mem_table *map = &reserved_mem_table[i]; + struct page *page = phys_to_page(map->start); + unsigned int nr_pages = map->size >> PAGE_SHIFT; - err |= kho_preserve_phys(map->start, map->size); + err |= kho_preserve_pages(page, nr_pages); } err |= kho_preserve_folio(page_folio(kho_fdt)); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e090f29eb03b..4deda33625f4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2307,12 +2307,13 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, bool drained = false; bool raised_max_event = false; unsigned long pflags; + bool allow_spinning = gfpflags_allow_spinning(gfp_mask); retry: if (consume_stock(memcg, nr_pages)) return 0; - if (!gfpflags_allow_spinning(gfp_mask)) + if (!allow_spinning) /* Avoid the refill and flush of the older stock */ batch = nr_pages; @@ -2348,7 +2349,7 @@ retry: if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; - memcg_memory_event(mem_over_limit, MEMCG_MAX); + __memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning); raised_max_event = true; psi_memstall_enter(&pflags); @@ -2415,7 +2416,7 @@ force: * a MEMCG_MAX event. */ if (!raised_max_event) - memcg_memory_event(mem_over_limit, MEMCG_MAX); + __memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning); /* * The allocation either can't fail or will lead to more memory diff --git a/mm/migrate.c b/mm/migrate.c index aee61a980374..e3065c9edb55 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -296,19 +296,16 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list) } static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, - struct folio *folio, - unsigned long idx) + struct folio *folio, pte_t old_pte, unsigned long idx) { struct page *page = folio_page(folio, idx); - bool contains_data; pte_t newpte; - void *addr; if (PageCompound(page)) return false; VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(pte_present(ptep_get(pvmw->pte)), page); + VM_BUG_ON_PAGE(pte_present(old_pte), page); if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || mm_forbids_zeropage(pvmw->vma->vm_mm)) @@ -319,15 +316,17 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, * this subpage has been non present. If the subpage is only zero-filled * then map it to the shared zeropage. */ - addr = kmap_local_page(page); - contains_data = memchr_inv(addr, 0, PAGE_SIZE); - kunmap_local(addr); - - if (contains_data) + if (!pages_identical(page, ZERO_PAGE(0))) return false; newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address), pvmw->vma->vm_page_prot)); + + if (pte_swp_soft_dirty(old_pte)) + newpte = pte_mksoft_dirty(newpte); + if (pte_swp_uffd_wp(old_pte)) + newpte = pte_mkuffd_wp(newpte); + set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); @@ -370,13 +369,13 @@ static bool remove_migration_pte(struct folio *folio, continue; } #endif + old_pte = ptep_get(pvmw.pte); if (rmap_walk_arg->map_unused_to_zeropage && - try_to_map_unused_to_zeropage(&pvmw, folio, idx)) + try_to_map_unused_to_zeropage(&pvmw, folio, old_pte, idx)) continue; folio_get(folio); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); - old_pte = ptep_get(pvmw.pte); entry = pte_to_swp_entry(old_pte); if (!is_migration_entry_young(entry)) diff --git a/mm/slub.c b/mm/slub.c index 135c408e0515..b1f15598fbfd 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -504,10 +504,18 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node) return s->node[node]; } -/* Get the barn of the current cpu's memory node */ +/* + * Get the barn of the current cpu's closest memory node. It may not exist on + * systems with memoryless nodes but without CONFIG_HAVE_MEMORYLESS_NODES + */ static inline struct node_barn *get_barn(struct kmem_cache *s) { - return get_node(s, numa_mem_id())->barn; + struct kmem_cache_node *n = get_node(s, numa_mem_id()); + + if (!n) + return NULL; + + return n->barn; } /* @@ -4982,6 +4990,10 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, } barn = get_barn(s); + if (!barn) { + local_unlock(&s->cpu_sheaves->lock); + return NULL; + } full = barn_replace_empty_sheaf(barn, pcs->main); @@ -5153,13 +5165,20 @@ next_batch: if (unlikely(pcs->main->size == 0)) { struct slab_sheaf *full; + struct node_barn *barn; if (pcs->spare && pcs->spare->size > 0) { swap(pcs->main, pcs->spare); goto do_alloc; } - full = barn_replace_empty_sheaf(get_barn(s), pcs->main); + barn = get_barn(s); + if (!barn) { + local_unlock(&s->cpu_sheaves->lock); + return allocated; + } + + full = barn_replace_empty_sheaf(barn, pcs->main); if (full) { stat(s, BARN_GET); @@ -5314,6 +5333,7 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size) { struct slub_percpu_sheaves *pcs; struct slab_sheaf *sheaf = NULL; + struct node_barn *barn; if (unlikely(size > s->sheaf_capacity)) { @@ -5355,8 +5375,11 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size) pcs->spare = NULL; stat(s, SHEAF_PREFILL_FAST); } else { + barn = get_barn(s); + stat(s, SHEAF_PREFILL_SLOW); - sheaf = barn_get_full_or_empty_sheaf(get_barn(s)); + if (barn) + sheaf = barn_get_full_or_empty_sheaf(barn); if (sheaf && sheaf->size) stat(s, BARN_GET); else @@ -5426,7 +5449,7 @@ void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp, * If the barn has too many full sheaves or we fail to refill the sheaf, * simply flush and free it. */ - if (data_race(barn->nr_full) >= MAX_FULL_SHEAVES || + if (!barn || data_race(barn->nr_full) >= MAX_FULL_SHEAVES || refill_sheaf(s, sheaf, gfp)) { sheaf_flush_unused(s, sheaf); free_empty_sheaf(s, sheaf); @@ -5943,10 +5966,9 @@ slab_empty: * put the full sheaf there. */ static void __pcs_install_empty_sheaf(struct kmem_cache *s, - struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty) + struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty, + struct node_barn *barn) { - struct node_barn *barn; - lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock)); /* This is what we expect to find if nobody interrupted us. */ @@ -5956,8 +5978,6 @@ static void __pcs_install_empty_sheaf(struct kmem_cache *s, return; } - barn = get_barn(s); - /* * Unlikely because if the main sheaf had space, we would have just * freed to it. Get rid of our empty sheaf. @@ -6002,6 +6022,11 @@ restart: lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock)); barn = get_barn(s); + if (!barn) { + local_unlock(&s->cpu_sheaves->lock); + return NULL; + } + put_fail = false; if (!pcs->spare) { @@ -6084,7 +6109,7 @@ got_empty: } pcs = this_cpu_ptr(s->cpu_sheaves); - __pcs_install_empty_sheaf(s, pcs, empty); + __pcs_install_empty_sheaf(s, pcs, empty, barn); return pcs; } @@ -6121,8 +6146,9 @@ bool free_to_pcs(struct kmem_cache *s, void *object) static void rcu_free_sheaf(struct rcu_head *head) { + struct kmem_cache_node *n; struct slab_sheaf *sheaf; - struct node_barn *barn; + struct node_barn *barn = NULL; struct kmem_cache *s; sheaf = container_of(head, struct slab_sheaf, rcu_head); @@ -6139,7 +6165,11 @@ static void rcu_free_sheaf(struct rcu_head *head) */ __rcu_free_sheaf_prepare(s, sheaf); - barn = get_node(s, sheaf->node)->barn; + n = get_node(s, sheaf->node); + if (!n) + goto flush; + + barn = n->barn; /* due to slab_free_hook() */ if (unlikely(sheaf->size == 0)) @@ -6157,11 +6187,12 @@ static void rcu_free_sheaf(struct rcu_head *head) return; } +flush: stat(s, BARN_PUT_FAIL); sheaf_flush_unused(s, sheaf); empty: - if (data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) { + if (barn && data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) { barn_put_empty_sheaf(barn, sheaf); return; } @@ -6191,6 +6222,10 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) } barn = get_barn(s); + if (!barn) { + local_unlock(&s->cpu_sheaves->lock); + goto fail; + } empty = barn_get_empty_sheaf(barn); @@ -6304,6 +6339,8 @@ next_batch: goto do_free; barn = get_barn(s); + if (!barn) + goto no_empty; if (!pcs->spare) { empty = barn_get_empty_sheaf(barn); diff --git a/mm/util.c b/mm/util.c index 6c1d64ed0221..8989d5767528 100644 --- a/mm/util.c +++ b/mm/util.c @@ -566,6 +566,7 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { + loff_t off = (loff_t)pgoff << PAGE_SHIFT; unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; @@ -573,7 +574,7 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, ret = security_mmap_file(file, prot, flag); if (!ret) - ret = fsnotify_mmap_perm(file, prot, pgoff >> PAGE_SHIFT, len); + ret = fsnotify_mmap_perm(file, prot, off, len); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig index 0aa21fcbf6ec..ea60e3ef0834 100644 --- a/net/ceph/Kconfig +++ b/net/ceph/Kconfig @@ -6,8 +6,7 @@ config CEPH_LIB select CRYPTO_AES select CRYPTO_CBC select CRYPTO_GCM - select CRYPTO_HMAC - select CRYPTO_SHA256 + select CRYPTO_LIB_SHA256 select CRYPTO select KEYS default n diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 1fbec4853f00..f8181acaf870 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1794,9 +1794,9 @@ void ceph_msg_revoke(struct ceph_msg *msg) WARN_ON(con->state != CEPH_CON_S_OPEN); dout("%s con %p msg %p was sending\n", __func__, con, msg); if (ceph_msgr2(from_msgr(con->msgr))) - ceph_con_v2_revoke(con); + ceph_con_v2_revoke(con, msg); else - ceph_con_v1_revoke(con); + ceph_con_v1_revoke(con, msg); ceph_msg_put(con->out_msg); con->out_msg = NULL; } else { @@ -2111,11 +2111,13 @@ int ceph_con_in_msg_alloc(struct ceph_connection *con, return ret; } -void ceph_con_get_out_msg(struct ceph_connection *con) +struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con) { struct ceph_msg *msg; - BUG_ON(list_empty(&con->out_queue)); + if (list_empty(&con->out_queue)) + return NULL; + msg = list_first_entry(&con->out_queue, struct ceph_msg, list_head); WARN_ON(msg->con != con); @@ -2142,7 +2144,7 @@ void ceph_con_get_out_msg(struct ceph_connection *con) * message or in case of a fault. */ WARN_ON(con->out_msg); - con->out_msg = ceph_msg_get(msg); + return con->out_msg = ceph_msg_get(msg); } /* diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index 0cb61c76b9b8..c9e002d96319 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -169,10 +169,9 @@ static void prepare_message_data(struct ceph_msg *msg, u32 data_len) * Prepare footer for currently outgoing message, and finish things * off. Assumes out_kvec* are already valid.. we just add on to the end. */ -static void prepare_write_message_footer(struct ceph_connection *con) +static void prepare_write_message_footer(struct ceph_connection *con, + struct ceph_msg *m) { - struct ceph_msg *m = con->out_msg; - m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE; dout("prepare_write_message_footer %p\n", con); @@ -192,9 +191,9 @@ static void prepare_write_message_footer(struct ceph_connection *con) /* * Prepare headers for the next outgoing message. */ -static void prepare_write_message(struct ceph_connection *con) +static void prepare_write_message(struct ceph_connection *con, + struct ceph_msg *m) { - struct ceph_msg *m; u32 crc; con_out_kvec_reset(con); @@ -210,9 +209,6 @@ static void prepare_write_message(struct ceph_connection *con) &con->v1.out_temp_ack); } - ceph_con_get_out_msg(con); - m = con->out_msg; - dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n", m, con->out_seq, le16_to_cpu(m->hdr.type), le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len), @@ -231,31 +227,31 @@ static void prepare_write_message(struct ceph_connection *con) /* fill in hdr crc and finalize hdr */ crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc)); - con->out_msg->hdr.crc = cpu_to_le32(crc); - memcpy(&con->v1.out_hdr, &con->out_msg->hdr, sizeof(con->v1.out_hdr)); + m->hdr.crc = cpu_to_le32(crc); + memcpy(&con->v1.out_hdr, &m->hdr, sizeof(con->v1.out_hdr)); /* fill in front and middle crc, footer */ crc = crc32c(0, m->front.iov_base, m->front.iov_len); - con->out_msg->footer.front_crc = cpu_to_le32(crc); + m->footer.front_crc = cpu_to_le32(crc); if (m->middle) { crc = crc32c(0, m->middle->vec.iov_base, m->middle->vec.iov_len); - con->out_msg->footer.middle_crc = cpu_to_le32(crc); + m->footer.middle_crc = cpu_to_le32(crc); } else - con->out_msg->footer.middle_crc = 0; + m->footer.middle_crc = 0; dout("%s front_crc %u middle_crc %u\n", __func__, - le32_to_cpu(con->out_msg->footer.front_crc), - le32_to_cpu(con->out_msg->footer.middle_crc)); - con->out_msg->footer.flags = 0; + le32_to_cpu(m->footer.front_crc), + le32_to_cpu(m->footer.middle_crc)); + m->footer.flags = 0; /* is there a data payload? */ - con->out_msg->footer.data_crc = 0; + m->footer.data_crc = 0; if (m->data_length) { - prepare_message_data(con->out_msg, m->data_length); + prepare_message_data(m, m->data_length); con->v1.out_more = 1; /* data + footer will follow */ } else { /* no, queue up footer too and be done */ - prepare_write_message_footer(con); + prepare_write_message_footer(con, m); } ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING); @@ -462,9 +458,9 @@ out: * 0 -> socket full, but more to do * <0 -> error */ -static int write_partial_message_data(struct ceph_connection *con) +static int write_partial_message_data(struct ceph_connection *con, + struct ceph_msg *msg) { - struct ceph_msg *msg = con->out_msg; struct ceph_msg_data_cursor *cursor = &msg->cursor; bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); u32 crc; @@ -516,7 +512,7 @@ static int write_partial_message_data(struct ceph_connection *con) else msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; con_out_kvec_reset(con); - prepare_write_message_footer(con); + prepare_write_message_footer(con, msg); return 1; /* must return > 0 to indicate success */ } @@ -1472,6 +1468,7 @@ bad_tag: */ int ceph_con_v1_try_write(struct ceph_connection *con) { + struct ceph_msg *msg; int ret = 1; dout("try_write start %p state %d\n", con, con->state); @@ -1518,14 +1515,15 @@ more: } /* msg pages? */ - if (con->out_msg) { + msg = con->out_msg; + if (msg) { if (con->v1.out_msg_done) { - ceph_msg_put(con->out_msg); + ceph_msg_put(msg); con->out_msg = NULL; /* we're done with this one */ goto do_next; } - ret = write_partial_message_data(con); + ret = write_partial_message_data(con, msg); if (ret == 1) goto more; /* we need to send the footer, too! */ if (ret == 0) @@ -1545,8 +1543,8 @@ do_next: goto more; } /* is anything else pending? */ - if (!list_empty(&con->out_queue)) { - prepare_write_message(con); + if ((msg = ceph_con_get_out_msg(con)) != NULL) { + prepare_write_message(con, msg); goto more; } if (con->in_seq > con->in_seq_acked) { @@ -1564,10 +1562,8 @@ out: return ret; } -void ceph_con_v1_revoke(struct ceph_connection *con) +void ceph_con_v1_revoke(struct ceph_connection *con, struct ceph_msg *msg) { - struct ceph_msg *msg = con->out_msg; - WARN_ON(con->v1.out_skip); /* footer */ if (con->v1.out_msg_done) { diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 5483b4eed94e..9e39378eda00 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -709,7 +709,7 @@ static int setup_crypto(struct ceph_connection *con, dout("%s con %p con_mode %d session_key_len %d con_secret_len %d\n", __func__, con, con->v2.con_mode, session_key_len, con_secret_len); - WARN_ON(con->v2.hmac_tfm || con->v2.gcm_tfm || con->v2.gcm_req); + WARN_ON(con->v2.hmac_key_set || con->v2.gcm_tfm || con->v2.gcm_req); if (con->v2.con_mode != CEPH_CON_MODE_CRC && con->v2.con_mode != CEPH_CON_MODE_SECURE) { @@ -723,22 +723,8 @@ static int setup_crypto(struct ceph_connection *con, return 0; /* auth_none */ } - noio_flag = memalloc_noio_save(); - con->v2.hmac_tfm = crypto_alloc_shash("hmac(sha256)", 0, 0); - memalloc_noio_restore(noio_flag); - if (IS_ERR(con->v2.hmac_tfm)) { - ret = PTR_ERR(con->v2.hmac_tfm); - con->v2.hmac_tfm = NULL; - pr_err("failed to allocate hmac tfm context: %d\n", ret); - return ret; - } - - ret = crypto_shash_setkey(con->v2.hmac_tfm, session_key, - session_key_len); - if (ret) { - pr_err("failed to set hmac key: %d\n", ret); - return ret; - } + hmac_sha256_preparekey(&con->v2.hmac_key, session_key, session_key_len); + con->v2.hmac_key_set = true; if (con->v2.con_mode == CEPH_CON_MODE_CRC) { WARN_ON(con_secret_len); @@ -793,38 +779,26 @@ static int setup_crypto(struct ceph_connection *con, return 0; /* auth_x, secure mode */ } -static int ceph_hmac_sha256(struct ceph_connection *con, - const struct kvec *kvecs, int kvec_cnt, u8 *hmac) +static void ceph_hmac_sha256(struct ceph_connection *con, + const struct kvec *kvecs, int kvec_cnt, + u8 hmac[SHA256_DIGEST_SIZE]) { - SHASH_DESC_ON_STACK(desc, con->v2.hmac_tfm); /* tfm arg is ignored */ - int ret; + struct hmac_sha256_ctx ctx; int i; - dout("%s con %p hmac_tfm %p kvec_cnt %d\n", __func__, con, - con->v2.hmac_tfm, kvec_cnt); + dout("%s con %p hmac_key_set %d kvec_cnt %d\n", __func__, con, + con->v2.hmac_key_set, kvec_cnt); - if (!con->v2.hmac_tfm) { + if (!con->v2.hmac_key_set) { memset(hmac, 0, SHA256_DIGEST_SIZE); - return 0; /* auth_none */ + return; /* auth_none */ } - desc->tfm = con->v2.hmac_tfm; - ret = crypto_shash_init(desc); - if (ret) - goto out; - - for (i = 0; i < kvec_cnt; i++) { - ret = crypto_shash_update(desc, kvecs[i].iov_base, - kvecs[i].iov_len); - if (ret) - goto out; - } - - ret = crypto_shash_final(desc, hmac); - -out: - shash_desc_zero(desc); - return ret; /* auth_x, both plain and secure modes */ + /* auth_x, both plain and secure modes */ + hmac_sha256_init(&ctx, &con->v2.hmac_key); + for (i = 0; i < kvec_cnt; i++) + hmac_sha256_update(&ctx, kvecs[i].iov_base, kvecs[i].iov_len); + hmac_sha256_final(&ctx, hmac); } static void gcm_inc_nonce(struct ceph_gcm_nonce *nonce) @@ -1455,17 +1429,14 @@ static int prepare_auth_request_more(struct ceph_connection *con, static int prepare_auth_signature(struct ceph_connection *con) { void *buf; - int ret; buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE, con_secure(con))); if (!buf) return -ENOMEM; - ret = ceph_hmac_sha256(con, con->v2.in_sign_kvecs, - con->v2.in_sign_kvec_cnt, CTRL_BODY(buf)); - if (ret) - return ret; + ceph_hmac_sha256(con, con->v2.in_sign_kvecs, con->v2.in_sign_kvec_cnt, + CTRL_BODY(buf)); return prepare_control(con, FRAME_TAG_AUTH_SIGNATURE, buf, SHA256_DIGEST_SIZE); @@ -1589,10 +1560,11 @@ static int prepare_ack(struct ceph_connection *con) return prepare_control(con, FRAME_TAG_ACK, con->v2.out_buf, 8); } -static void prepare_epilogue_plain(struct ceph_connection *con, bool aborted) +static void prepare_epilogue_plain(struct ceph_connection *con, + struct ceph_msg *msg, bool aborted) { dout("%s con %p msg %p aborted %d crcs %u %u %u\n", __func__, con, - con->out_msg, aborted, con->v2.out_epil.front_crc, + msg, aborted, con->v2.out_epil.front_crc, con->v2.out_epil.middle_crc, con->v2.out_epil.data_crc); encode_epilogue_plain(con, aborted); @@ -1603,10 +1575,9 @@ static void prepare_epilogue_plain(struct ceph_connection *con, bool aborted) * For "used" empty segments, crc is -1. For unused (trailing) * segments, crc is 0. */ -static void prepare_message_plain(struct ceph_connection *con) +static void prepare_message_plain(struct ceph_connection *con, + struct ceph_msg *msg) { - struct ceph_msg *msg = con->out_msg; - prepare_head_plain(con, con->v2.out_buf, sizeof(struct ceph_msg_header2), NULL, 0, false); @@ -1647,7 +1618,7 @@ static void prepare_message_plain(struct ceph_connection *con) con->v2.out_state = OUT_S_QUEUE_DATA; } else { con->v2.out_epil.data_crc = 0; - prepare_epilogue_plain(con, false); + prepare_epilogue_plain(con, msg, false); con->v2.out_state = OUT_S_FINISH_MESSAGE; } } @@ -1659,7 +1630,8 @@ static void prepare_message_plain(struct ceph_connection *con) * allocate pages for the entire tail of the message (currently up * to ~32M) and two sgs arrays (up to ~256K each)... */ -static int prepare_message_secure(struct ceph_connection *con) +static int prepare_message_secure(struct ceph_connection *con, + struct ceph_msg *msg) { void *zerop = page_address(ceph_zero_page); struct sg_table enc_sgt = {}; @@ -1674,7 +1646,7 @@ static int prepare_message_secure(struct ceph_connection *con) if (ret) return ret; - tail_len = tail_onwire_len(con->out_msg, true); + tail_len = tail_onwire_len(msg, true); if (!tail_len) { /* * Empty message: once the head is written, @@ -1685,7 +1657,7 @@ static int prepare_message_secure(struct ceph_connection *con) } encode_epilogue_secure(con, false); - ret = setup_message_sgs(&sgt, con->out_msg, zerop, zerop, zerop, + ret = setup_message_sgs(&sgt, msg, zerop, zerop, zerop, &con->v2.out_epil, NULL, 0, false); if (ret) goto out; @@ -1714,7 +1686,7 @@ static int prepare_message_secure(struct ceph_connection *con) goto out; dout("%s con %p msg %p sg_cnt %d enc_page_cnt %d\n", __func__, con, - con->out_msg, sgt.orig_nents, enc_page_cnt); + msg, sgt.orig_nents, enc_page_cnt); con->v2.out_state = OUT_S_QUEUE_ENC_PAGE; out: @@ -1723,19 +1695,19 @@ out: return ret; } -static int prepare_message(struct ceph_connection *con) +static int prepare_message(struct ceph_connection *con, struct ceph_msg *msg) { int lens[] = { sizeof(struct ceph_msg_header2), - front_len(con->out_msg), - middle_len(con->out_msg), - data_len(con->out_msg) + front_len(msg), + middle_len(msg), + data_len(msg) }; struct ceph_frame_desc desc; int ret; dout("%s con %p msg %p logical %d+%d+%d+%d\n", __func__, con, - con->out_msg, lens[0], lens[1], lens[2], lens[3]); + msg, lens[0], lens[1], lens[2], lens[3]); if (con->in_seq > con->in_seq_acked) { dout("%s con %p in_seq_acked %llu -> %llu\n", __func__, con, @@ -1746,15 +1718,15 @@ static int prepare_message(struct ceph_connection *con) reset_out_kvecs(con); init_frame_desc(&desc, FRAME_TAG_MESSAGE, lens, 4); encode_preamble(&desc, con->v2.out_buf); - fill_header2(CTRL_BODY(con->v2.out_buf), &con->out_msg->hdr, + fill_header2(CTRL_BODY(con->v2.out_buf), &msg->hdr, con->in_seq_acked); if (con_secure(con)) { - ret = prepare_message_secure(con); + ret = prepare_message_secure(con, msg); if (ret) return ret; } else { - prepare_message_plain(con); + prepare_message_plain(con, msg); } ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING); @@ -2460,10 +2432,8 @@ static int process_auth_signature(struct ceph_connection *con, return -EINVAL; } - ret = ceph_hmac_sha256(con, con->v2.out_sign_kvecs, - con->v2.out_sign_kvec_cnt, hmac); - if (ret) - return ret; + ceph_hmac_sha256(con, con->v2.out_sign_kvecs, con->v2.out_sign_kvec_cnt, + hmac); ceph_decode_need(&p, end, SHA256_DIGEST_SIZE, bad); if (crypto_memneq(p, hmac, SHA256_DIGEST_SIZE)) { @@ -3184,20 +3154,20 @@ int ceph_con_v2_try_read(struct ceph_connection *con) } } -static void queue_data(struct ceph_connection *con) +static void queue_data(struct ceph_connection *con, struct ceph_msg *msg) { struct bio_vec bv; con->v2.out_epil.data_crc = -1; - ceph_msg_data_cursor_init(&con->v2.out_cursor, con->out_msg, - data_len(con->out_msg)); + ceph_msg_data_cursor_init(&con->v2.out_cursor, msg, + data_len(msg)); get_bvec_at(&con->v2.out_cursor, &bv); set_out_bvec(con, &bv, true); con->v2.out_state = OUT_S_QUEUE_DATA_CONT; } -static void queue_data_cont(struct ceph_connection *con) +static void queue_data_cont(struct ceph_connection *con, struct ceph_msg *msg) { struct bio_vec bv; @@ -3218,7 +3188,7 @@ static void queue_data_cont(struct ceph_connection *con) * we are done. */ reset_out_kvecs(con); - prepare_epilogue_plain(con, false); + prepare_epilogue_plain(con, msg, false); con->v2.out_state = OUT_S_FINISH_MESSAGE; } @@ -3250,7 +3220,7 @@ static void queue_enc_page(struct ceph_connection *con) con->v2.out_state = OUT_S_FINISH_MESSAGE; } -static void queue_zeros(struct ceph_connection *con) +static void queue_zeros(struct ceph_connection *con, struct ceph_msg *msg) { dout("%s con %p out_zero %d\n", __func__, con, con->v2.out_zero); @@ -3267,7 +3237,7 @@ static void queue_zeros(struct ceph_connection *con) * Once it's written, we are done patching up for the revoke. */ reset_out_kvecs(con); - prepare_epilogue_plain(con, true); + prepare_epilogue_plain(con, msg, true); con->v2.out_state = OUT_S_FINISH_MESSAGE; } @@ -3294,6 +3264,7 @@ static void finish_message(struct ceph_connection *con) static int populate_out_iter(struct ceph_connection *con) { + struct ceph_msg *msg; int ret; dout("%s con %p state %d out_state %d\n", __func__, con, con->state, @@ -3309,18 +3280,18 @@ static int populate_out_iter(struct ceph_connection *con) switch (con->v2.out_state) { case OUT_S_QUEUE_DATA: WARN_ON(!con->out_msg); - queue_data(con); + queue_data(con, con->out_msg); goto populated; case OUT_S_QUEUE_DATA_CONT: WARN_ON(!con->out_msg); - queue_data_cont(con); + queue_data_cont(con, con->out_msg); goto populated; case OUT_S_QUEUE_ENC_PAGE: queue_enc_page(con); goto populated; case OUT_S_QUEUE_ZEROS: WARN_ON(con->out_msg); /* revoked */ - queue_zeros(con); + queue_zeros(con, con->out_msg); goto populated; case OUT_S_FINISH_MESSAGE: finish_message(con); @@ -3339,9 +3310,8 @@ static int populate_out_iter(struct ceph_connection *con) pr_err("prepare_keepalive2 failed: %d\n", ret); return ret; } - } else if (!list_empty(&con->out_queue)) { - ceph_con_get_out_msg(con); - ret = prepare_message(con); + } else if ((msg = ceph_con_get_out_msg(con)) != NULL) { + ret = prepare_message(con, msg); if (ret) { pr_err("prepare_message failed: %d\n", ret); return ret; @@ -3453,17 +3423,18 @@ static u32 crc32c_zeros(u32 crc, int zero_len) return crc; } -static void prepare_zero_front(struct ceph_connection *con, int resid) +static void prepare_zero_front(struct ceph_connection *con, + struct ceph_msg *msg, int resid) { int sent; - WARN_ON(!resid || resid > front_len(con->out_msg)); - sent = front_len(con->out_msg) - resid; + WARN_ON(!resid || resid > front_len(msg)); + sent = front_len(msg) - resid; dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid); if (sent) { con->v2.out_epil.front_crc = - crc32c(-1, con->out_msg->front.iov_base, sent); + crc32c(-1, msg->front.iov_base, sent); con->v2.out_epil.front_crc = crc32c_zeros(con->v2.out_epil.front_crc, resid); } else { @@ -3474,17 +3445,18 @@ static void prepare_zero_front(struct ceph_connection *con, int resid) out_zero_add(con, resid); } -static void prepare_zero_middle(struct ceph_connection *con, int resid) +static void prepare_zero_middle(struct ceph_connection *con, + struct ceph_msg *msg, int resid) { int sent; - WARN_ON(!resid || resid > middle_len(con->out_msg)); - sent = middle_len(con->out_msg) - resid; + WARN_ON(!resid || resid > middle_len(msg)); + sent = middle_len(msg) - resid; dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid); if (sent) { con->v2.out_epil.middle_crc = - crc32c(-1, con->out_msg->middle->vec.iov_base, sent); + crc32c(-1, msg->middle->vec.iov_base, sent); con->v2.out_epil.middle_crc = crc32c_zeros(con->v2.out_epil.middle_crc, resid); } else { @@ -3495,61 +3467,64 @@ static void prepare_zero_middle(struct ceph_connection *con, int resid) out_zero_add(con, resid); } -static void prepare_zero_data(struct ceph_connection *con) +static void prepare_zero_data(struct ceph_connection *con, + struct ceph_msg *msg) { dout("%s con %p\n", __func__, con); - con->v2.out_epil.data_crc = crc32c_zeros(-1, data_len(con->out_msg)); - out_zero_add(con, data_len(con->out_msg)); + con->v2.out_epil.data_crc = crc32c_zeros(-1, data_len(msg)); + out_zero_add(con, data_len(msg)); } -static void revoke_at_queue_data(struct ceph_connection *con) +static void revoke_at_queue_data(struct ceph_connection *con, + struct ceph_msg *msg) { int boundary; int resid; - WARN_ON(!data_len(con->out_msg)); + WARN_ON(!data_len(msg)); WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter)); resid = iov_iter_count(&con->v2.out_iter); - boundary = front_len(con->out_msg) + middle_len(con->out_msg); + boundary = front_len(msg) + middle_len(msg); if (resid > boundary) { resid -= boundary; WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN); dout("%s con %p was sending head\n", __func__, con); - if (front_len(con->out_msg)) - prepare_zero_front(con, front_len(con->out_msg)); - if (middle_len(con->out_msg)) - prepare_zero_middle(con, middle_len(con->out_msg)); - prepare_zero_data(con); + if (front_len(msg)) + prepare_zero_front(con, msg, front_len(msg)); + if (middle_len(msg)) + prepare_zero_middle(con, msg, middle_len(msg)); + prepare_zero_data(con, msg); WARN_ON(iov_iter_count(&con->v2.out_iter) != resid); con->v2.out_state = OUT_S_QUEUE_ZEROS; return; } - boundary = middle_len(con->out_msg); + boundary = middle_len(msg); if (resid > boundary) { resid -= boundary; dout("%s con %p was sending front\n", __func__, con); - prepare_zero_front(con, resid); - if (middle_len(con->out_msg)) - prepare_zero_middle(con, middle_len(con->out_msg)); - prepare_zero_data(con); - queue_zeros(con); + prepare_zero_front(con, msg, resid); + if (middle_len(msg)) + prepare_zero_middle(con, msg, middle_len(msg)); + prepare_zero_data(con, msg); + queue_zeros(con, msg); return; } WARN_ON(!resid); dout("%s con %p was sending middle\n", __func__, con); - prepare_zero_middle(con, resid); - prepare_zero_data(con); - queue_zeros(con); + prepare_zero_middle(con, msg, resid); + prepare_zero_data(con, msg); + queue_zeros(con, msg); } -static void revoke_at_queue_data_cont(struct ceph_connection *con) +static void revoke_at_queue_data_cont(struct ceph_connection *con, + struct ceph_msg *msg) { int sent, resid; /* current piece of data */ - WARN_ON(!data_len(con->out_msg)); + WARN_ON(!data_len(msg)); WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter)); resid = iov_iter_count(&con->v2.out_iter); WARN_ON(!resid || resid > con->v2.out_bvec.bv_len); @@ -3568,10 +3543,11 @@ static void revoke_at_queue_data_cont(struct ceph_connection *con) con->v2.out_iter.count -= resid; out_zero_add(con, con->v2.out_cursor.total_resid); - queue_zeros(con); + queue_zeros(con, msg); } -static void revoke_at_finish_message(struct ceph_connection *con) +static void revoke_at_finish_message(struct ceph_connection *con, + struct ceph_msg *msg) { int boundary; int resid; @@ -3579,39 +3555,39 @@ static void revoke_at_finish_message(struct ceph_connection *con) WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter)); resid = iov_iter_count(&con->v2.out_iter); - if (!front_len(con->out_msg) && !middle_len(con->out_msg) && - !data_len(con->out_msg)) { + if (!front_len(msg) && !middle_len(msg) && + !data_len(msg)) { WARN_ON(!resid || resid > MESSAGE_HEAD_PLAIN_LEN); dout("%s con %p was sending head (empty message) - noop\n", __func__, con); return; } - boundary = front_len(con->out_msg) + middle_len(con->out_msg) + + boundary = front_len(msg) + middle_len(msg) + CEPH_EPILOGUE_PLAIN_LEN; if (resid > boundary) { resid -= boundary; WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN); dout("%s con %p was sending head\n", __func__, con); - if (front_len(con->out_msg)) - prepare_zero_front(con, front_len(con->out_msg)); - if (middle_len(con->out_msg)) - prepare_zero_middle(con, middle_len(con->out_msg)); + if (front_len(msg)) + prepare_zero_front(con, msg, front_len(msg)); + if (middle_len(msg)) + prepare_zero_middle(con, msg, middle_len(msg)); con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN; WARN_ON(iov_iter_count(&con->v2.out_iter) != resid); con->v2.out_state = OUT_S_QUEUE_ZEROS; return; } - boundary = middle_len(con->out_msg) + CEPH_EPILOGUE_PLAIN_LEN; + boundary = middle_len(msg) + CEPH_EPILOGUE_PLAIN_LEN; if (resid > boundary) { resid -= boundary; dout("%s con %p was sending front\n", __func__, con); - prepare_zero_front(con, resid); - if (middle_len(con->out_msg)) - prepare_zero_middle(con, middle_len(con->out_msg)); + prepare_zero_front(con, msg, resid); + if (middle_len(msg)) + prepare_zero_middle(con, msg, middle_len(msg)); con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN; - queue_zeros(con); + queue_zeros(con, msg); return; } @@ -3619,9 +3595,9 @@ static void revoke_at_finish_message(struct ceph_connection *con) if (resid > boundary) { resid -= boundary; dout("%s con %p was sending middle\n", __func__, con); - prepare_zero_middle(con, resid); + prepare_zero_middle(con, msg, resid); con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN; - queue_zeros(con); + queue_zeros(con, msg); return; } @@ -3629,7 +3605,7 @@ static void revoke_at_finish_message(struct ceph_connection *con) dout("%s con %p was sending epilogue - noop\n", __func__, con); } -void ceph_con_v2_revoke(struct ceph_connection *con) +void ceph_con_v2_revoke(struct ceph_connection *con, struct ceph_msg *msg) { WARN_ON(con->v2.out_zero); @@ -3642,13 +3618,13 @@ void ceph_con_v2_revoke(struct ceph_connection *con) switch (con->v2.out_state) { case OUT_S_QUEUE_DATA: - revoke_at_queue_data(con); + revoke_at_queue_data(con, msg); break; case OUT_S_QUEUE_DATA_CONT: - revoke_at_queue_data_cont(con); + revoke_at_queue_data_cont(con, msg); break; case OUT_S_FINISH_MESSAGE: - revoke_at_finish_message(con); + revoke_at_finish_message(con, msg); break; default: WARN(1, "bad out_state %d", con->v2.out_state); @@ -3814,10 +3790,8 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con) memzero_explicit(&con->v2.in_gcm_nonce, CEPH_GCM_IV_LEN); memzero_explicit(&con->v2.out_gcm_nonce, CEPH_GCM_IV_LEN); - if (con->v2.hmac_tfm) { - crypto_free_shash(con->v2.hmac_tfm); - con->v2.hmac_tfm = NULL; - } + memzero_explicit(&con->v2.hmac_key, sizeof(con->v2.hmac_key)); + con->v2.hmac_key_set = false; if (con->v2.gcm_req) { aead_request_free(con->v2.gcm_req); con->v2.gcm_req = NULL; diff --git a/net/core/filter.c b/net/core/filter.c index 5d1838ff1ab9..76628df1fc82 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2281,6 +2281,7 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, if (IS_ERR(dst)) goto out_drop; + skb_dst_drop(skb); skb_dst_set(skb, dst); } else if (nh->nh_family != AF_INET6) { goto out_drop; @@ -2389,6 +2390,7 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, goto out_drop; } + skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index f16f390370dc..1eb8d9f8b104 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -143,14 +143,24 @@ static inline bool xp_unused_options_set(u32 options) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 addr = desc->addr - pool->tx_metadata_len; - u64 len = desc->len + pool->tx_metadata_len; - u64 offset = addr & (pool->chunk_size - 1); + u64 len = desc->len; + u64 addr, offset; - if (!desc->len) + if (!len) return false; - if (offset + len > pool->chunk_size) + /* Can overflow if desc->addr < pool->tx_metadata_len */ + if (check_sub_overflow(desc->addr, pool->tx_metadata_len, &addr)) + return false; + + offset = addr & (pool->chunk_size - 1); + + /* + * Can't overflow: @offset is guaranteed to be < ``U32_MAX`` + * (pool->chunk_size is ``u32``), @len is guaranteed + * to be <= ``U32_MAX``. + */ + if (offset + len + pool->tx_metadata_len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt) @@ -158,27 +168,42 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, if (xp_unused_options_set(desc->options)) return false; + return true; } static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len; - u64 len = desc->len + pool->tx_metadata_len; + u64 len = desc->len; + u64 addr, end; - if (!desc->len) + if (!len) return false; + /* Can't overflow: @len is guaranteed to be <= ``U32_MAX`` */ + len += pool->tx_metadata_len; if (len > pool->chunk_size) return false; - if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt || - xp_desc_crosses_non_contig_pg(pool, addr, len)) + /* Can overflow if desc->addr is close to 0 */ + if (check_sub_overflow(xp_unaligned_add_offset_to_addr(desc->addr), + pool->tx_metadata_len, &addr)) + return false; + + if (addr >= pool->addrs_cnt) + return false; + + /* Can overflow if pool->addrs_cnt is high enough */ + if (check_add_overflow(addr, len, &end) || end > pool->addrs_cnt) + return false; + + if (xp_desc_crosses_non_contig_pg(pool, addr, len)) return false; if (xp_unused_options_set(desc->options)) return false; + return true; } diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 04b75d4d01c3..2e43c66635a2 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -108,6 +108,7 @@ const xa_mark_t RUST_CONST_HELPER_XA_PRESENT = XA_PRESENT; const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC = XA_FLAGS_ALLOC; const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC1 = XA_FLAGS_ALLOC1; +const vm_flags_t RUST_CONST_HELPER_VM_MERGEABLE = VM_MERGEABLE; #if IS_ENABLED(CONFIG_ANDROID_BINDER_IPC_RUST) #include "../../drivers/android/binder/rust_binder.h" diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 1434cb6208cb..6af392f9cd02 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -223,9 +223,11 @@ KBUILD_USERCFLAGS += -Werror KBUILD_USERLDFLAGS += -Wl,--fatal-warnings KBUILD_RUSTFLAGS += -Dwarnings -endif - -# Hostprog flags are used during build bootstrapping and can not rely on CONFIG_ symbols. +# While hostprog flags are used during build bootstrapping (thus should not +# depend on CONFIG_ symbols), -Werror is disruptive and should be opted into. +# Only apply -Werror to hostprogs built after the initial Kconfig stage. KBUILD_HOSTCFLAGS += -Werror KBUILD_HOSTLDFLAGS += -Wl,--fatal-warnings KBUILD_HOSTRUSTFLAGS += -Dwarnings + +endif diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index 7c6ae9886f8f..ced4379550d7 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -82,9 +82,12 @@ endif # --------------------------------------------------------------------------- remove-section-y := .modinfo -remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' +remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' '!.rel*.dyn' +# for compatibility with binutils < 2.32 +# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c12d9fa2afe7abcbe407a00e15719e1a1350c2a7 +remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel.*' -remove-symbols := -w --strip-symbol='__mod_device_table__*' +remove-symbols := -w --strip-unneeded-symbol='__mod_device_table__*' # To avoid warnings: "empty loadable segment detected at ..." from GNU objcopy, # it is necessary to remove the PT_LOAD flag from the segment. diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index c77dc40f7689..15d113a1bc1d 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -788,6 +788,7 @@ class PrinterHelpersHeader(Printer): 'struct task_struct', 'struct cgroup', 'struct path', + 'const struct path', 'struct btf_ptr', 'struct inode', 'struct socket', diff --git a/sound/hda/codecs/hdmi/hdmi.c b/sound/hda/codecs/hdmi/hdmi.c index dc38bfd9dba5..111c9b5335af 100644 --- a/sound/hda/codecs/hdmi/hdmi.c +++ b/sound/hda/codecs/hdmi/hdmi.c @@ -1549,6 +1549,7 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x83e2, "HP EliteDesk 800 G4", 1), SND_PCI_QUIRK(0x103c, 0x83ef, "HP MP9 G4 Retail System AMS", 1), SND_PCI_QUIRK(0x103c, 0x845a, "HP EliteDesk 800 G4 DM 65W", 1), + SND_PCI_QUIRK(0x103c, 0x83f3, "HP ProDesk 400", 1), SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 3c42f66fe000..214eb9df6ef8 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3735,6 +3735,7 @@ enum { ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC, ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1, ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC, + ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -6164,6 +6165,14 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE, }, + [ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x17, 0x90170151 }, /* Internal Speaker LFE */ + { 0x1e, 0x90170150 }, /* Internal Speaker */ + { } + }, + } }; static const struct hda_quirk alc269_fixup_tbl[] = { @@ -6718,6 +6727,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1652, "ASUS ROG Zephyrus Do 15 SE", ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 4dea442d8c30..a126f04c3ed7 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -474,6 +474,12 @@ static void tasdevice_dspfw_init(void *context) if (tas_priv->fmw->nr_configurations > 0) tas_priv->cur_conf = 0; + /* Init common setting for different audio profiles */ + if (tas_priv->rcabin.init_profile_id >= 0) + tasdevice_select_cfg_blk(tas_priv, + tas_priv->rcabin.init_profile_id, + TASDEVICE_BIN_BLK_PRE_POWER_UP); + /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ @@ -770,6 +776,12 @@ static int tas2781_system_resume(struct device *dev) tasdevice_reset(tas_hda->priv); tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog); + /* Init common setting for different audio profiles */ + if (tas_hda->priv->rcabin.init_profile_id >= 0) + tasdevice_select_cfg_blk(tas_hda->priv, + tas_hda->priv->rcabin.init_profile_id, + TASDEVICE_BIN_BLK_PRE_POWER_UP); + if (tas_hda->priv->playback_started) tasdevice_tuning_switch(tas_hda->priv, 0); diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c index 70700bdb80a1..5ea40c1b159a 100644 --- a/sound/soc/codecs/rt722-sdca-sdw.c +++ b/sound/soc/codecs/rt722-sdca-sdw.c @@ -21,7 +21,7 @@ static int rt722_sdca_mbq_size(struct device *dev, unsigned int reg) switch (reg) { case 0x2f01 ... 0x2f0a: case 0x2f35 ... 0x2f36: - case 0x2f50: + case 0x2f50 ... 0x2f52: case 0x2f54: case 0x2f58 ... 0x2f5d: case SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0): diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index 333611490ae3..79b8b7e70a33 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1378,6 +1378,9 @@ static void rt722_sdca_dmic_preset(struct rt722_sdca_priv *rt722) /* PHYtiming TDZ/TZD control */ regmap_write(rt722->regmap, 0x2f03, 0x06); + if (rt722->hw_vid == RT722_VB) + regmap_write(rt722->regmap, 0x2f52, 0x00); + /* clear flag */ regmap_write(rt722->regmap, SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0), @@ -1415,6 +1418,9 @@ static void rt722_sdca_amp_preset(struct rt722_sdca_priv *rt722) SDW_SDCA_CTL(FUNC_NUM_AMP, RT722_SDCA_ENT_OT23, RT722_SDCA_CTL_VENDOR_DEF, CH_08), 0x04); + if (rt722->hw_vid == RT722_VB) + regmap_write(rt722->regmap, 0x2f54, 0x00); + /* clear flag */ regmap_write(rt722->regmap, SDW_SDCA_CTL(FUNC_NUM_AMP, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0), @@ -1506,6 +1512,9 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, 0x0010); + if (rt722->hw_vid == RT722_VB) + regmap_write(rt722->regmap, 0x2f51, 0x00); + /* clear flag */ regmap_write(rt722->regmap, SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT722_SDCA_ENT0, RT722_SDCA_CTL_FUNC_STATUS, 0), @@ -1516,6 +1525,7 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave) { struct rt722_sdca_priv *rt722 = dev_get_drvdata(dev); + unsigned int val; rt722->disable_irq = false; @@ -1545,6 +1555,10 @@ int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave) pm_runtime_get_noresume(&slave->dev); + rt722_sdca_index_read(rt722, RT722_VENDOR_REG, RT722_JD_PRODUCT_NUM, &val); + rt722->hw_vid = (val & 0x0f00) >> 8; + dev_dbg(&slave->dev, "%s hw_vid=0x%x\n", __func__, rt722->hw_vid); + rt722_sdca_dmic_preset(rt722); rt722_sdca_amp_preset(rt722); rt722_sdca_jack_preset(rt722); diff --git a/sound/soc/codecs/rt722-sdca.h b/sound/soc/codecs/rt722-sdca.h index 3c383705dd3c..823abee9ab76 100644 --- a/sound/soc/codecs/rt722-sdca.h +++ b/sound/soc/codecs/rt722-sdca.h @@ -39,6 +39,7 @@ struct rt722_sdca_priv { /* For DMIC */ bool fu1e_dapm_mute; bool fu1e_mixer_mute[4]; + int hw_vid; }; struct rt722_sdca_dmic_kctrl_priv { @@ -233,6 +234,11 @@ enum rt722_sdca_jd_src { RT722_JD1, }; +enum rt722_sdca_version { + RT722_VA, + RT722_VB, +}; + int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave); int rt722_sdca_init(struct device *dev, struct regmap *regmap, struct sdw_slave *slave); int rt722_sdca_index_write(struct rt722_sdca_priv *rt722, diff --git a/sound/soc/meson/aiu-encoder-i2s.c b/sound/soc/meson/aiu-encoder-i2s.c index a0dd914c8ed1..3b4061508c18 100644 --- a/sound/soc/meson/aiu-encoder-i2s.c +++ b/sound/soc/meson/aiu-encoder-i2s.c @@ -236,8 +236,12 @@ static int aiu_encoder_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) inv == SND_SOC_DAIFMT_IB_IF) val |= AIU_CLK_CTRL_LRCLK_INVERT; - if (inv == SND_SOC_DAIFMT_IB_NF || - inv == SND_SOC_DAIFMT_IB_IF) + /* + * The SoC changes data on the rising edge of the bitclock + * so an inversion of the bitclock is required in normal mode + */ + if (inv == SND_SOC_DAIFMT_NB_NF || + inv == SND_SOC_DAIFMT_NB_IF) val |= AIU_CLK_CTRL_AOCLK_INVERT; /* Signal skew */ @@ -328,4 +332,3 @@ const struct snd_soc_dai_ops aiu_encoder_i2s_dai_ops = { .startup = aiu_encoder_i2s_startup, .shutdown = aiu_encoder_i2s_shutdown, }; - diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c index 1dd8d2092c3b..da6c1e7263cd 100644 --- a/sound/soc/sof/intel/hda-pcm.c +++ b/sound/soc/sof/intel/hda-pcm.c @@ -29,6 +29,8 @@ #define SDnFMT_BITS(x) ((x) << 4) #define SDnFMT_CHAN(x) ((x) << 0) +#define HDA_MAX_PERIOD_TIME_HEADROOM 10 + static bool hda_always_enable_dmi_l1; module_param_named(always_enable_dmi_l1, hda_always_enable_dmi_l1, bool, 0444); MODULE_PARM_DESC(always_enable_dmi_l1, "SOF HDA always enable DMI l1"); @@ -291,19 +293,30 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev, * On playback start the DMA will transfer dsp_max_burst_size_in_ms * amount of data in one initial burst to fill up the host DMA buffer. * Consequent DMA burst sizes are shorter and their length can vary. - * To make sure that userspace allocate large enough ALSA buffer we need - * to place a constraint on the buffer time. + * To avoid immediate xrun by the initial burst we need to place + * constraint on the period size (via PERIOD_TIME) to cover the size of + * the host buffer. + * We need to add headroom of max 10ms as the firmware needs time to + * settle to the 1ms pacing and initially it can run faster for few + * internal periods. * * On capture the DMA will transfer 1ms chunks. - * - * Exact dsp_max_burst_size_in_ms constraint is racy, so set the - * constraint to a minimum of 2x dsp_max_burst_size_in_ms. */ - if (spcm->stream[direction].dsp_max_burst_size_in_ms) + if (spcm->stream[direction].dsp_max_burst_size_in_ms) { + unsigned int period_time = spcm->stream[direction].dsp_max_burst_size_in_ms; + + /* + * add headroom over the maximum burst size to cover the time + * needed for the DMA pace to settle. + * Limit the headroom time to HDA_MAX_PERIOD_TIME_HEADROOM + */ + period_time += min(period_time, HDA_MAX_PERIOD_TIME_HEADROOM); + snd_pcm_hw_constraint_minmax(substream->runtime, - SNDRV_PCM_HW_PARAM_BUFFER_TIME, - spcm->stream[direction].dsp_max_burst_size_in_ms * USEC_PER_MSEC * 2, + SNDRV_PCM_HW_PARAM_PERIOD_TIME, + period_time * USEC_PER_MSEC, UINT_MAX); + } /* binding pcm substream to hda stream */ substream->runtime->private_data = &dsp_stream->hstream; diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index a34f472ef175..9c3b3a9aaf83 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -1129,11 +1129,36 @@ u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev, struct snd_soc_component *component, struct snd_pcm_substream *substream) { - struct hdac_stream *hstream = substream->runtime->private_data; - struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream); + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct snd_soc_pcm_runtime *be_rtd = NULL; + struct hdac_ext_stream *hext_stream; + struct snd_soc_dai *cpu_dai; + struct snd_soc_dpcm *dpcm; u32 llp_l, llp_u; /* + * The LLP needs to be read from the Link DMA used for this FE as it is + * allowed to use any combination of Link and Host channels + */ + for_each_dpcm_be(rtd, substream->stream, dpcm) { + if (dpcm->fe != rtd) + continue; + + be_rtd = dpcm->be; + } + + if (!be_rtd) + return 0; + + cpu_dai = snd_soc_rtd_to_cpu(be_rtd, 0); + if (!cpu_dai) + return 0; + + hext_stream = snd_soc_dai_get_dma_data(cpu_dai, substream); + if (!hext_stream) + return 0; + + /* * The pplc_addr have been calculated during probe in * hda_dsp_stream_init(): * pplc_addr = sdev->bar[HDA_DSP_PP_BAR] + diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c index 473d416bc910..f449362a2905 100644 --- a/sound/soc/sof/ipc3-topology.c +++ b/sound/soc/sof/ipc3-topology.c @@ -2473,11 +2473,6 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif if (ret < 0) return ret; - /* free all the scheduler widgets now */ - ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify); - if (ret < 0) - return ret; - /* * Tear down all pipelines associated with PCMs that did not get suspended * and unset the prepare flag so that they can be set up again during resume. @@ -2493,6 +2488,11 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif } } + /* free all the scheduler widgets now. This will also power down the secondary cores */ + ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify); + if (ret < 0) + return ret; + list_for_each_entry(sroute, &sdev->route_list, list) sroute->setup = false; diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index 24f82a6f3610..6d81969e181c 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -19,12 +19,14 @@ * struct sof_ipc4_timestamp_info - IPC4 timestamp info * @host_copier: the host copier of the pcm stream * @dai_copier: the dai copier of the pcm stream - * @stream_start_offset: reported by fw in memory window (converted to frames) - * @stream_end_offset: reported by fw in memory window (converted to frames) + * @stream_start_offset: reported by fw in memory window (converted to + * frames at host_copier sampling rate) + * @stream_end_offset: reported by fw in memory window (converted to + * frames at host_copier sampling rate) * @llp_offset: llp offset in memory window - * @boundary: wrap boundary should be used for the LLP frame counter * @delay: Calculated and stored in pointer callback. The stored value is - * returned in the delay callback. + * returned in the delay callback. Expressed in frames at host copier + * sampling rate. */ struct sof_ipc4_timestamp_info { struct sof_ipc4_copier *host_copier; @@ -33,7 +35,6 @@ struct sof_ipc4_timestamp_info { u64 stream_end_offset; u32 llp_offset; - u64 boundary; snd_pcm_sframes_t delay; }; @@ -48,6 +49,18 @@ struct sof_ipc4_pcm_stream_priv { bool chain_dma_allocated; }; +/* + * Modulus to use to compare host and link position counters. The sampling + * rates may be different, so the raw hardware counters will wrap + * around at different times. To calculate differences, use + * DELAY_BOUNDARY as a common modulus. This value must be smaller than + * the wrap-around point of any hardware counter, and larger than any + * valid delay measurement. + */ +#define DELAY_BOUNDARY U32_MAX + +#define DELAY_MAX (DELAY_BOUNDARY >> 1) + static inline struct sof_ipc4_timestamp_info * sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps) { @@ -1049,6 +1062,35 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, return 0; } +static u64 sof_ipc4_frames_dai_to_host(struct sof_ipc4_timestamp_info *time_info, u64 value) +{ + u64 dai_rate, host_rate; + + if (!time_info->dai_copier || !time_info->host_copier) + return value; + + /* + * copiers do not change sampling rate, so we can use the + * out_format independently of stream direction + */ + dai_rate = time_info->dai_copier->data.out_format.sampling_frequency; + host_rate = time_info->host_copier->data.out_format.sampling_frequency; + + if (!dai_rate || !host_rate || dai_rate == host_rate) + return value; + + /* take care not to overflow u64, rates can be up to 768000 */ + if (value > U32_MAX) { + value = div64_u64(value, dai_rate); + value *= host_rate; + } else { + value *= host_rate; + value = div64_u64(value, dai_rate); + } + + return value; +} + static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream, struct snd_sof_pcm_stream *sps, @@ -1068,7 +1110,7 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, return -EINVAL; } else if (host_copier->data.gtw_cfg.node_id == SOF_IPC4_CHAIN_DMA_NODE_ID) { /* - * While the firmware does not supports time_info reporting for + * While the firmware does not support time_info reporting for * streams using ChainDMA, it is granted that ChainDMA can only * be used on Host+Link pairs where the link position is * accessible from the host side. @@ -1076,10 +1118,16 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, * Enable delay calculation in case of ChainDMA via host * accessible registers. * - * The ChainDMA uses 2x 1ms ping-pong buffer, dai side starts - * when 1ms data is available + * The ChainDMA prefills the link DMA with a preamble + * of zero samples. Set the stream start offset based + * on size of the preamble (driver provided fifo size + * multiplied by 2.5). We add 1ms of margin as the FW + * will align the buffer size to DMA hardware + * alignment that is not known to host. */ - time_info->stream_start_offset = substream->runtime->rate / MSEC_PER_SEC; + int pre_ms = SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS * 5 / 2 + 1; + + time_info->stream_start_offset = pre_ms * substream->runtime->rate / MSEC_PER_SEC; goto out; } @@ -1099,14 +1147,13 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, time_info->stream_end_offset = ppl_reg.stream_end_offset; do_div(time_info->stream_end_offset, dai_sample_size); + /* convert to host frame time */ + time_info->stream_start_offset = + sof_ipc4_frames_dai_to_host(time_info, time_info->stream_start_offset); + time_info->stream_end_offset = + sof_ipc4_frames_dai_to_host(time_info, time_info->stream_end_offset); + out: - /* - * Calculate the wrap boundary need to be used for delay calculation - * The host counter is in bytes, it will wrap earlier than the frames - * based link counter. - */ - time_info->boundary = div64_u64(~((u64)0), - frames_to_bytes(substream->runtime, 1)); /* Initialize the delay value to 0 (no delay) */ time_info->delay = 0; @@ -1149,6 +1196,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, /* For delay calculation we need the host counter */ host_cnt = snd_sof_pcm_get_host_byte_counter(sdev, component, substream); + + /* Store the original value to host_ptr */ host_ptr = host_cnt; /* convert the host_cnt to frames */ @@ -1167,6 +1216,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, sof_mailbox_read(sdev, time_info->llp_offset, &llp, sizeof(llp)); dai_cnt = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l; } + + dai_cnt = sof_ipc4_frames_dai_to_host(time_info, dai_cnt); dai_cnt += time_info->stream_end_offset; /* In two cases dai dma counter is not accurate @@ -1200,8 +1251,9 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, dai_cnt -= time_info->stream_start_offset; } - /* Wrap the dai counter at the boundary where the host counter wraps */ - div64_u64_rem(dai_cnt, time_info->boundary, &dai_cnt); + /* Convert to a common base before comparisons */ + dai_cnt &= DELAY_BOUNDARY; + host_cnt &= DELAY_BOUNDARY; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { head_cnt = host_cnt; @@ -1211,14 +1263,18 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, tail_cnt = host_cnt; } - if (head_cnt < tail_cnt) { - time_info->delay = time_info->boundary - tail_cnt + head_cnt; - goto out; - } + if (unlikely(head_cnt < tail_cnt)) + time_info->delay = DELAY_BOUNDARY - tail_cnt + head_cnt; + else + time_info->delay = head_cnt - tail_cnt; - time_info->delay = head_cnt - tail_cnt; + if (time_info->delay > DELAY_MAX) { + spcm_dbg_ratelimited(spcm, substream->stream, + "inaccurate delay, host %llu dai_cnt %llu", + host_cnt, dai_cnt); + time_info->delay = 0; + } -out: /* * Convert the host byte counter to PCM pointer which wraps in buffer * and it is in frames diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index b6a732d0adb4..221e9d4052b8 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -33,7 +33,6 @@ MODULE_PARM_DESC(ipc4_ignore_cpc, #define SOF_IPC4_GAIN_PARAM_ID 0 #define SOF_IPC4_TPLG_ABI_SIZE 6 -#define SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS 2 static DEFINE_IDA(alh_group_ida); static DEFINE_IDA(pipeline_ida); @@ -666,8 +665,13 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget) swidget->tuples, swidget->num_tuples, sizeof(u32), 1); /* Set default DMA buffer size if it is not specified in topology */ - if (!sps->dsp_max_burst_size_in_ms) - sps->dsp_max_burst_size_in_ms = SOF_IPC4_MIN_DMA_BUFFER_SIZE; + if (!sps->dsp_max_burst_size_in_ms) { + struct snd_sof_widget *pipe_widget = swidget->spipe->pipe_widget; + struct sof_ipc4_pipeline *pipeline = pipe_widget->private; + + sps->dsp_max_burst_size_in_ms = pipeline->use_chain_dma ? + SOF_IPC4_CHAIN_DMA_BUFFER_SIZE : SOF_IPC4_MIN_DMA_BUFFER_SIZE; + } } else { /* Capture data is copied from DSP to host in 1ms bursts */ spcm->stream[dir].dsp_max_burst_size_in_ms = 1; diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h index dfa1a6c2ffa8..191b51d97993 100644 --- a/sound/soc/sof/ipc4-topology.h +++ b/sound/soc/sof/ipc4-topology.h @@ -70,8 +70,11 @@ #define SOF_IPC4_CHAIN_DMA_NODE_ID 0x7fffffff #define SOF_IPC4_INVALID_NODE_ID 0xffffffff -/* FW requires minimum 2ms DMA buffer size */ -#define SOF_IPC4_MIN_DMA_BUFFER_SIZE 2 +/* FW requires minimum 4ms DMA buffer size */ +#define SOF_IPC4_MIN_DMA_BUFFER_SIZE 4 + +/* ChainDMA in fw uses 5ms DMA buffer */ +#define SOF_IPC4_CHAIN_DMA_BUFFER_SIZE 5 /* * The base of multi-gateways. Multi-gateways addressing starts from @@ -263,6 +266,8 @@ struct sof_ipc4_dma_stream_ch_map { #define SOF_IPC4_DMA_METHOD_HDA 1 #define SOF_IPC4_DMA_METHOD_GPDMA 2 /* defined for consistency but not used */ +#define SOF_IPC4_CHAIN_DMA_BUF_SIZE_MS 2 + /** * struct sof_ipc4_dma_config: DMA configuration * @dma_method: HDAudio or GPDMA diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index db6973c8eac3..a8b93a2eec9c 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -629,6 +629,11 @@ void snd_sof_pcm_init_elapsed_work(struct work_struct *work); (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir, \ ##__VA_ARGS__) +#define spcm_dbg_ratelimited(__spcm, __dir, __fmt, ...) \ + dev_dbg_ratelimited((__spcm)->scomp->dev, "pcm%u (%s), dir %d: " __fmt, \ + (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir, \ + ##__VA_ARGS__) + #define spcm_err(__spcm, __dir, __fmt, ...) \ dev_err((__spcm)->scomp->dev, "%s: pcm%u (%s), dir %d: " __fmt, \ __func__, (__spcm)->pcm.pcm_id, (__spcm)->pcm.pcm_name, __dir, \ diff --git a/sound/usb/fcp.c b/sound/usb/fcp.c index 5ee8d8b66058..11e9a96b46ff 100644 --- a/sound/usb/fcp.c +++ b/sound/usb/fcp.c @@ -641,12 +641,9 @@ static int fcp_ioctl_set_meter_map(struct usb_mixer_interface *mixer, return -EINVAL; /* Allocate and copy the map data */ - tmp_map = kmalloc_array(map.map_size, sizeof(s16), GFP_KERNEL); - if (!tmp_map) - return -ENOMEM; - - if (copy_from_user(tmp_map, arg->map, map.map_size * sizeof(s16))) - return -EFAULT; + tmp_map = memdup_array_user(arg->map, map.map_size, sizeof(s16)); + if (IS_ERR(tmp_map)) + return PTR_ERR(tmp_map); err = validate_meter_map(tmp_map, map.map_size, map.meter_slots); if (err < 0) diff --git a/tools/arch/x86/include/asm/asm.h b/tools/arch/x86/include/asm/asm.h index dbe39b44256b..6e1b357c374b 100644 --- a/tools/arch/x86/include/asm/asm.h +++ b/tools/arch/x86/include/asm/asm.h @@ -108,18 +108,6 @@ #endif -/* - * Macros to generate condition code outputs from inline assembly, - * The output operand must be type "bool". - */ -#ifdef __GCC_ASM_FLAG_OUTPUTS__ -# define CC_SET(c) "\n\t/* output condition code " #c "*/\n" -# define CC_OUT(c) "=@cc" #c -#else -# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n" -# define CC_OUT(c) [_cc_ ## c] "=qm" -#endif - #ifdef __KERNEL__ /* Exception table entry */ diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h index df5d9fa84dba..aceac94632c8 100644 --- a/tools/include/linux/objtool_types.h +++ b/tools/include/linux/objtool_types.h @@ -65,5 +65,6 @@ struct unwind_hint { #define ANNOTYPE_IGNORE_ALTS 6 #define ANNOTYPE_INTRA_FUNCTION_CALL 7 #define ANNOTYPE_REACHABLE 8 +#define ANNOTYPE_NOCFI 9 #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ae83d8649ef1..6829936d33f5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4891,7 +4891,7 @@ union bpf_attr { * * **-ENOENT** if the bpf_local_storage cannot be found. * - * long bpf_d_path(struct path *path, char *buf, u32 sz) + * long bpf_d_path(const struct path *path, char *buf, u32 sz) * Description * Return full path for given **struct path** object, which * needs to be the kernel BTF *path* object. The path is diff --git a/tools/lib/bpf/libbpf_utils.c b/tools/lib/bpf/libbpf_utils.c index 5d66bc6ff098..ac3beae54cf6 100644 --- a/tools/lib/bpf/libbpf_utils.c +++ b/tools/lib/bpf/libbpf_utils.c @@ -148,16 +148,20 @@ const char *libbpf_errstr(int err) } } -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpacked" -#pragma GCC diagnostic ignored "-Wattributes" -struct __packed_u32 { __u32 __val; } __attribute__((packed)); -#pragma GCC diagnostic pop - -#define get_unaligned_be32(p) be32_to_cpu((((struct __packed_u32 *)(p))->__val)) -#define put_unaligned_be32(v, p) do { \ - ((struct __packed_u32 *)(p))->__val = cpu_to_be32(v); \ -} while (0) +static inline __u32 get_unaligned_be32(const void *p) +{ + __be32 val; + + memcpy(&val, p, sizeof(val)); + return be32_to_cpu(val); +} + +static inline void put_unaligned_be32(__u32 val, void *p) +{ + __be32 be_val = cpu_to_be32(val); + + memcpy(p, &be_val, sizeof(be_val)); +} #define SHA256_BLOCK_LENGTH 64 #define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z))) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a72059fcbc83..a5770570b106 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2392,6 +2392,8 @@ static int __annotate_ifc(struct objtool_file *file, int type, struct instructio static int __annotate_late(struct objtool_file *file, int type, struct instruction *insn) { + struct symbol *sym; + switch (type) { case ANNOTYPE_NOENDBR: /* early */ @@ -2433,6 +2435,15 @@ static int __annotate_late(struct objtool_file *file, int type, struct instructi insn->dead_end = false; break; + case ANNOTYPE_NOCFI: + sym = insn->sym; + if (!sym) { + ERROR_INSN(insn, "dodgy NOCFI annotation"); + return -1; + } + insn->sym->nocfi = 1; + break; + default: ERROR_INSN(insn, "Unknown annotation type: %d", type); return -1; @@ -3994,6 +4005,37 @@ static int validate_retpoline(struct objtool_file *file) warnings++; } + if (!opts.cfi) + return warnings; + + /* + * kCFI call sites look like: + * + * movl $(-0x12345678), %r10d + * addl -4(%r11), %r10d + * jz 1f + * ud2 + * 1: cs call __x86_indirect_thunk_r11 + * + * Verify all indirect calls are kCFI adorned by checking for the + * UD2. Notably, doing __nocfi calls to regular (cfi) functions is + * broken. + */ + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + struct symbol *sym = insn->sym; + + if (sym && (sym->type == STT_NOTYPE || + sym->type == STT_FUNC) && !sym->nocfi) { + struct instruction *prev = + prev_insn_same_sym(file, insn); + + if (!prev || prev->type != INSN_BUG) { + WARN_INSN(insn, "no-cfi indirect call!"); + warnings++; + } + } + } + return warnings; } diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 0a2fa3ac0079..df8434d3b744 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -70,6 +70,7 @@ struct symbol { u8 local_label : 1; u8 frame_pointer : 1; u8 ignore : 1; + u8 nocfi : 1; struct list_head pv_target; struct reloc *relocs; struct section *group_sec; diff --git a/tools/perf/bench/find-bit-bench.c b/tools/perf/bench/find-bit-bench.c index 7e25b0e413f6..e697c20951bc 100644 --- a/tools/perf/bench/find-bit-bench.c +++ b/tools/perf/bench/find-bit-bench.c @@ -37,7 +37,7 @@ static noinline void workload(int val) accumulator++; } -#if (defined(__i386__) || defined(__x86_64__)) && defined(__GCC_ASM_FLAG_OUTPUTS__) +#if defined(__i386__) || defined(__x86_64__) static bool asm_test_bit(long nr, const unsigned long *addr) { bool oldbit; diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_htab.c b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c new file mode 100644 index 000000000000..16bd74be3dbe --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_pinning_htab.skel.h" + +static void unpin_map(const char *map_name, const char *pin_path) +{ + struct test_pinning_htab *skel; + struct bpf_map *map; + int err; + + skel = test_pinning_htab__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel open_and_load")) + return; + + map = bpf_object__find_map_by_name(skel->obj, map_name); + if (!ASSERT_OK_PTR(map, "bpf_object__find_map_by_name")) + goto out; + + err = bpf_map__pin(map, pin_path); + if (!ASSERT_OK(err, "bpf_map__pin")) + goto out; + + err = bpf_map__unpin(map, pin_path); + ASSERT_OK(err, "bpf_map__unpin"); +out: + test_pinning_htab__destroy(skel); +} + +void test_pinning_htab(void) +{ + if (test__start_subtest("timer_prealloc")) + unpin_map("timer_prealloc", "/sys/fs/bpf/timer_prealloc"); + if (test__start_subtest("timer_no_prealloc")) + unpin_map("timer_no_prealloc", "/sys/fs/bpf/timer_no_prealloc"); +} diff --git a/tools/testing/selftests/bpf/progs/test_pinning_htab.c b/tools/testing/selftests/bpf/progs/test_pinning_htab.c new file mode 100644 index 000000000000..ae227930c73c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pinning_htab.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct timer_val { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, struct timer_val); + __uint(max_entries, 1); +} timer_prealloc SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, struct timer_val); + __uint(max_entries, 1); + __uint(map_flags, BPF_F_NO_PREALLOC); +} timer_no_prealloc SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c index 3e2d76ee8050..55398c04290a 100644 --- a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c +++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c @@ -70,7 +70,7 @@ __success int BPF_PROG(path_d_path_from_file_argument, struct file *file) { int ret; - struct path *path; + const struct path *path; /* The f_path member is a path which is embedded directly within a * file. Therefore, a pointer to such embedded members are still diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c index 75e9561ba313..b7296edc6626 100644 --- a/usr/gen_init_cpio.c +++ b/usr/gen_init_cpio.c @@ -112,7 +112,10 @@ static int cpio_trailer(void) push_pad(padlen(offset, 512)) < 0) return -1; - return fsync(outfd); + if (fsync(outfd) < 0 && errno != EINVAL) + return -1; + + return 0; } static int cpio_mkslink(const char *name, const char *target, diff --git a/usr/include/headers_check.pl b/usr/include/headers_check.pl index 21c2fb9520e6..1fbc8785f96e 100755 --- a/usr/include/headers_check.pl +++ b/usr/include/headers_check.pl @@ -155,6 +155,8 @@ sub check_sizetypes if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) { check_include_typesh($included); } + # strip single-line comments, as types may be referenced within them + $line =~ s@/\*.*?\*/@@; if ($line =~ m/__[us](8|16|32|64)\b/) { printf STDERR "$filename:$lineno: " . "found __[us]{8,16,32,64} type " . |