diff --git a/.mailmap b/.mailmap index 8fb9f3898d7a..6803f3bd2865 100644 --- a/.mailmap +++ b/.mailmap @@ -242,6 +242,10 @@ Daniele Alessandrelli Danila Tikhonov Danilo Krummrich +Darrick J. Wong +Darrick J. Wong +Darrick J. Wong +Darrick J. Wong David Brownell David Collins David Gow @@ -577,6 +581,9 @@ Mark Brown Mark Starovoytov Markus Schneider-Pargmann Mark Yao +Martin K. Petersen +Martin K. Petersen +Martin K. Petersen Martin Kepplinger-Novakovic Martyna Szapar-Mudlaw Mathieu Othacehe diff --git a/CREDITS b/CREDITS index f8a33916e2a5..bba5071c29a5 100644 --- a/CREDITS +++ b/CREDITS @@ -1512,6 +1512,10 @@ N: Andy Gross E: agross@kernel.org D: Qualcomm SoC subsystem and drivers +N: Mark Gross +E: markgross@kernel.org +D: x86/mellanox platform maintenance and various x86 specific drivers + N: Grant Grundler E: grantgrundler@gmail.com W: http://obmouse.sourceforge.net/ @@ -4469,6 +4473,13 @@ S: The Netherlands N: Thomas Woller D: CS461x Cirrus Logic sound driver +N: Darrick J. Wong +E: djwong@kernel.org +D: ext4 filesystem +D: XFS filesystem and online fsck +D: Various hwmon drivers +S: USA + N: David Woodhouse E: dwmw2@infradead.org D: JFFS2 file system, Memory Technology Device subsystem, diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 1b58c029abd0..0cebc89799dd 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -986,6 +986,7 @@ Description: This sysfs entry can be used to enable/disable to adjust priority f 0x00000008 gc_lock 0x00000010 cp_global 0x00000020 io_rwsem + 0x00000040 nat_tree_lock ========== ================== What: /sys/fs/f2fs//lock_duration_priority @@ -1002,3 +1003,20 @@ Description: It can be used to tune priority of f2fs critical task, e.g. f2fs_ck threads, limitation as below: - it requires user has CAP_SYS_NICE capability. - the range is [100, 139], by default the value is 120. + +What: /sys/fs/f2fs//max_atc_write_bio_size +Date: June 2026 +Contact: Bart Van Assche +Description: Every time a write operation completes f2fs_write_end_io() is + called. This function may be called from an atomic context, + e.g. from inside an interrupt handler. This attribute controls + the maximum size of a write bio that is completed in atomic + (atc) context. The default value for this attribute is UINT_MAX + which means that this functionality is disabled by default. + +What: /sys/fs/f2fs//pinned_area_max_secno +Date: August 2026 +Contact: "Daeho Jeong" +Description: This is a read-only entry to show the upper bound section number + for pinned files. Pinned files will only be allocated within + sections 0 to pinned_area_max_secno - 1. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 7c2a8ed80071..86a2a0099178 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1130,9 +1130,9 @@ policy and the underlying scheduler. From the point of view of the cpu controlle processes can be categorized as follows: * Processes under the fair-class scheduler -* Processes under a BPF scheduler with the ``cgroup_set_weight`` callback +* Processes under a BPF scheduler with the corresponding ``cgroup_set_*`` callback * Everything else: ``SCHED_{FIFO,RR,DEADLINE}`` and processes under a BPF scheduler - without the ``cgroup_set_weight`` callback + without the corresponding ``cgroup_set_*`` callback For details on when a process is under the fair-class scheduler or a BPF scheduler, check out :ref:`Documentation/scheduler/sched-ext.rst `. @@ -1223,7 +1223,9 @@ will be referred to. All time durations are in microseconds. $PERIOD duration. "max" for $MAX indicates no limit. If only one number is written, $MAX is updated. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_bandwidth`` callback depending on what + the callback actually does. cpu.max.burst A read-write single value file which exists on non-root @@ -1231,7 +1233,9 @@ will be referred to. All time durations are in microseconds. The burst in the range [0, $MAX]. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_bandwidth`` callback depending on what + the callback actually does. cpu.pressure A read-write nested-keyed file. @@ -1283,7 +1287,9 @@ will be referred to. All time durations are in microseconds. own relative priorities, but the cgroup itself will be treated as very low priority relative to its peers. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_idle`` callback depending on what the + callback actually does. Memory ------ @@ -3064,7 +3070,7 @@ resources (res_a and res_b) are registered then: change in this file generates a file modified event. All fields in this file are hierarchical. - max + .max The number of times the cgroup's resource usage was about to go over the max boundary. diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index 395425a70db8..e4fd1cbbd4e0 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -47,6 +47,10 @@ properties: - qcom,sm8650-dsi-ctrl - qcom,sm8750-dsi-ctrl - const: qcom,mdss-dsi-ctrl + - items: + - const: qcom,shikra-dsi-ctrl + - const: qcom,qcm2290-dsi-ctrl + - const: qcom,mdss-dsi-ctrl - items: - enum: - qcom,qcs8300-dsi-ctrl diff --git a/Documentation/devicetree/bindings/display/msm/gmu.yaml b/Documentation/devicetree/bindings/display/msm/gmu.yaml index 8578c2f8122e..9e459f12ce3f 100644 --- a/Documentation/devicetree/bindings/display/msm/gmu.yaml +++ b/Documentation/devicetree/bindings/display/msm/gmu.yaml @@ -262,6 +262,7 @@ allOf: compatible: contains: enum: + - qcom,adreno-gmu-722.0 - qcom,adreno-gmu-730.1 - qcom,adreno-gmu-740.1 - qcom,adreno-gmu-750.1 diff --git a/Documentation/devicetree/bindings/display/msm/gpu.yaml b/Documentation/devicetree/bindings/display/msm/gpu.yaml index dbbd8b814189..e5efe2d35ddc 100644 --- a/Documentation/devicetree/bindings/display/msm/gpu.yaml +++ b/Documentation/devicetree/bindings/display/msm/gpu.yaml @@ -353,6 +353,7 @@ allOf: - qcom,adreno-610.0 - qcom,adreno-619.1 - qcom,adreno-07000200 + - qcom,adreno-07000400 then: properties: clocks: @@ -413,6 +414,7 @@ allOf: contains: enum: - qcom,adreno-44010000 + - qcom,adreno-44050a01 - qcom,adreno-44070001 then: properties: @@ -443,11 +445,13 @@ allOf: - qcom,adreno-680.1 - qcom,adreno-690.0 - qcom,adreno-730.1 + - qcom,adreno-43020100 - qcom,adreno-43030c00 - qcom,adreno-43050a01 - qcom,adreno-43050c01 - qcom,adreno-43051401 - qcom,adreno-44010000 + - qcom,adreno-44050a01 - qcom,adreno-44070001 then: # Starting with A6xx, the clocks are usually defined in the GMU node diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-dpu.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-dpu.yaml index be6cd8adb3b6..034d3df8d247 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-dpu.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-dpu.yaml @@ -13,7 +13,11 @@ $ref: /schemas/display/msm/dpu-common.yaml# properties: compatible: - const: qcom,qcm2290-dpu + oneOf: + - const: qcom,qcm2290-dpu + - items: + - const: qcom,shikra-dpu + - const: qcom,qcm2290-dpu reg: items: diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml index bb09ecd1a5b4..49a7b5c4c678 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/display/msm/qcom,qcm2290-mdss.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Qualcomm QCM220 Display MDSS +title: Qualcomm QCM2290 and Shikra Display MDSS maintainers: - Loic Poulain @@ -12,13 +12,18 @@ maintainers: description: Device tree bindings for MSM Mobile Display Subsystem(MDSS) that encapsulates sub-blocks like DPU display controller and DSI. Device tree bindings of MDSS - are mentioned for QCM2290 target. + are mentioned for QCM2290 and Shikra targets. Shikra uses the same MDSS/DPU/DSI + hardware as QCM2290 (DPU 6.5) and shares the same register layout. $ref: /schemas/display/msm/mdss-common.yaml# properties: compatible: - const: qcom,qcm2290-mdss + oneOf: + - const: qcom,qcm2290-mdss + - items: + - const: qcom,shikra-mdss + - const: qcom,qcm2290-mdss clocks: items: @@ -52,7 +57,8 @@ patternProperties: properties: compatible: - const: qcom,qcm2290-dpu + contains: + const: qcom,qcm2290-dpu "^dsi@[0-9a-f]+$": type: object @@ -60,9 +66,8 @@ patternProperties: properties: compatible: - items: - - const: qcom,qcm2290-dsi-ctrl - - const: qcom,mdss-dsi-ctrl + contains: + const: qcom,qcm2290-dsi-ctrl "^phy@[0-9a-f]+$": type: object diff --git a/Documentation/devicetree/bindings/rtc/microchip,pic32-rtc.txt b/Documentation/devicetree/bindings/rtc/microchip,pic32-rtc.txt deleted file mode 100644 index 180b7144bfcc..000000000000 --- a/Documentation/devicetree/bindings/rtc/microchip,pic32-rtc.txt +++ /dev/null @@ -1,21 +0,0 @@ -* Microchip PIC32 Real Time Clock and Calendar - -The RTCC keeps time in hours, minutes, and seconds, and one half second. It -provides a calendar in weekday, date, month, and year. It also provides a -configurable alarm. - -Required properties: -- compatible: should be: "microchip,pic32mzda-rtc" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: RTC alarm/event interrupt -- clocks: clock phandle - -Example: - - rtc: rtc@1f8c0000 { - compatible = "microchip,pic32mzda-rtc"; - reg = <0x1f8c0000 0x60>; - interrupts = <166 IRQ_TYPE_EDGE_RISING>; - clocks = <&PBCLK6>; - }; diff --git a/Documentation/devicetree/bindings/rtc/microchip,pic32mzda-rtc.yaml b/Documentation/devicetree/bindings/rtc/microchip,pic32mzda-rtc.yaml new file mode 100644 index 000000000000..481ee28c06e3 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/microchip,pic32mzda-rtc.yaml @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/microchip,pic32mzda-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip PIC32 Real Time Clock and Calendar + +maintainers: + - Alexandre Belloni + +description: | + The Microchip PIC32 Real Time Clock and Calendar (RTCC) keeps time in hours, + minutes, seconds, and one half second. It also provides a calendar with + weekday, date, month, and year, along with a configurable alarm. + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + const: microchip,pic32mzda-rtc + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + - clocks + +additionalProperties: false + +examples: + - | + #include + + rtc@1f8c0000 { + compatible = "microchip,pic32mzda-rtc"; + reg = <0x1f8c0000 0x60>; + interrupts = <166 IRQ_TYPE_EDGE_RISING>; + clocks = <&PBCLK6>; + }; diff --git a/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml b/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml index 1860f0e4c31a..ea7b039a91e7 100644 --- a/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml @@ -9,15 +9,19 @@ title: Renesas RZ/N1 SoCs Real-Time Clock maintainers: - Miquel Raynal -allOf: - - $ref: rtc.yaml# - properties: compatible: - items: - - enum: - - renesas,r9a06g032-rtc - - const: renesas,rzn1-rtc + oneOf: + - items: + - enum: + - renesas,r9a06g032-rtc + - const: renesas,rzn1-rtc + + - const: renesas,r9a09g077-rtc + + - items: + - const: renesas,r9a09g087-rtc + - const: renesas,r9a09g077-rtc reg: maxItems: 1 @@ -54,6 +58,23 @@ required: - clock-names - power-domains +allOf: + - $ref: rtc.yaml# + + - if: + properties: + compatible: + contains: + enum: + - renesas,r9a09g077-rtc + - renesas,r9a09g087-rtc + then: + properties: + clocks: + minItems: 2 + clock-names: + minItems: 2 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt deleted file mode 100644 index 7d7b5f6bda65..000000000000 --- a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt +++ /dev/null @@ -1,27 +0,0 @@ - Motorola mc146818 compatible RTC -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -Required properties: - - compatible : "motorola,mc146818" - - reg : should contain registers location and length. - -Optional properties: - - interrupts : should contain interrupt. - - ctrl-reg : Contains the initial value of the control register also - called "Register B". - - freq-reg : Contains the initial value of the frequency register also - called "Register A". - -"Register A" and "B" are usually initialized by the firmware (BIOS for -instance). If this is not done, it can be performed by the driver. - -ISA Example: - - rtc@70 { - compatible = "motorola,mc146818"; - interrupts = <8 3>; - interrupt-parent = <&ioapic1>; - ctrl-reg = <2>; - freq-reg = <0x26>; - reg = <1 0x70 2>; - }; diff --git a/Documentation/devicetree/bindings/rtc/rtc-cmos.yaml b/Documentation/devicetree/bindings/rtc/rtc-cmos.yaml new file mode 100644 index 000000000000..e37927e9916c --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/rtc-cmos.yaml @@ -0,0 +1,63 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/rtc-cmos.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Motorola mc146818 compatible RTC + +maintainers: + - Alexandre Belloni + +properties: + compatible: + oneOf: + - const: motorola,mc146818 + + - items: + - const: intel,ce4100-rtc + - const: motorola,mc146818 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + ctrl-reg: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Initial value of the control register + (also known as Register B). + + freq-reg: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Initial value of the frequency register + (also known as Register A). + +required: + - compatible + - reg + +allOf: + - $ref: rtc.yaml# + +unevaluatedProperties: false + +examples: + - | + bus { + #address-cells = <2>; + #size-cells = <1>; + + rtc@1,70 { + compatible = "motorola,mc146818"; + reg = <0x1 0x70 0x2>; + + interrupts = <8 3>; + + ctrl-reg = <2>; + freq-reg = <0x26>; + }; + }; diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt deleted file mode 100644 index 062ebb14cecf..000000000000 --- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt +++ /dev/null @@ -1,53 +0,0 @@ -TI Real Time Clock - -Required properties: -- compatible: - - "ti,da830-rtc" - for RTC IP used similar to that on DA8xx SoC family. - - "ti,am3352-rtc" - for RTC IP used similar to that on AM335x SoC family. - This RTC IP has special WAKE-EN Register to enable - Wakeup generation for event Alarm. It can also be - used to control an external PMIC via the - pmic_power_en pin. - - "ti,am4372-rtc" - for RTC IP used similar to that on AM437X SoC family. -- reg: Address range of rtc register set -- interrupts: rtc timer, alarm interrupts in order - -Optional properties: -- system-power-controller: whether the rtc is controlling the system power - through pmic_power_en -- clocks: Any internal or external clocks feeding in to rtc -- clock-names: Corresponding names of the clocks -- pinctrl-0: a phandle pointing to the pin settings for the device -- pinctrl-names: should be "default" - -Optional subnodes: -- generic pinctrl node - -Required pinctrl subnodes properties: -- pins - Names of ext_wakeup pins to configure - -Optional pinctrl subnodes properties: -- input-enable - Enables ext_wakeup -- ti,active-high - Set input active high (by default active low) - -Example: - -rtc@1c23000 { - compatible = "ti,da830-rtc"; - reg = <0x23000 0x1000>; - interrupts = <19 - 19>; - interrupt-parent = <&intc>; - system-power-controller; - clocks = <&clk_32k_rtc>, <&clk_32768_ck>; - clock-names = "ext-clk", "int-clk"; - - pinctrl-0 = <&ext_wakeup>; - pinctrl-names = "default"; - - ext_wakeup: ext-wakeup { - pins = "ext_wakeup0"; - input-enable; - ti,active-high; - }; -}; diff --git a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt deleted file mode 100644 index c6cf37758a77..000000000000 --- a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt +++ /dev/null @@ -1,32 +0,0 @@ -Palmas RTC controller bindings - -Required properties: -- compatible: - - "ti,palmas-rtc" for palma series of the RTC controller -- interrupts: Interrupt number of RTC submodule on device. - -Optional properties: - -- ti,backup-battery-chargeable: The Palmas series device like TPS65913 or - TPS80036 supports the backup battery for powering the RTC when main - battery is removed or in very low power state. The backup battery - can be chargeable or non-chargeable. This flag will tells whether - battery is chargeable or not. If charging battery then driver can - enable the charging. -- ti,backup-battery-charge-high-current: Enable high current charging in - backup battery. Device supports the < 100uA and > 100uA charging. - The high current will be > 100uA. Absence of this property will - charge battery to lower current i.e. < 100uA. - -Example: - palmas: tps65913@58 { - ... - palmas_rtc: rtc { - compatible = "ti,palmas-rtc"; - interrupt-parent = <&palmas>; - interrupts = <8 0>; - ti,backup-battery-chargeable; - ti,backup-battery-charge-high-current; - }; - ... - }; diff --git a/Documentation/devicetree/bindings/rtc/ti,omap-rtc.yaml b/Documentation/devicetree/bindings/rtc/ti,omap-rtc.yaml new file mode 100644 index 000000000000..02b3c23cf435 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/ti,omap-rtc.yaml @@ -0,0 +1,140 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/ti,omap-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments OMAP Real Time Clock + +maintainers: + - Keerthy + - Afzal Mohammed + +description: + The OMAP RTC is a year/month/day/hours/minutes/seconds BCD clock with + century-range alarm matching, driven by the 32kHz clock. + +properties: + compatible: + oneOf: + - const: ti,da830-rtc + - items: + - const: ti,am3352-rtc + - const: ti,da830-rtc + - items: + - const: ti,am4372-rtc + - const: ti,am3352-rtc + - const: ti,da830-rtc + + reg: + maxItems: 1 + + interrupts: + minItems: 2 + maxItems: 2 + + system-power-controller: + type: boolean + description: + Indicates that this RTC controls system power via the pmic_power_en pin. + + clocks: + minItems: 1 + maxItems: 2 + + clock-names: + minItems: 1 + items: + - enum: [ext-clk, int-clk] + - const: int-clk + + pinctrl-0: + description: + Phandle to pin configuration for the external wakeup pins. + + pinctrl-names: + minItems: 1 + + ti,hwmods: + $ref: /schemas/types.yaml#/definitions/string + description: + Name of the hwmod associated with the RTC. + const: rtc + deprecated: true + +patternProperties: + "^ext-wakeup(-[0-9]+)?$": + type: object + + description: + Child node describing external wakeup pin configuration. + + properties: + pins: + pattern: '^ext_wakeup[0-3]$' + + input-enable: + type: boolean + description: + Enables the external wakeup input on the selected pin. + + ti,active-high: + type: boolean + description: + Sets the wakeup input polarity to active high. By default the + input is active low. + + required: + - pins + + additionalProperties: false + +required: + - compatible + - reg + - interrupts + +allOf: + - $ref: rtc.yaml# + - if: + not: + properties: + compatible: + contains: + const: ti,am3352-rtc + then: + properties: + system-power-controller: false + patternProperties: + "^ext-wakeup(-[0-9]+)?$": false + +unevaluatedProperties: false + +examples: + - | + rtc@23000 { + compatible = "ti,da830-rtc"; + reg = <0x23000 0x1000>; + interrupts = <19>, <19>; + clocks = <&clk_32768_ck>; + clock-names = "int-clk"; + }; + + - | + rtc@0 { + compatible = "ti,am3352-rtc", "ti,da830-rtc"; + reg = <0x0 0x1000>; + interrupts = <75>, <76>; + system-power-controller; + clocks = <&clk_32k_rtc>, <&clk_32768_ck>; + clock-names = "ext-clk", "int-clk"; + + pinctrl-0 = <&ext_wakeup>; + pinctrl-names = "default"; + + ext-wakeup { + pins = "ext_wakeup0"; + input-enable; + ti,active-high; + }; + }; diff --git a/Documentation/devicetree/bindings/rtc/ti,palmas-rtc.yaml b/Documentation/devicetree/bindings/rtc/ti,palmas-rtc.yaml new file mode 100644 index 000000000000..ac64f0589c84 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/ti,palmas-rtc.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/ti,palmas-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments Palmas RTC + +maintainers: + - Eduard Bostina + +allOf: + - $ref: /schemas/rtc/rtc.yaml# + +properties: + compatible: + const: ti,palmas-rtc + + interrupts: + maxItems: 1 + + wakeup-source: true + + ti,backup-battery-chargeable: + type: boolean + description: + The backup battery can be chargeable or non-chargeable. This flag + indicates whether the battery is chargeable. If present, the driver + can enable charging. + + ti,backup-battery-charge-high-current: + type: boolean + description: + Enable high current charging in the backup battery. + Device supports the < 100uA and > 100uA charging. The high current will + be > 100uA. Absence of this property will charge battery to lower + current i.e. < 100uA. + +required: + - compatible + - interrupts + +unevaluatedProperties: false + +examples: + - | + pmic { + #address-cells = <1>; + #size-cells = <0>; + + rtc { + compatible = "ti,palmas-rtc"; + interrupts = <8 0>; + ti,backup-battery-chargeable; + ti,backup-battery-charge-high-current; + }; + }; diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst index 6d2276a87a5a..ee2ca0c0c654 100644 --- a/Documentation/filesystems/ceph.rst +++ b/Documentation/filesystems/ceph.rst @@ -194,6 +194,12 @@ Mount Options copies. Currently, it's only used in copy_file_range, which will revert to the default VFS implementation if this option is used. + nearfull_sync + Force written data to stable storage when the cluster or file data pool is + marked NEARFULL. This restores the legacy client-side backpressure + behavior. By default, CephFS writes are not forced synchronous solely + because of NEARFULL. + recover_session= Set auto reconnect mode in the case where the client is blocklisted. The available modes are "no" and "clean". The default is "no". diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index b45d7a687625..771216f45207 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -415,7 +415,13 @@ lookup_mode=%s Control the directory lookup behavior for casefolded auto F2FS determines the mode based on the on-disk `SB_ENC_NO_COMPAT_FALLBACK_FL` flag. - ================== ======================================== +resizable_tail_secno=%u Control the number of sections at the tail of the + filesystem reserved for online resizing. Pinned files + will only be allocated within sections 0 to + (MAIN_SECS - resizable_tail_secno) - 1. If set to 0 + (default), there is no tail restriction unless running + on a zoned block device where conventional zones are + used. ======================== ============================================================ Debugfs Entries @@ -1043,6 +1049,41 @@ So, the key idea is, user can do any file operations on /dev/vdc, and reclaim the space after the use, while the space is counted as /data. That doesn't require modifying partition size and filesystem format. +Dynamic Device Aliasing Management +---------------------------------- + +In addition to static device aliasing by deleting the aliasing file, F2FS +supports dynamic management of device aliasing. This mechanism allows the system +to dynamically transition partition ownership between F2FS userdata and external +entities (e.g., zRAM, raw partition) based on system requirements without +deleting the master aliasing file or requiring unmount/remount. + +The master aliasing file is created during the initial format of the file system +and remains as a persistent control entity (ioctl gateway) in the root directory. + +- Partition Reservation (In-service to Aliased) + When a specific partition needs to be dedicated to external services (e.g., zRAM), + a user can reserve the device alias range via ioctl. The kernel resets GC victim + information for the target range, marks segments as in-use to prevent new + allocations, and triggers forced GC to migrate existing valid data out of the + range. Finally, it reserves these blocks in the SIT to effectively exclude the + device from the usable capacity. + +- Partition Release (Aliased to In-service) + When external usage concludes, the space is reclaimed not by deleting the file, + but through the release ioctl. The kernel truncates blocks associated with + the file, releasing them back to general filesystem allocation. + +.. code-block:: + + # f2fs_io dev_alias release /mnt/f2fs/vdc.file + # df -h + /dev/vdb 64G 753M 64G 2% /mnt/f2fs + + # f2fs_io dev_alias reserve /mnt/f2fs/vdc.file + # df -h + /dev/vdb 64G 33G 32G 52% /mnt/f2fs + Per-file Read-Only Large Folio Support -------------------------------------- diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index db7cddcda50a..b1eb102ab843 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -360,6 +360,17 @@ attribute-sets: name: tsoff type: u32 byte-order: big-endian + - + name: filter-attrs + attributes: + - + name: orig-flags + type: u32 + doc: bitmask of tuple fields to filter on, original direction + - + name: reply-flags + type: u32 + doc: bitmask of tuple fields to filter on, reply direction - name: conntrack-attrs attributes: @@ -466,7 +477,7 @@ attribute-sets: - name: filter type: nest - nested-attributes: tuple-attrs + nested-attributes: filter-attrs - name: status-mask type: u32 @@ -591,10 +602,14 @@ operations: request: value: 0x101 attributes: - - mark - - filter + - tuple-orig + - tuple-reply - status + - mark - zone + - mark-mask + - filter + - status-mask reply: value: 0x100 attributes: diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst index c0f57d0c4f73..c23b9e48ce49 100644 --- a/Documentation/process/4.Coding.rst +++ b/Documentation/process/4.Coding.rst @@ -312,7 +312,8 @@ be found at https://sparse.wiki.kernel.org/index.php/Main_Page if your distributor does not package it); it can then be run on the code by adding "C=1" to your make command. -The "Coccinelle" tool (http://coccinelle.lip6.fr/) is able to find a wide +The "Coccinelle" tool +(https://coccinelle.gitlabpages.inria.fr/website) is able to find a wide variety of potential coding problems; it can also propose fixes for those problems. Quite a few "semantic patches" for the kernel have been packaged under the scripts/coccinelle directory; running "make coccicheck" will run diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 0e97fd019994..794ae80b3ba3 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -230,7 +230,7 @@ optional. The following modified excerpt is from void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) { - exit_type = ei->type; + exit_type = ei->kind; } SEC(".struct_ops") @@ -242,6 +242,21 @@ optional. The following modified excerpt is from .name = "simple", }; +Scheduler-Dependent Knobs +------------------------- + +The fair-class scheduler enforces CPU controller settings such as +``cpu.max``, ``cpu.weight`` and ``cpu.idle``. For sched_ext tasks, the +scheduler core communicates these settings to the BPF scheduler +through ``ops.cgroup_init()`` and reports subsequent changes through +the corresponding ``ops.cgroup_set_*()`` callbacks. Similarly, per-task +nice changes are converted to weights and reported through +``ops.set_weight()``. + +Each BPF scheduler is responsible for implementing the scheduling +semantics of these settings and may choose to ignore them. Consult the +loaded scheduler's documentation before relying on these controls. + Dispatch Queues --------------- diff --git a/Documentation/scsi/leapraid.rst b/Documentation/scsi/leapraid.rst index 99930ce2b8d0..d36ff627d9f0 100644 --- a/Documentation/scsi/leapraid.rst +++ b/Documentation/scsi/leapraid.rst @@ -22,6 +22,7 @@ Supported devices Features ======== + - PCIe Gen4 x8 host interface - Support for SAS and SATA devices - RAID levels: 0, 1, 10, 5, 50, 6, 60 @@ -50,16 +51,20 @@ LeapRAID specific disk attributes :: - /sys/class/scsi_disk/host:bus:target:lun/device/sas_device_handle - /sys/class/scsi_disk/host:bus:target:lun/device/ncq_cmd_prio_enable + /sys/block//device/sas_device_handle + /sys/block//device/sas_ncq_prio_supported + /sys/block//device/sas_ncq_prio_enable The read-only attribute "sas_device_handle" represents the disk's device handle, which is a unique identifier maintained by the firmware. -This attribute "ncq_cmd_prio_enable" controls NCQ command priority. A value +The read-only attribute "sas_ncq_prio_supported" reports whether a SATA +device supports NCQ command priority. + +The attribute "sas_ncq_prio_enable" controls NCQ command priority. A value of 0 disables NCQ priority handling for RT-priority I/O. Writing 1 enables NCQ priority handling when the device reports support for the feature through -VPD page 0x89. Unsupported devices keep the effective state at 0. +VPD page 0x89. Writes to unsupported devices fail with an error. LeapRAID module parameters ========================== @@ -100,6 +105,7 @@ in io_uring poll mode. The default value is 0. File Location ============= + The driver source is located at: ``drivers/scsi/leapraid/`` diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst index b2171472e6cb..e500ec84e3ef 100644 --- a/Documentation/sound/alsa-configuration.rst +++ b/Documentation/sound/alsa-configuration.rst @@ -2316,6 +2316,9 @@ quirk_flags applies the ``mixer_playback_min_mute`` flag and clears the ``ignore_ctl_error`` flag for the device 1234:abcd, and applies the ``skip_sample_rate`` flag for all devices. + New quirk flags may replace old ones by reusing the latter's bits, so the + new usage is preferred. Despite that, depending on the order of probing is + fragile, so it'd better migrate to the new usage anyway. * bit 0: ``get_sample_rate`` Skip reading sample rate for devices @@ -2389,23 +2392,21 @@ quirk_flags from snd_usb_handle_sync_urb. Instead fall through and enqueue a packet_info containing only size-0 packets, so the OUT ring keeps moving (emits silence). Needed by Behringer Flow 8 (1397:050c). - * bit 30: ``mixer_get_cur_broken`` - Some mixers are sticky, which means that setting their current volume - is a no-op, and reading the current volume returns a constant value. - The sticky check disables these mixers to prevent confusing userspace. - However, some devices do have a tunable volume despite the reported - current volume being constant. As the sticky check can't distinguish - between the two categories, setting this flag tells that the device - should fall into the second category when GET_CUR returns a constant - value, resulting in the sticky check being non-fatal and only - disabling GET_CUR instead of the whole mixer. The current volume will - then be provided by the internal cache that stores the last set - volume + * bit 30: ``mixer_get_cur_ok`` + On some devices, whether their GET_CUR being sticky depends on whether + hotpluggable components are present. When the hotpluggable components + are missing on probe, their GET_CUR behavior is classified as broken. + Set the flag to prevent the heuristics from gating GET_CUR. * bit 31: ``playback_urb_fixup`` Some devices show the stuttering at playback, and this quirk works around it by enforcing the fixed max URBs (12) instead of the dynamic calculation from the buffer size, and passing the `URB_ISO_ASAP` URB flag. + * bit 32: ``always_set_rate`` + Issue SET_CUR for the sample rate even when the clock already reports + the requested rate. A device advertising a single rate is otherwise + never sent the request at all, and some require it before streaming + will start. This module supports multiple devices, autoprobe and hotplugging. diff --git a/MAINTAINERS b/MAINTAINERS index 4b0254f62277..b23fb6f2f4ef 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9387,9 +9387,8 @@ S: Maintained F: drivers/edac/octeon_edac* EDAC-CAVIUM THUNDERX -M: Robert Richter L: linux-edac@vger.kernel.org -S: Odd Fixes +S: Orphan F: drivers/edac/thunderx_edac* EDAC-CORE @@ -9416,9 +9415,8 @@ S: Supported F: drivers/edac/dmc520_edac.c EDAC-E752X -M: Mark Gross L: linux-edac@vger.kernel.org -S: Maintained +S: Orphan F: drivers/edac/e752x_edac.c EDAC-E7XXX @@ -9493,9 +9491,8 @@ S: Maintained F: drivers/edac/igen6_edac.c EDAC-MPC85XX -M: Johannes Thumshirn L: linux-edac@vger.kernel.org -S: Maintained +S: Orphan F: drivers/edac/mpc85xx_edac.[ch] EDAC-NPCM @@ -13283,7 +13280,6 @@ F: drivers/crypto/intel/keembay/ocs-aes.h INTEL KEEM BAY OCS ECC CRYPTO DRIVER M: Prabhjot Khurana -M: Mark Gross S: Maintained F: Documentation/devicetree/bindings/crypto/intel,keembay-ocs-ecc.yaml F: drivers/crypto/intel/keembay/Kconfig @@ -14240,8 +14236,6 @@ F: tools/testing/selftests/ KERNEL SMB3 SERVER (KSMBD) M: Namjae Jeon M: Namjae Jeon -M: Steve French -M: Steve French R: Sergey Senozhatsky R: Tom Talpey R: ChenXiaoSong @@ -18776,8 +18770,6 @@ L: linux-scsi@vger.kernel.org S: Maintained F: Documentation/scsi/g_NCR5380.rst F: drivers/scsi/NCR5380.* -F: drivers/scsi/arm/cumana_1.c -F: drivers/scsi/arm/oak.c F: drivers/scsi/atari_scsi.* F: drivers/scsi/dmx3191d.c F: drivers/scsi/g_NCR5380.* @@ -22949,7 +22941,7 @@ REAL TIME CLOCK (RTC) SUBSYSTEM M: Alexandre Belloni L: linux-rtc@vger.kernel.org S: Maintained -Q: http://patchwork.ozlabs.org/project/rtc-linux/list/ +Q: https://patchwork.kernel.org/project/linux-rtc/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/abelloni/linux.git F: Documentation/admin-guide/rtc.rst F: Documentation/devicetree/bindings/rtc/ @@ -24571,7 +24563,7 @@ F: include/scsi/sg.h SCSI SUBSYSTEM M: "James E.J. Bottomley" -M: "Martin K. Petersen" +M: "Martin K. Petersen" L: linux-scsi@vger.kernel.org S: Maintained Q: https://patchwork.kernel.org/project/linux-scsi/list/ @@ -24601,7 +24593,7 @@ F: drivers/target/target_core_user.c F: include/uapi/linux/target_core_user.h SCSI TARGET SUBSYSTEM -M: "Martin K. Petersen" +M: "Martin K. Petersen" L: linux-scsi@vger.kernel.org L: target-devel@vger.kernel.org S: Supported @@ -25238,10 +25230,9 @@ F: Documentation/admin-guide/LSM/Smack.rst F: security/smack/ SMBDIRECT (RDMA Stream Transport with Read/Write-Offload, MS-SMBD) -M: Steve French -M: Steve French M: Namjae Jeon M: Namjae Jeon +M: Paulo Alcantara R: Stefan Metzmacher R: Tom Talpey L: linux-cifs@vger.kernel.org @@ -26543,6 +26534,7 @@ R: Andy Shevchenko L: linux-i2c@vger.kernel.org S: Supported F: drivers/i2c/busses/i2c-designware-* +F: include/linux/designware_i2c.h SYNOPSYS DESIGNWARE I2C DRIVER - AMDISP M: Nirujogi Pratap @@ -26955,8 +26947,7 @@ S: Maintained F: drivers/net/ethernet/tehuti/tn40* TELECOM CLOCK DRIVER FOR MCPL0010 -M: Mark Gross -S: Supported +S: Orphan F: drivers/char/tlclk.c TEMPO SEMICONDUCTOR DRIVERS @@ -29938,12 +29929,14 @@ F: include/uapi/linux/xilinx-v4l2-controls.h XILINX VERSAL EDAC DRIVER M: Shubhrajyoti Datta M: Sai Krishna Potthuri +R: Radhey Shyam Pandey S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,versal-ddrmc-edac.yaml F: drivers/edac/versal_edac.c XILINX VERSALNET EDAC DRIVER M: Shubhrajyoti Datta +R: Radhey Shyam Pandey S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,versal-net-ddrmc5.yaml F: drivers/edac/versalnet_edac.c @@ -29989,6 +29982,7 @@ F: include/dt-bindings/dma/xlnx-zynqmp-dpdma.h XILINX ZYNQMP OCM EDAC DRIVER M: Shubhrajyoti Datta M: Sai Krishna Potthuri +R: Radhey Shyam Pandey S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,zynqmp-ocmc-1.0.yaml F: drivers/edac/zynqmp_edac.c diff --git a/Makefile b/Makefile index 50d918840686..4ad67b737af7 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 7 -PATCHLEVEL = 2 +PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1083,6 +1083,16 @@ endif export CC_FLAGS_SCS endif +ifdef CONFIG_RUST_INLINE_HELPERS +# `rustc` normally emits traps for unreachable paths during code generation. +# With inline helpers, Clang performs code generation from the linked bitcode +# instead, so request the same behavior explicitly. Otherwise `objtool` may +# follow an impossible Rust path into the next function. +CC_FLAGS_RUST_INLINE_HELPERS := -mllvm -trap-unreachable \ + -mllvm -no-trap-after-noreturn +export CC_FLAGS_RUST_INLINE_HELPERS +endif + ifdef CONFIG_LTO_CLANG ifdef CONFIG_LTO_CLANG_FULL CC_FLAGS_LTO := -flto @@ -1118,7 +1128,8 @@ endif ifdef CONFIG_RUST # Always pass -Zsanitizer-cfi-normalize-integers as CONFIG_RUST selects # CONFIG_CFI_ICALL_NORMALIZE_INTEGERS. - RUSTC_FLAGS_CFI := -Zsanitizer=kcfi -Zsanitizer-cfi-normalize-integers + # Disable function merging as LLVM incorrectly merges functions with different KCFI types. + RUSTC_FLAGS_CFI := -Zsanitizer=kcfi -Zsanitizer-cfi-normalize-integers -Zmerge-functions=disabled KBUILD_RUSTFLAGS += $(RUSTC_FLAGS_CFI) export RUSTC_FLAGS_CFI endif diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index f10379dfe7a3..ffbc7f386131 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -99,7 +99,7 @@ config ARM select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARM_LPAE select HAVE_ARM_SMCCC if CPU_V7 - select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 + select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 && !CPU_32v3 select HAVE_CONTEXT_TRACKING_USER select HAVE_C_RECORDMCOUNT select HAVE_BUILDTIME_MCOUNT_SORT @@ -134,6 +134,7 @@ config ARM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_POSIX_CPU_TIMERS_TASK_WORK select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index a3d050ce9b79..2d2ea3ca880c 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -557,9 +557,16 @@ ENTRY(__switch_to) ldmia r4, {r4 - sl, fp, ip, lr} @ Load all regs saved previously #ifdef CONFIG_VMAP_STACK @ - @ Do a dummy read from the new stack while running from the old one so - @ that we can rely on do_translation_fault() to fix up any stale PMD - @ entries covering the vmalloc region. + @ For a non-lazy mm switch, check_vmalloc_seq() has ensured that + @ that the active mm's page tables have mappings for the prev + @ task's stack and the next task's stack. + @ + @ For a lazy mm switch the active mm's page tables have mappings + @ for the prev task's stack but might not have mappings for the + @ new task's stack. Do a dummy read from the new stack while + @ running from the old stack so that we can rely on + @ do_translation_fault() to populate missing PMD entries covering the + @ new task's stack in the old task's page tables. @ ldr r2, [ip] #ifdef CONFIG_KASAN_VMALLOC diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index cd4b34c96e35..38feb30dfb5f 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -929,10 +929,6 @@ static void hw_breakpoint_cfi_handler(struct pt_regs *regs) break; } } -#else -static void hw_breakpoint_cfi_handler(struct pt_regs *regs) -{ -} #endif /* @@ -964,9 +960,14 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, case ARM_ENTRY_SYNC_WATCHPOINT: watchpoint_handler(addr, fsr, regs); break; +#ifdef CONFIG_CFI case ARM_ENTRY_CFI_BREAKPOINT: - hw_breakpoint_cfi_handler(regs); + if (user_mode(regs)) + ret = 1; /* Don't handle userspace BKPT */ + else + hw_breakpoint_cfi_handler(regs); break; +#endif default: ret = 1; /* Unhandled fault. */ } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index e62cc4be5adf..0a09d4ff7718 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -181,7 +181,11 @@ __do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig, pr_err("8<--- cut here ---\n"); pr_err("%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n", tsk->comm, sig, addr, fsr); - show_pte(KERN_ERR, tsk->mm, addr); + if (likely(addr < TASK_SIZE)) { + mmap_write_lock(tsk->mm); + show_pte(KERN_ERR, tsk->mm, addr); + mmap_write_unlock(tsk->mm); + } show_regs(regs); } #endif @@ -633,10 +637,21 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs)) return; + if (likely(user_mode(regs))) + local_irq_enable(); + pr_alert("8<--- cut here ---\n"); pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n", inf->name, fsr, addr); - show_pte(KERN_ALERT, current->mm, addr); + if (likely(user_mode(regs))) { + if (addr < TASK_SIZE) { + mmap_write_lock(current->mm); + show_pte(KERN_ALERT, current->mm, addr); + mmap_write_unlock(current->mm); + } + } else { + show_pte(KERN_ALERT, current->mm, addr); + } arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr, fsr, 0); @@ -663,6 +678,9 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs) if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs)) return; + if (likely(user_mode(regs))) + local_irq_enable(); + pr_alert("8<--- cut here ---\n"); pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n", inf->name, ifsr, addr); diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 4727f4b5b6e8..0326067c6c75 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -8,8 +8,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm920. - * - * CONFIG_CPU_ARM920_CPU_IDLE -> nohlt */ #include #include diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index 5a4a3f4f2683..3fe6fdf0d325 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -9,8 +9,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm922. - * - * CONFIG_CPU_ARM922_CPU_IDLE -> nohlt */ #include #include diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 1c4830afe1d3..2d15467e4a08 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -15,8 +15,6 @@ * These are the low level assembler for performing cache and TLB * functions on the arm925. * - * CONFIG_CPU_ARM925_CPU_IDLE -> nohlt - * * Some additional notes based on deciphering the TI TRM on OMAP-5910: * * NOTE1: The TI925T Configuration Register bit "D-cache clean and flush diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index a09cc3e02efd..d94aa8199452 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -8,8 +8,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm926. - * - * CONFIG_CPU_ARM926_CPU_IDLE -> nohlt */ #include #include diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c index 7a2baa135f0f..2de28088dac8 100644 --- a/arch/arm/probes/kprobes/test-core.c +++ b/arch/arm/probes/kprobes/test-core.c @@ -1649,24 +1649,16 @@ static int __init run_all_tests(void) return ret; } - +late_initcall(run_all_tests); /* * Module setup */ -#ifdef MODULE - static void __exit kprobe_test_exit(void) { } - -module_init(run_all_tests) module_exit(kprobe_test_exit) + +MODULE_DESCRIPTION("Test code for ARM kprobes"); MODULE_LICENSE("GPL"); - -#else /* !MODULE */ - -late_initcall(run_all_tests); - -#endif diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index c2a627f39314..6dfbcacd9ba0 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -264,7 +264,7 @@ static inline void task_set_sve_vl_onexec(struct task_struct *task, #define SCTLR_USER_MASK \ (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | SCTLR_ELx_ENDA | SCTLR_ELx_ENDB | \ - SCTLR_EL1_TCF0_MASK) + SCTLR_EL1_TCF0_MASK | SCTLR_EL1_TCSO0_MASK) static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h index 50a195eda8ed..3aa8fa2fcec7 100644 --- a/arch/arm64/include/asm/ptdump.h +++ b/arch/arm64/include/asm/ptdump.h @@ -50,6 +50,8 @@ struct ptdump_pg_state { const struct addr_marker *marker; const struct mm_struct *mm; unsigned long start_address; + /* exclusive end, ULONG_MAX represents an end at 1 << 64 */ + unsigned long end_address; int level; ptval_t current_prot; bool check_wx; diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c index b68e1d328d4c..9b58d0aa38d2 100644 --- a/arch/arm64/kernel/compat_alignment.c +++ b/arch/arm64/kernel/compat_alignment.c @@ -114,8 +114,8 @@ do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs) static int do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs) { - unsigned int rd, rn, nr_regs, regbits; - unsigned long eaddr, newaddr; + unsigned int rd, rn, regbits; + unsigned long eaddr, newaddr, nr_regs; unsigned int val; /* count the number of registers in the mask to be transferred */ diff --git a/arch/arm64/kvm/ptdump.c b/arch/arm64/kvm/ptdump.c index c9140e22abcf..69899797dbad 100644 --- a/arch/arm64/kvm/ptdump.c +++ b/arch/arm64/kvm/ptdump.c @@ -130,7 +130,7 @@ static struct kvm_ptdump_guest_state *kvm_ptdump_parser_create(struct kvm_s2_mmu } st->ipa_marker[0].name = "Guest IPA"; - st->ipa_marker[1].start_address = BIT(pgtable->ia_bits); + st->ipa_marker[1].start_address = ULONG_MAX; st->mmu = mmu; return st; @@ -148,18 +148,21 @@ static int kvm_ptdump_guest_show(struct seq_file *m, void *unused) .flags = KVM_PGTABLE_WALK_LEAF, }; + guard(write_lock)(&kvm->mmu_lock); st->parser_state = (struct ptdump_pg_state) { .marker = &st->ipa_marker[0], + .end_address = BIT(mmu->pgt->ia_bits), .level = -1, .pg_level = &st->level[0], .seq = m, }; - write_lock(&kvm->mmu_lock); ret = kvm_pgtable_walk(mmu->pgt, 0, BIT(mmu->pgt->ia_bits), &walker); - write_unlock(&kvm->mmu_lock); + if (ret) + return ret; + note_page_flush(&st->parser_state.ptdump); - return ret; + return 0; } static int kvm_ptdump_guest_open(struct inode *m, struct file *file) diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index 5a76c59b5ada..9d9bcb6738f4 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -278,9 +278,19 @@ void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd) void note_page_flush(struct ptdump_state *pt_st) { + struct ptdump_pg_state *st = container_of(pt_st, struct ptdump_pg_state, ptdump); + unsigned long end = st->end_address; pte_t pte_zero = {0}; - note_page(pt_st, 0, -1, pte_val(pte_zero)); + /* + * Address spaces that end at 1 << 64 have end_address == ULONG_MAX, + * but note_page() expects the exclusive end. In this case adjust end + * to the wraparound value 0. + */ + if (end == ULONG_MAX) + end = 0; + + note_page(pt_st, end, -1, pte_val(pte_zero)); } void ptdump_walk(struct seq_file *s, struct ptdump_info *info) @@ -296,6 +306,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info) .marker = info->markers, .mm = info->mm, .pg_level = &kernel_pg_levels[0], + .end_address = end, .level = -1, .ptdump = { .note_page_pte = note_page_pte, @@ -337,6 +348,7 @@ bool ptdump_check_wx(void) { -1, NULL}, }, .pg_level = &kernel_pg_levels[0], + .end_address = ~0UL, .level = -1, .check_wx = true, .ptdump = { diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c index 1420bae0964f..9a0258acd998 100644 --- a/arch/m68k/coldfire/device.c +++ b/arch/m68k/coldfire/device.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/coldfire/m5441x.c b/arch/m68k/coldfire/m5441x.c index 5b5e09ecf487..ad3d0021578f 100644 --- a/arch/m68k/coldfire/m5441x.c +++ b/arch/m68k/coldfire/m5441x.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -242,6 +243,30 @@ static void __init m5441x_fec_init(void) mcf_write8(0x03, MCFGPIO_PAR_FEC); } +/* + * Reset Controller Module status register. Exposed to userspace as + * /sys/devices/platform/mcf-rcm-reset/power_on_reason by the mcf-rcm-reset + * driver (drivers/power/reset/mcf-rcm-reset.c). + */ +static struct resource m5441x_rcm_resource[] = { + { + .start = MCF_RSR, + .end = MCF_RSR, + .flags = IORESOURCE_MEM, + }, +}; + +static int __init m5441x_rcm_init(void) +{ + struct platform_device *pdev; + + pdev = platform_device_register_simple("mcf-rcm-reset", -1, + m5441x_rcm_resource, + ARRAY_SIZE(m5441x_rcm_resource)); + return PTR_ERR_OR_ZERO(pdev); +} +arch_initcall(m5441x_rcm_init); + void __init config_BSP(char *commandp, int size) { m5441x_clk_init(); diff --git a/arch/m68k/configs/m5235evb_defconfig b/arch/m68k/configs/m5235evb_defconfig new file mode 100644 index 000000000000..fcac4ccd332d --- /dev/null +++ b/arch/m68k/configs/m5235evb_defconfig @@ -0,0 +1,52 @@ +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_EXPERT=y +# CONFIG_FUTEX is not set +# CONFIG_EPOLL is not set +# CONFIG_SIGNALFD is not set +# CONFIG_TIMERFD is not set +# CONFIG_EVENTFD is not set +# CONFIG_AIO is not set +# CONFIG_KALLSYMS is not set +# CONFIG_MMU is not set +CONFIG_M523x=y +CONFIG_M5235EVB=y +CONFIG_RAMBASE=0x00000000 +CONFIG_RAMSIZE=0x01000000 +CONFIG_VECTORBASE=0x00000000 +CONFIG_IPSBAR=0x40000000 +CONFIG_KERNELBASE=0x00020000 +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_BINFMT_FLAT=y +# CONFIG_VM_EVENT_COUNTERS is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +# CONFIG_INET_DIAG is not set +# CONFIG_IPV6 is not set +# CONFIG_FW_LOADER is not set +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_RAM=y +CONFIG_MTD_UCLINUX=y +CONFIG_BLK_DEV_RAM=y +CONFIG_NETDEVICES=y +CONFIG_FEC=y +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_UNIX98_PTYS is not set +CONFIG_SERIAL_MCF=y +CONFIG_SERIAL_MCF_CONSOLE=y +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_EXT2_FS=y +# CONFIG_FILE_LOCKING is not set +# CONFIG_DNOTIFY is not set +CONFIG_ROMFS_FS=y +CONFIG_ROMFS_BACKED_BY_MTD=y +# CONFIG_NETWORK_FILESYSTEMS is not set +# CONFIG_SLUB_DEBUG is not set +CONFIG_BOOTPARAM=y +CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0" diff --git a/arch/m68k/configs/m5282evb_defconfig b/arch/m68k/configs/m5282evb_defconfig new file mode 100644 index 000000000000..85040dc3e45e --- /dev/null +++ b/arch/m68k/configs/m5282evb_defconfig @@ -0,0 +1,51 @@ +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_EXPERT=y +# CONFIG_FUTEX is not set +# CONFIG_EPOLL is not set +# CONFIG_SIGNALFD is not set +# CONFIG_TIMERFD is not set +# CONFIG_EVENTFD is not set +# CONFIG_AIO is not set +# CONFIG_KALLSYMS is not set +# CONFIG_MMU is not set +CONFIG_M528x=y +CONFIG_RAMBASE=0x00000000 +CONFIG_RAMSIZE=0x00800000 +CONFIG_VECTORBASE=0x00000000 +CONFIG_IPSBAR=0x40000000 +CONFIG_KERNELBASE=0x00020000 +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_BINFMT_FLAT=y +# CONFIG_VM_EVENT_COUNTERS is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +# CONFIG_INET_DIAG is not set +# CONFIG_IPV6 is not set +# CONFIG_FW_LOADER is not set +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_RAM=y +CONFIG_MTD_UCLINUX=y +CONFIG_BLK_DEV_RAM=y +CONFIG_NETDEVICES=y +CONFIG_FEC=y +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_UNIX98_PTYS is not set +CONFIG_SERIAL_MCF=y +CONFIG_SERIAL_MCF_CONSOLE=y +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_EXT2_FS=y +# CONFIG_FILE_LOCKING is not set +# CONFIG_DNOTIFY is not set +CONFIG_ROMFS_FS=y +CONFIG_ROMFS_BACKED_BY_MTD=y +# CONFIG_NETWORK_FILESYSTEMS is not set +# CONFIG_SLUB_DEBUG is not set +CONFIG_BOOTPARAM=y +CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0" diff --git a/arch/m68k/include/asm/mcfgpio.h b/arch/m68k/include/asm/mcfgpio.h index 7103cfa4edb6..29726aa40eb6 100644 --- a/arch/m68k/include/asm/mcfgpio.h +++ b/arch/m68k/include/asm/mcfgpio.h @@ -16,7 +16,7 @@ int __mcfgpio_request(unsigned gpio); void __mcfgpio_free(unsigned gpio); #ifdef CONFIG_GPIOLIB -#include +#include #else /* our alternate 'gpiolib' functions */ diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index c7e90b09645e..18e68680471e 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -1223,15 +1223,50 @@ _no_syscall_trace: * */ +/* Keep this literal; hi()/lo() can't use the UL-suffixed TASK_SIZE. */ +#define OR1K_ATOMIC_ADDR_LIMIT 0x7ffffffc + ENTRY(sys_or1k_atomic) /* FIXME: This ignores r3 and always does an XCHG */ + + /* Check both user pointers before accessing them. */ + l.movhi r13,hi(OR1K_ATOMIC_ADDR_LIMIT) + l.ori r13,r13,lo(OR1K_ATOMIC_ADDR_LIMIT) + l.sfgtu r4,r13 + l.bf 9f + l.nop + l.sfgtu r5,r13 + l.bf 9f + l.nop + DISABLE_INTERRUPTS(r17,r19) - l.lwz r29,0(r4) - l.lwz r27,0(r5) - l.sw 0(r4),r27 - l.sw 0(r5),r29 +10: l.lwz r29,0(r4) +11: l.lwz r27,0(r5) +12: l.sw 0(r4),r27 +13: l.sw 0(r5),r29 ENABLE_INTERRUPTS(r17) l.jr r9 l.or r11,r0,r0 + /* + * Either pointer was outside user space, or turned out to be + * unmapped/inaccessible when we actually touched it. + */ +9: l.jr r9 + l.addi r11,r0,-EFAULT + + .section .fixup, "ax" +14: + ENABLE_INTERRUPTS(r17) + l.j 9b + l.nop + .previous + + .section __ex_table, "a" + .long 10b, 14b + .long 11b, 14b + .long 12b, 14b + .long 13b, 14b + .previous + /* ============================================================[ EOF ]=== */ diff --git a/arch/openrisc/mm/tlb.c b/arch/openrisc/mm/tlb.c index 3115f2e4f864..2ee00bf301a4 100644 --- a/arch/openrisc/mm/tlb.c +++ b/arch/openrisc/mm/tlb.c @@ -74,11 +74,11 @@ void local_flush_tlb_all(void) #define flush_dtlb_page_eir(addr) mtspr(SPR_DTLBEIR, addr) #define flush_dtlb_page_no_eir(addr) \ - mtspr_off(SPR_DTLBMR_BASE(0), DTLB_OFFSET(addr), 0); + mtspr_off(SPR_DTLBMR_BASE(0), DTLB_OFFSET(addr), 0) #define flush_itlb_page_eir(addr) mtspr(SPR_ITLBEIR, addr) #define flush_itlb_page_no_eir(addr) \ - mtspr_off(SPR_ITLBMR_BASE(0), ITLB_OFFSET(addr), 0); + mtspr_off(SPR_ITLBMR_BASE(0), ITLB_OFFSET(addr), 0) void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) { diff --git a/arch/um/include/asm/timex.h b/arch/um/include/asm/timex.h new file mode 100644 index 000000000000..39e392ebc8c2 --- /dev/null +++ b/arch/um/include/asm/timex.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __UM_TIMEX_H +#define __UM_TIMEX_H + +/* + * Do not fall back to the host architecture header because latter likely + * includes facilities like cpu_feature_enabled() which are present only + * there. That would result in build breakages and/or efforts to "emulate" + * those facilities in UML. + */ +#include + +#endif diff --git a/arch/xtensa/include/asm/platform.h b/arch/xtensa/include/asm/platform.h index 94f13fabf7cd..f2e50fc12b4d 100644 --- a/arch/xtensa/include/asm/platform.h +++ b/arch/xtensa/include/asm/platform.h @@ -33,7 +33,7 @@ extern void platform_setup (char **); extern void platform_idle (void); /* - * platform_calibrate_ccount calibrates cpu clock freq (CONFIG_XTENSA_CALIBRATE) + * platform_calibrate_ccount calibrates cpu clock freq (CONFIG_XTENSA_CALIBRATE_CCOUNT) */ extern void platform_calibrate_ccount (void); diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 94a23f100726..e4c25d0c2158 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include @@ -459,12 +458,6 @@ void show_ipi_list(struct seq_file *p, int prec) } } -int setup_profiling_timer(unsigned int multiplier) -{ - pr_debug("setup_profiling_timer %d\n", multiplier); - return 0; -} - /* TLB flush functions */ struct flush_data { diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 1c3dfea843ec..09fda6a3fe3b 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 8b95221375a8..8e54625cb2ba 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -166,8 +166,9 @@ late_initcall(rs_init); static void iss_console_write(struct console *co, const char *s, unsigned count) { - if (s && *s != 0) - simc_write(1, s, min(count, strlen(s))); + count = s ? strnlen(s, count) : 0; + if (count) + simc_write(1, s, count); } static struct tty_driver* iss_console_device(struct console *c, int *index) diff --git a/crypto/acompress.c b/crypto/acompress.c index 032de704eb2c..4de1a2ad577f 100644 --- a/crypto/acompress.c +++ b/crypto/acompress.c @@ -559,12 +559,22 @@ EXPORT_SYMBOL_GPL(acomp_walk_virt); struct acomp_req *acomp_request_clone(struct acomp_req *req, size_t total, gfp_t gfp) { + struct crypto_tfm *tfm = req->base.tfm; struct acomp_req *nreq; + size_t len; - nreq = container_of(crypto_request_clone(&req->base, total, gfp), - struct acomp_req, base); - if (nreq == req) + len = sizeof(*req) + + crypto_acomp_reqsize(crypto_acomp_reqtfm(req)); + len = ALIGN(len, CRYPTO_MINALIGN); + + nreq = kzalloc(len, gfp); + if (!nreq) { + req->base.tfm = tfm->fb; return req; + } + + memcpy(nreq, req, sizeof(*req)); + nreq->base.flags &= ~CRYPTO_TFM_REQ_ON_STACK; if (req->src == &req->chain.ssg) nreq->src = &nreq->chain.ssg; diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 922ba9803a93..23a4e207a01e 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -954,7 +954,6 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle) INIT_LIST_HEAD(&resource->list_node); INIT_LIST_HEAD(&resource->dependents); device->power.state = ACPI_STATE_UNKNOWN; - device->flags.initialized = true; /* Evaluate the object to get the system level and resource order. */ status = acpi_evaluate_object(handle, NULL, NULL, &buffer); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 7dcf784199fa..f48715ed827c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1144,6 +1144,9 @@ static void acpi_bus_get_power_flags(struct acpi_device *device) if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources)) device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1; } + + if (acpi_bus_init_power(device)) + device->flags.power_manageable = 0; } static void acpi_bus_get_flags(struct acpi_device *device) @@ -1825,6 +1828,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, acpi_set_pnp_ids(handle, &device->pnp, type); acpi_init_properties(device); acpi_bus_get_flags(device); + device->flags.initialized = true; device->flags.enumeration_by_parent = acpi_device_enumeration_by_parent(device); acpi_device_clear_enumerated(device); diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index bcb2514b7bc0..909a265fd906 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -571,12 +571,44 @@ int btintel_version_info_tlv(struct hci_dev *hdev, } EXPORT_SYMBOL_GPL(btintel_version_info_tlv); +static u8 btintel_version_tlv_min_len(u8 type) +{ + switch (type) { + case INTEL_TLV_CNVI_TOP: + case INTEL_TLV_CNVR_TOP: + case INTEL_TLV_CNVI_BT: + case INTEL_TLV_CNVR_BT: + case INTEL_TLV_BUILD_NUM: + case INTEL_TLV_GIT_SHA1: + return sizeof(u32); + case INTEL_TLV_DEV_REV_ID: + case INTEL_TLV_TIME_STAMP: + return sizeof(u16); + case INTEL_TLV_IMAGE_TYPE: + case INTEL_TLV_BUILD_TYPE: + case INTEL_TLV_SECURE_BOOT: + case INTEL_TLV_OTP_LOCK: + case INTEL_TLV_API_LOCK: + case INTEL_TLV_DEBUG_LOCK: + case INTEL_TLV_LIMITED_CCE: + case INTEL_TLV_SBE_TYPE: + return sizeof(u8); + case INTEL_TLV_MIN_FW: + return 3; + case INTEL_TLV_OTP_BDADDR: + return sizeof(bdaddr_t); + default: + return 0; + } +} + int btintel_parse_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *version, struct sk_buff *skb) { /* Consume Command Complete Status field */ - skb_pull(skb, 1); + if (!skb_pull(skb, 1)) + return -EINVAL; /* Event parameters contain multiple TLVs. Read each of them * and only keep the required data. Also, it use existing legacy @@ -596,6 +628,9 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, if (skb->len < tlv->len + sizeof(*tlv)) return -EINVAL; + if (tlv->len < btintel_version_tlv_min_len(tlv->type)) + return -EINVAL; + switch (tlv->type) { case INTEL_TLV_CNVI_TOP: version->cnvi_top = get_unaligned_le32(tlv->val); @@ -667,7 +702,7 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, break; case INTEL_TLV_FW_ID: snprintf(version->fw_id, sizeof(version->fw_id), - "%s", tlv->val); + "%.*s", tlv->len, tlv->val); break; default: /* Ignore rest of information */ @@ -686,6 +721,7 @@ static int btintel_read_version_tlv(struct hci_dev *hdev, { struct sk_buff *skb; const u8 param[1] = { 0xFF }; + int err; if (!version) return -EINVAL; @@ -704,10 +740,10 @@ static int btintel_read_version_tlv(struct hci_dev *hdev, return -EIO; } - btintel_parse_version_tlv(hdev, version, skb); + err = btintel_parse_version_tlv(hdev, version, skb); kfree_skb(skb); - return 0; + return err; } /* ------- REGMAP IBT SUPPORT ------- */ diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 005c77a4f5eb..eec95e5f3dbb 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1696,6 +1696,9 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id) if (unlikely(!(intr_fh | intr_hw))) { /* Ignore interrupt, inta == 0 */ + bt_warn_ratelimited("Bluetooth: btintel_pcie: Received spurious interrupt\n"); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_AUTOMASK_ST, + BIT(entry->entry)); return IRQ_NONE; } diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index 516b8f74c434..5798a8db016e 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -307,9 +307,8 @@ static int mrvl_load_firmware(struct hci_dev *hdev, const char *name) err = wait_on_bit_timeout(&mrvl->flags, STATE_FW_REQ_PENDING, TASK_INTERRUPTIBLE, msecs_to_jiffies(2000)); - if (err == 1) { + if (err == -EINTR) { bt_dev_err(hdev, "Firmware load interrupted"); - err = -EINTR; break; } else if (err) { bt_dev_err(hdev, "Firmware request timeout"); diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig index 669f76000197..538a7d3c65bf 100644 --- a/drivers/char/ipmi/Kconfig +++ b/drivers/char/ipmi/Kconfig @@ -67,6 +67,15 @@ config IPMI_SI Currently, only KCS and SMIC are supported. If you are using IPMI, you should probably say "y" here. +config IPMI_SI_ASYNC_INIT + bool 'Asynchronous initialization of IPMI System Interface' + depends on IPMI_SI + default n + help + Offloads individual SMI inits. It speeds up the boot time. + It also introduces a very small risk that something else might fail + if it depends on synchronous IPMI init. + config IPMI_SSIF tristate 'IPMI SMBus handler (SSIF)' depends on I2C diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 680ff15c30ab..eae31ec92382 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -141,13 +141,14 @@ static ssize_t ipmb_write(struct file *file, const char __user *buf, u8 msg[MAX_MSG_LEN]; ssize_t ret; - if (count > sizeof(msg)) + if (!count || count > sizeof(msg)) return -EINVAL; if (copy_from_user(&msg, buf, count)) return -EFAULT; - if (count < msg[0]) + if (msg[IPMB_MSG_LEN_IDX] < IPMB_REQUEST_LEN_MIN || + count < (size_t)msg[IPMB_MSG_LEN_IDX] + 1) return -EINVAL; rq_sa = GET_7BIT_ADDR(msg[RQ_SA_8BIT_IDX]); @@ -360,8 +361,8 @@ MODULE_DEVICE_TABLE(i2c, ipmb_id); #ifdef CONFIG_ACPI static const struct acpi_device_id acpi_ipmb_id[] = { - { "IPMB0001", 0 }, - {}, + { .id = "IPMB0001" }, + { } }; MODULE_DEVICE_TABLE(acpi, acpi_ipmb_id); #endif diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index ab4c85f3d6fe..152dd6b5bb27 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1391,6 +1391,7 @@ static void _ipmi_destroy_user(struct ipmi_user *user) } } mutex_unlock(&intf->cmd_rcvrs_mutex); + synchronize_rcu(); while (rcvrs) { rcvr = rcvrs; rcvrs = rcvr->next; @@ -3301,6 +3302,7 @@ static int __ipmi_bmc_register(struct ipmi_smi *intf, list_del(&intf->bmc_link); mutex_unlock(&bmc->dyn_mutex); intf->bmc = &intf->tmp_bmc; + ida_free(&ipmi_bmc_ida, bmc->pdev.id); put_device(&bmc->pdev.dev); goto out; } @@ -3740,6 +3742,7 @@ int ipmi_add_smi(struct module *owner, sysfs_attr_init(&intf->maintenance_mode_devattr.attr); rv = device_create_file(intf->si_dev, &intf->maintenance_mode_devattr); if (rv) { + device_remove_file(intf->si_dev, &intf->nr_msgs_devattr); device_remove_file(intf->si_dev, &intf->nr_users_devattr); goto out_err_bmc_reg; } @@ -3757,12 +3760,14 @@ int ipmi_add_smi(struct module *owner, out_err_bmc_reg: ipmi_bmc_unregister(intf); out_err_started: + intf->in_shutdown = true; if (intf->handlers->shutdown) intf->handlers->shutdown(intf->send_info); out_err: list_del(&intf->link); mutex_unlock(&ipmi_interfaces_mutex); mutex_unlock(&smi_watchers_mutex); + cancel_work_sync(&intf->smi_work); kref_put(&intf->refcount, intf_free); return rv; diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 9a9d12be9bf7..6b95a7581328 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "ipmi_si.h" #include "ipmi_si_sm.h" #include @@ -252,6 +253,8 @@ struct smi_info { struct task_struct *thread; + struct work_struct init_work; + struct list_head link; }; @@ -272,6 +275,7 @@ static bool unload_when_empty = true; static int try_smi_init(struct smi_info *smi); static void cleanup_one_si(struct smi_info *smi_info); static void cleanup_ipmi_si(void); +static void smi_init_work_fn(struct work_struct *work); #ifdef DEBUG_TIMING void debug_timestamp(struct smi_info *smi_info, char *msg) @@ -1970,6 +1974,7 @@ int ipmi_si_add_smi(struct si_sm_io *io) if (!new_smi) return -ENOMEM; spin_lock_init(&new_smi->si_lock); + INIT_WORK(&new_smi->init_work, smi_init_work_fn); new_smi->io = *io; @@ -1982,7 +1987,12 @@ int ipmi_si_add_smi(struct si_sm_io *io) dev_info(dup->io.dev, "Removing SMBIOS-specified %s state machine in favor of ACPI\n", si_to_str[new_smi->io.si_info->type]); + list_del(&dup->link); + mutex_unlock(&smi_infos_lock); + cleanup_one_si(dup); + + mutex_lock(&smi_infos_lock); } else { dev_info(new_smi->io.dev, "%s-specified %s state machine: duplicate\n", @@ -2000,8 +2010,12 @@ int ipmi_si_add_smi(struct si_sm_io *io) list_add_tail(&new_smi->link, &smi_infos); - if (initialized) - rv = try_smi_init(new_smi); + if (initialized) { + if (IS_ENABLED(CONFIG_IPMI_SI_ASYNC_INIT)) + queue_work(system_dfl_wq, &new_smi->init_work); + else + rv = try_smi_init(new_smi); + } out_err: mutex_unlock(&smi_infos_lock); return rv; @@ -2174,6 +2188,15 @@ static bool __init ipmi_smi_info_same(struct smi_info *e1, struct smi_info *e2) e1->io.addr_data == e2->io.addr_data); } +static void smi_init_work_fn(struct work_struct *work) +{ + struct smi_info *smi = container_of(work, struct smi_info, init_work); + + mutex_lock(&smi_infos_lock); + try_smi_init(smi); + mutex_unlock(&smi_infos_lock); +} + static int __init init_ipmi_si(void) { struct smi_info *e, *e2; @@ -2219,8 +2242,12 @@ static int __init init_ipmi_si(void) break; } } - if (!dup) - try_smi_init(e); + if (!dup) { + if (IS_ENABLED(CONFIG_IPMI_SI_ASYNC_INIT)) + queue_work(system_unbound_wq, &e->init_work); + else + try_smi_init(e); + } } /* @@ -2253,8 +2280,12 @@ static int __init init_ipmi_si(void) break; } } - if (!dup) - try_smi_init(e); + if (!dup) { + if (IS_ENABLED(CONFIG_IPMI_SI_ASYNC_INIT)) + queue_work(system_unbound_wq, &e->init_work); + else + try_smi_init(e); + } } initialized = true; @@ -2344,31 +2375,36 @@ static void shutdown_smi(void *send_info) } /* - * Must be called with smi_infos_lock held, to serialize the - * smi_info->intf check. + * Must be called with smi_info unlinked from smi_infos and smi_infos_lock released. */ static void cleanup_one_si(struct smi_info *smi_info) { if (!smi_info) return; - list_del(&smi_info->link); + if (IS_ENABLED(CONFIG_IPMI_SI_ASYNC_INIT)) + cancel_work_sync(&smi_info->init_work); + ipmi_unregister_smi(smi_info->intf); kfree(smi_info); } void ipmi_si_remove_by_dev(struct device *dev) { - struct smi_info *e; + struct smi_info *e = NULL, *tmp; mutex_lock(&smi_infos_lock); - list_for_each_entry(e, &smi_infos, link) { - if (e->io.dev == dev) { - cleanup_one_si(e); + list_for_each_entry(tmp, &smi_infos, link) { + if (tmp->io.dev == dev) { + e = tmp; + list_del(&e->link); break; } } mutex_unlock(&smi_infos_lock); + + if (e) + cleanup_one_si(e); } struct device *ipmi_si_remove_by_data(int addr_space, enum si_type si_type, @@ -2377,6 +2413,7 @@ struct device *ipmi_si_remove_by_data(int addr_space, enum si_type si_type, /* remove */ struct smi_info *e, *tmp_e; struct device *dev = NULL; + LIST_HEAD(to_clean); mutex_lock(&smi_infos_lock); list_for_each_entry_safe(e, tmp_e, &smi_infos, link) { @@ -2386,17 +2423,23 @@ struct device *ipmi_si_remove_by_data(int addr_space, enum si_type si_type, continue; if (e->io.addr_data == addr) { dev = get_device(e->io.dev); - cleanup_one_si(e); + list_move_tail(&e->link, &to_clean); } } mutex_unlock(&smi_infos_lock); + list_for_each_entry_safe(e, tmp_e, &to_clean, link) { + list_del(&e->link); + cleanup_one_si(e); + } + return dev; } static void cleanup_ipmi_si(void) { struct smi_info *e, *tmp_e; + LIST_HEAD(to_clean); if (!initialized) return; @@ -2410,10 +2453,14 @@ static void cleanup_ipmi_si(void) ipmi_si_platform_shutdown(); mutex_lock(&smi_infos_lock); - list_for_each_entry_safe(e, tmp_e, &smi_infos, link) - cleanup_one_si(e); + list_splice_init(&smi_infos, &to_clean); mutex_unlock(&smi_infos_lock); + list_for_each_entry_safe(e, tmp_e, &to_clean, link) { + list_del(&e->link); + cleanup_one_si(e); + } + ipmi_si_hardcode_exit(); ipmi_si_hotmod_exit(); } diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c index bdc481ce1302..fa221cbb4b3b 100644 --- a/drivers/char/ipmi/ipmi_si_platform.c +++ b/drivers/char/ipmi/ipmi_si_platform.c @@ -387,8 +387,8 @@ static int acpi_ipmi_probe(struct platform_device *pdev) } static const struct acpi_device_id acpi_ipmi_match[] = { - { "IPI0001", 0 }, - { }, + { .id = "IPI0001" }, + { } }; MODULE_DEVICE_TABLE(acpi, acpi_ipmi_match); #else diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 07f1d2327bb7..2361103c5edc 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -2057,8 +2057,8 @@ static unsigned short *ssif_address_list(void) #ifdef CONFIG_ACPI static const struct acpi_device_id ssif_acpi_match[] = { - { "IPI0001", 0 }, - { }, + { .id = "IPI0001" }, + { } }; MODULE_DEVICE_TABLE(acpi, ssif_acpi_match); #endif diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index 8a8f692b6088..5f672f2c01b0 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -163,8 +163,7 @@ config TCG_NSC config TCG_ATMEL tristate "Atmel TPM Interface" - depends on HAS_IOPORT_MAP - depends on HAS_IOPORT + depends on X86 help If you have a TPM security chip from Atmel say Yes and it will be accessible from within Linux. To compile this driver diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c index 8d5179367eac..c15a9b7aaff8 100644 --- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -93,7 +93,9 @@ static u8 st33zp24_status(struct tpm_chip *chip) struct st33zp24_dev *tpm_dev = dev_get_drvdata(&chip->dev); u8 data; - tpm_dev->ops->recv(tpm_dev->phy_id, TPM_STS, &data, 1); + if (tpm_dev->ops->recv(tpm_dev->phy_id, TPM_STS, &data, 1) != 1) + return 0; + return data; } @@ -104,10 +106,10 @@ static bool check_locality(struct tpm_chip *chip) { struct st33zp24_dev *tpm_dev = dev_get_drvdata(&chip->dev); u8 data; - u8 status; + int status; status = tpm_dev->ops->recv(tpm_dev->phy_id, TPM_ACCESS, &data, 1); - if (status && (data & + if (status == 1 && (data & (TPM_ACCESS_ACTIVE_LOCALITY | TPM_ACCESS_VALID)) == (TPM_ACCESS_ACTIVE_LOCALITY | TPM_ACCESS_VALID)) return true; diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c index dc882fc9fa9e..233e81d3f149 100644 --- a/drivers/char/tpm/tpm-buf.c +++ b/drivers/char/tpm/tpm-buf.c @@ -3,94 +3,122 @@ * Handling of TPM command and other buffers. */ -#include #include -#include +#include +#include -/** - * tpm_buf_init() - Allocate and initialize a TPM command - * @buf: A &tpm_buf - * @tag: TPM_TAG_RQU_COMMAND, TPM2_ST_NO_SESSIONS or TPM2_ST_SESSIONS - * @ordinal: A command ordinal - * - * Return: 0 or -ENOMEM - */ -int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) +static void __tpm_buf_size_invariant(struct tpm_buf *buf, u16 buf_size) { - buf->data = (u8 *)__get_free_page(GFP_KERNEL); - if (!buf->data) - return -ENOMEM; + u32 buf_size_2 = (u32)buf->capacity + (u32)sizeof(*buf); - tpm_buf_reset(buf, tag, ordinal); - return 0; + if (!buf->capacity) { + if (buf_size > TPM_BUFSIZE) { + WARN(1, "%s: size overflow: %u\n", __func__, buf_size); + buf->flags |= TPM_BUF_INVALID; + } + } else { + if (buf_size != buf_size_2) { + WARN(1, "%s: size mismatch: %u != %u\n", __func__, + buf_size, buf_size_2); + buf->flags |= TPM_BUF_INVALID; + } + } } -EXPORT_SYMBOL_GPL(tpm_buf_init); -/** - * tpm_buf_reset() - Initialize a TPM command - * @buf: A &tpm_buf - * @tag: TPM_TAG_RQU_COMMAND, TPM2_ST_NO_SESSIONS or TPM2_ST_SESSIONS - * @ordinal: A command ordinal - */ -void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) +static void __tpm_buf_reset(struct tpm_buf *buf, u16 buf_size, u16 tag, + u32 ordinal) { struct tpm_header *head = (struct tpm_header *)buf->data; + __tpm_buf_size_invariant(buf, buf_size); + + if (buf->flags & TPM_BUF_INVALID) + return; + WARN_ON(tag != TPM_TAG_RQU_COMMAND && tag != TPM2_ST_NO_SESSIONS && tag != TPM2_ST_SESSIONS && tag != 0); buf->flags = 0; buf->length = sizeof(*head); + buf->capacity = buf_size - sizeof(*buf); + buf->handles = 0; head->tag = cpu_to_be16(tag); head->length = cpu_to_be32(sizeof(*head)); head->ordinal = cpu_to_be32(ordinal); - buf->handles = 0; } -EXPORT_SYMBOL_GPL(tpm_buf_reset); + +static void __tpm_buf_reset_sized(struct tpm_buf *buf, u16 buf_size) +{ + __tpm_buf_size_invariant(buf, buf_size); + + if (buf->flags & TPM_BUF_INVALID) + return; + + buf->flags = TPM_BUF_TPM2B; + buf->length = 2; + buf->capacity = buf_size - sizeof(*buf); + buf->handles = 0; + buf->data[0] = 0; + buf->data[1] = 0; +} /** - * tpm_buf_init_sized() - Allocate and initialize a sized (TPM2B) buffer - * @buf: A @tpm_buf - * - * Return: 0 or -ENOMEM + * tpm_buf_init() - Initialize a TPM command + * @buf: A &tpm_buf + * @buf_size: Size of the buffer. */ -int tpm_buf_init_sized(struct tpm_buf *buf) +void tpm_buf_init(struct tpm_buf *buf, u16 buf_size) { - buf->data = (u8 *)__get_free_page(GFP_KERNEL); - if (!buf->data) - return -ENOMEM; + memset(buf, 0, buf_size); + __tpm_buf_reset(buf, buf_size, TPM_TAG_RQU_COMMAND, 0); +} +EXPORT_SYMBOL_GPL(tpm_buf_init); - tpm_buf_reset_sized(buf); - return 0; +/** + * tpm_buf_init_sized() - Initialize a sized buffer + * @buf: A &tpm_buf + * @buf_size: Size of the buffer. + */ +void tpm_buf_init_sized(struct tpm_buf *buf, u16 buf_size) +{ + memset(buf, 0, buf_size); + __tpm_buf_reset_sized(buf, buf_size); } EXPORT_SYMBOL_GPL(tpm_buf_init_sized); /** - * tpm_buf_reset_sized() - Initialize a sized buffer + * tpm_buf_reset() - Re-initialize a TPM command + * @buf: A &tpm_buf + * @tag: TPM_TAG_RQU_COMMAND, TPM2_ST_NO_SESSIONS or TPM2_ST_SESSIONS + * @ordinal: A command ordinal + */ +void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + u16 buf_size = buf->capacity + sizeof(*buf); + + __tpm_buf_reset(buf, buf_size, tag, ordinal); +} +EXPORT_SYMBOL_GPL(tpm_buf_reset); + +/** + * tpm_buf_reset_sized() - Re-initialize a sized buffer * @buf: A &tpm_buf */ void tpm_buf_reset_sized(struct tpm_buf *buf) { - buf->flags = TPM_BUF_TPM2B; - buf->length = 2; - buf->data[0] = 0; - buf->data[1] = 0; + u16 buf_size = buf->capacity + sizeof(*buf); + + __tpm_buf_reset_sized(buf, buf_size); } EXPORT_SYMBOL_GPL(tpm_buf_reset_sized); -void tpm_buf_destroy(struct tpm_buf *buf) -{ - free_page((unsigned long)buf->data); -} -EXPORT_SYMBOL_GPL(tpm_buf_destroy); - /** * tpm_buf_length() - Return the number of bytes consumed by the data * @buf: A &tpm_buf * * Return: The number of bytes consumed by the buffer */ -u32 tpm_buf_length(struct tpm_buf *buf) +u16 tpm_buf_length(struct tpm_buf *buf) { return buf->length; } @@ -104,13 +132,14 @@ EXPORT_SYMBOL_GPL(tpm_buf_length); */ void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length) { - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) + u32 total_length = (u32)buf->length + (u32)new_length; + + if (buf->flags & TPM_BUF_INVALID) return; - if ((buf->length + new_length) > PAGE_SIZE) { + if (total_length > (u32)buf->capacity) { WARN(1, "tpm_buf: write overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; + buf->flags |= TPM_BUF_INVALID; return; } @@ -148,17 +177,20 @@ EXPORT_SYMBOL_GPL(tpm_buf_append_u32); /** * tpm_buf_append_handle() - Add a handle - * @chip: &tpm_chip instance * @buf: &tpm_buf instance * @handle: a TPM object handle * * Add a handle to the buffer, and increase the count tracking the number of * handles in the command buffer. Works only for command buffers. */ -void tpm_buf_append_handle(struct tpm_chip *chip, struct tpm_buf *buf, u32 handle) +void tpm_buf_append_handle(struct tpm_buf *buf, u32 handle) { + if (buf->flags & TPM_BUF_INVALID) + return; + if (buf->flags & TPM_BUF_TPM2B) { - dev_err(&chip->dev, "Invalid buffer type (TPM2B)\n"); + WARN(1, "tpm-buf: invalid type: TPM2B\n"); + buf->flags |= TPM_BUF_INVALID; return; } @@ -177,14 +209,13 @@ static void tpm_buf_read(struct tpm_buf *buf, off_t *offset, size_t count, void { off_t next_offset; - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_BOUNDARY_ERROR) + if (buf->flags & TPM_BUF_INVALID) return; next_offset = *offset + count; if (next_offset > buf->length) { WARN(1, "tpm_buf: read out of boundary\n"); - buf->flags |= TPM_BUF_BOUNDARY_ERROR; + buf->flags |= TPM_BUF_INVALID; return; } diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index 94231f052ea7..d915307ae833 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -32,28 +32,35 @@ struct tpm_readpubek_out { static ssize_t pubek_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct tpm_buf tpm_buf; struct tpm_readpubek_out *out; int i; char *str = buf; struct tpm_chip *chip = to_tpm_chip(dev); char anti_replay[20]; + struct tpm_buf *tpm_buf __free(kfree) = NULL; memset(&anti_replay, 0, sizeof(anti_replay)); if (tpm_try_get_ops(chip)) return 0; - if (tpm_buf_init(&tpm_buf, TPM_TAG_RQU_COMMAND, TPM_ORD_READPUBEK)) - goto out_ops; + tpm_buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!tpm_buf) { + tpm_put_ops(chip); + return 0; + } - tpm_buf_append(&tpm_buf, anti_replay, sizeof(anti_replay)); + tpm_buf_init(tpm_buf, TPM_BUFSIZE); + tpm_buf_reset(tpm_buf, TPM_TAG_RQU_COMMAND, TPM_ORD_READPUBEK); + tpm_buf_append(tpm_buf, anti_replay, sizeof(anti_replay)); - if (tpm_transmit_cmd(chip, &tpm_buf, READ_PUBEK_RESULT_MIN_BODY_SIZE, - "attempting to read the PUBEK")) - goto out_buf; + if (tpm_transmit_cmd(chip, tpm_buf, READ_PUBEK_RESULT_MIN_BODY_SIZE, + "attempting to read the PUBEK")) { + tpm_put_ops(chip); + return 0; + } - out = (struct tpm_readpubek_out *)&tpm_buf.data[10]; + out = (struct tpm_readpubek_out *)&tpm_buf->data[10]; str += sprintf(str, "Algorithm: %4ph\n" @@ -71,9 +78,6 @@ static ssize_t pubek_show(struct device *dev, struct device_attribute *attr, for (i = 0; i < 256; i += 16) str += sprintf(str, "%16ph\n", &out->modulus[i]); -out_buf: - tpm_buf_destroy(&tpm_buf); -out_ops: tpm_put_ops(chip); return str - buf; } diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 87d68ddf270a..fa554c5ad80b 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -33,7 +33,6 @@ #endif #define TPM_MINOR 224 /* officially assigned */ -#define TPM_BUFSIZE 4096 #define TPM_NUM_DEVICES 65536 #define TPM_RETRY 50 @@ -52,185 +51,6 @@ enum tpm_addr { TPM_ADDR = 0x4E, }; -#define TPM_WARN_RETRY 0x800 -#define TPM_WARN_DOING_SELFTEST 0x802 -#define TPM_ERR_DEACTIVATED 0x6 -#define TPM_ERR_DISABLED 0x7 -#define TPM_ERR_FAILEDSELFTEST 0x1C -#define TPM_ERR_INVALID_POSTINIT 38 - -#define TPM_TAG_RQU_COMMAND 193 - -/* TPM2 specific constants. */ -#define TPM2_SPACE_BUFFER_SIZE 16384 /* 16 kB */ - -struct stclear_flags_t { - __be16 tag; - u8 deactivated; - u8 disableForceClear; - u8 physicalPresence; - u8 physicalPresenceLock; - u8 bGlobalLock; -} __packed; - -struct tpm1_version { - u8 major; - u8 minor; - u8 rev_major; - u8 rev_minor; -} __packed; - -struct tpm1_version2 { - __be16 tag; - struct tpm1_version version; -} __packed; - -struct timeout_t { - __be32 a; - __be32 b; - __be32 c; - __be32 d; -} __packed; - -struct duration_t { - __be32 tpm_short; - __be32 tpm_medium; - __be32 tpm_long; -} __packed; - -struct permanent_flags_t { - __be16 tag; - u8 disable; - u8 ownership; - u8 deactivated; - u8 readPubek; - u8 disableOwnerClear; - u8 allowMaintenance; - u8 physicalPresenceLifetimeLock; - u8 physicalPresenceHWEnable; - u8 physicalPresenceCMDEnable; - u8 CEKPUsed; - u8 TPMpost; - u8 TPMpostLock; - u8 FIPS; - u8 operator; - u8 enableRevokeEK; - u8 nvLocked; - u8 readSRKPub; - u8 tpmEstablished; - u8 maintenanceDone; - u8 disableFullDALogicInfo; -} __packed; - -typedef union { - struct permanent_flags_t perm_flags; - struct stclear_flags_t stclear_flags; - __u8 owned; - __be32 num_pcrs; - struct tpm1_version version1; - struct tpm1_version2 version2; - __be32 manufacturer_id; - struct timeout_t timeout; - struct duration_t duration; -} cap_t; - -enum tpm_capabilities { - TPM_CAP_FLAG = 4, - TPM_CAP_PROP = 5, - TPM_CAP_VERSION_1_1 = 0x06, - TPM_CAP_VERSION_1_2 = 0x1A, -}; - -enum tpm_sub_capabilities { - TPM_CAP_PROP_PCR = 0x101, - TPM_CAP_PROP_MANUFACTURER = 0x103, - TPM_CAP_FLAG_PERM = 0x108, - TPM_CAP_FLAG_VOL = 0x109, - TPM_CAP_PROP_OWNER = 0x111, - TPM_CAP_PROP_TIS_TIMEOUT = 0x115, - TPM_CAP_PROP_TIS_DURATION = 0x120, -}; - -enum tpm2_pt_props { - TPM2_PT_NONE = 0x00000000, - TPM2_PT_GROUP = 0x00000100, - TPM2_PT_FIXED = TPM2_PT_GROUP * 1, - TPM2_PT_FAMILY_INDICATOR = TPM2_PT_FIXED + 0, - TPM2_PT_LEVEL = TPM2_PT_FIXED + 1, - TPM2_PT_REVISION = TPM2_PT_FIXED + 2, - TPM2_PT_DAY_OF_YEAR = TPM2_PT_FIXED + 3, - TPM2_PT_YEAR = TPM2_PT_FIXED + 4, - TPM2_PT_MANUFACTURER = TPM2_PT_FIXED + 5, - TPM2_PT_VENDOR_STRING_1 = TPM2_PT_FIXED + 6, - TPM2_PT_VENDOR_STRING_2 = TPM2_PT_FIXED + 7, - TPM2_PT_VENDOR_STRING_3 = TPM2_PT_FIXED + 8, - TPM2_PT_VENDOR_STRING_4 = TPM2_PT_FIXED + 9, - TPM2_PT_VENDOR_TPM_TYPE = TPM2_PT_FIXED + 10, - TPM2_PT_FIRMWARE_VERSION_1 = TPM2_PT_FIXED + 11, - TPM2_PT_FIRMWARE_VERSION_2 = TPM2_PT_FIXED + 12, - TPM2_PT_INPUT_BUFFER = TPM2_PT_FIXED + 13, - TPM2_PT_HR_TRANSIENT_MIN = TPM2_PT_FIXED + 14, - TPM2_PT_HR_PERSISTENT_MIN = TPM2_PT_FIXED + 15, - TPM2_PT_HR_LOADED_MIN = TPM2_PT_FIXED + 16, - TPM2_PT_ACTIVE_SESSIONS_MAX = TPM2_PT_FIXED + 17, - TPM2_PT_PCR_COUNT = TPM2_PT_FIXED + 18, - TPM2_PT_PCR_SELECT_MIN = TPM2_PT_FIXED + 19, - TPM2_PT_CONTEXT_GAP_MAX = TPM2_PT_FIXED + 20, - TPM2_PT_NV_COUNTERS_MAX = TPM2_PT_FIXED + 22, - TPM2_PT_NV_INDEX_MAX = TPM2_PT_FIXED + 23, - TPM2_PT_MEMORY = TPM2_PT_FIXED + 24, - TPM2_PT_CLOCK_UPDATE = TPM2_PT_FIXED + 25, - TPM2_PT_CONTEXT_HASH = TPM2_PT_FIXED + 26, - TPM2_PT_CONTEXT_SYM = TPM2_PT_FIXED + 27, - TPM2_PT_CONTEXT_SYM_SIZE = TPM2_PT_FIXED + 28, - TPM2_PT_ORDERLY_COUNT = TPM2_PT_FIXED + 29, - TPM2_PT_MAX_COMMAND_SIZE = TPM2_PT_FIXED + 30, - TPM2_PT_MAX_RESPONSE_SIZE = TPM2_PT_FIXED + 31, - TPM2_PT_MAX_DIGEST = TPM2_PT_FIXED + 32, - TPM2_PT_MAX_OBJECT_CONTEXT = TPM2_PT_FIXED + 33, - TPM2_PT_MAX_SESSION_CONTEXT = TPM2_PT_FIXED + 34, - TPM2_PT_PS_FAMILY_INDICATOR = TPM2_PT_FIXED + 35, - TPM2_PT_PS_LEVEL = TPM2_PT_FIXED + 36, - TPM2_PT_PS_REVISION = TPM2_PT_FIXED + 37, - TPM2_PT_PS_DAY_OF_YEAR = TPM2_PT_FIXED + 38, - TPM2_PT_PS_YEAR = TPM2_PT_FIXED + 39, - TPM2_PT_SPLIT_MAX = TPM2_PT_FIXED + 40, - TPM2_PT_TOTAL_COMMANDS = TPM2_PT_FIXED + 41, - TPM2_PT_LIBRARY_COMMANDS = TPM2_PT_FIXED + 42, - TPM2_PT_VENDOR_COMMANDS = TPM2_PT_FIXED + 43, - TPM2_PT_NV_BUFFER_MAX = TPM2_PT_FIXED + 44, - TPM2_PT_MODES = TPM2_PT_FIXED + 45, - TPM2_PT_MAX_CAP_BUFFER = TPM2_PT_FIXED + 46, - TPM2_PT_VAR = TPM2_PT_GROUP * 2, - TPM2_PT_PERMANENT = TPM2_PT_VAR + 0, - TPM2_PT_STARTUP_CLEAR = TPM2_PT_VAR + 1, - TPM2_PT_HR_NV_INDEX = TPM2_PT_VAR + 2, - TPM2_PT_HR_LOADED = TPM2_PT_VAR + 3, - TPM2_PT_HR_LOADED_AVAIL = TPM2_PT_VAR + 4, - TPM2_PT_HR_ACTIVE = TPM2_PT_VAR + 5, - TPM2_PT_HR_ACTIVE_AVAIL = TPM2_PT_VAR + 6, - TPM2_PT_HR_TRANSIENT_AVAIL = TPM2_PT_VAR + 7, - TPM2_PT_HR_PERSISTENT = TPM2_PT_VAR + 8, - TPM2_PT_HR_PERSISTENT_AVAIL = TPM2_PT_VAR + 9, - TPM2_PT_NV_COUNTERS = TPM2_PT_VAR + 10, - TPM2_PT_NV_COUNTERS_AVAIL = TPM2_PT_VAR + 11, - TPM2_PT_ALGORITHM_SET = TPM2_PT_VAR + 12, - TPM2_PT_LOADED_CURVES = TPM2_PT_VAR + 13, - TPM2_PT_LOCKOUT_COUNTER = TPM2_PT_VAR + 14, - TPM2_PT_MAX_AUTH_FAIL = TPM2_PT_VAR + 15, - TPM2_PT_LOCKOUT_INTERVAL = TPM2_PT_VAR + 16, - TPM2_PT_LOCKOUT_RECOVERY = TPM2_PT_VAR + 17, - TPM2_PT_NV_WRITE_RECOVERY = TPM2_PT_VAR + 18, - TPM2_PT_AUDIT_COUNTER_0 = TPM2_PT_VAR + 19, - TPM2_PT_AUDIT_COUNTER_1 = TPM2_PT_VAR + 20, -}; - -/* 128 bytes is an arbitrary cap. This could be as large as TPM_BUFSIZE - 18 - * bytes, but 128 is still a relatively large number of random bytes and - * anything much bigger causes users of struct tpm_cmd_t to start getting - * compiler warnings about stack frame size. */ -#define TPM_MAX_RNG_DATA 128 - extern const struct class tpm_class; extern const struct class tpmrm_class; extern dev_t tpm_devt; diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index b49a790f1bd5..7a8606e8c711 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -22,8 +22,6 @@ #include "tpm.h" -#define TPM_MAX_ORDINAL 243 - /* * Array with one entry per ordinal defining the maximum amount * of time the chip could take to return the result. The ordinal @@ -308,9 +306,6 @@ unsigned long tpm1_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) return duration; } -#define TPM_ORD_STARTUP 153 -#define TPM_ST_CLEAR 1 - /** * tpm1_startup() - turn on the TPM * @chip: TPM chip to use @@ -323,20 +318,18 @@ unsigned long tpm1_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) */ static int tpm1_startup(struct tpm_chip *chip) { - struct tpm_buf buf; - int rc; + struct tpm_buf *buf __free(kfree) = NULL; dev_info(&chip->dev, "starting up the TPM manually\n"); - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_STARTUP); - if (rc < 0) - return rc; + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; - tpm_buf_append_u16(&buf, TPM_ST_CLEAR); - - rc = tpm_transmit_cmd(chip, &buf, 0, "attempting to start the TPM"); - tpm_buf_destroy(&buf); - return rc; + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_STARTUP); + tpm_buf_append_u16(buf, TPM_ST_CLEAR); + return tpm_transmit_cmd(chip, buf, 0, "attempting to start the TPM"); } int tpm1_get_timeouts(struct tpm_chip *chip) @@ -459,64 +452,56 @@ int tpm1_get_timeouts(struct tpm_chip *chip) return 0; } -#define TPM_ORD_PCR_EXTEND 20 int tpm1_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash, const char *log_msg) { - struct tpm_buf buf; - int rc; + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCR_EXTEND); - if (rc) - return rc; + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCR_EXTEND); + tpm_buf_append_u32(buf, pcr_idx); + tpm_buf_append(buf, hash, TPM_DIGEST_SIZE); - tpm_buf_append_u32(&buf, pcr_idx); - tpm_buf_append(&buf, hash, TPM_DIGEST_SIZE); - - rc = tpm_transmit_cmd(chip, &buf, TPM_DIGEST_SIZE, log_msg); - tpm_buf_destroy(&buf); - return rc; + return tpm_transmit_cmd(chip, buf, TPM_DIGEST_SIZE, log_msg); } -#define TPM_ORD_GET_CAP 101 ssize_t tpm1_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, const char *desc, size_t min_cap_length) { - struct tpm_buf buf; int rc; - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_CAP); - if (rc) - return rc; + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_CAP); if (subcap_id == TPM_CAP_VERSION_1_1 || subcap_id == TPM_CAP_VERSION_1_2) { - tpm_buf_append_u32(&buf, subcap_id); - tpm_buf_append_u32(&buf, 0); + tpm_buf_append_u32(buf, subcap_id); + tpm_buf_append_u32(buf, 0); } else { if (subcap_id == TPM_CAP_FLAG_PERM || subcap_id == TPM_CAP_FLAG_VOL) - tpm_buf_append_u32(&buf, TPM_CAP_FLAG); + tpm_buf_append_u32(buf, TPM_CAP_FLAG); else - tpm_buf_append_u32(&buf, TPM_CAP_PROP); + tpm_buf_append_u32(buf, TPM_CAP_PROP); - tpm_buf_append_u32(&buf, 4); - tpm_buf_append_u32(&buf, subcap_id); + tpm_buf_append_u32(buf, 4); + tpm_buf_append_u32(buf, subcap_id); } - rc = tpm_transmit_cmd(chip, &buf, min_cap_length, desc); + + rc = tpm_transmit_cmd(chip, buf, min_cap_length, desc); if (!rc) - *cap = *(cap_t *)&buf.data[TPM_HEADER_SIZE + 4]; - tpm_buf_destroy(&buf); + *cap = *(cap_t *)&buf->data[TPM_HEADER_SIZE + 4]; + return rc; } EXPORT_SYMBOL_GPL(tpm1_getcap); -#define TPM_ORD_GET_RANDOM 70 -struct tpm1_get_random_out { - __be32 rng_data_len; - u8 rng_data[TPM_MAX_RNG_DATA]; -} __packed; - /** * tpm1_get_random() - get random bytes from the TPM's RNG * @chip: a &struct tpm_chip instance @@ -530,86 +515,80 @@ struct tpm1_get_random_out { int tpm1_get_random(struct tpm_chip *chip, u8 *dest, size_t max) { struct tpm1_get_random_out *out; + struct tpm_buf *buf __free(kfree) = NULL; u32 num_bytes = min_t(u32, max, TPM_MAX_RNG_DATA); - struct tpm_buf buf; u32 total = 0; int retries = 5; u32 recd; int rc; - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_RANDOM); - if (rc) - return rc; + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_RANDOM); do { - tpm_buf_append_u32(&buf, num_bytes); + tpm_buf_append_u32(buf, num_bytes); - rc = tpm_transmit_cmd(chip, &buf, sizeof(out->rng_data_len), + rc = tpm_transmit_cmd(chip, buf, sizeof(out->rng_data_len), "attempting get random"); if (rc) { if (rc > 0) rc = -EIO; - goto out; + return rc; } - out = (struct tpm1_get_random_out *)&buf.data[TPM_HEADER_SIZE]; + out = (struct tpm1_get_random_out *)&buf->data[TPM_HEADER_SIZE]; recd = be32_to_cpu(out->rng_data_len); - if (recd > num_bytes) { - rc = -EFAULT; - goto out; - } + if (recd > num_bytes) + return -EFAULT; + + if (tpm_buf_length(buf) < TPM_HEADER_SIZE + + sizeof(out->rng_data_len) + recd) + return -EFAULT; - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + - sizeof(out->rng_data_len) + recd) { - rc = -EFAULT; - goto out; - } memcpy(dest, out->rng_data, recd); dest += recd; total += recd; num_bytes -= recd; - tpm_buf_reset(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_RANDOM); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_RANDOM); } while (retries-- && total < max); rc = total ? (int)total : -EIO; -out: - tpm_buf_destroy(&buf); + return rc; } -#define TPM_ORD_PCRREAD 21 int tpm1_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) { - struct tpm_buf buf; int rc; - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCRREAD); + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCR_READ); + tpm_buf_append_u32(buf, pcr_idx); + + rc = tpm_transmit_cmd(chip, buf, TPM_DIGEST_SIZE, + "attempting to read a pcr value"); if (rc) return rc; - tpm_buf_append_u32(&buf, pcr_idx); + if (tpm_buf_length(buf) < TPM_DIGEST_SIZE) + return -EFAULT; - rc = tpm_transmit_cmd(chip, &buf, TPM_DIGEST_SIZE, - "attempting to read a pcr value"); - if (rc) - goto out; + memcpy(res_buf, &buf->data[TPM_HEADER_SIZE], TPM_DIGEST_SIZE); - if (tpm_buf_length(&buf) < TPM_DIGEST_SIZE) { - rc = -EFAULT; - goto out; - } - - memcpy(res_buf, &buf.data[TPM_HEADER_SIZE], TPM_DIGEST_SIZE); - -out: - tpm_buf_destroy(&buf); return rc; } -#define TPM_ORD_CONTINUE_SELFTEST 83 /** * tpm1_continue_selftest() - run TPM's selftest * @chip: TPM chip to use @@ -619,16 +598,13 @@ int tpm1_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) */ static int tpm1_continue_selftest(struct tpm_chip *chip) { - struct tpm_buf buf; - int rc; + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_CONTINUE_SELFTEST); - if (rc) - return rc; - - rc = tpm_transmit_cmd(chip, &buf, 0, "continue selftest"); - tpm_buf_destroy(&buf); - return rc; + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_CONTINUE_SELFTEST); + return tpm_transmit_cmd(chip, buf, 0, "continue selftest"); } /** @@ -726,8 +702,6 @@ int tpm1_auto_startup(struct tpm_chip *chip) return rc; } -#define TPM_ORD_SAVESTATE 152 - /** * tpm1_pm_suspend() - pm suspend handler * @chip: TPM chip to use. @@ -742,22 +716,24 @@ int tpm1_auto_startup(struct tpm_chip *chip) int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) { u8 dummy_hash[TPM_DIGEST_SIZE] = { 0 }; - struct tpm_buf buf; unsigned int try; + struct tpm_buf *buf __free(kfree) = NULL; int rc; - /* for buggy tpm, flush pcrs with extend to selected dummy */ if (tpm_suspend_pcr) rc = tpm1_pcr_extend(chip, tpm_suspend_pcr, dummy_hash, "extending dummy pcr before suspend"); + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SAVESTATE); - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SAVESTATE); - if (rc) - return rc; /* now do the actual savestate */ for (try = 0; try < TPM_RETRY; try++) { - rc = tpm_transmit_cmd(chip, &buf, 0, NULL); + rc = tpm_transmit_cmd(chip, buf, 0, NULL); /* * If the TPM indicates that it is too busy to respond to * this command then retry before giving up. It can take @@ -772,7 +748,7 @@ int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) break; tpm_msleep(TPM_TIMEOUT_RETRY); - tpm_buf_reset(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SAVESTATE); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SAVESTATE); } if (rc) @@ -782,8 +758,6 @@ int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) dev_warn(&chip->dev, "TPM savestate took %dms\n", try * TPM_TIMEOUT_RETRY); - tpm_buf_destroy(&buf); - return rc; } diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 52ee350da867..48cec39995fe 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -94,17 +94,6 @@ unsigned long tpm2_calc_ordinal_duration(u32 ordinal) return msecs_to_jiffies(TPM2_DURATION_DEFAULT); } -struct tpm2_pcr_read_out { - __be32 update_cnt; - __be32 pcr_selects_cnt; - __be16 hash_alg; - u8 pcr_select_size; - u8 pcr_select[TPM2_PCR_SELECT_MIN]; - __be32 digests_cnt; - __be16 digest_size; - u8 digest[]; -} __packed; - /** * tpm2_pcr_read() - read a PCR value * @chip: TPM chip to use. @@ -119,12 +108,13 @@ int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, { int i; int rc; - struct tpm_buf buf; struct tpm2_pcr_read_out *out; u8 pcr_select[TPM2_PCR_SELECT_MIN] = {0}; u16 digest_size; u16 expected_digest_size = 0; + struct tpm_buf *buf __free(kfree) = NULL; + if (pcr_idx >= TPM2_PLATFORM_PCR) return -EINVAL; @@ -139,36 +129,35 @@ int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, expected_digest_size = chip->allocated_banks[i].digest_size; } - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_PCR_READ); - if (rc) - return rc; + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_PCR_READ); pcr_select[pcr_idx >> 3] = 1 << (pcr_idx & 0x7); - tpm_buf_append_u32(&buf, 1); - tpm_buf_append_u16(&buf, digest->alg_id); - tpm_buf_append_u8(&buf, TPM2_PCR_SELECT_MIN); - tpm_buf_append(&buf, (const unsigned char *)pcr_select, + tpm_buf_append_u32(buf, 1); + tpm_buf_append_u16(buf, digest->alg_id); + tpm_buf_append_u8(buf, TPM2_PCR_SELECT_MIN); + tpm_buf_append(buf, (const unsigned char *)pcr_select, sizeof(pcr_select)); - rc = tpm_transmit_cmd(chip, &buf, 0, "attempting to read a pcr value"); + rc = tpm_transmit_cmd(chip, buf, 0, "attempting to read a pcr value"); if (rc) - goto out; + return rc; - out = (struct tpm2_pcr_read_out *)&buf.data[TPM_HEADER_SIZE]; + out = (struct tpm2_pcr_read_out *)&buf->data[TPM_HEADER_SIZE]; digest_size = be16_to_cpu(out->digest_size); if (digest_size > sizeof(digest->digest) || - (!digest_size_ptr && digest_size != expected_digest_size)) { - rc = -EINVAL; - goto out; - } + (!digest_size_ptr && digest_size != expected_digest_size)) + return -EINVAL; if (digest_size_ptr) *digest_size_ptr = digest_size; memcpy(digest->digest, out->digest, digest_size); -out: - tpm_buf_destroy(&buf); return rc; } @@ -184,7 +173,7 @@ int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests) { - struct tpm_buf buf; + struct tpm_buf *buf __free(kfree) = NULL; int rc; int i; @@ -194,55 +183,49 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, return rc; } - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_PCR_EXTEND); - if (rc) { + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { if (!disable_pcr_integrity) tpm2_end_auth_session(chip); - return rc; + return -ENOMEM; } + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_PCR_EXTEND); + if (!disable_pcr_integrity) { - rc = tpm_buf_append_name(chip, &buf, pcr_idx, NULL); + rc = tpm_buf_append_name(chip, buf, pcr_idx, NULL); if (rc) { - tpm_buf_destroy(&buf); + tpm2_end_auth_session(chip); return rc; } - tpm_buf_append_hmac_session(chip, &buf, 0, NULL, 0); + tpm_buf_append_hmac_session(chip, buf, 0, NULL, 0); } else { - tpm_buf_append_handle(chip, &buf, pcr_idx); - tpm_buf_append_auth(chip, &buf, NULL, 0); + tpm_buf_append_handle(buf, pcr_idx); + tpm_buf_append_auth(chip, buf, NULL, 0); } - tpm_buf_append_u32(&buf, chip->nr_allocated_banks); + tpm_buf_append_u32(buf, chip->nr_allocated_banks); for (i = 0; i < chip->nr_allocated_banks; i++) { - tpm_buf_append_u16(&buf, digests[i].alg_id); - tpm_buf_append(&buf, (const unsigned char *)&digests[i].digest, + tpm_buf_append_u16(buf, digests[i].alg_id); + tpm_buf_append(buf, (const unsigned char *)&digests[i].digest, chip->allocated_banks[i].digest_size); } if (!disable_pcr_integrity) { - rc = tpm_buf_fill_hmac_session(chip, &buf); - if (rc) { - tpm_buf_destroy(&buf); + rc = tpm_buf_fill_hmac_session(chip, buf); + if (rc) return rc; - } } - rc = tpm_transmit_cmd(chip, &buf, 0, "attempting extend a PCR value"); + rc = tpm_transmit_cmd(chip, buf, 0, "attempting extend a PCR value"); if (!disable_pcr_integrity) - rc = tpm_buf_check_hmac_response(chip, &buf, rc); - - tpm_buf_destroy(&buf); + rc = tpm_buf_check_hmac_response(chip, buf, rc); return rc; } -struct tpm2_get_random_out { - __be16 size; - u8 buffer[TPM_MAX_RNG_DATA]; -} __packed; - /** * tpm2_get_random() - get random bytes from the TPM RNG * @@ -258,7 +241,6 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) { struct tpm2_get_random_out *out; struct tpm_header *head; - struct tpm_buf buf; u32 recd; u32 num_bytes = max; int err; @@ -267,6 +249,8 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) u8 *dest_ptr = dest; off_t offset; + struct tpm_buf *buf __free(kfree) = NULL; + if (!num_bytes || max > TPM_MAX_RNG_DATA) return -EINVAL; @@ -274,55 +258,58 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) if (err) return err; - err = tpm_buf_init(&buf, 0, 0); - if (err) { + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { tpm2_end_auth_session(chip); - return err; + return -ENOMEM; } + tpm_buf_init(buf, TPM_BUFSIZE); + do { - tpm_buf_reset(&buf, TPM2_ST_SESSIONS, TPM2_CC_GET_RANDOM); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_GET_RANDOM); if (tpm2_chip_auth(chip)) { - tpm_buf_append_hmac_session(chip, &buf, + tpm_buf_append_hmac_session(chip, buf, TPM2_SA_ENCRYPT | TPM2_SA_CONTINUE_SESSION, NULL, 0); } else { - offset = buf.handles * 4 + TPM_HEADER_SIZE; - head = (struct tpm_header *)buf.data; - if (tpm_buf_length(&buf) == offset) + offset = buf->handles * 4 + TPM_HEADER_SIZE; + head = (struct tpm_header *)buf->data; + if (tpm_buf_length(buf) == offset) head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS); } - tpm_buf_append_u16(&buf, num_bytes); - err = tpm_buf_fill_hmac_session(chip, &buf); + tpm_buf_append_u16(buf, num_bytes); + err = tpm_buf_fill_hmac_session(chip, buf); if (err) - goto out; + return err; - err = tpm_transmit_cmd(chip, &buf, + err = tpm_transmit_cmd(chip, buf, offsetof(struct tpm2_get_random_out, buffer), "attempting get random"); - err = tpm_buf_check_hmac_response(chip, &buf, err); + err = tpm_buf_check_hmac_response(chip, buf, err); if (err) { if (err > 0) err = -EIO; - goto out; + tpm2_end_auth_session(chip); + return err; } - head = (struct tpm_header *)buf.data; + head = (struct tpm_header *)buf->data; offset = TPM_HEADER_SIZE; /* Skip the parameter size field: */ if (be16_to_cpu(head->tag) == TPM2_ST_SESSIONS) offset += 4; - out = (struct tpm2_get_random_out *)&buf.data[offset]; + out = (struct tpm2_get_random_out *)&buf->data[offset]; recd = min_t(u32, be16_to_cpu(out->size), num_bytes); - if (tpm_buf_length(&buf) < + if (tpm_buf_length(buf) < TPM_HEADER_SIZE + offsetof(struct tpm2_get_random_out, buffer) + recd) { - err = -EFAULT; - goto out; + tpm2_end_auth_session(chip); + return -EFAULT; } memcpy(dest_ptr, out->buffer, recd); @@ -331,13 +318,7 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) num_bytes -= recd; } while (retries-- && total < max); - tpm_buf_destroy(&buf); - return total ? total : -EIO; -out: - tpm_buf_destroy(&buf); - tpm2_end_auth_session(chip); - return err; } /** @@ -347,31 +328,21 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) */ void tpm2_flush_context(struct tpm_chip *chip, u32 handle) { - struct tpm_buf buf; - int rc; - - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_FLUSH_CONTEXT); - if (rc) { + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { dev_warn(&chip->dev, "0x%08x was not flushed, out of memory\n", handle); return; } - tpm_buf_append_u32(&buf, handle); + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_FLUSH_CONTEXT); + tpm_buf_append_u32(buf, handle); - tpm_transmit_cmd(chip, &buf, 0, "flushing context"); - tpm_buf_destroy(&buf); + tpm_transmit_cmd(chip, buf, 0, "flushing context"); } EXPORT_SYMBOL_GPL(tpm2_flush_context); -struct tpm2_get_cap_out { - u8 more_data; - __be32 subcap_id; - __be32 property_cnt; - __be32 property_id; - __be32 value; -} __packed; - /** * tpm2_get_tpm_pt() - get value of a TPM_CAP_TPM_PROPERTIES type property * @chip: a &tpm_chip instance @@ -387,19 +358,21 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc) { struct tpm2_get_cap_out *out; - struct tpm_buf buf; int rc; - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); - if (rc) - return rc; - tpm_buf_append_u32(&buf, TPM2_CAP_TPM_PROPERTIES); - tpm_buf_append_u32(&buf, property_id); - tpm_buf_append_u32(&buf, 1); - rc = tpm_transmit_cmd(chip, &buf, 0, NULL); + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); + tpm_buf_append_u32(buf, TPM2_CAP_TPM_PROPERTIES); + tpm_buf_append_u32(buf, property_id); + tpm_buf_append_u32(buf, 1); + rc = tpm_transmit_cmd(chip, buf, 0, NULL); if (!rc) { out = (struct tpm2_get_cap_out *) - &buf.data[TPM_HEADER_SIZE]; + &buf->data[TPM_HEADER_SIZE]; /* * To prevent failing boot up of some systems, Infineon TPM2.0 * returns SUCCESS on TPM2_Startup in field upgrade mode. Also @@ -411,7 +384,6 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, else rc = -ENODATA; } - tpm_buf_destroy(&buf); return rc; } EXPORT_SYMBOL_GPL(tpm2_get_tpm_pt); @@ -428,15 +400,14 @@ EXPORT_SYMBOL_GPL(tpm2_get_tpm_pt); */ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type) { - struct tpm_buf buf; - int rc; - - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_SHUTDOWN); - if (rc) + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) return; - tpm_buf_append_u16(&buf, shutdown_type); - tpm_transmit_cmd(chip, &buf, 0, "stopping the TPM"); - tpm_buf_destroy(&buf); + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_SHUTDOWN); + tpm_buf_append_u16(buf, shutdown_type); + tpm_transmit_cmd(chip, buf, 0, "stopping the TPM"); } /** @@ -454,20 +425,21 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type) */ static int tpm2_do_selftest(struct tpm_chip *chip) { - struct tpm_buf buf; int full; int rc; for (full = 0; full < 2; full++) { - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_SELF_TEST); - if (rc) - return rc; + struct tpm_buf *buf __free(kfree) = NULL; - tpm_buf_append_u8(&buf, full); - rc = tpm_transmit_cmd(chip, &buf, 0, + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_SELF_TEST); + tpm_buf_append_u8(buf, full); + rc = tpm_transmit_cmd(chip, buf, 0, "attempting the self test"); - tpm_buf_destroy(&buf); - if (rc == TPM2_RC_TESTING) rc = TPM2_RC_SUCCESS; if (rc == TPM2_RC_INITIALIZE || rc == TPM2_RC_SUCCESS) @@ -492,23 +464,24 @@ static int tpm2_do_selftest(struct tpm_chip *chip) int tpm2_probe(struct tpm_chip *chip) { struct tpm_header *out; - struct tpm_buf buf; int rc; - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); - if (rc) - return rc; - tpm_buf_append_u32(&buf, TPM2_CAP_TPM_PROPERTIES); - tpm_buf_append_u32(&buf, TPM_PT_TOTAL_COMMANDS); - tpm_buf_append_u32(&buf, 1); - rc = tpm_transmit_cmd(chip, &buf, 0, NULL); + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); + tpm_buf_append_u32(buf, TPM2_CAP_TPM_PROPERTIES); + tpm_buf_append_u32(buf, TPM_PT_TOTAL_COMMANDS); + tpm_buf_append_u32(buf, 1); + rc = tpm_transmit_cmd(chip, buf, 0, NULL); /* We ignore TPM return codes on purpose. */ if (rc >= 0) { - out = (struct tpm_header *)buf.data; + out = (struct tpm_header *)buf->data; if (be16_to_cpu(out->tag) == TPM2_ST_NO_SESSIONS) chip->flags |= TPM_CHIP_FLAG_TPM2; } - tpm_buf_destroy(&buf); return 0; } EXPORT_SYMBOL_GPL(tpm2_probe); @@ -539,16 +512,9 @@ static int tpm2_init_bank_info(struct tpm_chip *chip, u32 bank_index) return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size); } -struct tpm2_pcr_selection { - __be16 hash_alg; - u8 size_of_select; - u8 pcr_select[3]; -} __packed; - ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) { struct tpm2_pcr_selection pcr_selection; - struct tpm_buf buf; void *marker; void *end; void *pcr_select_offset; @@ -560,31 +526,32 @@ ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) int rc; int i = 0; - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); + tpm_buf_append_u32(buf, TPM2_CAP_PCRS); + tpm_buf_append_u32(buf, 0); + tpm_buf_append_u32(buf, 1); + + rc = tpm_transmit_cmd(chip, buf, 9, "get tpm pcr allocation"); if (rc) return rc; - tpm_buf_append_u32(&buf, TPM2_CAP_PCRS); - tpm_buf_append_u32(&buf, 0); - tpm_buf_append_u32(&buf, 1); - - rc = tpm_transmit_cmd(chip, &buf, 9, "get tpm pcr allocation"); - if (rc) - goto out; - nr_possible_banks = be32_to_cpup( - (__be32 *)&buf.data[TPM_HEADER_SIZE + 5]); + (__be32 *)&buf->data[TPM_HEADER_SIZE + 5]); if (nr_possible_banks > TPM2_MAX_PCR_BANKS) { pr_err("tpm: out of bank capacity: %u > %u\n", nr_possible_banks, TPM2_MAX_PCR_BANKS); - rc = -ENOMEM; - goto out; + return -ENOMEM; } - marker = &buf.data[TPM_HEADER_SIZE + 9]; + marker = &buf->data[TPM_HEADER_SIZE + 9]; - rsp_len = be32_to_cpup((__be32 *)&buf.data[2]); - end = &buf.data[rsp_len]; + rsp_len = be32_to_cpup((__be32 *)&buf->data[2]); + end = &buf->data[rsp_len]; for (i = 0; i < nr_possible_banks; i++) { pcr_select_offset = marker + @@ -616,21 +583,20 @@ ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) } chip->nr_allocated_banks = nr_alloc_banks; -out: - tpm_buf_destroy(&buf); return rc; } int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) { - struct tpm_buf buf; u32 nr_commands; __be32 *attrs; u32 cc; int i; int rc; + struct tpm_buf *buf __free(kfree) = NULL; + rc = tpm2_get_tpm_pt(chip, TPM_PT_TOTAL_COMMANDS, &nr_commands, NULL); if (rc) goto out; @@ -647,30 +613,31 @@ int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) goto out; } - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); - if (rc) - goto out; - - tpm_buf_append_u32(&buf, TPM2_CAP_COMMANDS); - tpm_buf_append_u32(&buf, TPM2_CC_FIRST); - tpm_buf_append_u32(&buf, nr_commands); - - rc = tpm_transmit_cmd(chip, &buf, 9 + 4 * nr_commands, NULL); - if (rc) { - tpm_buf_destroy(&buf); + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { + rc = -ENOMEM; goto out; } + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); + tpm_buf_append_u32(buf, TPM2_CAP_COMMANDS); + tpm_buf_append_u32(buf, TPM2_CC_FIRST); + tpm_buf_append_u32(buf, nr_commands); + + rc = tpm_transmit_cmd(chip, buf, 9 + 4 * nr_commands, NULL); + if (rc) + goto out; + if (nr_commands != - be32_to_cpup((__be32 *)&buf.data[TPM_HEADER_SIZE + 5])) { + be32_to_cpup((__be32 *)&buf->data[TPM_HEADER_SIZE + 5])) { rc = -EFAULT; - tpm_buf_destroy(&buf); goto out; } chip->nr_commands = nr_commands; - attrs = (__be32 *)&buf.data[TPM_HEADER_SIZE + 9]; + attrs = (__be32 *)&buf->data[TPM_HEADER_SIZE + 9]; for (i = 0; i < nr_commands; i++, attrs++) { chip->cc_attrs_tbl[i] = be32_to_cpup(attrs); cc = chip->cc_attrs_tbl[i] & 0xFFFF; @@ -682,8 +649,6 @@ int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) } } - tpm_buf_destroy(&buf); - out: if (rc > 0) rc = -ENODEV; @@ -704,20 +669,18 @@ EXPORT_SYMBOL_GPL(tpm2_get_cc_attrs_tbl); static int tpm2_startup(struct tpm_chip *chip) { - struct tpm_buf buf; - int rc; + struct tpm_buf *buf __free(kfree) = NULL; dev_info(&chip->dev, "starting up the TPM manually\n"); - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_STARTUP); - if (rc < 0) - return rc; + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; - tpm_buf_append_u16(&buf, TPM2_SU_CLEAR); - rc = tpm_transmit_cmd(chip, &buf, 0, "attempting to start the TPM"); - tpm_buf_destroy(&buf); - - return rc; + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_STARTUP); + tpm_buf_append_u16(buf, TPM2_SU_CLEAR); + return tpm_transmit_cmd(chip, buf, 0, "attempting to start the TPM"); } /** diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index a1ae5e1829cb..cf8f1fd6790b 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -167,8 +167,8 @@ static int tpm2_read_public(struct tpm_chip *chip, u32 handle, void *name) { u32 mso = tpm2_handle_mso(handle); off_t offset = TPM_HEADER_SIZE; + struct tpm_buf *buf __free(kfree) = NULL; int rc, name_size_alg; - struct tpm_buf buf; if (mso != TPM2_MSO_PERSISTENT && mso != TPM2_MSO_VOLATILE && mso != TPM2_MSO_NVRAM) { @@ -176,50 +176,40 @@ static int tpm2_read_public(struct tpm_chip *chip, u32 handle, void *name) return sizeof(u32); } - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_READ_PUBLIC); + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_READ_PUBLIC); + tpm_buf_append_u32(buf, handle); + + rc = tpm_transmit_cmd(chip, buf, 0, "TPM2_ReadPublic"); if (rc) - return rc; - - tpm_buf_append_u32(&buf, handle); - - rc = tpm_transmit_cmd(chip, &buf, 0, "TPM2_ReadPublic"); - if (rc) { - tpm_buf_destroy(&buf); return tpm_ret_to_err(rc); - } /* Skip TPMT_PUBLIC: */ - offset += tpm_buf_read_u16(&buf, &offset); + offset += tpm_buf_read_u16(buf, &offset); /* * Ensure space for the length field of TPM2B_NAME and hashAlg field of * TPMT_HA (the extra four bytes). */ - if (offset + 4 > tpm_buf_length(&buf)) { - tpm_buf_destroy(&buf); + if (offset + 4 > tpm_buf_length(buf)) return -EIO; - } - rc = tpm_buf_read_u16(&buf, &offset); - name_size_alg = name_size(&buf.data[offset]); - - if (name_size_alg < 0) { - tpm_buf_destroy(&buf); + rc = tpm_buf_read_u16(buf, &offset); + name_size_alg = name_size(&buf->data[offset]); + if (name_size_alg < 0) return name_size_alg; - } - if (rc != name_size_alg) { - tpm_buf_destroy(&buf); + if (rc != name_size_alg) return -EIO; - } - if (offset + rc > tpm_buf_length(&buf)) { - tpm_buf_destroy(&buf); + if (offset + rc > tpm_buf_length(buf)) return -EIO; - } - memcpy(name, &buf.data[offset], rc); - tpm_buf_destroy(&buf); + memcpy(name, &buf->data[offset], rc); return name_size_alg; } #endif /* CONFIG_TCG_TPM2_HMAC */ @@ -260,7 +250,7 @@ int tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, #endif if (!tpm2_chip_auth(chip)) { - tpm_buf_append_handle(chip, buf, handle); + tpm_buf_append_handle(buf, handle); return 0; } @@ -1005,8 +995,8 @@ static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key) */ int tpm2_start_auth_session(struct tpm_chip *chip) { + struct tpm_buf *buf __free(kfree) = NULL; struct tpm2_auth *auth; - struct tpm_buf buf; u32 null_key; int rc; @@ -1020,58 +1010,61 @@ int tpm2_start_auth_session(struct tpm_chip *chip) return -ENOMEM; rc = tpm2_load_null(chip, &null_key); - if (rc) - goto out; + if (rc) { + kfree_sensitive(auth); + return rc; + } auth->session = TPM_HEADER_SIZE; - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_START_AUTH_SESS); - if (rc) - goto out; + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { + kfree_sensitive(auth); + return -ENOMEM; + } + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_NO_SESSIONS, TPM2_CC_START_AUTH_SESS); /* salt key handle */ - tpm_buf_append_u32(&buf, null_key); + tpm_buf_append_u32(buf, null_key); /* bind key handle */ - tpm_buf_append_u32(&buf, TPM2_RH_NULL); + tpm_buf_append_u32(buf, TPM2_RH_NULL); /* nonce caller */ get_random_bytes(auth->our_nonce, sizeof(auth->our_nonce)); - tpm_buf_append_u16(&buf, sizeof(auth->our_nonce)); - tpm_buf_append(&buf, auth->our_nonce, sizeof(auth->our_nonce)); + tpm_buf_append_u16(buf, sizeof(auth->our_nonce)); + tpm_buf_append(buf, auth->our_nonce, sizeof(auth->our_nonce)); /* append encrypted salt and squirrel away unencrypted in auth */ - rc = tpm_buf_append_salt(&buf, chip, auth); + rc = tpm_buf_append_salt(buf, chip, auth); if (rc) { tpm2_flush_context(chip, null_key); - tpm_buf_destroy(&buf); - goto out; + kfree_sensitive(auth); + return rc; } /* session type (HMAC, audit or policy) */ - tpm_buf_append_u8(&buf, TPM2_SE_HMAC); + tpm_buf_append_u8(buf, TPM2_SE_HMAC); /* symmetric encryption parameters */ /* symmetric algorithm */ - tpm_buf_append_u16(&buf, TPM_ALG_AES); + tpm_buf_append_u16(buf, TPM_ALG_AES); /* bits for symmetric algorithm */ - tpm_buf_append_u16(&buf, AES_KEY_BITS); + tpm_buf_append_u16(buf, AES_KEY_BITS); /* symmetric algorithm mode (must be CFB) */ - tpm_buf_append_u16(&buf, TPM_ALG_CFB); + tpm_buf_append_u16(buf, TPM_ALG_CFB); /* hash algorithm for session */ - tpm_buf_append_u16(&buf, TPM_ALG_SHA256); + tpm_buf_append_u16(buf, TPM_ALG_SHA256); - rc = tpm_ret_to_err(tpm_transmit_cmd(chip, &buf, 0, "StartAuthSession")); + rc = tpm_ret_to_err(tpm_transmit_cmd(chip, buf, 0, "StartAuthSession")); tpm2_flush_context(chip, null_key); if (rc == TPM2_RC_SUCCESS) - rc = tpm2_parse_start_auth_session(auth, &buf); - - tpm_buf_destroy(&buf); + rc = tpm2_parse_start_auth_session(auth, buf); if (rc == TPM2_RC_SUCCESS) { chip->auth = auth; return 0; } -out: kfree_sensitive(auth); return rc; } @@ -1285,19 +1278,21 @@ static int tpm2_parse_create_primary(struct tpm_chip *chip, struct tpm_buf *buf, static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, u32 *handle, u8 *name) { + struct tpm_buf *template __free(kfree) = NULL; + struct tpm_buf *buf __free(kfree) = NULL; int rc; - struct tpm_buf buf; - struct tpm_buf template; - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE_PRIMARY); - if (rc) - return rc; + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; - rc = tpm_buf_init_sized(&template); - if (rc) { - tpm_buf_destroy(&buf); - return rc; - } + template = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!template) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE_PRIMARY); + tpm_buf_init_sized(template, TPM_BUFSIZE); /* * create the template. Note: in order for userspace to @@ -1309,75 +1304,72 @@ static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, */ /* key type */ - tpm_buf_append_u16(&template, TPM_ALG_ECC); + tpm_buf_append_u16(template, TPM_ALG_ECC); /* name algorithm */ - tpm_buf_append_u16(&template, TPM_ALG_SHA256); + tpm_buf_append_u16(template, TPM_ALG_SHA256); /* object properties */ - tpm_buf_append_u32(&template, TPM2_OA_NULL_KEY); + tpm_buf_append_u32(template, TPM2_OA_NULL_KEY); /* sauth policy (empty) */ - tpm_buf_append_u16(&template, 0); + tpm_buf_append_u16(template, 0); /* BEGIN parameters: key specific; for ECC*/ /* symmetric algorithm */ - tpm_buf_append_u16(&template, TPM_ALG_AES); + tpm_buf_append_u16(template, TPM_ALG_AES); /* bits for symmetric algorithm */ - tpm_buf_append_u16(&template, AES_KEY_BITS); + tpm_buf_append_u16(template, AES_KEY_BITS); /* algorithm mode (must be CFB) */ - tpm_buf_append_u16(&template, TPM_ALG_CFB); + tpm_buf_append_u16(template, TPM_ALG_CFB); /* scheme (NULL means any scheme) */ - tpm_buf_append_u16(&template, TPM_ALG_NULL); + tpm_buf_append_u16(template, TPM_ALG_NULL); /* ECC Curve ID */ - tpm_buf_append_u16(&template, TPM2_ECC_NIST_P256); + tpm_buf_append_u16(template, TPM2_ECC_NIST_P256); /* KDF Scheme */ - tpm_buf_append_u16(&template, TPM_ALG_NULL); + tpm_buf_append_u16(template, TPM_ALG_NULL); /* unique: key specific; for ECC it is two zero size points */ - tpm_buf_append_u16(&template, 0); - tpm_buf_append_u16(&template, 0); + tpm_buf_append_u16(template, 0); + tpm_buf_append_u16(template, 0); /* END parameters */ /* primary handle */ - tpm_buf_append_u32(&buf, hierarchy); - tpm_buf_append_empty_auth(&buf, TPM2_RS_PW); + tpm_buf_append_u32(buf, hierarchy); + tpm_buf_append_empty_auth(buf, TPM2_RS_PW); /* sensitive create size is 4 for two empty buffers */ - tpm_buf_append_u16(&buf, 4); + tpm_buf_append_u16(buf, 4); /* sensitive create auth data (empty) */ - tpm_buf_append_u16(&buf, 0); + tpm_buf_append_u16(buf, 0); /* sensitive create sensitive data (empty) */ - tpm_buf_append_u16(&buf, 0); + tpm_buf_append_u16(buf, 0); /* the public template */ - tpm_buf_append(&buf, template.data, template.length); - tpm_buf_destroy(&template); + tpm_buf_append(buf, template->data, template->length); /* outside info (empty) */ - tpm_buf_append_u16(&buf, 0); + tpm_buf_append_u16(buf, 0); /* creation PCR (none) */ - tpm_buf_append_u32(&buf, 0); + tpm_buf_append_u32(buf, 0); - rc = tpm_transmit_cmd(chip, &buf, 0, + rc = tpm_transmit_cmd(chip, buf, 0, "attempting to create NULL primary"); if (rc == TPM2_RC_SUCCESS) - rc = tpm2_parse_create_primary(chip, &buf, handle, hierarchy, + rc = tpm2_parse_create_primary(chip, buf, handle, hierarchy, name); - tpm_buf_destroy(&buf); - return rc; } diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 60354cd53b5c..5b0f233db898 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -15,19 +15,6 @@ #include #include "tpm.h" -enum tpm2_handle_types { - TPM2_HT_HMAC_SESSION = 0x02000000, - TPM2_HT_POLICY_SESSION = 0x03000000, - TPM2_HT_TRANSIENT = 0x80000000, -}; - -struct tpm2_context { - __be64 sequence; - __be32 saved_handle; - __be32 hierarchy; - __be16 blob_size; -} __packed; - static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space) { int i; @@ -71,24 +58,25 @@ void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space) int tpm2_load_context(struct tpm_chip *chip, u8 *buf, unsigned int *offset, u32 *handle) { - struct tpm_buf tbuf; struct tpm2_context *ctx; unsigned int body_size; int rc; - rc = tpm_buf_init(&tbuf, TPM2_ST_NO_SESSIONS, TPM2_CC_CONTEXT_LOAD); - if (rc) - return rc; + struct tpm_buf *tbuf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!tbuf) + return -ENOMEM; + + tpm_buf_init(tbuf, TPM_BUFSIZE); + tpm_buf_reset(tbuf, TPM2_ST_NO_SESSIONS, TPM2_CC_CONTEXT_LOAD); ctx = (struct tpm2_context *)&buf[*offset]; body_size = sizeof(*ctx) + be16_to_cpu(ctx->blob_size); - tpm_buf_append(&tbuf, &buf[*offset], body_size); + tpm_buf_append(tbuf, &buf[*offset], body_size); - rc = tpm_transmit_cmd(chip, &tbuf, 4, NULL); + rc = tpm_transmit_cmd(chip, tbuf, 4, NULL); if (rc < 0) { dev_warn(&chip->dev, "%s: failed with a system error %d\n", __func__, rc); - tpm_buf_destroy(&tbuf); return -EFAULT; } else if (tpm2_rc_value(rc) == TPM2_RC_HANDLE || rc == TPM2_RC_REFERENCE_H0) { @@ -103,64 +91,55 @@ int tpm2_load_context(struct tpm_chip *chip, u8 *buf, * flushed outside the space */ *handle = 0; - tpm_buf_destroy(&tbuf); return -ENOENT; } else if (tpm2_rc_value(rc) == TPM2_RC_INTEGRITY) { - tpm_buf_destroy(&tbuf); return -EINVAL; } else if (rc > 0) { dev_warn(&chip->dev, "%s: failed with a TPM error 0x%04X\n", __func__, rc); - tpm_buf_destroy(&tbuf); return -EFAULT; } - *handle = be32_to_cpup((__be32 *)&tbuf.data[TPM_HEADER_SIZE]); + *handle = be32_to_cpup((__be32 *)&tbuf->data[TPM_HEADER_SIZE]); *offset += body_size; - - tpm_buf_destroy(&tbuf); return 0; } int tpm2_save_context(struct tpm_chip *chip, u32 handle, u8 *buf, unsigned int buf_size, unsigned int *offset) { - struct tpm_buf tbuf; unsigned int body_size; int rc; - rc = tpm_buf_init(&tbuf, TPM2_ST_NO_SESSIONS, TPM2_CC_CONTEXT_SAVE); - if (rc) - return rc; + struct tpm_buf *tbuf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!tbuf) + return -ENOMEM; - tpm_buf_append_u32(&tbuf, handle); + tpm_buf_init(tbuf, TPM_BUFSIZE); + tpm_buf_reset(tbuf, TPM2_ST_NO_SESSIONS, TPM2_CC_CONTEXT_SAVE); + tpm_buf_append_u32(tbuf, handle); - rc = tpm_transmit_cmd(chip, &tbuf, 0, NULL); + rc = tpm_transmit_cmd(chip, tbuf, 0, NULL); if (rc < 0) { dev_warn(&chip->dev, "%s: failed with a system error %d\n", __func__, rc); - tpm_buf_destroy(&tbuf); return -EFAULT; } else if (tpm2_rc_value(rc) == TPM2_RC_REFERENCE_H0) { - tpm_buf_destroy(&tbuf); return -ENOENT; } else if (rc) { dev_warn(&chip->dev, "%s: failed with a TPM error 0x%04X\n", __func__, rc); - tpm_buf_destroy(&tbuf); return -EFAULT; } - body_size = tpm_buf_length(&tbuf) - TPM_HEADER_SIZE; + body_size = tpm_buf_length(tbuf) - TPM_HEADER_SIZE; if ((*offset + body_size) > buf_size) { dev_warn(&chip->dev, "%s: out of backing storage\n", __func__); - tpm_buf_destroy(&tbuf); return -ENOMEM; } - memcpy(&buf[*offset], &tbuf.data[TPM_HEADER_SIZE], body_size); + memcpy(&buf[*offset], &tbuf->data[TPM_HEADER_SIZE], body_size); *offset += body_size; - tpm_buf_destroy(&tbuf); return 0; } diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index 129aa222cc25..c84afb29d548 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -182,8 +182,10 @@ static int i2c_nuvoton_wait_for_stat(struct tpm_chip *chip, u8 mask, u8 value, timeout); if (rc > 0) return 0; - /* At this point we know that the SINT pin is asserted, so we - * do not need to do i2c_nuvoton_check_status */ + + disable_irq(priv->irq); + if (rc < 0) + return rc; } else { unsigned long ten_msec, stop; bool status_valid; diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index aa6d78898ef3..d737b3d67411 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -19,71 +19,9 @@ #ifndef __TPM_TIS_CORE_H__ #define __TPM_TIS_CORE_H__ +#include #include "tpm.h" -enum tis_access { - TPM_ACCESS_VALID = 0x80, - TPM_ACCESS_ACTIVE_LOCALITY = 0x20, - TPM_ACCESS_REQUEST_PENDING = 0x04, - TPM_ACCESS_REQUEST_USE = 0x02, -}; - -enum tis_status { - TPM_STS_VALID = 0x80, - TPM_STS_COMMAND_READY = 0x40, - TPM_STS_GO = 0x20, - TPM_STS_DATA_AVAIL = 0x10, - TPM_STS_DATA_EXPECT = 0x08, - TPM_STS_RESPONSE_RETRY = 0x02, - TPM_STS_READ_ZERO = 0x23, /* bits that must be zero on read */ -}; - -enum tis_int_flags { - TPM_GLOBAL_INT_ENABLE = 0x80000000, - TPM_INTF_BURST_COUNT_STATIC = 0x100, - TPM_INTF_CMD_READY_INT = 0x080, - TPM_INTF_INT_EDGE_FALLING = 0x040, - TPM_INTF_INT_EDGE_RISING = 0x020, - TPM_INTF_INT_LEVEL_LOW = 0x010, - TPM_INTF_INT_LEVEL_HIGH = 0x008, - TPM_INTF_LOCALITY_CHANGE_INT = 0x004, - TPM_INTF_STS_VALID_INT = 0x002, - TPM_INTF_DATA_AVAIL_INT = 0x001, -}; - -enum tis_defaults { - TIS_MEM_LEN = 0x5000, - TIS_SHORT_TIMEOUT = 750, /* ms */ - TIS_LONG_TIMEOUT = 4000, /* 4 secs */ - TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */ - TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */ -}; - -/* Some timeout values are needed before it is known whether the chip is - * TPM 1.0 or TPM 2.0. - */ -#define TIS_TIMEOUT_A_MAX max_t(int, TIS_SHORT_TIMEOUT, TPM2_TIMEOUT_A) -#define TIS_TIMEOUT_B_MAX max_t(int, TIS_LONG_TIMEOUT, TPM2_TIMEOUT_B) -#define TIS_TIMEOUT_C_MAX max_t(int, TIS_SHORT_TIMEOUT, TPM2_TIMEOUT_C) -#define TIS_TIMEOUT_D_MAX max_t(int, TIS_SHORT_TIMEOUT, TPM2_TIMEOUT_D) - -#define TPM_ACCESS(l) (0x0000 | ((l) << 12)) -#define TPM_INT_ENABLE(l) (0x0008 | ((l) << 12)) -#define TPM_INT_VECTOR(l) (0x000C | ((l) << 12)) -#define TPM_INT_STATUS(l) (0x0010 | ((l) << 12)) -#define TPM_INTF_CAPS(l) (0x0014 | ((l) << 12)) -#define TPM_STS(l) (0x0018 | ((l) << 12)) -#define TPM_STS3(l) (0x001b | ((l) << 12)) -#define TPM_DATA_FIFO(l) (0x0024 | ((l) << 12)) - -#define TPM_DID_VID(l) (0x0F00 | ((l) << 12)) -#define TPM_RID(l) (0x0F04 | ((l) << 12)) - -#define LPC_CNTRL_OFFSET 0x84 -#define LPC_CLKRUN_EN (1 << 2) -#define INTEL_LEGACY_BLK_BASE_ADDR 0xFED08000 -#define ILB_REMAP_SIZE 0x100 - enum tpm_tis_flags { TPM_TIS_ITPM_WORKAROUND = 0, TPM_TIS_INVALID_STATUS = 1, diff --git a/drivers/char/tpm/tpm_tis_spi.h b/drivers/char/tpm/tpm_tis_spi.h index d0f66f6f1931..ced416ecd92c 100644 --- a/drivers/char/tpm/tpm_tis_spi.h +++ b/drivers/char/tpm/tpm_tis_spi.h @@ -40,8 +40,12 @@ static inline int cr50_spi_probe(struct spi_device *spi) } #endif -#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_TCG_TIS_SPI_CR50) -extern int tpm_tis_spi_resume(struct device *dev); +#if defined(CONFIG_PM_SLEEP) + #if defined(CONFIG_TCG_TIS_SPI_CR50) + extern int tpm_tis_spi_resume(struct device *dev); + #else + #define tpm_tis_spi_resume tpm_tis_resume + #endif #else #define tpm_tis_spi_resume NULL #endif diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 7bb0f4d4a2ed..b81fd2a537df 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -395,40 +395,36 @@ static bool vtpm_proxy_tpm_req_canceled(struct tpm_chip *chip, u8 status) static int vtpm_proxy_request_locality(struct tpm_chip *chip, int locality) { - struct tpm_buf buf; int rc; const struct tpm_header *header; struct proxy_dev *proxy_dev = dev_get_drvdata(&chip->dev); + struct tpm_buf *buf __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tpm_buf_init(buf, TPM_BUFSIZE); if (chip->flags & TPM_CHIP_FLAG_TPM2) - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, - TPM2_CC_SET_LOCALITY); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_SET_LOCALITY); else - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, - TPM_ORD_SET_LOCALITY); - if (rc) - return rc; - tpm_buf_append_u8(&buf, locality); + tpm_buf_reset(buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SET_LOCALITY); + + tpm_buf_append_u8(buf, locality); proxy_dev->state |= STATE_DRIVER_COMMAND; - rc = tpm_transmit_cmd(chip, &buf, 0, "attempting to set locality"); + rc = tpm_transmit_cmd(chip, buf, 0, "attempting to set locality"); proxy_dev->state &= ~STATE_DRIVER_COMMAND; - if (rc < 0) { - locality = rc; - goto out; - } + if (rc < 0) + return rc; - header = (const struct tpm_header *)buf.data; + header = (const struct tpm_header *)buf->data; rc = be32_to_cpu(header->return_code); if (rc) locality = -1; -out: - tpm_buf_destroy(&buf); - return locality; } diff --git a/drivers/edac/al_mc_edac.c b/drivers/edac/al_mc_edac.c index 178b9e581a72..bf6921d8890b 100644 --- a/drivers/edac/al_mc_edac.c +++ b/drivers/edac/al_mc_edac.c @@ -302,12 +302,8 @@ static int al_mc_edac_probe(struct platform_device *pdev) IRQF_SHARED, pdev->name, pdev); - if (ret != 0) { - dev_err(&pdev->dev, - "failed to request UE IRQ %d (%d)\n", - al_mc->irq_ue, ret); + if (ret != 0) return ret; - } } if (al_mc->irq_ce > 0) { @@ -317,12 +313,8 @@ static int al_mc_edac_probe(struct platform_device *pdev) IRQF_SHARED, pdev->name, pdev); - if (ret != 0) { - dev_err(&pdev->dev, - "failed to request CE IRQ %d (%d)\n", - al_mc->irq_ce, ret); + if (ret != 0) return ret; - } } return 0; diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 4edd2088c2db..1d1e2b5ca14c 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1507,6 +1507,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) int edac_idx, rc; struct device_node *np; const struct edac_device_prv_data *prv = &a10_sdmmceccb_data; + bool is_s10 = device->edac->is_s10; rc = altr_check_ecc_deps(device); if (rc) @@ -1548,15 +1549,14 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) /* * Update the PortB IRQs - A10 has 4, S10 has 2, Index accordingly - * - * FIXME: Instead of ifdefs with different architectures the driver - * should properly use compatibles. */ -#ifdef CONFIG_64BIT - altdev->sb_irq = irq_of_parse_and_map(np, 1); -#else - altdev->sb_irq = irq_of_parse_and_map(np, 2); -#endif + + /* Using compatibles to determine the IRQ Index */ + if (is_s10) + altdev->sb_irq = irq_of_parse_and_map(np, 1); + else + altdev->sb_irq = irq_of_parse_and_map(np, 2); + if (!altdev->sb_irq) { edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB SBIRQ alloc\n"); rc = -ENODEV; @@ -1570,29 +1570,28 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) goto err_release_group_1; } -#ifdef CONFIG_64BIT - /* Use IRQ to determine SError origin instead of assigning IRQ */ - rc = of_property_read_u32_index(np, "interrupts", 1, &altdev->db_irq); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, - "Error PortB DBIRQ alloc\n"); - goto err_release_group_1; + if (is_s10) { + /* Use IRQ to determine SError origin instead of assigning IRQ */ + rc = of_property_read_u32_index(np, "interrupts", 1, &altdev->db_irq); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); + goto err_release_group_1; + } + } else { + altdev->db_irq = irq_of_parse_and_map(np, 3); + if (!altdev->db_irq) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); + rc = -ENODEV; + goto err_release_group_1; + } + rc = devm_request_irq(&altdev->ddev, altdev->db_irq, + prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, + ecc_name, altdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); + goto err_release_group_1; + } } -#else - altdev->db_irq = irq_of_parse_and_map(np, 3); - if (!altdev->db_irq) { - edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); - rc = -ENODEV; - goto err_release_group_1; - } - rc = devm_request_irq(&altdev->ddev, altdev->db_irq, - prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, - ecc_name, altdev); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); - goto err_release_group_1; - } -#endif rc = edac_device_add_device(dci); if (rc) { @@ -1974,29 +1973,29 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac, goto err_release_group1; } -#ifdef CONFIG_64BIT - /* Use IRQ to determine SError origin instead of assigning IRQ */ - rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, - "Unable to parse DB IRQ index\n"); - goto err_release_group1; + if (edac->is_s10) { + /* Use IRQ to determine SError origin instead of assigning IRQ */ + rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, + "Unable to parse DB IRQ index\n"); + goto err_release_group1; + } + } else { + altdev->db_irq = irq_of_parse_and_map(np, 1); + if (!altdev->db_irq) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n"); + rc = -ENODEV; + goto err_release_group1; + } + rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, + IRQF_TRIGGER_HIGH, + ecc_name, altdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); + goto err_release_group1; + } } -#else - altdev->db_irq = irq_of_parse_and_map(np, 1); - if (!altdev->db_irq) { - edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n"); - rc = -ENODEV; - goto err_release_group1; - } - rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, - IRQF_TRIGGER_HIGH, - ecc_name, altdev); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); - goto err_release_group1; - } -#endif rc = edac_device_add_device(dci); if (rc) { @@ -2059,7 +2058,6 @@ static const struct irq_domain_ops a10_eccmgr_ic_ops = { /************** Stratix 10 EDAC Double Bit Error Handler ************/ #define to_a10edac(p, m) container_of(p, struct altr_arria10_edac, m) -#ifdef CONFIG_64BIT /* panic routine issues reboot on non-zero panic_timeout */ extern int panic_timeout; @@ -2106,7 +2104,6 @@ static int s10_edac_dberr_handler(struct notifier_block *this, return NOTIFY_DONE; } -#endif /****************** Arria 10 EDAC Probe Function *********************/ static int altr_edac_a10_probe(struct platform_device *pdev) @@ -2122,6 +2119,8 @@ static int altr_edac_a10_probe(struct platform_device *pdev) platform_set_drvdata(pdev, edac); INIT_LIST_HEAD(&edac->a10_ecc_devices); + edac->is_s10 = !!device_get_match_data(&pdev->dev); + edac->ecc_mgr_map = altr_sysmgr_regmap_lookup_by_phandle(pdev->dev.of_node, "altr,sysmgr-syscon"); @@ -2153,8 +2152,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev) irq_set_chained_handler_and_data(edac->sb_irq, altr_edac_a10_irq_handler, edac); - -#ifdef CONFIG_64BIT + if (edac->is_s10) { int dberror, err_addr; @@ -2177,15 +2175,14 @@ static int altr_edac_a10_probe(struct platform_device *pdev) regmap_write(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST, 0); } - } -#else - edac->db_irq = platform_get_irq(pdev, 1); - if (edac->db_irq < 0) - return edac->db_irq; + } else { + edac->db_irq = platform_get_irq(pdev, 1); + if (edac->db_irq < 0) + return edac->db_irq; - irq_set_chained_handler_and_data(edac->db_irq, - altr_edac_a10_irq_handler, edac); -#endif + irq_set_chained_handler_and_data(edac->db_irq, + altr_edac_a10_irq_handler, edac); + } for_each_child_of_node(pdev->dev.of_node, child) { if (!of_device_is_available(child)) @@ -2207,7 +2204,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev) static const struct of_device_id altr_edac_a10_of_match[] = { { .compatible = "altr,socfpga-a10-ecc-manager" }, - { .compatible = "altr,socfpga-s10-ecc-manager" }, + { .compatible = "altr,socfpga-s10-ecc-manager", .data = (void *)1 }, {}, }; MODULE_DEVICE_TABLE(of, altr_edac_a10_of_match); diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h index f3e84172caa9..9387056fd65e 100644 --- a/drivers/edac/altera_edac.h +++ b/drivers/edac/altera_edac.h @@ -394,6 +394,7 @@ struct altr_arria10_edac { struct irq_chip irq_chip; struct list_head a10_ecc_devices; struct notifier_block panic_notifier; + bool is_s10; }; #endif /* #ifndef _ALTERA_EDAC_H */ diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index c6aa69dbd9fb..475235c402e8 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -4173,6 +4173,8 @@ static int __init amd64_edac_init(void) goto err_pci; } + request_module_nowait("amd_atl"); + /* register stuff with EDAC MCE */ if (boot_cpu_data.x86 >= 0x17) { amd_register_ecc_decoder(decode_umc_error); diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c index dadb8acbee3d..6e069b255595 100644 --- a/drivers/edac/aspeed_edac.c +++ b/drivers/edac/aspeed_edac.c @@ -214,10 +214,8 @@ static int config_irq(void *ctx, struct platform_device *pdev) rc = devm_request_irq(&pdev->dev, irq, mcr_isr, IRQF_TRIGGER_HIGH, DRV_NAME, ctx); - if (rc) { - dev_err(&pdev->dev, "unable to request irq %d\n", irq); + if (rc) return rc; - } /* enable interrupts */ regmap_update_bits(aspeed_regmap, ASPEED_MCR_INTR_CTRL, diff --git a/drivers/edac/debugfs.c b/drivers/edac/debugfs.c index 8195fc9c9354..447d0c620082 100644 --- a/drivers/edac/debugfs.c +++ b/drivers/edac/debugfs.c @@ -1,50 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only -#include - #include "edac_module.h" static struct dentry *edac_debugfs; -static ssize_t edac_fake_inject_write(struct file *file, - const char __user *data, - size_t count, loff_t *ppos) -{ - struct device *dev = file->private_data; - struct mem_ctl_info *mci = to_mci(dev); - static enum hw_event_mc_err_type type; - u16 errcount = mci->fake_inject_count; - - if (!errcount) - errcount = 1; - - type = mci->fake_inject_ue ? HW_EVENT_ERR_UNCORRECTED - : HW_EVENT_ERR_CORRECTED; - - printk(KERN_DEBUG - "Generating %d %s fake error%s to %d.%d.%d to test core handling. NOTE: this won't test the driver-specific decoding logic.\n", - errcount, - (type == HW_EVENT_ERR_UNCORRECTED) ? "UE" : "CE", - str_plural(errcount), - mci->fake_inject_layer[0], - mci->fake_inject_layer[1], - mci->fake_inject_layer[2] - ); - edac_mc_handle_error(type, mci, errcount, 0, 0, 0, - mci->fake_inject_layer[0], - mci->fake_inject_layer[1], - mci->fake_inject_layer[2], - "FAKE ERROR", "for EDAC testing only"); - - return count; -} - -static const struct file_operations debug_fake_inject_fops = { - .open = simple_open, - .write = edac_fake_inject_write, - .llseek = generic_file_llseek, -}; - void __init edac_debugfs_init(void) { edac_debugfs = debugfs_create_dir("edac", NULL); @@ -57,29 +16,7 @@ void edac_debugfs_exit(void) void edac_create_debugfs_nodes(struct mem_ctl_info *mci) { - struct dentry *parent; - char name[80]; - int i; - - parent = debugfs_create_dir(mci->dev.kobj.name, edac_debugfs); - - for (i = 0; i < mci->n_layers; i++) { - sprintf(name, "fake_inject_%s", - edac_layer_name[mci->layers[i].type]); - debugfs_create_u8(name, S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_layer[i]); - } - - debugfs_create_bool("fake_inject_ue", S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_ue); - - debugfs_create_u16("fake_inject_count", S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_count); - - debugfs_create_file("fake_inject", S_IWUSR, parent, &mci->dev, - &debug_fake_inject_fops); - - mci->debugfs = parent; + mci->debugfs = debugfs_create_dir(mci->dev.kobj.name, edac_debugfs); } /* Create a toplevel dir under EDAC's debugfs hierarchy */ diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index cf0d3c2dfc04..638be1f47c59 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -342,14 +342,10 @@ static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) } /* - * edac_device_reset_delay_period - * - * need to stop any outstanding workq queued up at this time - * because we will be resetting the sleep time. - * Then restart the workq on the new delay + * Stop any outstanding workq queued up at this time because sleep time will + * be reset. Then restart the workq on the new delay. */ -void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, - unsigned long msec) +void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec) { edac_dev->poll_msec = msec; edac_dev->delay = msecs_to_jiffies(msec); diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index b1c2717cd023..6359007701ba 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -84,18 +84,23 @@ static ssize_t edac_device_ctl_poll_msec_show(struct edac_device_ctl_info return sprintf(data, "%u\n", ctl_info->poll_msec); } -static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info - *ctl_info, const char *data, - size_t count) +static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info *ctl_info, + const char *data, size_t count) { - unsigned long value; + unsigned int value; + int ret; - /* get the value and enforce that it is non-zero, must be at least - * one millisecond for the delay period, between scans - * Then cancel last outstanding delay for the work request - * and set a new one. + /* + * Get the value, make sure it is non-zero, must be at least one millisecond + * for the delay period between scans. */ - value = simple_strtoul(data, NULL, 0); + ret = kstrtouint(data, 0, &value); + if (ret < 0) + return ret; + + if (value < 1) + return -EINVAL; + edac_device_reset_delay_period(ctl_info, value); return count; diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index c2ed6c696e54..9b4b5582fa9f 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -129,7 +129,7 @@ static ssize_t dimmdev_location_show(struct device *dev, ssize_t count; count = edac_dimm_info_location(dimm, data, PAGE_SIZE); - count += scnprintf(data + count, PAGE_SIZE - count, "\n"); + count += sysfs_emit_at(data, count, "\n"); return count; } diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index 47593afdc234..eceef5539186 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -52,8 +52,7 @@ bool edac_queue_work(struct delayed_work *work, unsigned long delay); bool edac_stop_work(struct delayed_work *work); bool edac_mod_work(struct delayed_work *work, unsigned long delay); -extern void edac_device_reset_delay_period(struct edac_device_ctl_info - *edac_dev, unsigned long msec); +extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec); extern void edac_mc_reset_delay_period(unsigned long value); /* diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index a8879d72d064..68d16cc8298d 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -235,10 +235,8 @@ static int highbank_mc_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler, 0, dev_name(&pdev->dev), mci); - if (res < 0) { - dev_err(&pdev->dev, "Unable to request irq %d\n", irq); + if (res < 0) goto err2; - } devres_close_group(&pdev->dev, NULL); return 0; diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 94ab80197c2e..6f5fdf43e773 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -416,7 +416,23 @@ static void populate_dimm_info(struct dimm_data *dd, u32 addr_decode, int dimm, { dd->size = field_get(cfg->reg_mad_dimm_size_mask[dimm], addr_decode) * cfg->reg_mad_dimm_size_granularity; dd->ranks = field_get(cfg->reg_mad_dimm_rank_mask[dimm], addr_decode) + 1; - dd->dtype = field_get(cfg->reg_mad_dimm_width_mask[dimm], addr_decode) + DEV_X8; + + switch (field_get(cfg->reg_mad_dimm_width_mask[dimm], addr_decode)) { + case 0: + dd->dtype = DEV_X8; + break; + case 1: + dd->dtype = DEV_X16; + break; + case 2: + dd->dtype = DEV_X32; + break; + case 3: + dd->dtype = DEV_X64; + break; + default: + dd->dtype = DEV_UNKNOWN; + } } static void ie31200_get_dimm_config(struct mem_ctl_info *mci, void __iomem *window, diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index f1fc20d4ebf6..776c5db2f598 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -42,7 +42,8 @@ #define GET_BITFIELD(v, lo, hi) (((v) & GENMASK_ULL(hi, lo)) >> (lo)) -#define NUM_IMC 2 /* Max memory controllers */ +/* Probing upper bound, not a hardware capability limit. */ +#define MAX_IMC_TO_PROBE 8 #define NUM_CHANNELS 2 /* Max channels */ #define NUM_DIMMS 2 /* Max DIMMs per channel */ @@ -122,6 +123,43 @@ #define MEM_SLICE_HASH_MASK(v) (GET_BITFIELD(v, 6, 19) << 6) #define MEM_SLICE_HASH_LSB_MASK_BIT(v) GET_BITFIELD(v, 24, 26) +/* + * A slice represents a portion of memory space participating in an + * interleave relationship within the memory hierarchy. + * + * It can represent in different levels such as: + * + * - a pair of memory controllers + * - a memory controller + * - a memory channel + * - a memory sub-channel / DIMM + * + * +--------+ + * | | + * | Zone 1 | + * | | + * +--------+ +--------+ + * | | | | + * | | | | + * | Zone 0 | | Zone 0 | + * | | | | + * | | | | + * +--------+ +--------+ + * + * Slice L Slice S + * + * Memory space is divided into: + * + * - Zone 0 : Interleaved region + * - Zone 1 : Non-interleaved region (upper part of the large slice). + */ +struct slice { + /* Slice address. */ + u64 addr; + /* Slice that @addr belongs to. */ + int id; +}; + struct igen6_imc { int mc; struct mem_ctl_info *mci; @@ -175,8 +213,6 @@ static struct res_config { /* Set imc->dimm_{l_size,s_size,l_map}[chan]. */ void (*set_dimm_params)(struct igen6_imc *imc, int chan); bool (*ibecc_available)(struct pci_dev *pdev); - /* Extract error address logged in IBECC */ - u64 (*err_addr)(u64 ecclog); /* Convert error address logged in IBECC to system physical address */ u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc); /* Convert error address logged in IBECC to integrated memory controller address */ @@ -184,11 +220,11 @@ static struct res_config { } *res_cfg; static struct igen6_pvt { - struct igen6_imc imc[NUM_IMC]; void __iomem *memss_pma_cr; u64 ms_hash; u64 ms_s_size; int ms_l_map; + struct igen6_imc imc[]; } *igen6_pvt; /* The top of low usable DRAM */ @@ -225,7 +261,8 @@ static char ecclog_buf[ECCLOG_POOL_SIZE]; static struct irq_work ecclog_irq_work; static struct work_struct ecclog_work; -/* Compute die IDs for Elkhart Lake with IBECC */ +/* SoC compute die IDs with IBECC capability. */ +/* Elkhart Lake */ #define DID_EHL_SKU5 0x4514 #define DID_EHL_SKU6 0x4528 #define DID_EHL_SKU7 0x452a @@ -238,22 +275,22 @@ static struct work_struct ecclog_work; #define DID_EHL_SKU14 0x4534 #define DID_EHL_SKU15 0x4536 -/* Compute die IDs for ICL-NNPI with IBECC */ +/* ICL-NNPI */ #define DID_ICL_SKU8 0x4581 #define DID_ICL_SKU10 0x4585 #define DID_ICL_SKU11 0x4589 #define DID_ICL_SKU12 0x458d -/* Compute die IDs for Tiger Lake with IBECC */ +/* Tiger Lake */ #define DID_TGL_SKU 0x9a14 -/* Compute die IDs for Alder Lake with IBECC */ +/* Alder Lake */ #define DID_ADL_SKU1 0x4601 #define DID_ADL_SKU2 0x4602 #define DID_ADL_SKU3 0x4621 #define DID_ADL_SKU4 0x4641 -/* Compute die IDs for Alder Lake-N with IBECC */ +/* Alder Lake-N */ #define DID_ADL_N_SKU1 0x4614 #define DID_ADL_N_SKU2 0x4617 #define DID_ADL_N_SKU3 0x461b @@ -267,38 +304,38 @@ static struct work_struct ecclog_work; #define DID_ADL_N_SKU11 0x467c #define DID_ADL_N_SKU12 0x4632 -/* Compute die IDs for Arizona Beach with IBECC */ +/* Arizona Beach */ #define DID_AZB_SKU1 0x4676 -/* Compute did IDs for Amston Lake with IBECC */ +/* Amston Lake */ #define DID_ASL_SKU1 0x464a #define DID_ASL_SKU2 0x4646 #define DID_ASL_SKU3 0x4652 -/* Compute die IDs for Raptor Lake-P with IBECC */ +/* Raptor Lake-P */ #define DID_RPL_P_SKU1 0xa706 #define DID_RPL_P_SKU2 0xa707 #define DID_RPL_P_SKU3 0xa708 #define DID_RPL_P_SKU4 0xa716 #define DID_RPL_P_SKU5 0xa718 -/* Compute die IDs for Meteor Lake-PS with IBECC */ +/* Meteor Lake-PS */ #define DID_MTL_PS_SKU1 0x7d21 #define DID_MTL_PS_SKU2 0x7d22 #define DID_MTL_PS_SKU3 0x7d23 #define DID_MTL_PS_SKU4 0x7d24 -/* Compute die IDs for Meteor Lake-P with IBECC */ +/* Meteor Lake-P */ #define DID_MTL_P_SKU1 0x7d01 #define DID_MTL_P_SKU2 0x7d02 #define DID_MTL_P_SKU3 0x7d14 -/* Compute die IDs for Arrow Lake-UH with IBECC */ +/* Arrow Lake-UH */ #define DID_ARL_UH_SKU1 0x7d06 #define DID_ARL_UH_SKU2 0x7d20 #define DID_ARL_UH_SKU3 0x7d30 -/* Compute die IDs for Panther Lake-H with IBECC */ +/* Panther Lake-H */ #define DID_PTL_H_SKU1 0xb000 #define DID_PTL_H_SKU2 0xb001 #define DID_PTL_H_SKU3 0xb002 @@ -314,15 +351,114 @@ static struct work_struct ecclog_work; #define DID_PTL_H_SKU13 0xb02a #define DID_PTL_H_SKU14 0xb00a -/* Compute die IDs for Wildcat Lake with IBECC */ +/* Starfire */ +#define DID_STF_SKU1 0xb02b + +/* Wildcat Lake */ #define DID_WCL_SKU1 0xfd00 -/* Compute die IDs for Nova Lake-H/HX with IBECC */ +/* Nova Lake-H/HX */ #define DID_NVL_H_SKU1 0xd701 #define DID_NVL_H_SKU2 0xd702 #define DID_NVL_H_SKU3 0xd704 #define DID_NVL_H_SKU4 0xd705 +/* Remove the interleave bit and shift upper part down to fill gap. */ +static u64 squeeze_addr(u64 addr, int intlv_bit) +{ + u64 slice_addr; + + slice_addr = GET_BITFIELD(addr, intlv_bit + 1, 63) << intlv_bit; + slice_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); + + return slice_addr; +} + +/* Shift the upper bits up and insert a zero at the @intlv_bit bit position. */ +static u64 inflate_addr(u64 addr, int intlv_bit) +{ + u64 inflated_addr; + + /* Insert a zero at @intlv_bit position. */ + inflated_addr = GET_BITFIELD(addr, intlv_bit, 63) << (intlv_bit + 1); + inflated_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); + + return inflated_addr; +} + +static u64 compute_hash(u64 addr, u64 hash_mask, u64 hash_base, int intlv_bit) +{ + u64 hash_addr; + int i; + + /* + * In hash mode, @intlv_bit is the lowest selected bit of @addr + * to be XORed. While @mask may or may not include this @intlv_bit, + * we enforce that @mask includes @intlv_bit to ensure @intlv_bit is + * XORed exactly once. + */ + hash_mask |= BIT_ULL(intlv_bit); + hash_addr = addr & hash_mask; + + for (i = 6; i < 20; i++) + hash_base ^= (hash_addr >> i) & 1; + + return hash_base; +} + +/* + * Converts a higher-level address (system / IMC / channel) into a lower-level + * slice address and identifier. + */ +static void translate_to_lower_level(u64 addr, u64 hash_mask, u64 hash_base, + int intlv_bit, u64 s_size, int l_map, + struct slice *slice) +{ + /* In non-interleave zone. */ + if (addr >= 2 * s_size) { + slice->addr = addr - s_size; + slice->id = l_map; + return; + } + + /* In interleave zone. */ + slice->addr = squeeze_addr(addr, intlv_bit); + + /* Non-hash mode. */ + if (!hash_mask) { + slice->id = GET_BITFIELD(addr, intlv_bit, intlv_bit); + return; + } + + /* Hash mode. */ + slice->id = compute_hash(addr, hash_mask, hash_base, intlv_bit); +} + +/* Reconstruct address for upper memory hierarchy level. */ +static u64 translate_to_upper_level(u64 addr, u64 hash_mask, u64 hash_base, + int intlv_bit, u64 s_size) +{ + u64 inflated_addr, hash_val; + + /* In non-interleave zone. */ + if (addr >= s_size) + return addr + s_size; + + /* + * In interleave zone. + * + * Insert a zero at @intlv_bit position. + */ + inflated_addr = inflate_addr(addr, intlv_bit); + + /* + * Reconstruct the removed interleave bit and use it to replace + * the zero at @intlv_bit position. + */ + hash_val = compute_hash(inflated_addr, hash_mask, hash_base, intlv_bit); + return inflated_addr | (hash_val << intlv_bit); +} + static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) { union { @@ -354,6 +490,46 @@ static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) return 0; } +/* Check whether the memory controller is absent. */ +static bool imc_absent(void __iomem *window) +{ + return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0; +} + +/* Return MMIO base address of the memory controller if it's present, otherwise return NULL. */ +static void __iomem *map_imc_window(u64 mchbar, int pmc) +{ + void __iomem *window; + + window = ioremap(mchbar + pmc * MCHBAR_SIZE, MCHBAR_SIZE); + if (!window) + return NULL; + + if (imc_absent(window)) { + iounmap(window); + return NULL; + } + + return window; +} + +/* Return the number of present memory controllers. */ +static int get_imc_num(u64 mchbar) +{ + void __iomem *window; + int lmc, pmc; + + for (lmc = 0, pmc = 0; pmc < MAX_IMC_TO_PROBE; pmc++) { + window = map_imc_window(mchbar, pmc); + if (window) { + iounmap(window); + lmc++; + } + } + + return lmc; +} + static bool ehl_ibecc_available(struct pci_dev *pdev) { u32 v; @@ -450,21 +626,9 @@ static u64 mem_addr_to_sys_addr(u64 maddr) return maddr; } -static u64 mem_slice_hash(u64 addr, u64 mask, u64 hash_init, int intlv_bit) -{ - u64 hash_addr = addr & mask, hash = hash_init; - u64 intlv = (addr >> intlv_bit) & 1; - int i; - - for (i = 6; i < 20; i++) - hash ^= (hash_addr >> i) & 1; - - return hash ^ intlv; -} - static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) { - u64 maddr, hash, mask, ms_s_size; + u64 mask, ms_s_size; int intlv_bit; u32 ms_hash; @@ -477,12 +641,7 @@ static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) mask = MEM_SLICE_HASH_MASK(ms_hash); intlv_bit = MEM_SLICE_HASH_LSB_MASK_BIT(ms_hash) + 6; - maddr = GET_BITFIELD(eaddr, intlv_bit, 63) << (intlv_bit + 1) | - GET_BITFIELD(eaddr, 0, intlv_bit - 1); - - hash = mem_slice_hash(maddr, mask, mc, intlv_bit); - - return maddr | (hash << intlv_bit); + return translate_to_upper_level(eaddr, mask, mc, intlv_bit, ms_s_size); } static u64 tgl_err_addr_to_sys_addr(u64 eaddr, int mc) @@ -504,8 +663,9 @@ static u64 adl_err_addr_to_sys_addr(u64 eaddr, int mc) static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) { - u64 imc_addr, ms_s_size = igen6_pvt->ms_s_size; + u64 ms_s_size = igen6_pvt->ms_s_size; struct igen6_imc *imc = &igen6_pvt->imc[mc]; + struct slice slice; int intlv_bit; u32 mc_hash; @@ -516,15 +676,8 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) intlv_bit = MAC_MC_HASH_LSB(mc_hash) + 6; - imc_addr = GET_BITFIELD(eaddr, intlv_bit + 1, 63) << intlv_bit | - GET_BITFIELD(eaddr, 0, intlv_bit - 1); - - return imc_addr; -} - -static u64 rpl_p_err_addr(u64 ecclog) -{ - return field_get(res_cfg->reg_eccerrlog_addr_mask, ecclog); + translate_to_lower_level(eaddr, 0, 0, intlv_bit, ms_s_size, 0, &slice); + return slice.addr; } static enum mem_type ptl_h_get_mem_type(struct igen6_imc *imc) @@ -686,6 +839,7 @@ static struct res_config tgl_cfg = { .err_addr_to_imc_addr = tgl_err_addr_to_imc_addr, }; +/* Shared by Alder Lake, Alder Lake-N, Arizona Beach, Amston Lake, and Raptor Lake-P */ static struct res_config adl_cfg = { .machine_check = true, .num_imc = 2, @@ -701,37 +855,6 @@ static struct res_config adl_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config adl_n_cfg = { - .machine_check = true, - .num_imc = 1, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - -static struct res_config rpl_p_cfg = { - .machine_check = true, - .num_imc = 2, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr = rpl_p_err_addr, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config mtl_ps_cfg = { .machine_check = true, .num_imc = 2, @@ -749,6 +872,7 @@ static struct res_config mtl_ps_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +/* Shared by Meteor Lake-P, Arrow Lake-UH, and Wildcat Lake */ static struct res_config mtl_p_cfg = { .machine_check = true, .num_imc = 2, @@ -764,6 +888,7 @@ static struct res_config mtl_p_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +/* Shared by Panther Lake-H and Starfire */ static struct res_config ptl_h_cfg = { .machine_check = true, .num_imc = 2, @@ -794,21 +919,6 @@ static struct res_config ptl_h_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config wcl_cfg = { - .machine_check = true, - .num_imc = 1, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(38, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x170, - .ibecc_available = mtl_p_ibecc_available, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config nvl_h_cfg = { .machine_check = true, .num_imc = 2, @@ -861,27 +971,27 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_AZB_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_AZB_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU1), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU2), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU3), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, @@ -892,6 +1002,7 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU1), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU2), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU3), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_WCL_SKU1), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU1), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU2), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU3), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, @@ -906,7 +1017,7 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_PTL_H_SKU12), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU13), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU14), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, - { PCI_VDEVICE(INTEL, DID_WCL_SKU1), .driver_data = (kernel_ulong_t)&wcl_cfg }, + { PCI_VDEVICE(INTEL, DID_STF_SKU1), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU1), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU2), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU3), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, @@ -1007,55 +1118,13 @@ static void set_dimm_params(struct igen6_imc *imc, int chan) imc->dimm_s_size[chan] = MAD_DIMM_CH_DIMM_S_SIZE(val); } -static int decode_chan_idx(u64 addr, u64 mask, int intlv_bit) -{ - u64 hash_addr = addr & mask, hash = 0; - u64 intlv = (addr >> intlv_bit) & 1; - int i; - - for (i = 6; i < 20; i++) - hash ^= (hash_addr >> i) & 1; - - return (int)hash ^ intlv; -} - -static u64 decode_channel_addr(u64 addr, int intlv_bit) -{ - u64 channel_addr; - - /* Remove the interleave bit and shift upper part down to fill gap */ - channel_addr = GET_BITFIELD(addr, intlv_bit + 1, 63) << intlv_bit; - channel_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); - - return channel_addr; -} - -static void decode_addr(u64 addr, u32 hash, u64 s_size, int l_map, - int *idx, u64 *sub_addr) -{ - int intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; - - if (addr > 2 * s_size) { - *sub_addr = addr - s_size; - *idx = l_map; - return; - } - - if (CHANNEL_HASH_MODE(hash)) { - *sub_addr = decode_channel_addr(addr, intlv_bit); - *idx = decode_chan_idx(addr, CHANNEL_HASH_MASK(hash), intlv_bit); - } else { - *sub_addr = decode_channel_addr(addr, 6); - *idx = GET_BITFIELD(addr, 6, 6); - } -} - static int igen6_decode(struct decoded_addr *res) { struct igen6_imc *imc = &igen6_pvt->imc[res->mc]; - u64 addr = res->imc_addr, sub_addr, s_size; - int idx, l_map; - u32 hash; + u64 addr = res->imc_addr, s_size; + int intlv_bit, l_map; + u32 hash, hash_mask; + struct slice slice; if (addr >= igen6_tom) { edac_dbg(0, "Address 0x%llx out of range\n", addr); @@ -1066,17 +1135,25 @@ static int igen6_decode(struct decoded_addr *res) hash = readl(imc->window + CHANNEL_HASH_OFFSET); s_size = imc->ch_s_size; l_map = imc->ch_l_map; - decode_addr(addr, hash, s_size, l_map, &idx, &sub_addr); - res->channel_idx = idx; - res->channel_addr = sub_addr; + hash_mask = CHANNEL_HASH_MODE(hash) ? CHANNEL_HASH_MASK(hash) : 0; + intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; + + translate_to_lower_level(addr, hash_mask, 0, intlv_bit, s_size, l_map, &slice); + + res->channel_idx = slice.id; + res->channel_addr = slice.addr; /* Decode sub-channel/DIMM */ hash = readl(imc->window + CHANNEL_EHASH_OFFSET); - s_size = imc->dimm_s_size[idx]; - l_map = imc->dimm_l_map[idx]; - decode_addr(res->channel_addr, hash, s_size, l_map, &idx, &sub_addr); - res->sub_channel_idx = idx; - res->sub_channel_addr = sub_addr; + s_size = imc->dimm_s_size[res->channel_idx]; + l_map = imc->dimm_l_map[res->channel_idx]; + hash_mask = CHANNEL_HASH_MODE(hash) ? CHANNEL_HASH_MASK(hash) : 0; + intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; + + translate_to_lower_level(res->channel_addr, hash_mask, 0, intlv_bit, s_size, l_map, &slice); + + res->sub_channel_idx = slice.id; + res->sub_channel_addr = slice.addr; return 0; } @@ -1230,11 +1307,7 @@ static void ecclog_work_cb(struct work_struct *work) llist_for_each_entry_safe(node, tmp, head, llnode) { memset(&res, 0, sizeof(res)); - if (res_cfg->err_addr) - eaddr = res_cfg->err_addr(node->ecclog); - else - eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; - + eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; res.mc = node->mc; res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc); res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc); @@ -1476,18 +1549,27 @@ static struct igen6_pvt *igen6_pvt_setup(struct pci_dev *pdev) { void __iomem *memss_pma_cr; struct igen6_pvt *pvt; + int imc_num, rc; u64 mchbar; - int rc; - - pvt = kzalloc_obj(*igen6_pvt); - if (!pvt) - return NULL; rc = get_mchbar(pdev, &mchbar); - if (rc) { - kfree(pvt); + if (rc) + return NULL; + + imc_num = get_imc_num(mchbar); + if (!imc_num) { + igen6_printk(KERN_ERR, "No mc found.\n"); return NULL; } + edac_dbg(2, "%d mcs found.\n", imc_num); + + /* Use the runtime detected IMC count. */ + if (res_cfg->num_imc != imc_num) + res_cfg->num_imc = imc_num; + + pvt = kzalloc_flex(*pvt, imc, imc_num); + if (!pvt) + return NULL; memss_pma_cr = ioremap(mchbar, MCHBAR_SIZE * 2); if (!memss_pma_cr) { @@ -1572,12 +1654,6 @@ static void igen6_check(struct mem_ctl_info *mci) irq_work_queue(&ecclog_irq_work); } -/* Check whether the memory controller is absent. */ -static bool igen6_imc_absent(void __iomem *window) -{ - return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0; -} - static void imc_release(struct device *dev) { /* Nothing to do, the 'imc' owns the 'dev' and will also release it. */ @@ -1689,26 +1765,15 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar) { void __iomem *window; int lmc, pmc, rc; - u64 base; - for (lmc = 0, pmc = 0; pmc < NUM_IMC; pmc++) { - base = mchbar + pmc * MCHBAR_SIZE; - window = ioremap(base, MCHBAR_SIZE); - if (!window) { - igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx for mc%d\n", base, pmc); - rc = -ENOMEM; - goto out_unregister_mcis; - } - - if (igen6_imc_absent(window)) { - iounmap(window); - edac_dbg(2, "Skip absent mc%d\n", pmc); + for (lmc = 0, pmc = 0; pmc < MAX_IMC_TO_PROBE; pmc++) { + window = map_imc_window(mchbar, pmc); + if (!window) continue; - } rc = igen6_register_mci(lmc, window, pdev); if (rc) - goto out_iounmap; + goto err_unregister; /* Done, if all present MCs are detected and registered. */ if (++lmc >= res_cfg->num_imc) @@ -1728,10 +1793,8 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar) return 0; -out_iounmap: +err_unregister: iounmap(window); - -out_unregister_mcis: igen6_unregister_mcis(); return rc; diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 75c04dfc3962..9c0a1e48f96f 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -729,10 +729,8 @@ static int thunderx_lmc_probe(struct pci_dev *pdev, thunderx_lmc_err_isr, thunderx_lmc_threaded_isr, 0, "[EDAC] ThunderX LMC", mci); - if (ret) { - dev_err(&pdev->dev, "Cannot set ISR: %d\n", ret); + if (ret) goto err_free; - } lmc->node = FIELD_GET(THUNDERX_NODE, pci_resource_start(pdev, 0)); diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 9955396c9a52..62b8166dc287 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -1924,11 +1924,8 @@ static int xgene_edac_probe(struct platform_device *pdev) rc = devm_request_irq(&pdev->dev, irq, xgene_edac_isr, IRQF_SHARED, dev_name(&pdev->dev), edac); - if (rc) { - dev_err(&pdev->dev, - "Could not request IRQ %d\n", irq); + if (rc) goto out_err; - } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c index 724beb96ed1a..04fab30ab5dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c @@ -807,6 +807,153 @@ static uint32_t kgd_gfx_v11_hqd_sdma_get_doorbell(struct amdgpu_device *adev, return 0; } +static void lock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_lock(&adev->srbm_mutex); + mutex_lock(&adev->grbm_idx_mutex); + +} + +static void unlock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_unlock(&adev->grbm_idx_mutex); + mutex_unlock(&adev->srbm_mutex); +} + +/** + * get_wave_count: Read device registers to get number of waves in flight for + * a particular queue. The method also returns the doorbell offset associated + * with the queue. + * + * @adev: Handle of device whose registers are to be read + * @queue_idx: Index of queue in the queue-map bit-field + * @queue_cnt: Stores the wave count and doorbell offset for an active queue + * @inst: xcc's instance number on a multi-XCC setup + */ +static void get_wave_count(struct amdgpu_device *adev, int queue_idx, + struct kfd_cu_occupancy *queue_cnt, uint32_t inst) +{ + int pipe_idx; + int queue_slot; + unsigned int reg_val; + unsigned int wave_cnt; + /* + * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID + * parameters to read out waves in flight. Get doorbell offset if there are + * non-zero waves in flight. + */ + pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; + queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; + soc21_grbm_select(adev, 1, pipe_idx, queue_slot, 0); + reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, 0, + regSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot); + wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; + if (wave_cnt != 0) { + queue_cnt->wave_cnt += wave_cnt; + queue_cnt->doorbell_off = + (RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL) & + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK) >> + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT; + } +} + +/** + * kgd_gfx_v11_get_cu_occupancy: Reads relevant registers associated with each + * shader engine and aggregates the number of waves that are in flight for the + * process whose pasid is provided as a parameter. The process could have ZERO + * or more queues running and submitting waves to compute units. + * + * @adev: Handle of device from which to get number of waves in flight + * @cu_occupancy: Array that gets filled with wave_cnt and doorbell offset + * for comparison later. + * @max_waves_per_cu: Output parameter updated with maximum number of waves + * possible per Compute Unit + * @inst: xcc's instance number on a multi-XCC setup + * + * Note: It's possible that the device has too many queues (oversubscription) + * in which case a VMID could be remapped to a different PASID. This could lead + * to an inaccurate wave count. Following is a high-level sequence: + * Time T1: vmid = getVmid(); vmid is associated with Pasid P1 + * Time T2: passId = getPasId(vmid); vmid is associated with Pasid P2 + * In the sequence above wave count obtained from time T1 will be incorrectly + * lost or added to total wave count. + * + * The registers that provide the waves in flight are: + * + * SPI_CSQ_WF_ACTIVE_STATUS - bit-map of queues per pipe. The bit is ON if a + * queue is slotted, OFF if there is no queue. A process could have ZERO or + * more queues slotted and submitting waves to be run on compute units. Even + * when there is a queue it is possible there could be zero wave fronts, this + * can happen when queue is waiting on top-of-pipe events - e.g. waitRegMem + * command + * + * For each bit that is ON from above: + * + * Read (SPI_CSQ_WF_ACTIVE_COUNT_0 + queue_idx) register. It provides the + * number of waves that are in flight for the queue at specified index. The + * index ranges from 0 to 7. + * + * If non-zero waves are in flight, store the corresponding doorbell offset + * of the queue, along with the wave count. + * + * Determine if the queue belongs to the process by comparing the doorbell + * offset against the process's queues. If it matches, aggregate the wave + * count for the process. + * + * Reading registers referenced above involves programming GRBM appropriately + */ +static void kgd_gfx_v11_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst) +{ + int qidx; + int se_idx; + int se_cnt; + int queue_map; + int max_queue_cnt; + DECLARE_BITMAP(cp_queue_bitmap, AMDGPU_MAX_QUEUES); + + lock_spi_csq_mutexes(adev); + soc21_grbm_select(adev, 1, 0, 0, 0); + + /* + * Iterate through the shader engines and arrays of the device + * to get number of waves in flight + */ + bitmap_complement(cp_queue_bitmap, adev->gfx.mec_bitmap[0].queue_bitmap, + AMDGPU_MAX_QUEUES); + max_queue_cnt = adev->gfx.mec.num_pipe_per_mec * + adev->gfx.mec.num_queue_per_pipe; + se_cnt = adev->gfx.config.max_shader_engines; + for (se_idx = 0; se_idx < se_cnt; se_idx++) { + amdgpu_gfx_select_se_sh(adev, se_idx, 0, 0xffffffff, inst); + queue_map = RREG32_SOC15(GC, 0, + regSPI_CSQ_WF_ACTIVE_STATUS); + + for (qidx = 0; qidx < max_queue_cnt; qidx++) { + /* Skip queues that are not associated with + * compute functions + */ + if (!test_bit(qidx, cp_queue_bitmap)) + continue; + + if (!(queue_map & (1 << qidx))) + continue; + + /* Get number of waves in flight and aggregate them */ + get_wave_count(adev, qidx, &cu_occupancy[qidx], inst); + } + } + + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, inst); + soc21_grbm_select(adev, 0, 0, 0, 0); + unlock_spi_csq_mutexes(adev); + + /* Update the output parameters and return */ + *max_waves_per_cu = adev->gfx.cu_info.simd_per_cu * + adev->gfx.cu_info.max_waves_per_simd; +} + const struct kfd2kgd_calls gfx_v11_kfd2kgd = { .program_sh_mem_settings = program_sh_mem_settings_v11, .set_pasid_vmid_mapping = set_pasid_vmid_mapping_v11, @@ -832,5 +979,6 @@ const struct kfd2kgd_calls gfx_v11_kfd2kgd = { .clear_address_watch = kgd_gfx_v11_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v11_hqd_get_pq_addr, .hqd_reset = kgd_gfx_v11_hqd_reset, + .get_cu_occupancy = kgd_gfx_v11_get_cu_occupancy, .hqd_sdma_get_doorbell = kgd_gfx_v11_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c index e11ba3e91841..62b9db64368e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c @@ -368,6 +368,153 @@ static uint32_t kgd_gfx_v12_hqd_sdma_get_doorbell(struct amdgpu_device *adev, return 0; } +static void lock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_lock(&adev->srbm_mutex); + mutex_lock(&adev->grbm_idx_mutex); + +} + +static void unlock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_unlock(&adev->grbm_idx_mutex); + mutex_unlock(&adev->srbm_mutex); +} + +/** + * get_wave_count: Read device registers to get number of waves in flight for + * a particular queue. The method also returns the doorbell offset associated + * with the queue. + * + * @adev: Handle of device whose registers are to be read + * @queue_idx: Index of queue in the queue-map bit-field + * @queue_cnt: Stores the wave count and doorbell offset for an active queue + * @inst: xcc's instance number on a multi-XCC setup + */ +static void get_wave_count(struct amdgpu_device *adev, int queue_idx, + struct kfd_cu_occupancy *queue_cnt, uint32_t inst) +{ + int pipe_idx; + int queue_slot; + unsigned int reg_val; + unsigned int wave_cnt; + /* + * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID + * parameters to read out waves in flight. Get doorbell offset if there are + * non-zero waves in flight. + */ + pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; + queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; + soc24_grbm_select(adev, 1, pipe_idx, queue_slot, 0); + reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, 0, + regSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot); + wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; + if (wave_cnt != 0) { + queue_cnt->wave_cnt += wave_cnt; + queue_cnt->doorbell_off = + (RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL) & + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK) >> + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT; + } +} + +/** + * kgd_gfx_v12_get_cu_occupancy: Reads relevant registers associated with each + * shader engine and aggregates the number of waves that are in flight for the + * process whose pasid is provided as a parameter. The process could have ZERO + * or more queues running and submitting waves to compute units. + * + * @adev: Handle of device from which to get number of waves in flight + * @cu_occupancy: Array that gets filled with wave_cnt and doorbell offset + * for comparison later. + * @max_waves_per_cu: Output parameter updated with maximum number of waves + * possible per Compute Unit + * @inst: xcc's instance number on a multi-XCC setup + * + * Note: It's possible that the device has too many queues (oversubscription) + * in which case a VMID could be remapped to a different PASID. This could lead + * to an inaccurate wave count. Following is a high-level sequence: + * Time T1: vmid = getVmid(); vmid is associated with Pasid P1 + * Time T2: passId = getPasId(vmid); vmid is associated with Pasid P2 + * In the sequence above wave count obtained from time T1 will be incorrectly + * lost or added to total wave count. + * + * The registers that provide the waves in flight are: + * + * SPI_CSQ_WF_ACTIVE_STATUS - bit-map of queues per pipe. The bit is ON if a + * queue is slotted, OFF if there is no queue. A process could have ZERO or + * more queues slotted and submitting waves to be run on compute units. Even + * when there is a queue it is possible there could be zero wave fronts, this + * can happen when queue is waiting on top-of-pipe events - e.g. waitRegMem + * command + * + * For each bit that is ON from above: + * + * Read (SPI_CSQ_WF_ACTIVE_COUNT_0 + queue_idx) register. It provides the + * number of waves that are in flight for the queue at specified index. The + * index ranges from 0 to 7. + * + * If non-zero waves are in flight, store the corresponding doorbell offset + * of the queue, along with the wave count. + * + * Determine if the queue belongs to the process by comparing the doorbell + * offset against the process's queues. If it matches, aggregate the wave + * count for the process. + * + * Reading registers referenced above involves programming GRBM appropriately + */ +static void kgd_gfx_v12_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst) +{ + int qidx; + int se_idx; + int se_cnt; + int queue_map; + int max_queue_cnt; + DECLARE_BITMAP(cp_queue_bitmap, AMDGPU_MAX_QUEUES); + + lock_spi_csq_mutexes(adev); + soc24_grbm_select(adev, 1, 0, 0, 0); + + /* + * Iterate through the shader engines and arrays of the device + * to get number of waves in flight + */ + bitmap_complement(cp_queue_bitmap, adev->gfx.mec_bitmap[0].queue_bitmap, + AMDGPU_MAX_QUEUES); + max_queue_cnt = adev->gfx.mec.num_pipe_per_mec * + adev->gfx.mec.num_queue_per_pipe; + se_cnt = adev->gfx.config.max_shader_engines; + for (se_idx = 0; se_idx < se_cnt; se_idx++) { + amdgpu_gfx_select_se_sh(adev, se_idx, 0, 0xffffffff, inst); + queue_map = RREG32_SOC15(GC, 0, + regSPI_CSQ_WF_ACTIVE_STATUS); + + for (qidx = 0; qidx < max_queue_cnt; qidx++) { + /* Skip queues that are not associated with + * compute functions + */ + if (!test_bit(qidx, cp_queue_bitmap)) + continue; + + if (!(queue_map & (1 << qidx))) + continue; + + /* Get number of waves in flight and aggregate them */ + get_wave_count(adev, qidx, &cu_occupancy[qidx], inst); + } + } + + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, inst); + soc24_grbm_select(adev, 0, 0, 0, 0); + unlock_spi_csq_mutexes(adev); + + /* Update the output parameters and return */ + *max_waves_per_cu = adev->gfx.cu_info.simd_per_cu * + adev->gfx.cu_info.max_waves_per_simd; +} + const struct kfd2kgd_calls gfx_v12_kfd2kgd = { .init_interrupts = init_interrupts_v12, .hqd_dump = hqd_dump_v12, @@ -381,5 +528,6 @@ const struct kfd2kgd_calls gfx_v12_kfd2kgd = { .set_wave_launch_mode = kgd_gfx_v12_set_wave_launch_mode, .set_address_watch = kgd_gfx_v12_set_address_watch, .clear_address_watch = kgd_gfx_v12_clear_address_watch, - .hqd_sdma_get_doorbell = kgd_gfx_v12_hqd_sdma_get_doorbell + .hqd_sdma_get_doorbell = kgd_gfx_v12_hqd_sdma_get_doorbell, + .get_cu_occupancy = kgd_gfx_v12_get_cu_occupancy, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12_1.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12_1.c index 38ca1aea33b2..070001fd34b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12_1.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12_1.c @@ -371,6 +371,153 @@ static uint32_t kgd_gfx_v12_1_hqd_sdma_get_doorbell(struct amdgpu_device *adev, return 0; } +static void lock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_lock(&adev->srbm_mutex); + mutex_lock(&adev->grbm_idx_mutex); + +} + +static void unlock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_unlock(&adev->grbm_idx_mutex); + mutex_unlock(&adev->srbm_mutex); +} + +/** + * get_wave_count: Read device registers to get number of waves in flight for + * a particular queue. The method also returns the doorbell offset associated + * with the queue. + * + * @adev: Handle of device whose registers are to be read + * @queue_idx: Index of queue in the queue-map bit-field + * @queue_cnt: Stores the wave count and doorbell offset for an active queue + * @inst: xcc's instance number on a multi-XCC setup + */ +static void get_wave_count(struct amdgpu_device *adev, int queue_idx, + struct kfd_cu_occupancy *queue_cnt, uint32_t inst) +{ + int pipe_idx; + int queue_slot; + unsigned int reg_val; + unsigned int wave_cnt; + /* + * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID + * parameters to read out waves in flight. Get doorbell offset if there are + * non-zero waves in flight. + */ + pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; + queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; + amdgpu_gfx_select_me_pipe_q(adev, 1, pipe_idx, queue_slot, 0, inst); + reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, GET_INST(GC, inst), + regSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot); + wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; + if (wave_cnt != 0) { + queue_cnt->wave_cnt += wave_cnt; + queue_cnt->doorbell_off = + (RREG32_SOC15(GC, GET_INST(GC, inst), regCP_HQD_PQ_DOORBELL_CONTROL) & + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK) >> + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT; + } +} + +/** + * kgd_gfx_v12_1_get_cu_occupancy: Reads relevant registers associated with + * each shader engine and aggregates the number of waves that are in flight + * for the process whose pasid is provided as a parameter. The process could + * have ZERO or more queues running and submitting waves to compute units. + * + * @adev: Handle of device from which to get number of waves in flight + * @cu_occupancy: Array that gets filled with wave_cnt and doorbell offset + * for comparison later. + * @max_waves_per_cu: Output parameter updated with maximum number of waves + * possible per Compute Unit + * @inst: xcc's instance number on a multi-XCC setup + * + * Note: It's possible that the device has too many queues (oversubscription) + * in which case a VMID could be remapped to a different PASID. This could lead + * to an inaccurate wave count. Following is a high-level sequence: + * Time T1: vmid = getVmid(); vmid is associated with Pasid P1 + * Time T2: passId = getPasId(vmid); vmid is associated with Pasid P2 + * In the sequence above wave count obtained from time T1 will be incorrectly + * lost or added to total wave count. + * + * The registers that provide the waves in flight are: + * + * SPI_CSQ_WF_ACTIVE_STATUS - bit-map of queues per pipe. The bit is ON if a + * queue is slotted, OFF if there is no queue. A process could have ZERO or + * more queues slotted and submitting waves to be run on compute units. Even + * when there is a queue it is possible there could be zero wave fronts, this + * can happen when queue is waiting on top-of-pipe events - e.g. waitRegMem + * command + * + * For each bit that is ON from above: + * + * Read (SPI_CSQ_WF_ACTIVE_COUNT_0 + queue_idx) register. It provides the + * number of waves that are in flight for the queue at specified index. The + * index ranges from 0 to 7. + * + * If non-zero waves are in flight, store the corresponding doorbell offset + * of the queue, along with the wave count. + * + * Determine if the queue belongs to the process by comparing the doorbell + * offset against the process's queues. If it matches, aggregate the wave + * count for the process. + * + * Reading registers referenced above involves programming GRBM appropriately + */ +static void kgd_gfx_v12_1_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst) +{ + int qidx; + int se_idx; + int se_cnt; + int queue_map; + int max_queue_cnt; + DECLARE_BITMAP(cp_queue_bitmap, AMDGPU_MAX_QUEUES); + + lock_spi_csq_mutexes(adev); + amdgpu_gfx_select_me_pipe_q(adev, 1, 0, 0, 0, inst); + + /* + * Iterate through the shader engines and arrays of the device + * to get number of waves in flight + */ + bitmap_complement(cp_queue_bitmap, adev->gfx.mec_bitmap[0].queue_bitmap, + AMDGPU_MAX_QUEUES); + max_queue_cnt = adev->gfx.mec.num_pipe_per_mec * + adev->gfx.mec.num_queue_per_pipe; + se_cnt = adev->gfx.config.max_shader_engines; + for (se_idx = 0; se_idx < se_cnt; se_idx++) { + amdgpu_gfx_select_se_sh(adev, se_idx, 0, 0xffffffff, inst); + queue_map = RREG32_SOC15(GC, GET_INST(GC, inst), + regSPI_CSQ_WF_ACTIVE_STATUS); + + for (qidx = 0; qidx < max_queue_cnt; qidx++) { + /* Skip queues that are not associated with + * compute functions + */ + if (!test_bit(qidx, cp_queue_bitmap)) + continue; + + if (!(queue_map & (1 << qidx))) + continue; + + /* Get number of waves in flight and aggregate them */ + get_wave_count(adev, qidx, &cu_occupancy[qidx], inst); + } + } + + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, inst); + amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0, inst); + unlock_spi_csq_mutexes(adev); + + /* Update the output parameters and return */ + *max_waves_per_cu = adev->gfx.cu_info.simd_per_cu * + adev->gfx.cu_info.max_waves_per_simd; +} + const struct kfd2kgd_calls gfx_v12_1_kfd2kgd = { .init_interrupts = init_interrupts_v12_1, .hqd_dump = hqd_dump_v12_1, @@ -384,5 +531,6 @@ const struct kfd2kgd_calls gfx_v12_1_kfd2kgd = { .set_wave_launch_mode = kgd_gfx_v12_1_set_wave_launch_mode, .set_address_watch = kgd_gfx_v12_1_set_address_watch, .clear_address_watch = kgd_gfx_v12_1_clear_address_watch, - .hqd_sdma_get_doorbell = kgd_gfx_v12_1_hqd_sdma_get_doorbell + .hqd_sdma_get_doorbell = kgd_gfx_v12_1_hqd_sdma_get_doorbell, + .get_cu_occupancy = kgd_gfx_v12_1_get_cu_occupancy }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 34481ee7065a..d66881684ee5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1795,6 +1795,12 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( size >>= 1; aligned_size = PAGE_ALIGN(size); + /* reject AQL queue with size < 2 */ + if (!aligned_size) { + ret = -EINVAL; + goto err_alignment_size; + } + (*mem)->alloc_flags = flags; amdgpu_sync_create(&(*mem)->sync); @@ -1886,6 +1892,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags, xcp_id); err_reserve_limit: amdgpu_sync_free(&(*mem)->sync); +err_alignment_size: mutex_destroy(&(*mem)->lock); if (gobj) drm_gem_object_put(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 53539ceeda16..44bed0ba64a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -609,6 +609,13 @@ void amdgpu_device_detect_runtime_pm_mode(struct amdgpu_device *adev) int bamaco_support; adev->pm.rpm_mode = AMDGPU_RUNPM_NONE; + if (pci_is_thunderbolt_attached(adev->pdev) || + dev_is_removable(&adev->pdev->dev)) { + dev_info(adev->dev, + "Runtime PM disabled for externally attached device\n"); + return; + } + bamaco_support = amdgpu_device_supports_baco(adev); switch (amdgpu_runtime_pm) { @@ -2523,7 +2530,11 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (r) goto init_failed; - amdgpu_ttm_enable_buffer_funcs(adev); + /* If SDMA is not brought up during hwini, the ttm buffer funcs enablement + * is delayed after reset-on-init completes. + */ + if (amdgpu_ip_member_of_hwini(adev, AMD_IP_BLOCK_TYPE_SDMA)) + amdgpu_ttm_enable_buffer_funcs(adev); /* Don't init kfd if whole hive need to be reset during init */ if (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) { @@ -3733,6 +3744,14 @@ static void amdgpu_device_sys_interface_fini(struct amdgpu_device *adev) amdgpu_ptl_sysfs_fini(adev); } +static bool +amdgpu_device_should_register_switcheroo(struct amdgpu_device *adev, bool px) +{ + return !pci_is_thunderbolt_attached(adev->pdev) && + (px || (!dev_is_removable(&adev->pdev->dev) && + apple_gmux_detect(NULL, NULL))); +} + /** * amdgpu_device_init - initialize the driver * @@ -4183,8 +4202,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, px = amdgpu_device_supports_px(adev); - if (px || (!dev_is_removable(&adev->pdev->dev) && - apple_gmux_detect(NULL, NULL))) + if (amdgpu_device_should_register_switcheroo(adev, px)) vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, px); @@ -4349,8 +4367,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) px = amdgpu_device_supports_px(adev); - if (px || (!dev_is_removable(&adev->pdev->dev) && - apple_gmux_detect(NULL, NULL))) + if (amdgpu_device_should_register_switcheroo(adev, px)) vga_switcheroo_unregister_client(adev->pdev); if (px) @@ -5037,6 +5054,31 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, amdgpu_fence_driver_force_completion(ring, fence); } + /* + * MES scheduler rings have no drm scheduler, so they are missed by the + * loop above. Realign their polling fence too (one per XCC), otherwise the + * first post-reset submission polls forever on a stale seq. sched.ready is + * only set while the driver owns the ring. + */ + for (i = 0; i < AMDGPU_MAX_MES_INST_PIPES; i++) { + struct amdgpu_ring *mes_ring = &adev->mes.ring[i]; + + if (mes_ring->fence_drv.initialized && mes_ring->sched.ready) + amdgpu_fence_driver_force_completion(mes_ring, fence); + } + + /* + * KIQ rings are polling-fence/no_scheduler like MES, so realign their + * fence too (one ring per XCC), otherwise the first post-reset KIQ + * submission polls forever on a stale seq. + */ + for (i = 0; i < AMDGPU_MAX_GC_INSTANCES; i++) { + struct amdgpu_ring *kiq_ring = &adev->gfx.kiq[i].ring; + + if (kiq_ring->fence_drv.initialized && kiq_ring->sched.ready) + amdgpu_fence_driver_force_completion(kiq_ring, fence); + } + amdgpu_fence_driver_isr_toggle(adev, false); r = amdgpu_reset_prepare_hwcontext(adev, reset_context); @@ -5137,8 +5179,6 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context) if (r) goto out; - amdgpu_ttm_enable_buffer_funcs(tmp_adev); - r = amdgpu_device_ip_resume_phase3(tmp_adev); if (r) goto out; @@ -6647,8 +6687,8 @@ struct dma_fence *amdgpu_device_enforce_isolation(struct amdgpu_device *adev, struct amdgpu_ring *ring, struct amdgpu_job *job) { - struct amdgpu_isolation *isolation = &adev->isolation[ring->xcp_id]; struct drm_sched_fence *f = job->base.s_fence; + struct amdgpu_isolation *isolation; struct dma_fence *dep; void *owner; int r; @@ -6661,6 +6701,9 @@ struct dma_fence *amdgpu_device_enforce_isolation(struct amdgpu_device *adev, ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE) return NULL; + isolation = &adev->isolation[ring->xcp_id == AMDGPU_XCP_NO_PARTITION ? + 0 : ring->xcp_id]; + /* * All submissions where enforce isolation is false are handled as if * they come from a single client. Use ~0l as the owner to distinct it diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index a404d8aa13ee..164e85b66e2d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1307,8 +1307,19 @@ static int amdgpu_discovery_sysfs_ips(struct amdgpu_device *adev, ip_hw_instance->num_instance); ip_hw_instance->num_base_addresses = ip->num_base_address; - for (kk = 0; kk < ip_hw_instance->num_base_addresses; kk++) - ip_hw_instance->base_addr[kk] = ip->base_address[kk]; + for (kk = 0; kk < ip_hw_instance->num_base_addresses; kk++) { + /* + * Standalone mode uses a raw copy of the discovery + * binary; decode 64-bit addresses here. The shared + * bin is already collapsed to 32-bit in place. + */ + if (reg_base_64 && ip_top->standalone_mode) + ip_hw_instance->base_addr[kk] = + lower_32_bits(le64_to_cpu(ip->base_address_64[kk])) & 0x3FFFFFFF; + else + ip_hw_instance->base_addr[kk] = + le32_to_cpu(ip->base_address[kk]); + } kobject_init(&ip_hw_instance->kobj, &ip_hw_instance_ktype); ip_hw_instance->kobj.kset = &ip_hw_id->hw_id_kset; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 0ab380ca7e64..5c33c19fd9bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2557,6 +2557,7 @@ amdgpu_pci_remove(struct pci_dev *pdev) if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) { pm_runtime_get_sync(dev->dev); pm_runtime_forbid(dev->dev); + pm_runtime_dont_use_autosuspend(dev->dev); } amdgpu_driver_unload_kms(dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index da4dc489e80b..360e6f00cb7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -222,7 +222,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, vm_af = job->hw_vm_fence; /* VM sequence */ vm_af->ib_wptr = ring->wptr; - amdgpu_vm_flush(ring, job, need_pipe_sync, &emit_spm_needed, + amdgpu_vm_flush(ring, job, &need_pipe_sync, &emit_spm_needed, &emit_gds_needed); vm_af->ib_dw_size = amdgpu_ring_get_dw_distance(ring, vm_af->ib_wptr, ring->wptr); @@ -235,6 +235,10 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, if (ring->funcs->insert_start) ring->funcs->insert_start(ring); + /* this may have been handled by amdgpu_vm_flush */ + if (need_pipe_sync) + amdgpu_ring_emit_pipeline_sync(ring); + if (emit_spm_needed) adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, ring, job->vmid); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index bcfbd7213dd6..0a816b3c5ff9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -287,22 +287,24 @@ static bool amdgpu_userq_buffer_va_mapped(struct amdgpu_vm *vm, u64 addr) static bool amdgpu_userq_buffer_vas_mapped(struct amdgpu_usermode_queue *queue) { - int i, r = 0; + int i; + bool mapped; for (i = 0; i < ARRAY_SIZE(queue->userq_vas.va_array); i++) { if (!queue->userq_vas.va_array[i]) continue; - r += amdgpu_userq_buffer_va_mapped(queue->vm, + + mapped = amdgpu_userq_buffer_va_mapped(queue->vm, queue->userq_vas.va_array[i]); dev_dbg(queue->userq_mgr->adev->dev, "validate the userq mapping:%p va:%llx r:%d\n", - queue, queue->userq_vas.va_array[i], r); + queue, queue->userq_vas.va_array[i], mapped); + + if (!mapped) + return false; } - if (r != 0) - return true; - - return false; + return true; } @@ -416,19 +418,12 @@ static void amdgpu_userq_wait_for_last_fence(struct amdgpu_usermode_queue *queue dma_fence_wait(f, false); } -static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue) +static void amdgpu_userq_detach_doorbell(struct amdgpu_usermode_queue *queue) { - struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr; - struct amdgpu_device *adev = uq_mgr->adev; + struct amdgpu_device *adev = queue->userq_mgr->adev; - /* Wait for mode-1 reset to complete */ down_read(&adev->reset_domain->sem); - - /* Use interrupt-safe locking since IRQ handlers may access these XArrays */ xa_erase_irq(&adev->userq_doorbell_xa, queue->doorbell_index); - amdgpu_userq_fence_driver_free(queue); - queue->fence_drv = NULL; - up_read(&adev->reset_domain->sem); } @@ -549,18 +544,19 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que cancel_delayed_work_sync(&uq_mgr->resume_work); - /* Cancel any pending hang detection work and cleanup */ - cancel_delayed_work_sync(&queue->hang_detect_work); - mutex_lock(&uq_mgr->userq_mutex); amdgpu_userq_wait_for_last_fence(queue); + amdgpu_userq_detach_doorbell(queue); + cancel_delayed_work_sync(&queue->hang_detect_work); + #if defined(CONFIG_DEBUG_FS) debugfs_remove_recursive(queue->debugfs_queue); #endif r = amdgpu_userq_unmap_helper(queue); atomic_dec(&uq_mgr->userq_count[queue->queue_type]); - amdgpu_userq_cleanup(queue); + amdgpu_userq_fence_driver_free(queue); + queue->fence_drv = NULL; mutex_unlock(&uq_mgr->userq_mutex); /* @@ -572,7 +568,6 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que if (r) queue_work(adev->reset_domain->wq, &uq_mgr->reset_work); - cancel_delayed_work_sync(&queue->hang_detect_work); uq_funcs->mqd_destroy(queue); queue->userq_mgr = NULL; @@ -700,10 +695,10 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) args->in.queue_size, &queue->userq_vas.va.queue_rb) || amdgpu_userq_input_va_validate(adev, queue, args->in.rptr_va, - AMDGPU_GPU_PAGE_SIZE, + sizeof(u64), &queue->userq_vas.va.rptr) || amdgpu_userq_input_va_validate(adev, queue, args->in.wptr_va, - AMDGPU_GPU_PAGE_SIZE, + sizeof(u64), &queue->userq_vas.va.wptr)) { r = -EINVAL; amdgpu_bo_unreserve(fpriv->vm.root.bo); @@ -746,7 +741,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) ((queue->queue_type != AMDGPU_HW_IP_GFX) && (queue->queue_type != AMDGPU_HW_IP_COMPUTE))) { /* Serialize the map against an in-progress GPU reset (MES is - * unresponsive during recovery), matching amdgpu_userq_cleanup(). + * unresponsive during recovery), matching amdgpu_userq_detach_doorbell(). */ down_read(&adev->reset_domain->sem); r = amdgpu_userq_map_helper(queue); @@ -848,6 +843,12 @@ static int amdgpu_userq_input_args_validate(struct drm_device *dev, drm_file_err(filp, "invalidate userq queue rptr or wptr\n"); return -EINVAL; } + + if (!IS_ALIGNED(args->in.wptr_va, sizeof(u64)) || + !IS_ALIGNED(args->in.rptr_va, sizeof(u64))) { + drm_file_err(filp, "user queue rptr or wptr is not 8-byte aligned\n"); + return -EINVAL; + } break; case AMDGPU_USERQ_OP_FREE: if (args->in.ip_type || @@ -1046,6 +1047,30 @@ amdgpu_userq_vm_validate_and_restore_queue(struct amdgpu_userq_mgr *uq_mgr) drm_exec_retry_on_contention(&exec); if (unlikely(ret)) goto unlock_all; + + /* + * WPTR BOs are VM-mapped, but each BO has its own reservation + * object. Lock them into this drm_exec ww context so the later + * amdgpu_bo_gpu_offset() reads are done with the BO resv locked. + */ + xa_for_each(&uq_mgr->userq_xa, tmp_key, queue) { + struct ttm_operation_ctx wptr_ctx = { false, false }; + + bo = queue->wptr_obj.obj; + if (!bo) + continue; + + ret = drm_exec_prepare_obj(&exec, &bo->tbo.base, + TTM_NUM_MOVE_FENCES + 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto unlock_all; + + amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); + ret = ttm_bo_validate(&bo->tbo, &bo->placement, &wptr_ctx); + if (unlikely(ret)) + goto unlock_all; + } } if (invalidated) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index 7e80442ec3e5..4b023e024d9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -191,14 +191,15 @@ void amdgpu_userq_fence_driver_destroy(struct kref *ref) struct dma_fence *f; spin_lock_irqsave(&fence_drv->fence_list_lock, flags); + lockdep_assert_held(&fence_drv->fence_list_lock); list_for_each_entry_safe(fence, tmp, &fence_drv->fences, link) { f = &fence->base; - - if (!dma_fence_is_signaled(f)) { + spin_lock(dma_fence_spinlock(f)); + if (!dma_fence_is_signaled_locked(f)) { dma_fence_set_error(f, -ECANCELED); - dma_fence_signal(f); + dma_fence_signal_locked(f); } - + spin_unlock(dma_fence_spinlock(f)); list_del(&fence->link); dma_fence_put(f); } @@ -423,11 +424,16 @@ amdgpu_userq_fence_driver_set_error(struct amdgpu_userq_fence *fence, struct dma_fence *f; spin_lock_irqsave(&fence_drv->fence_list_lock, flags); - + lockdep_assert_held(&fence_drv->fence_list_lock); f = rcu_dereference_protected(&fence->base, lockdep_is_held(&fence_drv->fence_list_lock)); - if (f && !dma_fence_is_signaled_locked(f)) - dma_fence_set_error(f, error); + if (f) { + /* nest f->lock inside fence_list_lock */ + spin_lock(dma_fence_spinlock(f)); + if (!dma_fence_is_signaled_locked(f)) + dma_fence_set_error(f, error); + spin_unlock(dma_fence_spinlock(f)); + } spin_unlock_irqrestore(&fence_drv->fence_list_lock, flags); } @@ -537,7 +543,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, * amdgpu_userq_ensure_ev_fence() can't be called while holding the resv * locks. */ - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES, (num_read_bo_handles + num_write_bo_handles)); drm_exec_until_all_locked(&exec) { @@ -643,7 +649,7 @@ amdgpu_userq_wait_count_fences(struct drm_file *filp, /* TODO: It is actually not necessary to lock them */ num_read_bo_handles = wait_info->num_bo_read_handles; num_write_bo_handles = wait_info->num_bo_write_handles; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES, num_read_bo_handles + num_write_bo_handles); drm_exec_until_all_locked(&exec) { @@ -778,7 +784,7 @@ amdgpu_userq_wait_return_fence_info(struct drm_device *dev, struct drm_file *fil /* Lock all the GEM objects */ num_read_bo_handles = wait_info->num_bo_read_handles; num_write_bo_handles = wait_info->num_bo_write_handles; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES, num_read_bo_handles + num_write_bo_handles); drm_exec_until_all_locked(&exec) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 228a405a94c4..ecd7caa95d4b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -517,7 +517,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev) } memset_io(ptr, 0, size); /* to restore uvd fence seq */ - amdgpu_fence_driver_force_completion(&adev->uvd.inst[i].ring, NULL); + if (adev->uvd.inst[i].ring.fence_drv.initialized) + amdgpu_fence_driver_force_completion(&adev->uvd.inst[i].ring, NULL); } } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index d2ad5b0e8759..aedf72c2333e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -772,11 +772,13 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, * Emit a VM flush when it is necessary. */ void amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, - bool need_pipe_sync, bool *emit_spm_needed, + bool *need_pipe_sync, bool *emit_spm_needed, bool *emit_gds_needed) { struct amdgpu_device *adev = ring->adev; - struct amdgpu_isolation *isolation = &adev->isolation[ring->xcp_id]; + struct amdgpu_isolation *isolation = + &adev->isolation[ring->xcp_id == AMDGPU_XCP_NO_PARTITION ? + 0 : ring->xcp_id]; unsigned vmhub = ring->vm_hub; struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; struct amdgpu_vmid *id = &id_mgr->ids[job->vmid]; @@ -827,8 +829,7 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (gds_switch_needed && emit_fence) *emit_gds_needed = false; - if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync && - !cleaner_shader_needed && !spm_update_needed) + if (!emit_fence) return; amdgpu_ring_ib_begin(ring); @@ -847,8 +848,10 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, patch = amdgpu_ring_init_cond_exec(ring, ring->cond_exe_gpu_addr); - if (need_pipe_sync) + if (*need_pipe_sync) { amdgpu_ring_emit_pipeline_sync(ring); + *need_pipe_sync = false; + } if (cleaner_shader_needed) ring->funcs->emit_cleaner_shader(ring); @@ -861,21 +864,19 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (pasid_mapping_needed) amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid); - if (emit_fence) { - if (spm_update_needed) - adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, ring, job->vmid); + if (spm_update_needed) + adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, ring, job->vmid); - if (gds_switch_needed) - amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base, + if (gds_switch_needed) + amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base, job->gds_size, job->gws_base, job->gws_size, job->oa_base, job->oa_size); - amdgpu_fence_emit(ring, job->hw_vm_fence, 0); - fence = &job->hw_vm_fence->base; - /* get a ref for the job */ - dma_fence_get(fence); - } + amdgpu_fence_emit(ring, job->hw_vm_fence, 0); + fence = &job->hw_vm_fence->base; + /* get a ref for the job */ + dma_fence_get(fence); if (vm_flush_needed) { mutex_lock(&id_mgr->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 7f2ba728e3ed..d32183cd9e0f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -512,7 +512,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, int (*callback)(void *p, struct amdgpu_bo *bo), void *param); void amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, - bool need_pipe_sync, bool *emit_spm_needed, + bool *need_pipe_sync, bool *emit_spm_needed, bool *emit_gds_needed); int amdgpu_vm_update_pdes(struct amdgpu_device *adev, struct amdgpu_vm *vm, bool immediate); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 2725230aa5e3..45e31b3daf06 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -1380,6 +1380,9 @@ static void amdgpu_xgmi_reset_on_init_work(struct work_struct *work) amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain); list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { + /* Enable ttm buffers funcs after the reset lock has been dropped. */ + amdgpu_ttm_enable_buffer_funcs(tmp_adev); + r = amdgpu_ras_init_badpage_info(tmp_adev); if (r && r != -EHWPOISON) dev_err(tmp_adev->dev, diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index fae709f134bb..14a5abe42d1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -146,7 +146,7 @@ static int mes_userq_map(struct amdgpu_usermode_queue *queue) queue_input.wptr_mc_addr = queue->wptr_obj.gpu_addr; if (mes->use_rs64mem) { - if (!uq_mgr->proc_ctx_allocated) { + if (!uq_mgr->proc_ctx_allocated) { r = amdgpu_mes_alloc_proc_ctx_index(mes, &uq_mgr->proc_ctx_array_index); if (r) { DRM_ERROR("Failed to allocate userq process index err:%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index a9497e2e07f7..4dbbeaf97ad1 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -891,7 +891,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_phys_funcs = { static const struct amdgpu_ring_funcs vce_v3_0_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCE, - .align_mask = 0xf, + .align_mask = 0x1f, .nop = VCE_CMD_NO_OP, .support_64bit_ptrs = false, .no_user_fence = true, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 81bba3ec2a93..00d8f35846f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1964,9 +1964,13 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, len_dw = msg[1] / 4; num_buffers = msg[2]; - /* Verify that all indices fit within the claimed length. Each index is 4 DWORDs */ - if (num_buffers > len_dw || 6 + num_buffers * 4 > len_dw) { - DRM_ERROR("VCN message has too many buffers!\n"); + /* Verify that all indices fit within the claimed length. + * There are 6 dwords in the header before the first buffer. + * Each buffer has 4 dwords. Any trailing dwords after the + * last buffer are ignored. + */ + if (len_dw < 6 || num_buffers > (len_dw - 6) / 4) { + DRM_ERROR("Invalid VCN message!\n"); r = -EINVAL; goto out; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 0cce78b205a8..c2ddf3cb368f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1880,9 +1880,13 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, len_dw = msg[1] / 4; num_buffers = msg[2]; - /* Verify that all indices fit within the claimed length. Each index is 4 DWORDs */ - if (num_buffers > len_dw || 6 + num_buffers * 4 > len_dw) { - DRM_ERROR("VCN message has too many buffers!\n"); + /* Verify that all indices fit within the claimed length. + * There are 6 dwords in the header before the first buffer. + * Each buffer has 4 dwords. Any trailing dwords after the + * last buffer are ignored. + */ + if (len_dw < 6 || num_buffers > (len_dw - 6) / 4) { + DRM_ERROR("Invalid VCN message!\n"); r = -EINVAL; goto out; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 309510e23315..7fcfc150a7fc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1200,7 +1200,8 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, if (flags & KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM) size >>= 1; - atomic64_add(PAGE_ALIGN(size), &pdd->vram_usage); + size = PAGE_ALIGN(size); + atomic64_add(size, &pdd->vram_usage); } mutex_unlock(&p->mutex); @@ -3329,7 +3330,7 @@ static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, v return 0; } -static inline uint32_t profile_lock_device(struct kfd_process *p, +static inline int profile_lock_device(struct kfd_process *p, uint32_t gpu_id, uint32_t op) { struct kfd_process_device *pdd; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index a23384571193..4bc947c3bd0d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -769,6 +769,11 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; + if (qd && !mqd_mgr->restore_mqd) { + pr_debug("restore_mqd not implemented for this GPU\n"); + retval = -EOPNOTSUPP; + goto deallocate_vmid; + } if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) { retval = allocate_hqd(dqm, q); if (retval) @@ -2236,6 +2241,11 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; + if (qd && !mqd_mgr->restore_mqd) { + pr_debug("restore_mqd not implemented for this GPU\n"); + retval = -EOPNOTSUPP; + goto out_deallocate_doorbell; + } if (q->properties.type == KFD_QUEUE_TYPE_SDMA || q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index f5af1dd3b70e..253365a8257e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -134,7 +134,7 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys, u64 gart_s, gart_d; struct dma_fence *next; u64 size; - int r; + int r = 0; ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]); entity = &adev->mman.move_entities[0]; @@ -258,15 +258,6 @@ svm_migrate_get_sys_page(struct vm_area_struct *vma, unsigned long addr) return page; } -static void svm_migrate_put_sys_page(unsigned long addr) -{ - struct page *page; - - page = pfn_to_page(addr >> PAGE_SHIFT); - unlock_page(page); - put_page(page); -} - static unsigned long svm_migrate_successful_pages(struct migrate_vma *migrate) { unsigned long mpages = 0; @@ -293,7 +284,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, dma_addr_t *src; u64 *dst; u64 i, j; - int r; + int r = 0; pr_debug("svms 0x%p [0x%lx 0x%lx 0x%llx]\n", prange->svms, prange->start, prange->last, ttm_res_offset); @@ -319,6 +310,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, DMA_BIDIRECTIONAL); r = dma_mapping_error(dev, src[i]); if (r) { + src[i] = 0; dev_err(dev, "%s: fail %d dma_map_page\n", __func__, r); goto out_free_vram_pages; @@ -343,7 +335,8 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, pr_debug_ratelimited("dma mapping src to 0x%llx, pfn 0x%lx\n", src[i] >> PAGE_SHIFT, page_to_pfn(spage)); - if (j >= (cursor.size >> PAGE_SHIFT) - 1 && i < npages - 1) { + /* accumulated j + 1 pages reach end of current drm_buddy_block */ + if (j + 1 >= (cursor.size >> PAGE_SHIFT)) { r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j + 1, FROM_RAM_TO_VRAM, @@ -357,7 +350,8 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, } } - r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j, + if (j > 0) + r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j, FROM_RAM_TO_VRAM, mfence); out_free_vram_pages: @@ -591,9 +585,10 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, dma_addr_t *scratch, u64 npages) { struct device *dev = adev->dev; - u64 *src; + struct page *dpage = NULL; dma_addr_t *dst; - struct page *dpage; + u64 *src; + u64 i = 0, j; u64 addr; int r = 0; @@ -647,6 +642,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, r = dma_mapping_error(dev, dst[i]); if (r) { dev_err(adev->dev, "%s: fail %d dma_map_page\n", __func__, r); + dst[i] = 0; goto out_oom; } @@ -654,17 +650,39 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, dst[i] >> PAGE_SHIFT, page_to_pfn(dpage)); migrate->dst[i] = migrate_pfn(page_to_pfn(dpage)); + + dpage = NULL; j++; } - r = svm_migrate_copy_memory_gart(adev, dst + i - j, src + i - j, j, - FROM_VRAM_TO_RAM, mfence); - + if (j > 0) + r = svm_migrate_copy_memory_gart(adev, dst + i - j, src + i - j, j, + FROM_VRAM_TO_RAM, mfence); out_oom: if (r) { pr_debug("failed %d copy to ram\n", r); + + /* first release current dpage when dma_map_page fail */ + if (dpage) { + unlock_page(dpage); + put_page(dpage); + } + + /* release previous allocated sys pages and unmap dma address */ while (i--) { - svm_migrate_put_sys_page(dst[i]); + + if (dst[i]) { + dma_unmap_page(dev, dst[i], PAGE_SIZE, + DMA_BIDIRECTIONAL); + dst[i] = 0; + } + + dpage = migrate_pfn_to_page(migrate->dst[i]); + if (!dpage) + continue; + + unlock_page(dpage); + put_page(dpage); migrate->dst[i] = 0; } } 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 284aac4d96bc..ec483276d753 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1589,6 +1589,9 @@ static int dm_suspend(struct amdgpu_ip_block *ip_block) res = amdgpu_dm_commit_zero_streams(dm->dc); if (res != DC_OK) { drm_err(adev_to_drm(adev), "Failed to commit zero streams: %d\n", res); + dc_state_release(dm->cached_dc_state); + dm->cached_dc_state = NULL; + mutex_unlock(&dm->dc_lock); return -EINVAL; } @@ -1884,6 +1887,9 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) r = dm_dmub_hw_init(adev); if (r) { drm_err(adev_to_drm(adev), "DMUB interface failed to initialize: status=%d\n", r); + dc_state_release(dm->cached_dc_state); + dm->cached_dc_state = NULL; + mutex_unlock(&dm->dc_lock); return r; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c index b66ca60e697d..e61bbc310f33 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c @@ -106,10 +106,10 @@ int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, } EXPORT_IF_KUNIT(get_brightness_range); -/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */ -static inline u32 scale_input_to_fw(int min, int max, u64 input) +/* Rescale userspace [0..max] to the firmware curve's [0..255]. */ +static inline u32 scale_input_to_fw(int max, u64 input) { - return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min); + return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max); } /* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */ @@ -123,7 +123,7 @@ void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps, unsigned int min, unsigned int max, uint32_t *user_brightness) { - u32 brightness = scale_input_to_fw(min, max, *user_brightness); + u32 brightness = scale_input_to_fw(max, *user_brightness); u8 lower_signal, upper_signal, upper_lum, lower_lum, lum; int left, right; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index 7b68c6846039..d55dc06167a8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -471,6 +471,12 @@ bool __is_lut_linear(const struct drm_color_lut *lut, uint32_t size) uint32_t expected; int delta; + /* A LUT with fewer than two entries can't be interpolated and would + * divide by zero below (size - 1); it can't be treated as linear. + */ + if (size < 2) + return false; + for (i = 0; i < size; i++) { /* All color values should equal */ if ((lut[i].red != lut[i].green) || (lut[i].green != lut[i].blue)) @@ -1489,6 +1495,13 @@ __set_dm_plane_degamma(struct drm_plane_state *plane_state, degamma_lut = __extract_blob_lut(dm_plane_state->degamma_lut, °amma_size); + if (degamma_lut && degamma_size != MAX_COLOR_LUT_ENTRIES) { + drm_dbg(plane_state->state->dev, + "Invalid Plane Degamma LUT size. Should be %u but got %u.\n", + MAX_COLOR_LUT_ENTRIES, degamma_size); + return -EINVAL; + } + has_degamma_lut = degamma_lut && !__is_lut_linear(degamma_lut, degamma_size); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 9be63996b062..d0239a3de2e1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -1735,7 +1735,9 @@ int amdgpu_dm_register_hpd_handlers(struct amdgpu_device *adev) if (int_params.irq_source == DC_IRQ_SOURCE_INVALID || int_params.irq_source < DC_IRQ_SOURCE_HPD1 || int_params.irq_source > DC_IRQ_SOURCE_HPD6) { - drm_err(adev_to_drm(adev), "Failed to register hpd irq!\n"); + drm_err(adev_to_drm(adev), + "Failed to register hpd irq %u for %s!\n", + int_params.irq_source, connector->name); return -EINVAL; } @@ -1753,7 +1755,9 @@ int amdgpu_dm_register_hpd_handlers(struct amdgpu_device *adev) if (int_params.irq_source == DC_IRQ_SOURCE_INVALID || int_params.irq_source < DC_IRQ_SOURCE_HPD1RX || int_params.irq_source > DC_IRQ_SOURCE_HPD6RX) { - drm_err(adev_to_drm(adev), "Failed to register hpd rx irq!\n"); + drm_err(adev_to_drm(adev), + "Failed to register hpd rx irq %u for %s!\n", + int_params.irq_source, connector->name); return -EINVAL; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_calcs_dchub.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_calcs_dchub.c index 05a99c4f761b..38ccf9dab31f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_calcs_dchub.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_calcs_dchub.c @@ -74,7 +74,9 @@ void dcn5_calculate_byte_per_pixel_and_block_sizes( *BytePerPixelDETC = 0; *BytePerPixelY = 8; *BytePerPixelC = 0; - } else if (SourcePixelFormat == dml2_444_32 || SourcePixelFormat == dml2_rgbe || SourcePixelFormat == dml2_422_packed_10 || SourcePixelFormat == dml2_422_packed_12) { + } else if (SourcePixelFormat == dml2_444_32 || + SourcePixelFormat == dml2_rgbe || + SourcePixelFormat == dml2_422_packed_12) { *BytePerPixelDETY = 4; *BytePerPixelDETC = 0; *BytePerPixelY = 4; diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn6_calcs_dchub.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn6_calcs_dchub.c index cae6bee93fe3..a4e2f8604650 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn6_calcs_dchub.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn6_calcs_dchub.c @@ -569,20 +569,11 @@ void dcn6_calculate_flip_schedule( if (GPUVMEnable) { if (l->dual_plane) { - if (GPUVMEnable) { - l->min_row_height = dpte_row_height; - l->min_row_height_chroma = dpte_row_height_chroma; - } else { - l->min_row_height = meta_row_height; - l->min_row_height_chroma = meta_row_height_chroma; - } + l->min_row_height = dpte_row_height; + l->min_row_height_chroma = dpte_row_height_chroma; l->min_row_time = math_min2(l->min_row_height * LineTime / VRatio, l->min_row_height_chroma * LineTime / VRatioChroma); } else { - if (GPUVMEnable) - l->min_row_height = dpte_row_height; - else - l->min_row_height = meta_row_height; - + l->min_row_height = dpte_row_height; l->min_row_time = l->min_row_height * LineTime / VRatio; } DML_LOG_VERBOSE("DML::%s: min_row_time = %f\n", __func__, l->min_row_time); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 89265b083935..7146f8356233 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -639,7 +639,7 @@ static bool construct_phy(struct dc_link *link, DC_LOG_DC("BIOS object table - hpd_gpio id: %d", enc_init_data.hpd_gpio->id); DC_LOG_DC("BIOS object table - hpd_gpio en: %d", enc_init_data.hpd_gpio->en); - } else { + } else if (link->ctx->dce_version > DCN_VERSION_4_01) { struct graphics_object_hpd_info hpd_info; if (link->ctx->dc_bios->funcs->get_hpd_info(link->ctx->dc_bios, link->link_id, &hpd_info) == BP_RESULT_OK) { diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c index 3bcc7bf0900c..366f6d821242 100644 --- a/drivers/gpu/drm/drm_mode_config.c +++ b/drivers/gpu/drm/drm_mode_config.c @@ -869,8 +869,9 @@ static void validate_blend_mode_for_alpha_formats(struct drm_plane *plane) for (i = 0; i < plane->format_count; i++) { fmt = drm_format_info(plane->format_types[i]); if (fmt->has_alpha) { - WARN(1, "[PLANE:%d:%s] pixel format with alpha exposed but blend mode not setup", - plane->base.id, plane->name); + drm_warn(plane->dev, + "[PLANE:%d:%s] pixel format with alpha exposed but blend mode not setup. Please fix.\n", + plane->base.id, plane->name); break; } } diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index c17e9777beae..0259e60b8011 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -25,6 +25,8 @@ extern bool hang_debug; +#define A3XX_VBIF_XIN_HALT_CTRL0_MASK GENMASK(5, 0) + static void a3xx_dump(struct msm_gpu *gpu); static bool a3xx_idle(struct msm_gpu *gpu); @@ -496,6 +498,38 @@ static u64 a3xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) return busy_cycles; } +static int a3xx_vbif_halt(struct msm_gpu *gpu) +{ + u32 ack; + int ret; + + gpu_write(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL0, + A3XX_VBIF_XIN_HALT_CTRL0_MASK); + ret = spin_until(((ack = gpu_read(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL1)) & + A3XX_VBIF_XIN_HALT_CTRL0_MASK) == + A3XX_VBIF_XIN_HALT_CTRL0_MASK); + gpu_write(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL0, 0); + + if (ret) + return -EBUSY; + + return 0; +} + +static int a3xx_pm_suspend(struct msm_gpu *gpu) +{ + int ret; + + if (!a3xx_idle(gpu)) + return -EBUSY; + + ret = a3xx_vbif_halt(gpu); + if (ret) + return ret; + + return msm_gpu_pm_suspend(gpu); +} + static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { ring->memptrs->rptr = gpu_read(gpu, REG_AXXX_CP_RB_RPTR); @@ -581,7 +615,7 @@ const struct adreno_gpu_funcs a3xx_gpu_funcs = { .get_param = adreno_get_param, .set_param = adreno_set_param, .hw_init = a3xx_hw_init, - .pm_suspend = msm_gpu_pm_suspend, + .pm_suspend = a3xx_pm_suspend, .pm_resume = msm_gpu_pm_resume, .recover = a3xx_recover, .submit = a3xx_submit, diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 57135acc8e2c..5d96b8f63156 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1275,6 +1275,11 @@ static irqreturn_t a5xx_irq(struct msm_gpu *gpu) status & ~A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR); if (priv->disable_err_irq) { + /* Turn off interrupts to avoid interrupt storm */ + gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, + A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | + A5XX_RBBM_INT_0_MASK_CP_SW); + status &= A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | A5XX_RBBM_INT_0_MASK_CP_SW; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 3e6f409d13a2..90a0c7ffb3c8 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -1199,7 +1199,7 @@ static const struct adreno_reglist a730_hwcg[] = { { REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080 }, { REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222220 }, { REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222 }, - { REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222 }, + { REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22220222 }, { REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00222222 }, { REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777 }, { REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777 }, @@ -1454,7 +1454,7 @@ DECLARE_ADRENO_REGLIST_PIPE_LIST(a7xx_dyn_pwrup_reglist); static const struct adreno_info a7xx_gpus[] = { { - .chip_ids = ADRENO_CHIP_IDS(0x07000200), + .chip_ids = ADRENO_CHIP_IDS(0x07000200, 0x07000400), .family = ADRENO_6XX_GEN1, /* NOT a mistake! */ .fw = { [ADRENO_FW_SQE] = "a702_sqe.fw", @@ -1500,6 +1500,40 @@ static const struct adreno_info a7xx_gpus[] = { .gmu_cgc_mode = 0x00020000, }, .preempt_record_size = 2860 * SZ_1K, + }, { + .chip_ids = ADRENO_CHIP_IDS(0x43020100), + .family = ADRENO_7XX_GEN1, + .fw = { + [ADRENO_FW_SQE] = "qcom/gen71700_sqe.fw", + [ADRENO_FW_GMU] = "qcom/gen71700_gmu.bin", + }, + .gmem = SZ_1M, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV | + ADRENO_QUIRK_PREEMPTION, + .funcs = &a7xx_gpu_funcs, + .a6xx = &(const struct a6xx_info) { + .hwcg = a730_hwcg, + .protect = &a730_protect, + .pwrup_reglist = &a7xx_pwrup_reglist, + .dyn_pwrup_reglist = &a7xx_dyn_pwrup_reglist, + .gbif_cx = a640_gbif, + .gmu_chipid = 0x07110000, + .gmu_cgc_mode = 0x00020000, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, + }, + .preempt_record_size = 1536 * SZ_1K, }, { .chip_ids = ADRENO_CHIP_IDS(0x43050a01), /* "C510v2" */ .family = ADRENO_7XX_GEN2, @@ -2180,7 +2214,7 @@ static const struct adreno_reglist a840_gbif[] = { { REG_A6XX_GBIF_QSB_SIDE1, 0x00071e20 }, { REG_A6XX_GBIF_QSB_SIDE2, 0x00071e20 }, { REG_A6XX_GBIF_QSB_SIDE3, 0x00071e20 }, - { REG_A8XX_GBIF_CX_CONFIG, 0x20023000 }, + { REG_A6XX_GBIF_CX_CONFIG, 0x20023000 }, { }, }; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 2e5d7b53a0c3..27cac853975f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -642,7 +642,7 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) int ret; u32 val; - if (test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status)) + if (!test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status)) return; if (adreno_is_a840(adreno_gpu)) @@ -710,7 +710,8 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 2, 0); gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR + 2, 0); gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 4, - adreno_is_a740_family(adreno_gpu) ? 0x80000021 : 0x80000000); + (adreno_is_a740_family(adreno_gpu) || + adreno_is_a722(adreno_gpu)) ? 0x80000021 : 0x80000000); gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR + 4, 0); gmu_write_rscc(gmu, REG_A6XX_RSCC_OVERRIDE_START_ADDR, 0); gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_SEQ_START_ADDR, 0x4520); @@ -718,7 +719,7 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_MATCH_VALUE_HI, 0x4514); /* The second spin of A7xx GPUs messed with some register offsets.. */ - if (adreno_is_a740_family(adreno_gpu)) + if (adreno_is_a740_family(adreno_gpu) || adreno_is_a722(adreno_gpu)) seqmem0_drv0_reg = REG_A7XX_RSCC_SEQ_MEM_0_DRV0_A740; /* Load RSC sequencer uCode for sleep and wakeup */ @@ -1032,9 +1033,11 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) gpu_write(gpu, gbif_cx[i].offset, gbif_cx[i].value); if (adreno_is_a8xx(adreno_gpu)) { - gpu_write(gpu, REG_A8XX_GBIF_CX_CONFIG, 0x20023000); + gpu_write(gpu, REG_A6XX_GBIF_CX_CONFIG, 0x20023000); gmu_write(gmu, REG_A6XX_GMU_MRC_GBIF_QOS_CTRL, 0x33); - } + } else if (adreno_is_a722(adreno_gpu)) + gpu_rmw(gpu, REG_A6XX_GBIF_CX_CONFIG, GENMASK(31, 29), + FIELD_PREP(GENMASK(31, 29), 2)); /* Set up the lowest idle level on the GMU */ a6xx_gmu_power_config(gmu); @@ -1087,7 +1090,8 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) u32 val, seqmem_off = 0; /* The second spin of A7xx GPUs messed with some register offsets.. */ - if (adreno_is_a740_family(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) + if (adreno_is_a740_family(adreno_gpu) || adreno_is_a722(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) seqmem_off = 4; /* Make sure there are no outstanding RPMh votes */ @@ -1100,7 +1104,8 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS + seqmem_off, val, (val & 1), 100, 1000); - if (!adreno_is_a740_family(adreno_gpu) && !adreno_is_a8xx(adreno_gpu)) + if (!adreno_is_a740_family(adreno_gpu) && !adreno_is_a722(adreno_gpu) && + !adreno_is_a8xx(adreno_gpu)) return; gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS4_DRV0_STATUS + seqmem_off, @@ -1465,6 +1470,9 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) /* Stop the interrupts and mask the hardware */ a6xx_gmu_irq_disable(gmu); + /* Halt the gmu cm3 core */ + gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); + /* Tell RPMh to power off the GPU */ a6xx_rpmh_stop(gmu); @@ -1546,7 +1554,7 @@ static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo, flags |= MSM_BO_MAP_PRIV; } - bo->obj = msm_gem_new(dev, size, flags); + bo->obj = msm_gem_new(dev, size, flags, NULL); if (IS_ERR(bo->obj)) return PTR_ERR(bo->obj); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 8b3bb2fd433b..f9de9329dee3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -229,7 +229,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, { bool sysprof = msm_gpu_sysprof_no_perfcntr_zap(&a6xx_gpu->base.base); struct msm_context *ctx = submit->queue->ctx; - struct drm_gpuvm *vm = msm_context_vm(submit->dev, ctx); + struct drm_gpuvm *vm = ctx->vm; struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; phys_addr_t ttbr; u32 asid; @@ -1273,7 +1273,8 @@ static int hw_init(struct msm_gpu *gpu) if (!(adreno_is_a650_family(adreno_gpu) || adreno_is_a702(adreno_gpu) || adreno_is_a730(adreno_gpu))) { - gmem_range_min = adreno_is_a740_family(adreno_gpu) ? SZ_16M : SZ_1M; + gmem_range_min = (adreno_is_a740_family(adreno_gpu) || + adreno_is_a722(adreno_gpu)) ? SZ_16M : SZ_1M; /* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */ gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN, gmem_range_min); @@ -1338,6 +1339,7 @@ static int hw_init(struct msm_gpu *gpu) /* Enable fault detection */ if (adreno_is_a612(adreno_gpu) || + adreno_is_a722(adreno_gpu) || adreno_is_a730(adreno_gpu) || adreno_is_a740_family(adreno_gpu)) gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0xcfffff); @@ -1911,8 +1913,11 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu) gpu_write(gpu, REG_A6XX_RBBM_INT_CLEAR_CMD, status); - if (priv->disable_err_irq) + if (priv->disable_err_irq) { + /* Turn off interrupts to avoid interrupt storm */ + gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS); status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS; + } if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT) a6xx_fault_detect_irq(gpu); @@ -2770,8 +2775,9 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu->ubwc_config = qcom_ubwc_config_get_data(); if (IS_ERR(adreno_gpu->ubwc_config)) { + ret = PTR_ERR(adreno_gpu->ubwc_config); a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_CAST(adreno_gpu->ubwc_config); + return ERR_PTR(ret); } /* Set up the preemption specific bits and pieces for each ringbuffer */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 166365359fa6..26c17861cd5d 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -11,12 +11,14 @@ static const unsigned int *gen7_0_0_external_core_regs[] __always_unused; static const unsigned int *gen7_2_0_external_core_regs[] __always_unused; static const unsigned int *gen7_9_0_external_core_regs[] __always_unused; +static const unsigned int *gen7_17_0_external_core_regs[] __always_unused; static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused; #include "adreno_gen7_0_0_snapshot.h" #include "adreno_gen7_2_0_snapshot.h" #include "adreno_gen7_9_0_snapshot.h" +#include "adreno_gen7_17_0_snapshot.h" struct a6xx_gpu_state_obj { const void *handle; @@ -404,8 +406,13 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu, int i; if (adreno_gpu->info->family == ADRENO_7XX_GEN1) { - debugbus_blocks = gen7_0_0_debugbus_blocks; - debugbus_blocks_count = ARRAY_SIZE(gen7_0_0_debugbus_blocks); + if (adreno_is_a722(adreno_gpu)) { + debugbus_blocks = gen7_17_0_debugbus_blocks; + debugbus_blocks_count = ARRAY_SIZE(gen7_17_0_debugbus_blocks); + } else { + debugbus_blocks = gen7_0_0_debugbus_blocks; + debugbus_blocks_count = ARRAY_SIZE(gen7_0_0_debugbus_blocks); + } gbif_debugbus_blocks = a7xx_gbif_debugbus_blocks; gbif_debugbus_blocks_count = ARRAY_SIZE(a7xx_gbif_debugbus_blocks); } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) { @@ -678,8 +685,13 @@ static void a7xx_get_dbgahb_clusters(struct msm_gpu *gpu, unsigned dbgahb_clusters_size; if (adreno_gpu->info->family == ADRENO_7XX_GEN1) { - dbgahb_clusters = gen7_0_0_sptp_clusters; - dbgahb_clusters_size = ARRAY_SIZE(gen7_0_0_sptp_clusters); + if (adreno_is_a722(adreno_gpu)) { + dbgahb_clusters = gen7_17_0_sptp_clusters; + dbgahb_clusters_size = ARRAY_SIZE(gen7_17_0_sptp_clusters); + } else { + dbgahb_clusters = gen7_0_0_sptp_clusters; + dbgahb_clusters_size = ARRAY_SIZE(gen7_0_0_sptp_clusters); + } } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) { dbgahb_clusters = gen7_2_0_sptp_clusters; dbgahb_clusters_size = ARRAY_SIZE(gen7_2_0_sptp_clusters); @@ -839,8 +851,13 @@ static void a7xx_get_clusters(struct msm_gpu *gpu, unsigned clusters_size; if (adreno_gpu->info->family == ADRENO_7XX_GEN1) { - clusters = gen7_0_0_clusters; - clusters_size = ARRAY_SIZE(gen7_0_0_clusters); + if (adreno_is_a722(adreno_gpu)) { + clusters = gen7_17_0_clusters; + clusters_size = ARRAY_SIZE(gen7_17_0_clusters); + } else { + clusters = gen7_0_0_clusters; + clusters_size = ARRAY_SIZE(gen7_0_0_clusters); + } } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) { clusters = gen7_2_0_clusters; clusters_size = ARRAY_SIZE(gen7_2_0_clusters); @@ -977,8 +994,13 @@ static void a7xx_get_shaders(struct msm_gpu *gpu, int i; if (adreno_gpu->info->family == ADRENO_7XX_GEN1) { - shader_blocks = gen7_0_0_shader_blocks; - num_shader_blocks = ARRAY_SIZE(gen7_0_0_shader_blocks); + if (adreno_is_a722(adreno_gpu)) { + shader_blocks = gen7_17_0_shader_blocks; + num_shader_blocks = ARRAY_SIZE(gen7_17_0_shader_blocks); + } else { + shader_blocks = gen7_0_0_shader_blocks; + num_shader_blocks = ARRAY_SIZE(gen7_0_0_shader_blocks); + } } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) { shader_blocks = gen7_2_0_shader_blocks; num_shader_blocks = ARRAY_SIZE(gen7_2_0_shader_blocks); @@ -1244,9 +1266,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1], &a6xx_state->gmu_registers[1], true); - if (adreno_is_a621(adreno_gpu) || adreno_is_a623(adreno_gpu)) + if (adreno_is_a621(adreno_gpu)) _a6xx_get_gmu_registers(gpu, a6xx_state, &a621_gpucc_reg, &a6xx_state->gmu_registers[2], false); + else if (adreno_is_a623(adreno_gpu) || adreno_is_a663(adreno_gpu)) + _a6xx_get_gmu_registers(gpu, a6xx_state, &a623_gpucc_reg, + &a6xx_state->gmu_registers[2], false); else _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gpucc_reg, &a6xx_state->gmu_registers[2], false); @@ -1376,8 +1401,13 @@ static void a7xx_get_registers(struct msm_gpu *gpu, const struct gen7_reg_list *reglist; if (adreno_gpu->info->family == ADRENO_7XX_GEN1) { - reglist = gen7_0_0_reg_list; - pre_crashdumper_regs = gen7_0_0_pre_crashdumper_gpu_registers; + if (adreno_is_a722(adreno_gpu)) { + reglist = gen7_17_0_reg_list; + pre_crashdumper_regs = gen7_9_0_pre_crashdumper_gpu_registers; + } else { + reglist = gen7_0_0_reg_list; + pre_crashdumper_regs = gen7_0_0_pre_crashdumper_gpu_registers; + } } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) { reglist = gen7_2_0_reg_list; pre_crashdumper_regs = gen7_0_0_pre_crashdumper_gpu_registers; @@ -1433,7 +1463,9 @@ static void a7xx_get_post_crashdumper_registers(struct msm_gpu *gpu, const u32 *regs; BUG_ON(adreno_gpu->info->family > ADRENO_7XX_GEN3); - regs = gen7_0_0_post_crashdumper_registers; + regs = adreno_is_a722(adreno_gpu) ? + gen7_17_0_post_crashdumper_registers : + gen7_0_0_post_crashdumper_registers; a7xx_get_ahb_gpu_registers(gpu, a6xx_state, regs, @@ -1540,19 +1572,35 @@ static void a7xx_get_indexed_registers(struct msm_gpu *gpu, { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); const struct a6xx_indexed_registers *indexed_regs; + const struct a6xx_indexed_registers *mempool_regs; int i, indexed_count, mempool_count; + bool concurrent_binning; - if (adreno_gpu->info->family <= ADRENO_7XX_GEN2) { + if (adreno_is_a722(adreno_gpu)) { + /* + * Eliza has no BV or LPAC SQE — skip the BV/LPAC indexed + * registers and the BV mempool + */ + indexed_regs = gen7_17_0_cp_indexed_reglist; + indexed_count = ARRAY_SIZE(gen7_17_0_cp_indexed_reglist); + mempool_regs = a7xx_cp_mempool_indexed; + mempool_count = ARRAY_SIZE(a7xx_cp_mempool_indexed); + concurrent_binning = false; + } else if (adreno_gpu->info->family <= ADRENO_7XX_GEN2) { indexed_regs = a7xx_indexed_reglist; indexed_count = ARRAY_SIZE(a7xx_indexed_reglist); + mempool_regs = a7xx_cp_bv_mempool_indexed; + mempool_count = ARRAY_SIZE(a7xx_cp_bv_mempool_indexed); + concurrent_binning = true; } else { BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3); indexed_regs = gen7_9_0_cp_indexed_reg_list; indexed_count = ARRAY_SIZE(gen7_9_0_cp_indexed_reg_list); + mempool_regs = a7xx_cp_bv_mempool_indexed; + mempool_count = ARRAY_SIZE(a7xx_cp_bv_mempool_indexed); + concurrent_binning = true; } - mempool_count = ARRAY_SIZE(a7xx_cp_bv_mempool_indexed); - a6xx_state->indexed_regs = state_kcalloc(a6xx_state, indexed_count + mempool_count, sizeof(*a6xx_state->indexed_regs)); @@ -1567,15 +1615,17 @@ static void a7xx_get_indexed_registers(struct msm_gpu *gpu, &a6xx_state->indexed_regs[i]); gpu_rmw(gpu, REG_A6XX_CP_CHICKEN_DBG, 0, BIT(2)); - gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, 0, BIT(2)); + if (concurrent_binning) + gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, 0, BIT(2)); /* Get the contents of the CP_BV mempool */ for (i = 0; i < mempool_count; i++) - a6xx_get_indexed_regs(gpu, a6xx_state, &a7xx_cp_bv_mempool_indexed[i], + a6xx_get_indexed_regs(gpu, a6xx_state, &mempool_regs[i], &a6xx_state->indexed_regs[indexed_count + i]); gpu_rmw(gpu, REG_A6XX_CP_CHICKEN_DBG, BIT(2), 0); - gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, BIT(2), 0); + if (concurrent_binning) + gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, BIT(2), 0); return; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index b49d8427b59e..6f592394f866 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -377,6 +377,17 @@ static const u32 a6xx_gmu_gpucc_registers[] = { }; static const u32 a621_gmu_gpucc_registers[] = { + /* GPU CC */ + 0x24000, 0x2400e, 0x24400, 0x2440e, 0x24800, 0x24805, 0x24c00, 0x24cff, + 0x25800, 0x25804, 0x25c00, 0x25c04, 0x26000, 0x26004, 0x26400, 0x26405, + 0x26414, 0x2641d, 0x2642a, 0x26430, 0x26432, 0x26432, 0x26441, 0x26455, + 0x26466, 0x26468, 0x26478, 0x2647a, 0x26489, 0x2648a, 0x2649c, 0x2649e, + 0x264a0, 0x264a3, 0x264b3, 0x264b5, 0x264c5, 0x264c7, 0x264d6, 0x264d8, + 0x264e8, 0x264e9, 0x264f9, 0x264fc, 0x2650b, 0x2650c, 0x2651c, 0x2651e, + 0x26540, 0x26570, 0x26600, 0x26616, 0x26620, 0x2662d, +}; + +static const u32 a623_gmu_gpucc_registers[] = { /* GPU CC */ 0x24000, 0x2400e, 0x24400, 0x2440e, 0x25800, 0x25804, 0x25c00, 0x25c04, 0x26000, 0x26004, 0x26400, 0x26405, 0x26414, 0x2641d, 0x2642a, 0x26430, @@ -402,6 +413,7 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = { static const struct a6xx_registers a6xx_gpucc_reg = REGS(a6xx_gmu_gpucc_registers, 0, 0); static const struct a6xx_registers a621_gpucc_reg = REGS(a621_gmu_gpucc_registers, 0, 0); +static const struct a6xx_registers a623_gpucc_reg = REGS(a623_gmu_gpucc_registers, 0, 0); static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu); static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu); @@ -462,6 +474,11 @@ static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = { REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL }, }; +static const struct a6xx_indexed_registers a7xx_cp_mempool_indexed[] = { + { "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL }, +}; + #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count } static const struct a6xx_debugbus_block { diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c index 9e44fd1ae634..add93c1fa039 100644 --- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c @@ -228,7 +228,7 @@ static void a8xx_set_hwcg(struct msm_gpu *gpu, bool state) * GMU enables clk gating in GBIF during boot up. So, * override that here when hwcg feature is disabled */ - gpu_rmw(gpu, REG_A8XX_GBIF_CX_CONFIG, BIT(0), 0); + gpu_rmw(gpu, REG_A6XX_GBIF_CX_CONFIG, BIT(0), 0); } } @@ -1211,8 +1211,11 @@ irqreturn_t a8xx_irq(struct msm_gpu *gpu) gpu_write(gpu, REG_A8XX_RBBM_INT_CLEAR_CMD, status); - if (priv->disable_err_irq) + if (priv->disable_err_irq) { + /* Turn off interrupts to avoid interrupt storm */ + gpu_write(gpu, REG_A8XX_RBBM_INT_0_MASK, A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS); status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS; + } if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT) a8xx_fault_detect_irq(gpu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_17_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_17_0_snapshot.h new file mode 100644 index 000000000000..00a4a0fc97d2 --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_17_0_snapshot.h @@ -0,0 +1,428 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) Qualcomm Innovation Center, Inc. All rights reserved. + */ +#ifndef __ADRENO_GEN7_17_0_SNAPSHOT_H +#define __ADRENO_GEN7_17_0_SNAPSHOT_H + +#include "a6xx_gpu_state.h" + +/* + * Snapshot tables for Adreno A722 (Eliza). + * Cluster sub-arrays that are identical to A730 reference gen7_0_0_* + * symbols; adreno_gen7_0_0_snapshot.h is included first in the TU. + */ + +static const u32 gen7_17_0_rscc_registers[] = { + 0x14000, 0x14034, 0x14036, 0x14036, 0x14040, 0x14042, 0x14044, 0x14045, + 0x14047, 0x14047, 0x14080, 0x14084, 0x14089, 0x1408c, 0x14091, 0x14094, + 0x14099, 0x1409c, 0x140a1, 0x140a4, 0x140a9, 0x140ac, 0x140b1, 0x140b4, + 0x140b9, 0x140bc, 0x14100, 0x14104, 0x14114, 0x14119, 0x14124, 0x14132, + 0x14154, 0x1416b, 0x14340, 0x14341, 0x14344, 0x14344, 0x14346, 0x1437c, + 0x143f0, 0x143f8, 0x143fa, 0x143fe, 0x14400, 0x14404, 0x14406, 0x1440a, + 0x1440c, 0x14410, 0x14412, 0x14416, 0x14418, 0x1441c, 0x1441e, 0x14422, + 0x14424, 0x14424, 0x14498, 0x144a0, 0x144a2, 0x144a6, 0x144a8, 0x144ac, + 0x144ae, 0x144b2, 0x144b4, 0x144b8, 0x144ba, 0x144be, 0x144c0, 0x144c4, + 0x144c6, 0x144ca, 0x144cc, 0x144cc, 0x14540, 0x14548, 0x1454a, 0x1454e, + 0x14550, 0x14554, 0x14556, 0x1455a, 0x1455c, 0x14560, 0x14562, 0x14566, + 0x14568, 0x1456c, 0x1456e, 0x14572, 0x14574, 0x14574, 0x145e8, 0x145f0, + 0x145f2, 0x145f6, 0x145f8, 0x145fc, 0x145fe, 0x14602, 0x14604, 0x14608, + 0x1460a, 0x1460e, 0x14610, 0x14614, 0x14616, 0x1461a, 0x1461c, 0x1461c, + 0x14690, 0x14698, 0x1469a, 0x1469e, 0x146a0, 0x146a4, 0x146a6, 0x146aa, + 0x146ac, 0x146b0, 0x146b2, 0x146b6, 0x146b8, 0x146bc, 0x146be, 0x146c2, + 0x146c4, 0x146c4, 0x14738, 0x14740, 0x14742, 0x14746, 0x14748, 0x1474c, + 0x1474e, 0x14752, 0x14754, 0x14758, 0x1475a, 0x1475e, 0x14760, 0x14764, + 0x14766, 0x1476a, 0x1476c, 0x1476c, 0x147e0, 0x147e8, 0x147ea, 0x147ee, + 0x147f0, 0x147f4, 0x147f6, 0x147fa, 0x147fc, 0x14800, 0x14802, 0x14806, + 0x14808, 0x1480c, 0x1480e, 0x14812, 0x14814, 0x14814, 0x14888, 0x14890, + 0x14892, 0x14896, 0x14898, 0x1489c, 0x1489e, 0x148a2, 0x148a4, 0x148a8, + 0x148aa, 0x148ae, 0x148b0, 0x148b4, 0x148b6, 0x148ba, 0x148bc, 0x148bc, + 0x14930, 0x14938, 0x1493a, 0x1493e, 0x14940, 0x14944, 0x14946, 0x1494a, + 0x1494c, 0x14950, 0x14952, 0x14956, 0x14958, 0x1495c, 0x1495e, 0x14962, + 0x14964, 0x14964, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_rscc_registers), 8)); + +static const u32 gen7_17_0_cpr_registers[] = { + 0x26800, 0x26805, 0x26808, 0x2680c, 0x26814, 0x26814, 0x2681c, 0x2681c, + 0x26820, 0x26838, 0x26840, 0x26840, 0x26848, 0x26848, 0x26850, 0x26850, + 0x26880, 0x2688e, 0x26980, 0x269b0, 0x269c0, 0x269c2, 0x269c6, 0x269c8, + 0x269e0, 0x269ee, 0x269fb, 0x269ff, 0x26a02, 0x26a07, 0x26a09, 0x26a0b, + 0x26a10, 0x26b0f, 0x27440, 0x27441, 0x27444, 0x27444, 0x27480, 0x274a2, + 0x274ac, 0x274c4, 0x274c8, 0x274da, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_cpr_registers), 8)); + +static const u32 gen7_17_0_gpucc_registers[] = { + 0x24000, 0x2400f, 0x24400, 0x2440f, 0x24800, 0x24805, 0x24c00, 0x24cff, + 0x25400, 0x25404, 0x25800, 0x25804, 0x25c00, 0x25c04, 0x26000, 0x26004, + 0x26400, 0x26405, 0x26414, 0x2641d, 0x2642a, 0x2642c, 0x2642e, 0x26432, + 0x26434, 0x26434, 0x26443, 0x26457, 0x26459, 0x2645d, 0x2645f, 0x26464, + 0x26477, 0x26479, 0x26489, 0x2648b, 0x2649a, 0x2649b, 0x264ad, 0x264af, + 0x264b1, 0x264b5, 0x264d6, 0x264d8, 0x264e7, 0x264e9, 0x264f9, 0x264fa, + 0x2650a, 0x2650d, 0x2651f, 0x26520, 0x2652d, 0x2652f, 0x2653e, 0x2653e, + 0x26540, 0x2654e, 0x26554, 0x26573, 0x26576, 0x26576, 0x26593, 0x26593, + 0x26600, 0x26616, 0x26620, 0x2662d, 0x26630, 0x26631, 0x26635, 0x26635, + 0x26637, 0x26637, 0x2663a, 0x2663a, 0x26642, 0x26642, 0x26656, 0x26658, + 0x2665b, 0x2665d, 0x2665f, 0x26662, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_gpucc_registers), 8)); + +static const u32 *gen7_17_0_external_core_regs[] = { + gen7_17_0_gpucc_registers, + gen7_17_0_cpr_registers, +}; + +static const u32 gen7_17_0_debugbus_blocks[] = { + A7XX_DBGBUS_CP_0_0, + A7XX_DBGBUS_CP_0_1, + A7XX_DBGBUS_RBBM, + A7XX_DBGBUS_HLSQ, + A7XX_DBGBUS_UCHE_0, + A7XX_DBGBUS_TESS_BR, + A7XX_DBGBUS_PC_BR, + A7XX_DBGBUS_VFDP_BR, + A7XX_DBGBUS_VPC_BR, + A7XX_DBGBUS_TSE_BR, + A7XX_DBGBUS_RAS_BR, + A7XX_DBGBUS_VSC, + A7XX_DBGBUS_COM_0, + A7XX_DBGBUS_LRZ_BR, + A7XX_DBGBUS_UFC_0, + A7XX_DBGBUS_UFC_1, + A7XX_DBGBUS_GMU_GX, + A7XX_DBGBUS_DBGC, + A7XX_DBGBUS_GPC_BR, + A7XX_DBGBUS_LARC, + A7XX_DBGBUS_HLSQ_SPTP, + A7XX_DBGBUS_RB_0, + A7XX_DBGBUS_RB_1, + A7XX_DBGBUS_UCHE_WRAPPER, + A7XX_DBGBUS_CCU_0, + A7XX_DBGBUS_CCU_1, + A7XX_DBGBUS_VFD_BR_0, + A7XX_DBGBUS_VFD_BR_1, + A7XX_DBGBUS_VFD_BR_2, + A7XX_DBGBUS_VFD_BR_3, + A7XX_DBGBUS_USP_0, + A7XX_DBGBUS_USP_1, + A7XX_DBGBUS_TP_0, + A7XX_DBGBUS_TP_1, + A7XX_DBGBUS_TP_2, + A7XX_DBGBUS_TP_3, + A7XX_DBGBUS_USPTP_0, + A7XX_DBGBUS_USPTP_1, + A7XX_DBGBUS_USPTP_2, + A7XX_DBGBUS_USPTP_3, +}; + +static const struct gen7_sel_reg gen7_17_0_rb_rac_sel = { + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, + .val = 0x0, +}; + +static const struct gen7_sel_reg gen7_17_0_rb_rbp_sel = { + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, + .val = 0x9, +}; + +static const u32 gen7_17_0_post_crashdumper_registers[] = { + 0x00535, 0x00535, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_post_crashdumper_registers), 8)); + +static const u32 gen7_17_0_gpu_registers[] = { + 0x00000, 0x00000, 0x00002, 0x00002, 0x00011, 0x00012, 0x00016, 0x0001b, + 0x0001f, 0x00032, 0x00038, 0x0003c, 0x00042, 0x00042, 0x00044, 0x00044, + 0x00047, 0x00047, 0x00049, 0x0004a, 0x0004c, 0x0004c, 0x00050, 0x00050, + 0x00056, 0x00056, 0x00073, 0x00075, 0x000ad, 0x000ae, 0x000b0, 0x000b0, + 0x000b4, 0x000b4, 0x000b8, 0x000b8, 0x000bc, 0x000bc, 0x000c0, 0x000c0, + 0x000c4, 0x000c4, 0x000c8, 0x000c8, 0x000cc, 0x000cc, 0x000d0, 0x000d0, + 0x000d4, 0x000d4, 0x000d8, 0x000d8, 0x000dc, 0x000dc, 0x000e0, 0x000e0, + 0x000e4, 0x000e4, 0x000e8, 0x000e8, 0x000ec, 0x000ec, 0x000f0, 0x000f0, + 0x000f4, 0x000f4, 0x000f8, 0x000f8, 0x00100, 0x00100, 0x00104, 0x0010b, + 0x0010f, 0x0011d, 0x0012f, 0x0012f, 0x00200, 0x0020d, 0x00215, 0x00243, + 0x00260, 0x00268, 0x00272, 0x00274, 0x00286, 0x00286, 0x0028a, 0x0028a, + 0x0028c, 0x0028c, 0x00300, 0x00401, 0x00500, 0x00500, 0x00507, 0x0050b, + 0x0050f, 0x0050f, 0x00511, 0x00511, 0x00533, 0x00534, 0x00540, 0x00555, + 0x00564, 0x00567, 0x00800, 0x00808, 0x00810, 0x00813, 0x00820, 0x00821, + 0x00823, 0x00827, 0x00830, 0x00834, 0x00840, 0x00841, 0x00843, 0x00847, + 0x0084f, 0x00886, 0x008a0, 0x008ab, 0x008c0, 0x008c0, 0x008c4, 0x008c5, + 0x008d0, 0x008dd, 0x008f0, 0x008f3, 0x00900, 0x00903, 0x00908, 0x00911, + 0x00928, 0x0093e, 0x00942, 0x0094d, 0x00980, 0x00984, 0x0098d, 0x0098f, + 0x009b0, 0x009b4, 0x009c2, 0x009c9, 0x009ce, 0x009d7, 0x00a00, 0x00a00, + 0x00a02, 0x00a03, 0x00a10, 0x00a4f, 0x00a67, 0x00a6c, 0x00a9c, 0x00a9f, + 0x00c00, 0x00c00, 0x00c02, 0x00c04, 0x00c06, 0x00c06, 0x00c10, 0x00cd9, + 0x00ce0, 0x00d0c, 0x00df0, 0x00df4, 0x00e01, 0x00e02, 0x00e07, 0x00e0e, + 0x00e10, 0x00e12, 0x00e17, 0x00e17, 0x00e19, 0x00e19, 0x00e1b, 0x00e2b, + 0x00e30, 0x00e32, 0x00e38, 0x00e3c, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_gpu_registers), 8)); + +static const u32 gen7_17_0_dbgc_registers[] = { + 0x00600, 0x0061c, 0x0061e, 0x00634, 0x00640, 0x0065a, 0x00679, 0x0067a, + 0x00699, 0x00699, 0x0069b, 0x0069e, 0x18400, 0x1841c, 0x1841e, 0x18434, + 0x18440, 0x1845c, 0x18479, 0x1847c, 0x18580, 0x18581, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_dbgc_registers), 8)); + +static const u32 gen7_17_0_noncontext_pipe_br_registers[] = { + 0x00887, 0x0088c, 0x08600, 0x08600, 0x08602, 0x08602, 0x08610, 0x0861b, + 0x08620, 0x08620, 0x08630, 0x08630, 0x08637, 0x08639, 0x08640, 0x08640, + 0x09600, 0x09600, 0x09602, 0x09603, 0x0960a, 0x09616, 0x09624, 0x0963a, + 0x09640, 0x09640, 0x09e00, 0x09e00, 0x09e02, 0x09e07, 0x09e0a, 0x09e16, + 0x09e19, 0x09e19, 0x09e1c, 0x09e1c, 0x09e20, 0x09e25, 0x09e30, 0x09e31, + 0x09e40, 0x09e51, 0x09e64, 0x09e64, 0x09e70, 0x09e72, 0x09e78, 0x09e79, + 0x09e80, 0x09fff, 0x0a600, 0x0a600, 0x0a603, 0x0a603, 0x0a610, 0x0a61f, + 0x0a630, 0x0a631, 0x0a638, 0x0a638, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_noncontext_pipe_br_registers), 8)); + +static const u32 gen7_17_0_noncontext_rb_rac_pipe_br_registers[] = { + 0x08e10, 0x08e1c, 0x08e20, 0x08e25, 0x08e51, 0x08e54, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_noncontext_rb_rac_pipe_br_registers), 8)); + +static const u32 gen7_17_0_noncontext_rb_rbp_pipe_br_registers[] = { + 0x08e01, 0x08e01, 0x08e04, 0x08e04, 0x08e06, 0x08e09, 0x08e0c, 0x08e0c, + 0x08e28, 0x08e28, 0x08e2c, 0x08e35, 0x08e3b, 0x08e3f, 0x08e50, 0x08e50, + 0x08e5b, 0x08e5d, 0x08e5f, 0x08e5f, 0x08e61, 0x08e61, 0x08e63, 0x08e65, + 0x08e68, 0x08e68, 0x08e70, 0x08e79, 0x08e80, 0x08e8f, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_noncontext_rb_rbp_pipe_br_registers), 8)); + +static const u32 gen7_17_0_pc_cluster_fe_pipe_br_registers[] = { + 0x09800, 0x09804, 0x09806, 0x0980a, 0x09810, 0x09811, 0x09884, 0x09886, + 0x09970, 0x09972, 0x09b00, 0x09b08, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_pc_cluster_fe_pipe_br_registers), 8)); + +static const u32 gen7_17_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers[] = { + 0x0aa40, 0x0aabf, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers), 8)); + +static const u32 gen7_17_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers[] = { + 0x0aa40, 0x0aabf, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers), 8)); + +static const u32 gen7_17_0_non_context_tpl1_pipe_none_usptp_registers[] = { + 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c, 0x0b60f, 0x0b621, + 0x0b630, 0x0b633, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_non_context_tpl1_pipe_none_usptp_registers), 8)); + +static const u32 gen7_17_0_non_context_tpl1_pipe_br_usptp_registers[] = { + 0x0b600, 0x0b600, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_non_context_tpl1_pipe_br_usptp_registers), 8)); + +static const u32 gen7_17_0_tpl1_cluster_sp_vs_pipe_br_usptp_registers[] = { + 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_tpl1_cluster_sp_vs_pipe_br_usptp_registers), 8)); + +static const u32 gen7_17_0_tpl1_cluster_sp_ps_pipe_br_usptp_registers[] = { + 0x0b180, 0x0b183, 0x0b190, 0x0b195, 0x0b2c0, 0x0b2d5, 0x0b300, 0x0b307, + 0x0b309, 0x0b309, 0x0b310, 0x0b310, + UINT_MAX, UINT_MAX, +}; +static_assert(IS_ALIGNED(sizeof(gen7_17_0_tpl1_cluster_sp_ps_pipe_br_usptp_registers), 8)); + +/* No BV pipe — gen7_0_0_* sub-arrays are shared from adreno_gen7_0_0_snapshot.h */ +static struct gen7_cluster_registers gen7_17_0_clusters[] = { + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, + gen7_17_0_noncontext_pipe_br_registers, }, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, + gen7_17_0_noncontext_rb_rac_pipe_br_registers, &gen7_17_0_rb_rac_sel, }, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, + gen7_17_0_noncontext_rb_rbp_pipe_br_registers, &gen7_17_0_rb_rbp_sel, }, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_17_0_rb_rac_sel, }, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_17_0_rb_rac_sel, }, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_17_0_rb_rbp_sel, }, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_17_0_rb_rbp_sel, }, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_gras_cluster_gras_pipe_br_registers, }, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_gras_cluster_gras_pipe_br_registers, }, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_17_0_pc_cluster_fe_pipe_br_registers, }, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_17_0_pc_cluster_fe_pipe_br_registers, }, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, + gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, + gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, +}; + +/* No BV pipe; 2 SPs, 2 USPTPs */ +static struct gen7_sptp_cluster_registers gen7_17_0_sptp_clusters[] = { + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, + gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, + gen7_0_0_sp_noncontext_pipe_br_sp_top_registers, 0xae00 }, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, + gen7_0_0_sp_noncontext_pipe_br_usptp_registers, 0xae00 }, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, + gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, + gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, + gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, + gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, + gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, + gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, + gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, + gen7_17_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, + gen7_17_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, + gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, + gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_NONE, 0, A7XX_USPTP, + gen7_17_0_non_context_tpl1_pipe_none_usptp_registers, 0xb600 }, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, + gen7_17_0_non_context_tpl1_pipe_br_usptp_registers, 0xb600 }, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, + gen7_17_0_tpl1_cluster_sp_vs_pipe_br_usptp_registers, 0xb000 }, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, + gen7_17_0_tpl1_cluster_sp_vs_pipe_br_usptp_registers, 0xb000 }, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, + gen7_17_0_tpl1_cluster_sp_ps_pipe_br_usptp_registers, 0xb000 }, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, + gen7_17_0_tpl1_cluster_sp_ps_pipe_br_usptp_registers, 0xb000 }, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, + gen7_17_0_tpl1_cluster_sp_ps_pipe_br_usptp_registers, 0xb000 }, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, + gen7_17_0_tpl1_cluster_sp_ps_pipe_br_usptp_registers, 0xb000 }, +}; + +static struct gen7_shader_block gen7_17_0_shader_blocks[] = { + { A7XX_TP0_TMO_DATA, 0x0200, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_TP0_SMO_DATA, 0x0080, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_TP0_MIPMAP_BASE_DATA, 0x03c0, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA_1, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_0_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_1_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_2_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_3_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_4_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_5_DATA, 0x0800, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_CB_RAM, 0x0390, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_TAG, 0x0090, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_TMO_TAG, 0x0080, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_SMO_TAG, 0x0080, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_STATE_DATA, 0x0040, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_HWAVE_RAM, 0x0100, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_L0_INST_BUF, 0x0050, 2, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x0300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM, 0x0280, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_1, 0x0200, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0064, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0064, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_1, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_STPROC_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BV_BE_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_DATAPATH_META, 0x0020, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INDIRECT_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, +}; + +static struct gen7_reg_list gen7_17_0_reg_list[] = { + { gen7_17_0_gpu_registers, NULL }, + { gen7_17_0_dbgc_registers, NULL }, + { NULL, NULL }, +}; + +static const struct a6xx_indexed_registers gen7_17_0_cp_indexed_reglist[] = { + { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, + REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL }, + { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, + REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, + REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size }, +}; + +#endif /* __ADRENO_GEN7_17_0_SNAPSHOT_H */ diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 489462065ea9..8cd2020d4b7e 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -357,6 +357,12 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, return 0; } +static bool +valid_per_process_vm(struct msm_gpu *gpu, struct drm_gpuvm *vm) +{ + return vm && (vm != gpu->vm); +} + int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, uint32_t param, uint64_t *value, uint32_t *len) { @@ -415,12 +421,12 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, *value = gpu->suspend_count; return 0; case MSM_PARAM_VA_START: - if (vm == gpu->vm) + if (!valid_per_process_vm(gpu, vm)) return UERR(EINVAL, drm, "requires per-process pgtables"); *value = vm->mm_start; return 0; case MSM_PARAM_VA_SIZE: - if (vm == gpu->vm) + if (!valid_per_process_vm(gpu, vm)) return UERR(EINVAL, drm, "requires per-process pgtables"); *value = vm->mm_range; return 0; @@ -504,9 +510,11 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_context *ctx, if (!perfmon_capable()) return UERR(EPERM, drm, "invalid permissions"); return msm_context_set_sysprof(ctx, gpu, value); - case MSM_PARAM_EN_VM_BIND: + case MSM_PARAM_EN_VM_BIND: { + guard(rwsem_read)(&ctx->ctxlock); + /* We can only support VM_BIND with per-process pgtables: */ - if (ctx->vm == gpu->vm) + if (!gpu->funcs->create_private_vm) return UERR(EINVAL, drm, "requires per-process pgtables"); /* @@ -519,6 +527,7 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_context *ctx, ctx->userspace_managed_vm = value; return 0; + } default: return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 1f201322cb6e..114a40f79ef3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -562,6 +562,11 @@ static inline int adreno_is_x185(struct adreno_gpu *gpu) return gpu->info->chip_ids[0] == 0x43050c01; } +static inline int adreno_is_a722(struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x43020100; +} + static inline int adreno_is_a740_family(struct adreno_gpu *gpu) { if (WARN_ON_ONCE(!gpu->info)) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h index 06da1583fb1e..85f455a9f29c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h @@ -86,42 +86,42 @@ static const struct dpu_sspp_cfg kaanapali_sspp[] = { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x97000, .len = 0x84, .features = DMA_SDM845_MASK_SDMA, - .sblk = &dpu_dma_sblk, + .sblk = &dpu_dma_sblk_v13, .xin_id = 1, .type = SSPP_TYPE_DMA, }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0xa0000, .len = 0x84, .features = DMA_SDM845_MASK_SDMA, - .sblk = &dpu_dma_sblk, + .sblk = &dpu_dma_sblk_v13, .xin_id = 5, .type = SSPP_TYPE_DMA, }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0xa9000, .len = 0x84, .features = DMA_SDM845_MASK_SDMA, - .sblk = &dpu_dma_sblk, + .sblk = &dpu_dma_sblk_v13, .xin_id = 9, .type = SSPP_TYPE_DMA, }, { .name = "sspp_11", .id = SSPP_DMA3, .base = 0xb2000, .len = 0x84, .features = DMA_SDM845_MASK_SDMA, - .sblk = &dpu_dma_sblk, + .sblk = &dpu_dma_sblk_v13, .xin_id = 13, .type = SSPP_TYPE_DMA, }, { .name = "sspp_12", .id = SSPP_DMA4, .base = 0xbb000, .len = 0x84, .features = DMA_CURSOR_SDM845_MASK_SDMA, - .sblk = &dpu_dma_sblk, + .sblk = &dpu_dma_sblk_v13, .xin_id = 14, .type = SSPP_TYPE_DMA, }, { .name = "sspp_13", .id = SSPP_DMA5, .base = 0xc4000, .len = 0x84, .features = DMA_CURSOR_SDM845_MASK_SDMA, - .sblk = &dpu_dma_sblk, + .sblk = &dpu_dma_sblk_v13, .xin_id = 15, .type = SSPP_TYPE_DMA, }, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index 13cc658065c5..fea173e37464 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -34,7 +34,7 @@ enum dpu_perf_mode { /** * dpu_core_perf_adjusted_mode_clk - Adjust given mode clock rate according to * the perf clock factor. - * @crtc_clk_rate - Unadjusted mode clock rate + * @mode_clk_rate: unadjusted mode clock rate * @perf_cfg: performance configuration */ u64 dpu_core_perf_adjusted_mode_clk(u64 mode_clk_rate, @@ -394,6 +394,10 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc, trace_dpu_core_perf_update_clk(kms->dev, !crtc->enabled, clk_rate); + /* If we're going offline, PM callbacks will disable the clocks instead */ + if (!clk_rate) + return 0; + clk_rate = min(clk_rate, kms->perf.max_core_clk_rate); ret = dev_pm_opp_set_rate(&kms->pdev->dev, clk_rate); if (ret) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 778e231d4967..1f20695f81e3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -710,8 +710,7 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc, if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) topology->num_cdm++; } else if (disp_info->intf_type == INTF_DP) { - if (msm_dp_is_yuv_420_enabled(priv->kms->dp[disp_info->h_tile_instance[0]], - adj_mode)) + if (drm_mode_is_420_only(&connector->display_info, adj_mode)) topology->num_cdm++; } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 2e10add84fd7..9a993cdfab85 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -303,6 +303,16 @@ static const u32 wb2_formats_rgb_yuv[] = { .num_formats = ARRAY_SIZE(plane_formats), \ } +#define _DMA_SBLK_V13() \ + { \ + .sspp_rec0_blk = {.name = "sspp_rec0", \ + .base = 0x1000, .len = 0x180,}, \ + .sspp_rec1_blk = {.name = "sspp_rec1", \ + .base = 0x3000, .len = 0x180,}, \ + .format_list = plane_formats, \ + .num_formats = ARRAY_SIZE(plane_formats), \ + } + static const struct dpu_rotation_cfg dpu_rot_sc7280_cfg_v2 = { .rot_maxheight = 1088, .rot_num_formats = ARRAY_SIZE(rotation_v2_formats), @@ -353,6 +363,8 @@ static const struct dpu_sspp_sub_blks dpu_rgb_sblk = _RGB_SBLK(); static const struct dpu_sspp_sub_blks dpu_dma_sblk = _DMA_SBLK(); +static const struct dpu_sspp_sub_blks dpu_dma_sblk_v13 = _DMA_SBLK_V13(); + /************************************************************* * MIXER sub blocks config *************************************************************/ diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 7726edb0d4ed..9b1d1982e683 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -398,7 +398,7 @@ static int mdp4_kms_init(struct drm_device *dev) ret = mdp_kms_init(&mdp4_kms->base, &kms_funcs); if (ret) { DRM_DEV_ERROR(dev->dev, "failed to init kms\n"); - goto fail; + return ret; } kms = priv->kms; @@ -409,7 +409,7 @@ static int mdp4_kms_init(struct drm_device *dev) ret = regulator_enable(mdp4_kms->vdd); if (ret) { DRM_DEV_ERROR(dev->dev, "failed to enable regulator vdd: %d\n", ret); - goto fail; + return ret; } } @@ -421,7 +421,7 @@ static int mdp4_kms_init(struct drm_device *dev) DRM_DEV_ERROR(dev->dev, "unexpected MDP version: v%d.%d\n", major, minor); ret = -ENXIO; - goto fail; + return ret; } mdp4_kms->rev = minor; @@ -430,7 +430,7 @@ static int mdp4_kms_init(struct drm_device *dev) if (!mdp4_kms->lut_clk) { DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n"); ret = -ENODEV; - goto fail; + return ret; } clk_set_rate(mdp4_kms->lut_clk, max_clk); } @@ -452,7 +452,7 @@ static int mdp4_kms_init(struct drm_device *dev) vm = msm_kms_init_vm(mdp4_kms->dev, NULL); if (IS_ERR(vm)) { ret = PTR_ERR(vm); - goto fail; + return ret; } kms->vm = vm; @@ -460,22 +460,22 @@ static int mdp4_kms_init(struct drm_device *dev) ret = modeset_init(mdp4_kms); if (ret) { DRM_DEV_ERROR(dev->dev, "modeset_init failed: %d\n", ret); - goto fail; + return ret; } - mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC | MSM_BO_SCANOUT); + mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC | MSM_BO_SCANOUT, NULL); if (IS_ERR(mdp4_kms->blank_cursor_bo)) { ret = PTR_ERR(mdp4_kms->blank_cursor_bo); DRM_DEV_ERROR(dev->dev, "could not allocate blank-cursor bo: %d\n", ret); mdp4_kms->blank_cursor_bo = NULL; - goto fail; + return ret; } ret = msm_gem_get_and_pin_iova(mdp4_kms->blank_cursor_bo, kms->vm, &mdp4_kms->blank_cursor_iova); if (ret) { DRM_DEV_ERROR(dev->dev, "could not pin blank-cursor bo: %d\n", ret); - goto fail; + return ret; } dev->mode_config.min_width = 0; @@ -484,12 +484,6 @@ static int mdp4_kms_init(struct drm_device *dev) dev->mode_config.max_height = 2048; return 0; - -fail: - if (kms) - mdp4_destroy(kms); - - return ret; } static const struct dev_pm_ops mdp4_pm_ops = { diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 0a004ab9fc85..3934cd060b27 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -517,7 +517,7 @@ static int mdp5_kms_init(struct drm_device *dev) ret = mdp_kms_init(&mdp5_kms->base, &kms_funcs); if (ret) { DRM_DEV_ERROR(&pdev->dev, "failed to init kms\n"); - goto fail; + return ret; } config = mdp5_cfg_get_config(mdp5_kms->cfg); @@ -540,7 +540,7 @@ static int mdp5_kms_init(struct drm_device *dev) vm = msm_kms_init_vm(mdp5_kms->dev, pdev->dev.parent); if (IS_ERR(vm)) { ret = PTR_ERR(vm); - goto fail; + return ret; } kms->vm = vm; @@ -550,7 +550,7 @@ static int mdp5_kms_init(struct drm_device *dev) ret = modeset_init(mdp5_kms); if (ret) { DRM_DEV_ERROR(&pdev->dev, "modeset_init failed: %d\n", ret); - goto fail; + return ret; } dev->mode_config.min_width = 0; @@ -562,11 +562,6 @@ static int mdp5_kms_init(struct drm_device *dev) dev->vblank_disable_immediate = true; return 0; -fail: - if (kms) - mdp5_kms_destroy(kms); - - return ret; } static void mdp5_destroy(struct mdp5_kms *mdp5_kms) diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 41018e82efa1..df222943ae57 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -284,10 +284,8 @@ int msm_dp_audio_prepare(struct drm_bridge *bridge, * such cases check for connection status and bail out if not * connected. */ - if (!msm_dp_display->power_on) { - rc = -EINVAL; + if (!msm_dp_display->power_on) goto end; - } audio = msm_dp_audio_get_data(msm_dp_display); if (IS_ERR(audio)) { diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 86ef8c89ad44..59070f399e2d 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -114,7 +114,6 @@ struct msm_dp_ctrl_private { struct drm_device *drm_dev; struct device *dev; struct drm_dp_aux *aux; - struct msm_dp_panel *panel; struct msm_dp_link *link; void __iomem *ahb_base; void __iomem *link_base; @@ -202,7 +201,8 @@ static int msm_dp_aux_link_configure(struct drm_dp_aux *aux, /* * NOTE: resetting DP controller will also clear any pending HPD related interrupts */ -void msm_dp_ctrl_reset(struct msm_dp_ctrl *msm_dp_ctrl) +void msm_dp_ctrl_reset(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel) { struct msm_dp_ctrl_private *ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); @@ -217,10 +217,9 @@ void msm_dp_ctrl_reset(struct msm_dp_ctrl *msm_dp_ctrl) sw_reset &= ~DP_SW_RESET; msm_dp_write_ahb(ctrl, REG_DP_SW_RESET, sw_reset); - if (!ctrl->hw_revision) { + if (!ctrl->hw_revision) ctrl->hw_revision = msm_dp_read_ahb(ctrl, REG_DP_HW_VERSION); - ctrl->panel->hw_revision = ctrl->hw_revision; - } + panel->hw_revision = ctrl->hw_revision; } static u32 msm_dp_ctrl_get_aux_interrupt(struct msm_dp_ctrl_private *ctrl) @@ -388,26 +387,49 @@ void msm_dp_ctrl_push_idle(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "mainlink off\n"); } -static void msm_dp_ctrl_config_ctrl(struct msm_dp_ctrl_private *ctrl) +static void msm_dp_ctrl_config_ctrl_streams(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *msm_dp_panel) { u32 config = 0, tbd; - const u8 *dpcd = ctrl->panel->dpcd; + + /* + * RMW: called from atomic_enable(), serialized by the DRM atomic framework. + * Clear stream-specific fields before OR-ing to avoid bit accumulation. + */ + config = msm_dp_read_link(ctrl, REG_DP_CONFIGURATION_CTRL); + config &= ~(DP_CONFIGURATION_CTRL_RGB_YUV_MASK | + DP_CONFIGURATION_CTRL_BPC_MASK | + DP_CONFIGURATION_CTRL_SEND_VSC); + + if (msm_dp_panel->msm_dp_mode.out_fmt_is_yuv_420) + config |= DP_CONFIGURATION_CTRL_RGB_YUV; /* YUV420 */ + + tbd = msm_dp_link_get_test_bits_depth(ctrl->link, + msm_dp_panel->msm_dp_mode.bpp); + + config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; + + if (msm_dp_panel->psr_cap.version) + config |= DP_CONFIGURATION_CTRL_SEND_VSC; + + drm_dbg_dp(ctrl->drm_dev, "stream DP_CONFIGURATION_CTRL=0x%x\n", config); + + msm_dp_write_link(ctrl, REG_DP_CONFIGURATION_CTRL, config); +} + +static void msm_dp_ctrl_config_ctrl_link(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) +{ + u32 config = 0; + const u8 *dpcd = panel->dpcd; /* Default-> LSCLK DIV: 1/4 LCLK */ config |= (2 << DP_CONFIGURATION_CTRL_LSCLK_DIV_SHIFT); - if (ctrl->panel->msm_dp_mode.out_fmt_is_yuv_420) - config |= DP_CONFIGURATION_CTRL_RGB_YUV; /* YUV420 */ - /* Scrambler reset enable */ if (drm_dp_alternate_scrambler_reset_cap(dpcd)) config |= DP_CONFIGURATION_CTRL_ASSR; - tbd = msm_dp_link_get_test_bits_depth(ctrl->link, - ctrl->panel->msm_dp_mode.bpp); - - config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; - /* Num of Lanes */ config |= ((ctrl->link->link_params.num_lanes - 1) << DP_CONFIGURATION_CTRL_NUM_OF_LANES_SHIFT); @@ -421,10 +443,7 @@ static void msm_dp_ctrl_config_ctrl(struct msm_dp_ctrl_private *ctrl) config |= DP_CONFIGURATION_CTRL_STATIC_DYNAMIC_CN; config |= DP_CONFIGURATION_CTRL_SYNC_ASYNC_CLK; - if (ctrl->panel->psr_cap.version) - config |= DP_CONFIGURATION_CTRL_SEND_VSC; - - drm_dbg_dp(ctrl->drm_dev, "DP_CONFIGURATION_CTRL=0x%x\n", config); + drm_dbg_dp(ctrl->drm_dev, "link DP_CONFIGURATION_CTRL=0x%x\n", config); msm_dp_write_link(ctrl, REG_DP_CONFIGURATION_CTRL, config); } @@ -443,16 +462,13 @@ static void msm_dp_ctrl_lane_mapping(struct msm_dp_ctrl_private *ctrl) ln_mapping); } -static void msm_dp_ctrl_configure_source_params(struct msm_dp_ctrl_private *ctrl) +static void msm_dp_ctrl_config_misc1_misc0(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *msm_dp_panel) { u32 colorimetry_cfg, test_bits_depth, misc_val; - msm_dp_ctrl_lane_mapping(ctrl); - msm_dp_setup_peripheral_flush(ctrl); - - msm_dp_ctrl_config_ctrl(ctrl); - - test_bits_depth = msm_dp_link_get_test_bits_depth(ctrl->link, ctrl->panel->msm_dp_mode.bpp); + test_bits_depth = msm_dp_link_get_test_bits_depth(ctrl->link, + msm_dp_panel->msm_dp_mode.bpp); colorimetry_cfg = msm_dp_link_get_colorimetry_config(ctrl->link); misc_val = msm_dp_read_link(ctrl, REG_DP_MISC1_MISC0); @@ -466,8 +482,16 @@ static void msm_dp_ctrl_configure_source_params(struct msm_dp_ctrl_private *ctrl drm_dbg_dp(ctrl->drm_dev, "misc settings = 0x%x\n", misc_val); msm_dp_write_link(ctrl, REG_DP_MISC1_MISC0, misc_val); +} - msm_dp_panel_timing_cfg(ctrl->panel, ctrl->msm_dp_ctrl.wide_bus_en); +static void msm_dp_ctrl_configure_source_params(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) +{ + msm_dp_ctrl_config_ctrl_streams(ctrl, panel); + + msm_dp_ctrl_config_misc1_misc0(ctrl, panel); + + msm_dp_panel_timing_cfg(panel, ctrl->msm_dp_ctrl.wide_bus_en); } /* @@ -1237,20 +1261,21 @@ static void _dp_ctrl_calc_tu(struct msm_dp_ctrl_private *ctrl, } static void msm_dp_ctrl_calc_tu_parameters(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, struct msm_dp_vc_tu_mapping_table *tu_table) { struct msm_dp_tu_calc_input in; - struct drm_display_mode *drm_mode; + const struct drm_display_mode *drm_mode; - drm_mode = &ctrl->panel->msm_dp_mode.drm_mode; + drm_mode = &panel->msm_dp_mode.drm_mode; in.lclk = ctrl->link->link_params.rate / 1000; in.pclk_khz = drm_mode->clock; in.hactive = drm_mode->hdisplay; in.hporch = drm_mode->htotal - drm_mode->hdisplay; in.nlanes = ctrl->link->link_params.num_lanes; - in.bpp = ctrl->panel->msm_dp_mode.bpp; - in.pixel_enc = ctrl->panel->msm_dp_mode.out_fmt_is_yuv_420 ? 420 : 444; + in.bpp = panel->msm_dp_mode.bpp; + in.pixel_enc = panel->msm_dp_mode.out_fmt_is_yuv_420 ? 420 : 444; in.dsc_en = 0; in.async_en = 0; in.fec_en = 0; @@ -1260,14 +1285,15 @@ static void msm_dp_ctrl_calc_tu_parameters(struct msm_dp_ctrl_private *ctrl, _dp_ctrl_calc_tu(ctrl, &in, tu_table); } -static void msm_dp_ctrl_setup_tr_unit(struct msm_dp_ctrl_private *ctrl) +static void msm_dp_ctrl_setup_tr_unit(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { u32 msm_dp_tu = 0x0; u32 valid_boundary = 0x0; u32 valid_boundary2 = 0x0; struct msm_dp_vc_tu_mapping_table tu_calc_table; - msm_dp_ctrl_calc_tu_parameters(ctrl, &tu_calc_table); + msm_dp_ctrl_calc_tu_parameters(ctrl, panel, &tu_calc_table); msm_dp_tu |= tu_calc_table.tu_size_minus1; valid_boundary |= tu_calc_table.valid_boundary_link; @@ -1419,6 +1445,7 @@ static int msm_dp_ctrl_set_pattern_state_bit(struct msm_dp_ctrl_private *ctrl, } static int msm_dp_ctrl_link_train_1(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, int *training_step, enum drm_dp_phy dp_phy) { int delay_us; @@ -1427,7 +1454,7 @@ static int msm_dp_ctrl_link_train_1(struct msm_dp_ctrl_private *ctrl, int const maximum_retries = 4; delay_us = drm_dp_read_clock_recovery_delay(ctrl->aux, - ctrl->panel->dpcd, dp_phy, false); + panel->dpcd, dp_phy, false); msm_dp_write_link(ctrl, REG_DP_STATE_CTRL, 0); @@ -1513,14 +1540,15 @@ static int msm_dp_ctrl_link_rate_down_shift(struct msm_dp_ctrl_private *ctrl) return ret; } -static int msm_dp_ctrl_link_lane_down_shift(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_link_lane_down_shift(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { if (ctrl->link->link_params.num_lanes == 1) return -1; ctrl->link->link_params.num_lanes /= 2; - ctrl->link->link_params.rate = ctrl->panel->link_info.rate; + ctrl->link->link_params.rate = panel->link_info.rate; ctrl->link->phy_params.p_level = 0; ctrl->link->phy_params.v_level = 0; @@ -1529,6 +1557,7 @@ static int msm_dp_ctrl_link_lane_down_shift(struct msm_dp_ctrl_private *ctrl) } static void msm_dp_ctrl_clear_training_pattern(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, enum drm_dp_phy dp_phy) { int delay_us; @@ -1536,11 +1565,12 @@ static void msm_dp_ctrl_clear_training_pattern(struct msm_dp_ctrl_private *ctrl, msm_dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_DISABLE, dp_phy); delay_us = drm_dp_read_channel_eq_delay(ctrl->aux, - ctrl->panel->dpcd, dp_phy, false); + panel->dpcd, dp_phy, false); fsleep(delay_us); } static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, int *training_step, enum drm_dp_phy dp_phy) { int delay_us; @@ -1551,16 +1581,16 @@ static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, u8 link_status[DP_LINK_STATUS_SIZE]; delay_us = drm_dp_read_channel_eq_delay(ctrl->aux, - ctrl->panel->dpcd, dp_phy, false); + panel->dpcd, dp_phy, false); msm_dp_write_link(ctrl, REG_DP_STATE_CTRL, 0); *training_step = DP_TRAINING_2; - if (drm_dp_tps4_supported(ctrl->panel->dpcd)) { + if (drm_dp_tps4_supported(panel->dpcd)) { pattern = DP_TRAINING_PATTERN_4; state_ctrl_bit = 4; - } else if (drm_dp_tps3_supported(ctrl->panel->dpcd)) { + } else if (drm_dp_tps3_supported(panel->dpcd)) { pattern = DP_TRAINING_PATTERN_3; state_ctrl_bit = 3; } else { @@ -1597,18 +1627,19 @@ static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, } static int msm_dp_ctrl_link_train_1_2(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, int *training_step, enum drm_dp_phy dp_phy) { int ret; - ret = msm_dp_ctrl_link_train_1(ctrl, training_step, dp_phy); + ret = msm_dp_ctrl_link_train_1(ctrl, panel, training_step, dp_phy); if (ret) { DRM_ERROR("link training #1 on phy %d failed. ret=%d\n", dp_phy, ret); return ret; } drm_dbg_dp(ctrl->drm_dev, "link training #1 on phy %d successful\n", dp_phy); - ret = msm_dp_ctrl_link_train_2(ctrl, training_step, dp_phy); + ret = msm_dp_ctrl_link_train_2(ctrl, panel, training_step, dp_phy); if (ret) { DRM_ERROR("link training #2 on phy %d failed. ret=%d\n", dp_phy, ret); return ret; @@ -1619,16 +1650,18 @@ static int msm_dp_ctrl_link_train_1_2(struct msm_dp_ctrl_private *ctrl, } static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, int *training_step) { int i; int ret = 0; - const u8 *dpcd = ctrl->panel->dpcd; + const u8 *dpcd = panel->dpcd; u8 encoding[] = { 0, DP_SET_ANSI_8B10B }; u8 assr; struct msm_dp_link_info link_info = {0}; - msm_dp_ctrl_config_ctrl(ctrl); + msm_dp_ctrl_config_ctrl_link(ctrl, panel); + msm_dp_ctrl_config_ctrl_streams(ctrl, panel); link_info.num_lanes = ctrl->link->link_params.num_lanes; link_info.rate = ctrl->link->link_params.rate; @@ -1651,8 +1684,8 @@ static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, for (i = ctrl->link->lttpr_count - 1; i >= 0; i--) { enum drm_dp_phy dp_phy = DP_PHY_LTTPR(i); - ret = msm_dp_ctrl_link_train_1_2(ctrl, training_step, dp_phy); - msm_dp_ctrl_clear_training_pattern(ctrl, dp_phy); + ret = msm_dp_ctrl_link_train_1_2(ctrl, panel, training_step, dp_phy); + msm_dp_ctrl_clear_training_pattern(ctrl, panel, dp_phy); if (ret) break; @@ -1663,7 +1696,7 @@ static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, goto end; } - ret = msm_dp_ctrl_link_train_1_2(ctrl, training_step, DP_PHY_DPRX); + ret = msm_dp_ctrl_link_train_1_2(ctrl, panel, training_step, DP_PHY_DPRX); if (ret) { DRM_ERROR("link training on sink failed. ret=%d\n", ret); goto end; @@ -1676,6 +1709,7 @@ static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, } static int msm_dp_ctrl_setup_main_link(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel, int *training_step) { int ret = 0; @@ -1691,7 +1725,7 @@ static int msm_dp_ctrl_setup_main_link(struct msm_dp_ctrl_private *ctrl, * a link training pattern, we have to first do soft reset. */ - ret = msm_dp_ctrl_link_train(ctrl, training_step); + ret = msm_dp_ctrl_link_train(ctrl, panel, training_step); return ret; } @@ -1790,11 +1824,12 @@ static void msm_dp_ctrl_link_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) str_on_off(ctrl->core_clks_on)); } -static int msm_dp_ctrl_enable_mainlink_clocks(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_enable_mainlink_clocks(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { int ret = 0; struct phy *phy = ctrl->phy; - const u8 *dpcd = ctrl->panel->dpcd; + const u8 *dpcd = panel->dpcd; ctrl->phy_opts.dp.lanes = ctrl->link->link_params.num_lanes; ctrl->phy_opts.dp.link_rate = ctrl->link->link_params.rate / 100; @@ -1846,13 +1881,14 @@ static void msm_dp_ctrl_psr_exit(struct msm_dp_ctrl_private *ctrl) msm_dp_write_link(ctrl, REG_PSR_CMD, cmd); } -void msm_dp_ctrl_config_psr(struct msm_dp_ctrl *msm_dp_ctrl) +void msm_dp_ctrl_config_psr(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel) { struct msm_dp_ctrl_private *ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); u32 cfg; - if (!ctrl->panel->psr_cap.version) + if (!panel->psr_cap.version) return; /* enable PSR1 function */ @@ -1867,12 +1903,13 @@ void msm_dp_ctrl_config_psr(struct msm_dp_ctrl *msm_dp_ctrl) drm_dp_dpcd_write(ctrl->aux, DP_PSR_EN_CFG, &cfg, 1); } -void msm_dp_ctrl_set_psr(struct msm_dp_ctrl *msm_dp_ctrl, bool enter) +void msm_dp_ctrl_set_psr(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel, bool enter) { struct msm_dp_ctrl_private *ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); - if (!ctrl->panel->psr_cap.version) + if (!panel->psr_cap.version) return; /* @@ -1942,7 +1979,8 @@ void msm_dp_ctrl_phy_exit(struct msm_dp_ctrl *msm_dp_ctrl) phy_exit(phy); } -static int msm_dp_ctrl_reinitialize_mainlink(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_reinitialize_mainlink(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { struct phy *phy = ctrl->phy; int ret = 0; @@ -1950,20 +1988,19 @@ static int msm_dp_ctrl_reinitialize_mainlink(struct msm_dp_ctrl_private *ctrl) msm_dp_ctrl_mainlink_disable(ctrl); ctrl->phy_opts.dp.lanes = ctrl->link->link_params.num_lanes; phy_configure(phy, &ctrl->phy_opts); + /* * Disable and re-enable the mainlink clock since the * link clock might have been adjusted as part of the * link maintenance. */ - dev_pm_opp_set_rate(ctrl->dev, 0); - msm_dp_ctrl_link_clk_disable(&ctrl->msm_dp_ctrl); phy_power_off(phy); /* hw recommended delay before re-enabling clocks */ msleep(20); - ret = msm_dp_ctrl_enable_mainlink_clocks(ctrl); + ret = msm_dp_ctrl_enable_mainlink_clocks(ctrl, panel); if (ret) { DRM_ERROR("Failed to enable mainlink clks. ret=%d\n", ret); return ret; @@ -1972,7 +2009,8 @@ static int msm_dp_ctrl_reinitialize_mainlink(struct msm_dp_ctrl_private *ctrl) return ret; } -static int msm_dp_ctrl_deinitialize_mainlink(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_deinitialize_mainlink(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { struct phy *phy; @@ -1980,9 +2018,8 @@ static int msm_dp_ctrl_deinitialize_mainlink(struct msm_dp_ctrl_private *ctrl) msm_dp_ctrl_mainlink_disable(ctrl); - msm_dp_ctrl_reset(&ctrl->msm_dp_ctrl); + msm_dp_ctrl_reset(&ctrl->msm_dp_ctrl, panel); - dev_pm_opp_set_rate(ctrl->dev, 0); msm_dp_ctrl_link_clk_disable(&ctrl->msm_dp_ctrl); phy_power_off(phy); @@ -1994,7 +2031,8 @@ static int msm_dp_ctrl_deinitialize_mainlink(struct msm_dp_ctrl_private *ctrl) return 0; } -static int msm_dp_ctrl_link_maintenance(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_link_maintenance(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { int ret = 0; int training_step = DP_TRAINING_NONE; @@ -2004,11 +2042,11 @@ static int msm_dp_ctrl_link_maintenance(struct msm_dp_ctrl_private *ctrl) ctrl->link->phy_params.p_level = 0; ctrl->link->phy_params.v_level = 0; - ret = msm_dp_ctrl_setup_main_link(ctrl, &training_step); + ret = msm_dp_ctrl_setup_main_link(ctrl, panel, &training_step); if (ret) goto end; - msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); + msm_dp_ctrl_clear_training_pattern(ctrl, panel, DP_PHY_DPRX); msm_dp_write_link(ctrl, REG_DP_STATE_CTRL, DP_STATE_CTRL_SEND_VIDEO); @@ -2152,7 +2190,43 @@ static bool msm_dp_ctrl_send_phy_test_pattern(struct msm_dp_ctrl_private *ctrl) return success; } -static int msm_dp_ctrl_process_phy_test_request(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_on_pixel_clk(struct msm_dp_ctrl_private *ctrl, unsigned long pixel_rate) +{ + int ret; + + ret = clk_set_rate(ctrl->pixel_clk, pixel_rate * 1000); + if (ret) { + DRM_ERROR("Failed to set pixel clock rate. ret=%d\n", ret); + return ret; + } + + if (WARN_ON_ONCE(ctrl->stream_clks_on)) + return 0; + + ret = clk_prepare_enable(ctrl->pixel_clk); + if (ret) { + DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); + return ret; + } + ctrl->stream_clks_on = true; + + return ret; +} + +void msm_dp_ctrl_off_pixel_clk(struct msm_dp_ctrl *msm_dp_ctrl) +{ + struct msm_dp_ctrl_private *ctrl; + + ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); + + if (ctrl->stream_clks_on) { + clk_disable_unprepare(ctrl->pixel_clk); + ctrl->stream_clks_on = false; + } +} + +static int msm_dp_ctrl_process_phy_test_request(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { int ret; unsigned long pixel_rate; @@ -2168,38 +2242,27 @@ static int msm_dp_ctrl_process_phy_test_request(struct msm_dp_ctrl_private *ctrl * running. Add the global reset just before disabling the * link clocks and core clocks. */ - msm_dp_ctrl_off(&ctrl->msm_dp_ctrl); + msm_dp_ctrl_off_pixel_clk(&ctrl->msm_dp_ctrl); + msm_dp_ctrl_off_link(&ctrl->msm_dp_ctrl, panel); - ret = msm_dp_ctrl_on_link(&ctrl->msm_dp_ctrl); + ret = msm_dp_ctrl_on_link(&ctrl->msm_dp_ctrl, panel); if (ret) { DRM_ERROR("failed to enable DP link controller\n"); return ret; } - pixel_rate = ctrl->panel->msm_dp_mode.drm_mode.clock; - ret = clk_set_rate(ctrl->pixel_clk, pixel_rate * 1000); - if (ret) { - DRM_ERROR("Failed to set pixel clock rate. ret=%d\n", ret); + pixel_rate = panel->msm_dp_mode.drm_mode.clock; + ret = msm_dp_ctrl_on_pixel_clk(ctrl, pixel_rate); + if (ret) return ret; - } - - if (ctrl->stream_clks_on) { - drm_dbg_dp(ctrl->drm_dev, "pixel clks already enabled\n"); - } else { - ret = clk_prepare_enable(ctrl->pixel_clk); - if (ret) { - DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); - return ret; - } - ctrl->stream_clks_on = true; - } msm_dp_ctrl_send_phy_test_pattern(ctrl); return 0; } -void msm_dp_ctrl_handle_sink_request(struct msm_dp_ctrl *msm_dp_ctrl) +void msm_dp_ctrl_handle_sink_request(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel) { struct msm_dp_ctrl_private *ctrl; u32 sink_request = 0x0; @@ -2214,14 +2277,14 @@ void msm_dp_ctrl_handle_sink_request(struct msm_dp_ctrl *msm_dp_ctrl) if (sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) { drm_dbg_dp(ctrl->drm_dev, "PHY_TEST_PATTERN request\n"); - if (msm_dp_ctrl_process_phy_test_request(ctrl)) { + if (msm_dp_ctrl_process_phy_test_request(ctrl, panel)) { DRM_ERROR("process phy_test_req failed\n"); return; } } if (sink_request & DP_LINK_STATUS_UPDATED) { - if (msm_dp_ctrl_link_maintenance(ctrl)) { + if (msm_dp_ctrl_link_maintenance(ctrl, panel)) { DRM_ERROR("LM failed: TEST_LINK_TRAINING\n"); return; } @@ -2229,7 +2292,7 @@ void msm_dp_ctrl_handle_sink_request(struct msm_dp_ctrl *msm_dp_ctrl) if (sink_request & DP_TEST_LINK_TRAINING) { msm_dp_link_send_test_response(ctrl->link); - if (msm_dp_ctrl_link_maintenance(ctrl)) { + if (msm_dp_ctrl_link_maintenance(ctrl, panel)) { DRM_ERROR("LM failed: TEST_LINK_TRAINING\n"); return; } @@ -2265,7 +2328,8 @@ static bool msm_dp_ctrl_channel_eq_ok(struct msm_dp_ctrl_private *ctrl) return drm_dp_channel_eq_ok(link_status, num_lanes); } -int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) +int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel) { int rc = 0; struct msm_dp_ctrl_private *ctrl; @@ -2281,8 +2345,8 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); - rate = ctrl->panel->link_info.rate; - pixel_rate = ctrl->panel->msm_dp_mode.drm_mode.clock; + rate = panel->link_info.rate; + pixel_rate = panel->msm_dp_mode.drm_mode.clock; msm_dp_ctrl_core_clk_enable(&ctrl->msm_dp_ctrl); @@ -2294,8 +2358,8 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) } else { ctrl->link->link_params.rate = rate; ctrl->link->link_params.num_lanes = - ctrl->panel->link_info.num_lanes; - if (ctrl->panel->msm_dp_mode.out_fmt_is_yuv_420) + panel->link_info.num_lanes; + if (panel->msm_dp_mode.out_fmt_is_yuv_420) pixel_rate >>= 1; } @@ -2303,13 +2367,13 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) ctrl->link->link_params.rate, ctrl->link->link_params.num_lanes, pixel_rate); - rc = msm_dp_ctrl_enable_mainlink_clocks(ctrl); + rc = msm_dp_ctrl_enable_mainlink_clocks(ctrl, panel); if (rc) return rc; while (--link_train_max_retries) { training_step = DP_TRAINING_NONE; - rc = msm_dp_ctrl_setup_main_link(ctrl, &training_step); + rc = msm_dp_ctrl_setup_main_link(ctrl, panel, &training_step); if (rc == 0) { /* training completed successfully */ break; @@ -2328,7 +2392,7 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) * some lanes are ready, * reduce lane number */ - rc = msm_dp_ctrl_link_lane_down_shift(ctrl); + rc = msm_dp_ctrl_link_lane_down_shift(ctrl, panel); if (rc < 0) { /* lane == 1 already */ /* end with failure */ break; @@ -2349,7 +2413,7 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) ctrl->link->link_params.num_lanes)) rc = msm_dp_ctrl_link_rate_down_shift(ctrl); else - rc = msm_dp_ctrl_link_lane_down_shift(ctrl); + rc = msm_dp_ctrl_link_lane_down_shift(ctrl, panel); if (rc < 0) { /* end with failure */ @@ -2357,10 +2421,10 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) } /* stop link training before start re training */ - msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); + msm_dp_ctrl_clear_training_pattern(ctrl, panel, DP_PHY_DPRX); } - rc = msm_dp_ctrl_reinitialize_mainlink(ctrl); + rc = msm_dp_ctrl_reinitialize_mainlink(ctrl, panel); if (rc) { DRM_ERROR("Failed to reinitialize mainlink. rc=%d\n", rc); break; @@ -2381,20 +2445,21 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) * link training failed * end txing train pattern here */ - msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); + msm_dp_ctrl_clear_training_pattern(ctrl, panel, DP_PHY_DPRX); - msm_dp_ctrl_deinitialize_mainlink(ctrl); + msm_dp_ctrl_deinitialize_mainlink(ctrl, panel); rc = -ECONNRESET; } return rc; } -static int msm_dp_ctrl_link_retrain(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_link_retrain(struct msm_dp_ctrl_private *ctrl, + struct msm_dp_panel *panel) { int training_step = DP_TRAINING_NONE; - return msm_dp_ctrl_setup_main_link(ctrl, &training_step); + return msm_dp_ctrl_setup_main_link(ctrl, panel, &training_step); } static void msm_dp_ctrl_config_msa(struct msm_dp_ctrl_private *ctrl, @@ -2465,7 +2530,44 @@ static void msm_dp_ctrl_config_msa(struct msm_dp_ctrl_private *ctrl, msm_dp_write_link(ctrl, REG_DP_SOFTWARE_NVID, nvid); } -int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, bool force_link_train) +int msm_dp_ctrl_prepare_stream_on(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel, + bool force_link_train) +{ + int ret = 0; + struct msm_dp_ctrl_private *ctrl; + + if (!msm_dp_ctrl) + return -EINVAL; + + ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); + + drm_dbg_dp(ctrl->drm_dev, "rate=%d, num_lanes=%d\n", + ctrl->link->link_params.rate, + ctrl->link->link_params.num_lanes); + + drm_dbg_dp(ctrl->drm_dev, + "core_clk_on=%d link_clk_on=%d stream_clk_on=%d\n", + ctrl->core_clks_on, ctrl->link_clks_on, ctrl->stream_clks_on); + + if (!ctrl->link_clks_on) { /* link clk is off */ + ret = msm_dp_ctrl_enable_mainlink_clocks(ctrl, panel); + if (ret) { + DRM_ERROR("Failed to start link clocks. ret=%d\n", ret); + return ret; + } + } + + if (force_link_train || !msm_dp_ctrl_channel_eq_ok(ctrl)) + msm_dp_ctrl_link_retrain(ctrl, panel); + + /* stop txing train pattern to end link training */ + msm_dp_ctrl_clear_training_pattern(ctrl, panel, DP_PHY_DPRX); + + return ret; +} + +int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, struct msm_dp_panel *panel) { int ret = 0; bool mainlink_ready = false; @@ -2478,49 +2580,17 @@ int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, bool force_link_train ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); - pixel_rate = pixel_rate_orig = ctrl->panel->msm_dp_mode.drm_mode.clock; + pixel_rate_orig = panel->msm_dp_mode.drm_mode.clock; + pixel_rate = pixel_rate_orig; - if (msm_dp_ctrl->wide_bus_en || ctrl->panel->msm_dp_mode.out_fmt_is_yuv_420) + if (msm_dp_ctrl->wide_bus_en || panel->msm_dp_mode.out_fmt_is_yuv_420) pixel_rate >>= 1; - drm_dbg_dp(ctrl->drm_dev, "rate=%d, num_lanes=%d, pixel_rate=%lu\n", - ctrl->link->link_params.rate, - ctrl->link->link_params.num_lanes, pixel_rate); + drm_dbg_dp(ctrl->drm_dev, "pixel_rate=%lu\n", pixel_rate); - drm_dbg_dp(ctrl->drm_dev, - "core_clk_on=%d link_clk_on=%d stream_clk_on=%d\n", - ctrl->core_clks_on, ctrl->link_clks_on, ctrl->stream_clks_on); - - if (!ctrl->link_clks_on) { /* link clk is off */ - ret = msm_dp_ctrl_enable_mainlink_clocks(ctrl); - if (ret) { - DRM_ERROR("Failed to start link clocks. ret=%d\n", ret); - goto end; - } - } - - ret = clk_set_rate(ctrl->pixel_clk, pixel_rate * 1000); - if (ret) { - DRM_ERROR("Failed to set pixel clock rate. ret=%d\n", ret); - goto end; - } - - if (ctrl->stream_clks_on) { - drm_dbg_dp(ctrl->drm_dev, "pixel clks already enabled\n"); - } else { - ret = clk_prepare_enable(ctrl->pixel_clk); - if (ret) { - DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); - goto end; - } - ctrl->stream_clks_on = true; - } - - if (force_link_train || !msm_dp_ctrl_channel_eq_ok(ctrl)) - msm_dp_ctrl_link_retrain(ctrl); - - /* stop txing train pattern to end link training */ - msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); + ret = msm_dp_ctrl_on_pixel_clk(ctrl, pixel_rate); + if (ret) + return ret; /* * Set up transfer unit values and set controller state to send @@ -2528,16 +2598,20 @@ int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, bool force_link_train */ reinit_completion(&ctrl->video_comp); - msm_dp_ctrl_configure_source_params(ctrl); + msm_dp_ctrl_lane_mapping(ctrl); + msm_dp_setup_peripheral_flush(ctrl); + msm_dp_ctrl_config_ctrl_link(ctrl, panel); + + msm_dp_ctrl_configure_source_params(ctrl, panel); msm_dp_ctrl_config_msa(ctrl, ctrl->link->link_params.rate, pixel_rate_orig, - ctrl->panel->msm_dp_mode.out_fmt_is_yuv_420); + panel->msm_dp_mode.out_fmt_is_yuv_420); - msm_dp_panel_clear_dsc_dto(ctrl->panel); + msm_dp_panel_clear_dsc_dto(panel); - msm_dp_ctrl_setup_tr_unit(ctrl); + msm_dp_ctrl_setup_tr_unit(ctrl, panel); msm_dp_write_link(ctrl, REG_DP_STATE_CTRL, DP_STATE_CTRL_SEND_VIDEO); @@ -2549,11 +2623,10 @@ int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, bool force_link_train drm_dbg_dp(ctrl->drm_dev, "mainlink %s\n", mainlink_ready ? "READY" : "NOT READY"); -end: return ret; } -void msm_dp_ctrl_off_link_stream(struct msm_dp_ctrl *msm_dp_ctrl) +void msm_dp_ctrl_reinit_phy(struct msm_dp_ctrl *msm_dp_ctrl) { struct msm_dp_ctrl_private *ctrl; struct phy *phy; @@ -2561,29 +2634,13 @@ void msm_dp_ctrl_off_link_stream(struct msm_dp_ctrl *msm_dp_ctrl) ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); phy = ctrl->phy; - msm_dp_panel_disable_vsc_sdp(ctrl->panel); - - /* set dongle to D3 (power off) mode */ - msm_dp_link_psm_config(ctrl->link, &ctrl->panel->link_info, true); - - msm_dp_ctrl_mainlink_disable(ctrl); - - if (ctrl->stream_clks_on) { - clk_disable_unprepare(ctrl->pixel_clk); - ctrl->stream_clks_on = false; - } - - dev_pm_opp_set_rate(ctrl->dev, 0); - msm_dp_ctrl_link_clk_disable(&ctrl->msm_dp_ctrl); - - phy_power_off(phy); - /* aux channel down, reinit phy */ phy_exit(phy); phy_init(phy); } -void msm_dp_ctrl_off(struct msm_dp_ctrl *msm_dp_ctrl) +void msm_dp_ctrl_off_link(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel) { struct msm_dp_ctrl_private *ctrl; struct phy *phy; @@ -2591,24 +2648,19 @@ void msm_dp_ctrl_off(struct msm_dp_ctrl *msm_dp_ctrl) ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); phy = ctrl->phy; - msm_dp_panel_disable_vsc_sdp(ctrl->panel); + msm_dp_panel_disable_vsc_sdp(panel); msm_dp_ctrl_mainlink_disable(ctrl); - msm_dp_ctrl_reset(&ctrl->msm_dp_ctrl); + msm_dp_ctrl_reset(&ctrl->msm_dp_ctrl, panel); - if (ctrl->stream_clks_on) { - clk_disable_unprepare(ctrl->pixel_clk); - ctrl->stream_clks_on = false; - } - - dev_pm_opp_set_rate(ctrl->dev, 0); msm_dp_ctrl_link_clk_disable(&ctrl->msm_dp_ctrl); phy_power_off(phy); } -irqreturn_t msm_dp_ctrl_isr(struct msm_dp_ctrl *msm_dp_ctrl) +irqreturn_t msm_dp_ctrl_isr(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel) { struct msm_dp_ctrl_private *ctrl; u32 isr; @@ -2619,7 +2671,7 @@ irqreturn_t msm_dp_ctrl_isr(struct msm_dp_ctrl *msm_dp_ctrl) ctrl = container_of(msm_dp_ctrl, struct msm_dp_ctrl_private, msm_dp_ctrl); - if (ctrl->panel->psr_cap.version) { + if (panel->psr_cap.version) { isr = msm_dp_ctrl_get_psr_interrupt(ctrl); if (isr) @@ -2708,7 +2760,7 @@ static int msm_dp_ctrl_clk_init(struct msm_dp_ctrl *msm_dp_ctrl) } struct msm_dp_ctrl *msm_dp_ctrl_get(struct device *dev, struct msm_dp_link *link, - struct msm_dp_panel *panel, struct drm_dp_aux *aux, + struct drm_dp_aux *aux, struct phy *phy, void __iomem *ahb_base, void __iomem *link_base) @@ -2716,7 +2768,7 @@ struct msm_dp_ctrl *msm_dp_ctrl_get(struct device *dev, struct msm_dp_link *link struct msm_dp_ctrl_private *ctrl; int ret; - if (!dev || !panel || !aux || !link) { + if (!dev || !aux || !link) { DRM_ERROR("invalid input\n"); return ERR_PTR(-EINVAL); } @@ -2744,7 +2796,6 @@ struct msm_dp_ctrl *msm_dp_ctrl_get(struct device *dev, struct msm_dp_link *link init_completion(&ctrl->video_comp); /* in parameters */ - ctrl->panel = panel; ctrl->aux = aux; ctrl->link = link; ctrl->dev = dev; diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h index f68bee62713f..5902cf7e746a 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.h +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h @@ -16,28 +16,37 @@ struct msm_dp_ctrl { struct phy; -int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl); -int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, bool force_link_train); -void msm_dp_ctrl_off_link_stream(struct msm_dp_ctrl *msm_dp_ctrl); -void msm_dp_ctrl_off(struct msm_dp_ctrl *msm_dp_ctrl); +int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel); +int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, struct msm_dp_panel *panel); +int msm_dp_ctrl_prepare_stream_on(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel, + bool force_link_train); +void msm_dp_ctrl_off_link(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel); +void msm_dp_ctrl_off_pixel_clk(struct msm_dp_ctrl *msm_dp_ctrl); void msm_dp_ctrl_push_idle(struct msm_dp_ctrl *msm_dp_ctrl); -irqreturn_t msm_dp_ctrl_isr(struct msm_dp_ctrl *msm_dp_ctrl); -void msm_dp_ctrl_handle_sink_request(struct msm_dp_ctrl *msm_dp_ctrl); +irqreturn_t msm_dp_ctrl_isr(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel); +void msm_dp_ctrl_handle_sink_request(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel); struct msm_dp_ctrl *msm_dp_ctrl_get(struct device *dev, struct msm_dp_link *link, - struct msm_dp_panel *panel, struct drm_dp_aux *aux, struct phy *phy, void __iomem *ahb_base, void __iomem *link_base); -void msm_dp_ctrl_reset(struct msm_dp_ctrl *msm_dp_ctrl); +void msm_dp_ctrl_reset(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel); void msm_dp_ctrl_phy_init(struct msm_dp_ctrl *msm_dp_ctrl); void msm_dp_ctrl_phy_exit(struct msm_dp_ctrl *msm_dp_ctrl); void msm_dp_ctrl_irq_phy_exit(struct msm_dp_ctrl *msm_dp_ctrl); -void msm_dp_ctrl_set_psr(struct msm_dp_ctrl *msm_dp_ctrl, bool enable); -void msm_dp_ctrl_config_psr(struct msm_dp_ctrl *msm_dp_ctrl); +void msm_dp_ctrl_set_psr(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel, bool enable); +void msm_dp_ctrl_config_psr(struct msm_dp_ctrl *msm_dp_ctrl, + struct msm_dp_panel *panel); int msm_dp_ctrl_core_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl); void msm_dp_ctrl_core_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl); @@ -45,4 +54,5 @@ void msm_dp_ctrl_core_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl); void msm_dp_ctrl_enable_irq(struct msm_dp_ctrl *msm_dp_ctrl); void msm_dp_ctrl_disable_irq(struct msm_dp_ctrl *msm_dp_ctrl); +void msm_dp_ctrl_reinit_phy(struct msm_dp_ctrl *msm_dp_ctrl); #endif /* _DP_CTRL_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index dc6f33809ca5..bc646d172abe 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -63,7 +63,6 @@ struct msm_dp_display_private { struct msm_dp_panel *panel; struct msm_dp_ctrl *ctrl; - struct msm_dp_display_mode msm_dp_mode; struct msm_dp msm_dp_display; /* wait for audio signaling */ @@ -269,6 +268,7 @@ static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) const struct drm_display_info *info = &connector->display_info; int rc = 0; u8 dpcd[DP_RECEIVER_CAP_SIZE]; + const struct drm_edid *drm_edid = NULL; rc = drm_dp_read_dpcd_caps(dp->aux, dpcd); if (rc) @@ -276,10 +276,20 @@ static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) dp->link->lttpr_count = msm_dp_display_lttpr_init(dp, dpcd); - rc = msm_dp_panel_read_sink_caps(dp->panel, connector); + rc = msm_dp_panel_read_link_caps(dp->panel, connector); if (rc) goto end; + drm_edid = drm_edid_read_ddc(connector, &dp->aux->ddc); + drm_edid_connector_update(connector, drm_edid); + + if (!drm_edid) { + DRM_ERROR("panel edid read failed\n"); + /* check edid read fail is due to unplug */ + if (!msm_dp_aux_is_link_connected(dp->aux)) + return -ETIMEDOUT; + } + msm_dp_link_process_request(dp->link); if (!dp->msm_dp_display.is_edp) @@ -291,7 +301,7 @@ static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) dp->msm_dp_display.psr_supported = dp->panel->psr_cap.version && psr_enabled; dp->audio_supported = info->has_audio; - msm_dp_panel_handle_sink_request(dp->panel); + msm_dp_panel_handle_sink_request(dp->panel, drm_edid); /* * set sink to normal operation mode -- D0 @@ -302,6 +312,7 @@ static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) msm_dp_link_reset_phy_params_vx_px(dp->link); end: + drm_edid_free(drm_edid); return rc; } @@ -348,7 +359,7 @@ static void msm_dp_display_host_init(struct msm_dp_display_private *dp) dp->phy_initialized); msm_dp_ctrl_core_clk_enable(dp->ctrl); - msm_dp_ctrl_reset(dp->ctrl); + msm_dp_ctrl_reset(dp->ctrl, dp->panel); msm_dp_ctrl_enable_irq(dp->ctrl); msm_dp_aux_init(dp->aux); dp->core_initialized = true; @@ -360,7 +371,7 @@ static void msm_dp_display_host_deinit(struct msm_dp_display_private *dp) dp->msm_dp_display.connector_type, dp->core_initialized, dp->phy_initialized); - msm_dp_ctrl_reset(dp->ctrl); + msm_dp_ctrl_reset(dp->ctrl, dp->panel); msm_dp_ctrl_disable_irq(dp->ctrl); msm_dp_aux_deinit(dp->aux); msm_dp_ctrl_core_clk_disable(dp->ctrl); @@ -381,7 +392,7 @@ static int msm_dp_display_handle_irq_hpd(struct msm_dp_display_private *dp) drm_dbg_dp(dp->drm_dev, "%d\n", sink_request); - msm_dp_ctrl_handle_sink_request(dp->ctrl); + msm_dp_ctrl_handle_sink_request(dp->ctrl, dp->panel); if (sink_request & DP_TEST_LINK_VIDEO_PATTERN) msm_dp_display_handle_video_request(dp); @@ -453,7 +464,7 @@ static int msm_dp_hpd_unplug_handle(struct msm_dp_display_private *dp) /* Don't forget modes for eDP */ if (!dp->msm_dp_display.is_edp) - msm_dp_panel_unplugged(dp->panel, dp->msm_dp_display.connector); + drm_edid_connector_update(dp->msm_dp_display.connector, NULL); /* triggered by irq_hdp with sink_count = 0 */ if (dp->link->sink_count == 0) @@ -515,7 +526,6 @@ static int msm_dp_irq_hpd_handle(struct msm_dp_display_private *dp) static void msm_dp_display_deinit_sub_modules(struct msm_dp_display_private *dp) { msm_dp_audio_put(dp->audio); - msm_dp_panel_put(dp->panel); msm_dp_aux_put(dp->aux); } @@ -560,13 +570,13 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) goto error_link; } - dp->ctrl = msm_dp_ctrl_get(dev, dp->link, dp->panel, dp->aux, - phy, dp->ahb_base, dp->link_base); + dp->ctrl = msm_dp_ctrl_get(dev, dp->link, dp->aux, + phy, dp->ahb_base, dp->link_base); if (IS_ERR(dp->ctrl)) { rc = PTR_ERR(dp->ctrl); DRM_ERROR("failed to initialize ctrl, rc = %d\n", rc); dp->ctrl = NULL; - goto error_ctrl; + goto error_link; } dp->audio = msm_dp_audio_get(dp->msm_dp_display.pdev, dp->link_base); @@ -574,13 +584,11 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) rc = PTR_ERR(dp->audio); pr_err("failed to initialize audio, rc = %d\n", rc); dp->audio = NULL; - goto error_ctrl; + goto error_link; } return rc; -error_ctrl: - msm_dp_panel_put(dp->panel); error_link: msm_dp_aux_put(dp->aux); error: @@ -588,20 +596,64 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) } static int msm_dp_display_set_mode(struct msm_dp *msm_dp_display, - struct msm_dp_display_mode *mode) + const struct drm_display_mode *adjusted_mode, + struct msm_dp_panel *msm_dp_panel) { struct msm_dp_display_private *dp; + u32 bpp; dp = container_of(msm_dp_display, struct msm_dp_display_private, msm_dp_display); - drm_mode_copy(&dp->panel->msm_dp_mode.drm_mode, &mode->drm_mode); - dp->panel->msm_dp_mode.bpp = mode->bpp; - dp->panel->msm_dp_mode.out_fmt_is_yuv_420 = mode->out_fmt_is_yuv_420; - msm_dp_panel_init_panel_info(dp->panel); + if (msm_dp_display_check_video_test(msm_dp_display)) + bpp = msm_dp_display_get_test_bpp(msm_dp_display); + else + bpp = msm_dp_panel->connector->display_info.bpc * 3; + + msm_dp_panel_init_panel_info(msm_dp_panel, adjusted_mode, bpp ? bpp : 24); + + /* populate wide_bus_support to different layers */ + dp->ctrl->wide_bus_en = + msm_dp_panel->msm_dp_mode.out_fmt_is_yuv_420 ? false : dp->wide_bus_supported; return 0; } -static int msm_dp_display_enable(struct msm_dp_display_private *dp, bool force_link_train) +static int msm_dp_display_prepare_link(struct msm_dp_display_private *dp) +{ + struct msm_dp *msm_dp_display = &dp->msm_dp_display; + int rc = 0; + bool force_link_train = false; + + drm_dbg_dp(dp->drm_dev, "sink_count=%d\n", dp->link->sink_count); + + if (msm_dp_display->is_edp) + msm_dp_hpd_plug_handle(dp); + + rc = pm_runtime_resume_and_get(&msm_dp_display->pdev->dev); + if (rc) { + DRM_ERROR("failed to pm_runtime_resume\n"); + return rc; + } + + if (dp->link->sink_count == 0) + return -ENOTCONN; + + if (!msm_dp_display->power_on) { + msm_dp_display_host_phy_init(dp); + force_link_train = true; + } + + rc = msm_dp_ctrl_on_link(dp->ctrl, dp->panel); + if (rc) { + DRM_ERROR("Failed link training (rc=%d)\n", rc); + // TODO: schedule drm_connector_set_link_status_property() + return rc; + } + + return msm_dp_ctrl_prepare_stream_on(dp->ctrl, dp->panel, force_link_train); +} + +static int msm_dp_display_enable(struct msm_dp_display_private *dp, + struct msm_dp_panel *msm_dp_panel) { int rc = 0; struct msm_dp *msm_dp_display = &dp->msm_dp_display; @@ -612,7 +664,7 @@ static int msm_dp_display_enable(struct msm_dp_display_private *dp, bool force_l return 0; } - rc = msm_dp_ctrl_on_stream(dp->ctrl, force_link_train); + rc = msm_dp_ctrl_on_stream(dp->ctrl, msm_dp_panel); if (!rc) msm_dp_display->power_on = true; @@ -637,18 +689,15 @@ static int msm_dp_display_post_enable(struct msm_dp *msm_dp_display) msm_dp_display_handle_plugged_change(msm_dp_display, true); if (msm_dp_display->psr_supported) - msm_dp_ctrl_config_psr(dp->ctrl); + msm_dp_ctrl_config_psr(dp->ctrl, dp->panel); return 0; } -static int msm_dp_display_disable(struct msm_dp_display_private *dp) +static void msm_dp_display_audio_notify_disable(struct msm_dp_display_private *dp) { struct msm_dp *msm_dp_display = &dp->msm_dp_display; - if (!msm_dp_display->power_on) - return 0; - /* wait only if audio was enabled */ if (msm_dp_display->audio_enabled) { /* signal the disconnect event */ @@ -659,21 +708,31 @@ static int msm_dp_display_disable(struct msm_dp_display_private *dp) } msm_dp_display->audio_enabled = false; +} - if (dp->link->sink_count == 0) { - /* - * irq_hpd with sink_count = 0 - * hdmi unplugged out of dongle - */ - msm_dp_ctrl_off_link_stream(dp->ctrl); - } else { - /* - * unplugged interrupt - * dongle unplugged out of DUT - */ - msm_dp_ctrl_off(dp->ctrl); +static int msm_dp_display_disable(struct msm_dp_display_private *dp, + struct msm_dp_panel *msm_dp_panel) +{ + struct msm_dp *msm_dp_display = &dp->msm_dp_display; + + if (!msm_dp_display->power_on) + return 0; + + msm_dp_panel_disable_vsc_sdp(msm_dp_panel); + + msm_dp_ctrl_off_pixel_clk(dp->ctrl); + + /* dongle is still connected but sinks are disconnected */ + if (dp->link->sink_count == 0) + msm_dp_link_psm_config(dp->link, &msm_dp_panel->link_info, true); + + msm_dp_ctrl_off_link(dp->ctrl, msm_dp_panel); + + if (dp->link->sink_count == 0) + /* re-init the PHY so that we can listen to Dongle disconnect */ + msm_dp_ctrl_reinit_phy(dp->ctrl); + else msm_dp_display_host_phy_exit(dp); - } msm_dp_display->power_on = false; @@ -682,24 +741,22 @@ static int msm_dp_display_disable(struct msm_dp_display_private *dp) } /** - * msm_dp_bridge_mode_valid - callback to determine if specified mode is valid - * @bridge: Pointer to drm bridge structure + * msm_dp_display_mode_valid - callback to determine if specified mode is valid + * @dp: Pointer to dp display structure * @info: display info * @mode: Pointer to drm mode structure * Returns: Validity status for specified mode */ -enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +enum drm_mode_status msm_dp_display_mode_valid(struct msm_dp *dp, + const struct drm_display_info *info, + const struct drm_display_mode *mode) { const u32 num_components = 3, default_bpp = 24; struct msm_dp_display_private *msm_dp_display; struct msm_dp_link_info *link_info; u32 mode_rate_khz = 0, supported_rate_khz = 0, mode_bpp = 0; - struct msm_dp *dp; int mode_pclk_khz = mode->clock; - - dp = to_dp_bridge(bridge)->msm_dp_display; + bool is_yuv_420; if (!dp || !mode_pclk_khz || !dp->connector) { DRM_ERROR("invalid params\n"); @@ -709,9 +766,16 @@ enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge, msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); link_info = &msm_dp_display->panel->link_info; - if ((drm_mode_is_420_only(&dp->connector->display_info, mode) && - msm_dp_display->panel->vsc_sdp_supported) || - msm_dp_wide_bus_available(dp)) + is_yuv_420 = drm_mode_is_420_only(&dp->connector->display_info, mode); + + /* + * YUV 420 is carried over DP by signalling the colorimetry through a + * VSC SDP, so a 420-only mode cannot be driven without VSC SDP support. + */ + if (is_yuv_420 && !msm_dp_display->panel->vsc_sdp_supported) + return MODE_NO_420; + + if (is_yuv_420 || msm_dp_display->wide_bus_supported) mode_pclk_khz /= 2; if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ) @@ -744,8 +808,7 @@ int msm_dp_display_get_modes(struct msm_dp *dp) msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); - return msm_dp_panel_get_modes(msm_dp_display->panel, - dp->connector); + return drm_edid_connector_add_modes(msm_dp_display->panel->connector); } bool msm_dp_display_check_video_test(struct msm_dp *dp) @@ -808,7 +871,7 @@ void msm_dp_display_set_psr(struct msm_dp *msm_dp_display, bool enter) } dp = container_of(msm_dp_display, struct msm_dp_display_private, msm_dp_display); - msm_dp_ctrl_set_psr(dp->ctrl, enter); + msm_dp_ctrl_set_psr(dp->ctrl, dp->panel, enter); } /** @@ -918,7 +981,7 @@ static irqreturn_t msm_dp_display_irq_handler(int irq, void *dev_id) } /* DP controller isr */ - ret |= msm_dp_ctrl_isr(dp->ctrl); + ret |= msm_dp_ctrl_isr(dp->ctrl, dp->panel); return ret; } @@ -1277,22 +1340,10 @@ void __exit msm_dp_unregister(void) platform_driver_unregister(&msm_dp_display_driver); } -bool msm_dp_is_yuv_420_enabled(const struct msm_dp *msm_dp_display, - const struct drm_display_mode *mode) -{ - struct msm_dp_display_private *dp; - const struct drm_display_info *info; - - dp = container_of(msm_dp_display, struct msm_dp_display_private, msm_dp_display); - info = &msm_dp_display->connector->display_info; - - return dp->panel->vsc_sdp_supported && drm_mode_is_420_only(info, mode); -} - bool msm_dp_needs_periph_flush(const struct msm_dp *msm_dp_display, const struct drm_display_mode *mode) { - return msm_dp_is_yuv_420_enabled(msm_dp_display, mode); + return drm_mode_is_420_only(&msm_dp_display->connector->display_info, mode); } bool msm_dp_wide_bus_available(const struct msm_dp *msm_dp_display) @@ -1301,7 +1352,7 @@ bool msm_dp_wide_bus_available(const struct msm_dp *msm_dp_display) dp = container_of(msm_dp_display, struct msm_dp_display_private, msm_dp_display); - if (dp->msm_dp_mode.out_fmt_is_yuv_420) + if (dp->panel->msm_dp_mode.out_fmt_is_yuv_420) return false; return dp->wide_bus_supported; @@ -1352,66 +1403,57 @@ int msm_dp_modeset_init(struct msm_dp *msm_dp_display, struct drm_device *dev, return 0; } -void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, - struct drm_atomic_commit *state) +void msm_dp_display_atomic_pre_enable(struct msm_dp *msm_dp_display, + struct drm_atomic_commit *state) { - struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); - struct msm_dp *dp = msm_dp_bridge->msm_dp_display; - int rc = 0; - struct msm_dp_display_private *msm_dp_display; - bool force_link_train = false; + struct msm_dp_display_private *dp; + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; - msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); - if (!msm_dp_display->msm_dp_mode.drm_mode.clock) { - DRM_ERROR("invalid params\n"); + dp = container_of(msm_dp_display, struct msm_dp_display_private, msm_dp_display); + + crtc = drm_atomic_get_new_crtc_for_encoder(state, msm_dp_display->bridge->encoder); + if (!crtc) return; - } + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); - if (dp->is_edp) - msm_dp_hpd_plug_handle(msm_dp_display); - - if (pm_runtime_resume_and_get(&dp->pdev->dev)) { - DRM_ERROR("failed to pm_runtime_resume\n"); - return; - } - - if (msm_dp_display->link->sink_count == 0) - return; - - rc = msm_dp_display_set_mode(dp, &msm_dp_display->msm_dp_mode); - if (rc) { - DRM_ERROR("Failed to perform a mode set, rc=%d\n", rc); - return; - } - - if (!dp->power_on) { - msm_dp_display_host_phy_init(msm_dp_display); - force_link_train = true; - } - - rc = msm_dp_ctrl_on_link(msm_dp_display->ctrl); - if (rc) { - DRM_ERROR("Failed link training (rc=%d)\n", rc); - // TODO: schedule drm_connector_set_link_status_property() - return; - } - - msm_dp_display_enable(msm_dp_display, force_link_train); - - rc = msm_dp_display_post_enable(dp); - if (rc) { - DRM_ERROR("DP display post enable failed, rc=%d\n", rc); - msm_dp_display_disable(msm_dp_display); - } - - drm_dbg_dp(dp->drm_dev, "type=%d Done\n", dp->connector_type); + /* + * The DPU encoder's .atomic_enable() reads the mode's YUV420 / wide bus + * state and runs before the bridge's .atomic_enable(), so the mode must + * be programmed here, in .atomic_pre_enable(). + */ + msm_dp_display_set_mode(msm_dp_display, &crtc_state->adjusted_mode, dp->panel); } -void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, +void msm_dp_display_atomic_enable(struct msm_dp *msm_dp_display, struct drm_atomic_commit *state) { - struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); - struct msm_dp *dp = msm_dp_bridge->msm_dp_display; + int rc = 0; + struct msm_dp_display_private *dp; + + dp = container_of(msm_dp_display, struct msm_dp_display_private, msm_dp_display); + + rc = msm_dp_display_prepare_link(dp); + if (rc) { + DRM_ERROR("DP display prepare failed, rc=%d\n", rc); + return; + } + + rc = msm_dp_display_enable(dp, dp->panel); + if (rc) + DRM_ERROR("DP display enable failed, rc=%d\n", rc); + + rc = msm_dp_display_post_enable(msm_dp_display); + if (rc) { + DRM_ERROR("DP display post enable failed, rc=%d\n", rc); + msm_dp_display_disable(dp, dp->panel); + } + + drm_dbg_dp(msm_dp_display->drm_dev, "type=%d Done\n", msm_dp_display->connector_type); +} + +void msm_dp_display_atomic_disable(struct msm_dp *dp) +{ struct msm_dp_display_private *msm_dp_display; msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); @@ -1419,11 +1461,17 @@ void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, msm_dp_ctrl_push_idle(msm_dp_display->ctrl); } -void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, - struct drm_atomic_commit *state) +static void msm_dp_display_unprepare(struct msm_dp_display_private *dp) +{ + struct msm_dp *msm_dp_display = &dp->msm_dp_display; + + pm_runtime_put_sync(&msm_dp_display->pdev->dev); + + drm_dbg_dp(dp->drm_dev, "type=%d Done\n", msm_dp_display->connector_type); +} + +void msm_dp_display_atomic_post_disable(struct msm_dp *dp) { - struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); - struct msm_dp *dp = msm_dp_bridge->msm_dp_display; struct msm_dp_display_private *msm_dp_display; msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); @@ -1431,50 +1479,11 @@ void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, if (dp->is_edp) msm_dp_hpd_unplug_handle(msm_dp_display); - msm_dp_display_disable(msm_dp_display); + msm_dp_display_audio_notify_disable(msm_dp_display); - drm_dbg_dp(dp->drm_dev, "type=%d Done\n", dp->connector_type); + msm_dp_display_disable(msm_dp_display, msm_dp_display->panel); - pm_runtime_put_sync(&dp->pdev->dev); -} - -void msm_dp_bridge_mode_set(struct drm_bridge *drm_bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adjusted_mode) -{ - struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); - struct msm_dp *dp = msm_dp_bridge->msm_dp_display; - struct msm_dp_display_private *msm_dp_display; - struct msm_dp_panel *msm_dp_panel; - - msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); - msm_dp_panel = msm_dp_display->panel; - - memset(&msm_dp_display->msm_dp_mode, 0x0, sizeof(struct msm_dp_display_mode)); - - if (msm_dp_display_check_video_test(dp)) - msm_dp_display->msm_dp_mode.bpp = msm_dp_display_get_test_bpp(dp); - else /* Default num_components per pixel = 3 */ - msm_dp_display->msm_dp_mode.bpp = dp->connector->display_info.bpc * 3; - - if (!msm_dp_display->msm_dp_mode.bpp) - msm_dp_display->msm_dp_mode.bpp = 24; /* Default bpp */ - - drm_mode_copy(&msm_dp_display->msm_dp_mode.drm_mode, adjusted_mode); - - msm_dp_display->msm_dp_mode.v_active_low = - !!(msm_dp_display->msm_dp_mode.drm_mode.flags & DRM_MODE_FLAG_NVSYNC); - - msm_dp_display->msm_dp_mode.h_active_low = - !!(msm_dp_display->msm_dp_mode.drm_mode.flags & DRM_MODE_FLAG_NHSYNC); - - msm_dp_display->msm_dp_mode.out_fmt_is_yuv_420 = - drm_mode_is_420_only(&dp->connector->display_info, adjusted_mode) && - msm_dp_panel->vsc_sdp_supported; - - /* populate wide_bus_support to different layers */ - msm_dp_display->ctrl->wide_bus_en = - msm_dp_display->msm_dp_mode.out_fmt_is_yuv_420 ? false : msm_dp_display->wide_bus_supported; + msm_dp_display_unprepare(msm_dp_display); } void msm_dp_bridge_hpd_enable(struct drm_bridge *bridge) diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h index 0b65e16c790d..83117e7619f3 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.h +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -33,5 +33,14 @@ void msm_dp_display_signal_audio_start(struct msm_dp *msm_dp_display); void msm_dp_display_signal_audio_complete(struct msm_dp *msm_dp_display); void msm_dp_display_set_psr(struct msm_dp *dp, bool enter); void msm_dp_display_debugfs_init(struct msm_dp *msm_dp_display, struct dentry *dentry, bool is_edp); +void msm_dp_display_atomic_post_disable(struct msm_dp *dp_display); +void msm_dp_display_atomic_disable(struct msm_dp *dp_display); +void msm_dp_display_atomic_pre_enable(struct msm_dp *dp_display, + struct drm_atomic_commit *state); +void msm_dp_display_atomic_enable(struct msm_dp *dp_display, + struct drm_atomic_commit *state); +enum drm_mode_status msm_dp_display_mode_valid(struct msm_dp *dp, + const struct drm_display_info *info, + const struct drm_display_mode *mode); #endif /* _DP_DISPLAY_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index 06881bfd6181..c1e4147bfef1 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -49,14 +49,60 @@ static void msm_dp_bridge_debugfs_init(struct drm_bridge *bridge, struct dentry msm_dp_display_debugfs_init(dp, root, false); } +static void msm_dp_bridge_atomic_pre_enable(struct drm_bridge *drm_bridge, + struct drm_atomic_commit *state) +{ + struct msm_dp_bridge *dp_bridge = to_dp_bridge(drm_bridge); + struct msm_dp *dp = dp_bridge->msm_dp_display; + + msm_dp_display_atomic_pre_enable(dp, state); +} + +static void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, + struct drm_atomic_commit *state) +{ + struct msm_dp_bridge *dp_bridge = to_dp_bridge(drm_bridge); + struct msm_dp *dp = dp_bridge->msm_dp_display; + + msm_dp_display_atomic_enable(dp, state); +} + +static void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, + struct drm_atomic_commit *state) +{ + struct msm_dp_bridge *dp_bridge = to_dp_bridge(drm_bridge); + struct msm_dp *dp = dp_bridge->msm_dp_display; + + msm_dp_display_atomic_disable(dp); +} + +static void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, + struct drm_atomic_commit *state) +{ + struct msm_dp_bridge *dp_bridge = to_dp_bridge(drm_bridge); + struct msm_dp *dp = dp_bridge->msm_dp_display; + + msm_dp_display_atomic_post_disable(dp); +} + +static enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *drm_bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + struct msm_dp_bridge *dp_bridge = to_dp_bridge(drm_bridge); + struct msm_dp *dp = dp_bridge->msm_dp_display; + + return msm_dp_display_mode_valid(dp, info, mode); +} + static const struct drm_bridge_funcs msm_dp_bridge_ops = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .atomic_create_state = drm_atomic_helper_bridge_create_state, + .atomic_pre_enable = msm_dp_bridge_atomic_pre_enable, .atomic_enable = msm_dp_bridge_atomic_enable, .atomic_disable = msm_dp_bridge_atomic_disable, .atomic_post_disable = msm_dp_bridge_atomic_post_disable, - .mode_set = msm_dp_bridge_mode_set, .mode_valid = msm_dp_bridge_mode_valid, .get_modes = msm_dp_bridge_get_modes, .detect = msm_dp_bridge_detect, @@ -116,7 +162,7 @@ static void msm_edp_bridge_atomic_enable(struct drm_bridge *drm_bridge, return; } - msm_dp_bridge_atomic_enable(drm_bridge, state); + msm_dp_display_atomic_enable(dp, state); } static void msm_edp_bridge_atomic_disable(struct drm_bridge *drm_bridge, @@ -230,10 +276,10 @@ static void msm_edp_bridge_debugfs_init(struct drm_bridge *bridge, struct dentry } static const struct drm_bridge_funcs msm_edp_bridge_ops = { + .atomic_pre_enable = msm_dp_bridge_atomic_pre_enable, .atomic_enable = msm_edp_bridge_atomic_enable, .atomic_disable = msm_edp_bridge_atomic_disable, .atomic_post_disable = msm_edp_bridge_atomic_post_disable, - .mode_set = msm_dp_bridge_mode_set, .mode_valid = msm_edp_bridge_mode_valid, .atomic_create_state = drm_atomic_helper_bridge_create_state, .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, diff --git a/drivers/gpu/drm/msm/dp/dp_drm.h b/drivers/gpu/drm/msm/dp/dp_drm.h index 041aa026ae2e..da412c788503 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.h +++ b/drivers/gpu/drm/msm/dp/dp_drm.h @@ -27,18 +27,6 @@ int msm_dp_bridge_init(struct msm_dp *msm_dp_display, struct drm_device *dev, enum drm_connector_status msm_dp_bridge_detect(struct drm_bridge *bridge, struct drm_connector *connector); -void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, - struct drm_atomic_commit *state); -void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, - struct drm_atomic_commit *state); -void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, - struct drm_atomic_commit *state); -enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode); -void msm_dp_bridge_mode_set(struct drm_bridge *drm_bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adjusted_mode); void msm_dp_bridge_hpd_enable(struct drm_bridge *bridge); void msm_dp_bridge_hpd_disable(struct drm_bridge *bridge); void msm_dp_bridge_hpd_notify(struct drm_bridge *bridge, diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 6bb021820d7c..e76dad0f6663 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -232,8 +232,8 @@ static u32 msm_dp_panel_get_supported_bpp(struct msm_dp_panel *msm_dp_panel, return min_supported_bpp; } -int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, - struct drm_connector *connector) +int msm_dp_panel_read_link_caps(struct msm_dp_panel *msm_dp_panel, + struct drm_connector *connector) { int rc, bw_code; int count; @@ -271,36 +271,9 @@ int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, rc = drm_dp_read_downstream_info(panel->aux, msm_dp_panel->dpcd, msm_dp_panel->downstream_ports); - if (rc) - return rc; - - drm_edid_free(msm_dp_panel->drm_edid); - - msm_dp_panel->drm_edid = drm_edid_read_ddc(connector, &panel->aux->ddc); - - drm_edid_connector_update(connector, msm_dp_panel->drm_edid); - - if (!msm_dp_panel->drm_edid) { - DRM_ERROR("panel edid read failed\n"); - /* check edid read fail is due to unplug */ - if (!msm_dp_aux_is_link_connected(panel->aux)) { - rc = -ETIMEDOUT; - goto end; - } - } - -end: return rc; } -void msm_dp_panel_unplugged(struct msm_dp_panel *msm_dp_panel, - struct drm_connector *connector) -{ - drm_edid_connector_update(connector, NULL); - drm_edid_free(msm_dp_panel->drm_edid); - msm_dp_panel->drm_edid = NULL; -} - u32 msm_dp_panel_get_mode_bpp(struct msm_dp_panel *msm_dp_panel, u32 mode_edid_bpp, u32 mode_pclk_khz) { @@ -324,20 +297,6 @@ u32 msm_dp_panel_get_mode_bpp(struct msm_dp_panel *msm_dp_panel, return bpp; } -int msm_dp_panel_get_modes(struct msm_dp_panel *msm_dp_panel, - struct drm_connector *connector) -{ - if (!msm_dp_panel) { - DRM_ERROR("invalid input\n"); - return -EINVAL; - } - - if (msm_dp_panel->drm_edid) - return drm_edid_connector_add_modes(connector); - - return 0; -} - static u8 msm_dp_panel_get_edid_checksum(const struct edid *edid) { edid += edid->extensions; @@ -345,7 +304,8 @@ static u8 msm_dp_panel_get_edid_checksum(const struct edid *edid) return edid->checksum; } -void msm_dp_panel_handle_sink_request(struct msm_dp_panel *msm_dp_panel) +void msm_dp_panel_handle_sink_request(struct msm_dp_panel *msm_dp_panel, + const struct drm_edid *drm_edid) { struct msm_dp_panel_private *panel; @@ -358,7 +318,7 @@ void msm_dp_panel_handle_sink_request(struct msm_dp_panel *msm_dp_panel) if (panel->link->sink_request & DP_TEST_LINK_EDID_READ) { /* FIXME: get rid of drm_edid_raw() */ - const struct edid *edid = drm_edid_raw(msm_dp_panel->drm_edid); + const struct edid *edid = drm_edid_raw(drm_edid); u8 checksum; if (edid) @@ -687,15 +647,27 @@ int msm_dp_panel_timing_cfg(struct msm_dp_panel *msm_dp_panel, bool wide_bus_en) return 0; } -int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel) +int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel, + const struct drm_display_mode *adjusted_mode, + u32 bpp) { struct drm_display_mode *drm_mode; struct msm_dp_panel_private *panel; - drm_mode = &msm_dp_panel->msm_dp_mode.drm_mode; - panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); + drm_mode_copy(&msm_dp_panel->msm_dp_mode.drm_mode, adjusted_mode); + msm_dp_panel->msm_dp_mode.bpp = bpp; + msm_dp_panel->msm_dp_mode.v_active_low = + !!(adjusted_mode->flags & DRM_MODE_FLAG_NVSYNC); + msm_dp_panel->msm_dp_mode.h_active_low = + !!(adjusted_mode->flags & DRM_MODE_FLAG_NHSYNC); + msm_dp_panel->msm_dp_mode.out_fmt_is_yuv_420 = + drm_mode_is_420_only(&msm_dp_panel->connector->display_info, adjusted_mode) && + msm_dp_panel->vsc_sdp_supported; + + drm_mode = &msm_dp_panel->msm_dp_mode.drm_mode; + /* * print resolution info as this is a result * of user initiated action of cable connection @@ -755,10 +727,3 @@ struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux return msm_dp_panel; } -void msm_dp_panel_put(struct msm_dp_panel *msm_dp_panel) -{ - if (!msm_dp_panel) - return; - - drm_edid_free(msm_dp_panel->drm_edid); -} diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index 9173e90a5053..4519ac374220 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -33,7 +33,6 @@ struct msm_dp_panel { u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]; struct msm_dp_link_info link_info; - const struct drm_edid *drm_edid; struct drm_connector *connector; struct msm_dp_display_mode msm_dp_mode; struct msm_dp_panel_psr psr_cap; @@ -44,18 +43,17 @@ struct msm_dp_panel { u32 max_bw_code; }; -int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel); +int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel, + const struct drm_display_mode *adjusted_mode, + u32 bpp); int msm_dp_panel_deinit(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_timing_cfg(struct msm_dp_panel *msm_dp_panel, bool wide_bus_en); -int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, - struct drm_connector *connector); -void msm_dp_panel_unplugged(struct msm_dp_panel *msm_dp_panel, - struct drm_connector *connector); +int msm_dp_panel_read_link_caps(struct msm_dp_panel *msm_dp_panel, + struct drm_connector *connector); u32 msm_dp_panel_get_mode_bpp(struct msm_dp_panel *msm_dp_panel, u32 mode_max_bpp, u32 mode_pclk_khz); -int msm_dp_panel_get_modes(struct msm_dp_panel *msm_dp_panel, - struct drm_connector *connector); -void msm_dp_panel_handle_sink_request(struct msm_dp_panel *msm_dp_panel); +void msm_dp_panel_handle_sink_request(struct msm_dp_panel *msm_dp_panel, + const struct drm_edid *drm_edid); void msm_dp_panel_tpg_config(struct msm_dp_panel *msm_dp_panel, bool enable); void msm_dp_panel_clear_dsc_dto(struct msm_dp_panel *msm_dp_panel); @@ -94,5 +92,4 @@ struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux struct msm_dp_link *link, void __iomem *link_base, void __iomem *p0_base); -void msm_dp_panel_put(struct msm_dp_panel *msm_dp_panel); #endif /* _DP_PANEL_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h index 3689642b7fc0..dda4b642c81b 100644 --- a/drivers/gpu/drm/msm/dp/dp_reg.h +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -149,8 +149,10 @@ #define DP_CONFIGURATION_CTRL_ENHANCED_FRAMING (0x00000040) #define DP_CONFIGURATION_CTRL_SEND_VSC (0x00000080) #define DP_CONFIGURATION_CTRL_BPC (0x00000100) +#define DP_CONFIGURATION_CTRL_BPC_MASK GENMASK(9, 8) #define DP_CONFIGURATION_CTRL_ASSR (0x00000400) #define DP_CONFIGURATION_CTRL_RGB_YUV (0x00000800) +#define DP_CONFIGURATION_CTRL_RGB_YUV_MASK GENMASK(12, 11) #define DP_CONFIGURATION_CTRL_LSCLK_DIV (0x00002000) #define DP_CONFIGURATION_CTRL_NUM_OF_LANES_SHIFT (0x04) #define DP_CONFIGURATION_CTRL_BPC_SHIFT (0x08) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index de1ba11987fc..7e4e3718b536 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -550,8 +550,6 @@ int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host) void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host) { - /* Drop the performance state vote */ - dev_pm_opp_set_rate(&msm_host->pdev->dev, 0); clk_disable_unprepare(msm_host->esc_clk); clk_disable_unprepare(msm_host->pixel_clk); clk_disable_unprepare(msm_host->byte_intf_clk); @@ -671,12 +669,24 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi) int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi) { + long rounded_byte_clk_rate; + if (!msm_host->mode) { pr_err("%s: mode not set\n", __func__); return -EINVAL; } dsi_calc_pclk(msm_host, is_bonded_dsi); + + rounded_byte_clk_rate = clk_round_rate(msm_host->byte_clk, + msm_host->byte_clk_rate); + if (rounded_byte_clk_rate < 0) { + pr_err("%s: failed to round byte clock rate, %ld\n", + __func__, rounded_byte_clk_rate); + return rounded_byte_clk_rate; + } + + msm_host->byte_clk_rate = rounded_byte_clk_rate; msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk); return 0; } diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 21a59d66e8dc..f5d3e806f8fd 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -111,6 +111,7 @@ struct msm_dsi_phy { struct msm_dsi_dphy_timing timing; const struct msm_dsi_phy_cfg *cfg; void *tuning_cfg; + void *pll_data; enum msm_dsi_phy_usecase usecase; bool regulator_ldo_mode; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 984a66085dfb..5d805a797abd 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -426,8 +426,11 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) u32 data; spin_lock_irqsave(&pll->pll_enable_lock, flags); - pll->pll_enable_cnt++; - WARN_ON(pll->pll_enable_cnt == INT_MAX); + if (pll->pll_enable_cnt++) { + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + WARN_ON(pll->pll_enable_cnt == INT_MAX); + return; + } data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; @@ -873,6 +876,7 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) spin_lock_init(&pll_7nm->pll_enable_lock); pll_7nm->phy = phy; + phy->pll_data = pll_7nm; ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws); if (ret) { @@ -961,8 +965,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, u32 const delay_us = 5; u32 const timeout_us = 1000; struct msm_dsi_dphy_timing *timing = &phy->timing; + struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; bool less_than_1500_mhz; + unsigned long flags; u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0; u32 glbl_pemph_ctrl_0; u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0; @@ -1084,10 +1090,13 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, glbl_rescode_bot_ctrl = 0x3c; } + spin_lock_irqsave(&pll->pll_enable_lock, flags); + pll->pll_enable_cnt = 1; /* de-assert digital and pll power down */ data = DSI_7nm_PHY_CMN_CTRL_0_DIGTOP_PWRDN_B | DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* Assert PLL core reset */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL); @@ -1200,7 +1209,9 @@ static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable) static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) { + struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; + unsigned long flags; u32 data; DBG(""); @@ -1227,8 +1238,11 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); writel(0, base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0); + spin_lock_irqsave(&pll->pll_enable_lock, flags); + pll->pll_enable_cnt = 0; /* Turn off all PHY blocks */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_CTRL_0); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* make sure phy is turned off */ wmb(); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index 49433f7727c3..436d4f9fe346 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -112,6 +112,25 @@ static inline u32 hdmi_read(struct hdmi *hdmi, u32 reg) return readl(hdmi->mmio + reg); } +static inline void hdmi_clear_bits(struct hdmi *hdmi, u32 reg, u32 mask) +{ + u32 val; + + val = hdmi_read(hdmi, reg); + val &= ~mask; + hdmi_write(hdmi, reg, val); +} + +static inline void hdmi_update_bits(struct hdmi *hdmi, u32 reg, u32 mask, u32 data) +{ + u32 val; + + val = hdmi_read(hdmi, reg); + val &= ~mask; + val |= data & mask; + hdmi_write(hdmi, reg, val); +} + static inline u32 hdmi_qfprom_read(struct hdmi *hdmi, u32 reg) { return readl(hdmi->qfprom_mmio + reg); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 7abb9243dba5..157f19bd90b4 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -58,16 +58,13 @@ static int msm_hdmi_bridge_clear_avi_infoframe(struct drm_bridge *bridge) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - u32 val; - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); - val &= ~(HDMI_INFOFRAME_CTRL0_AVI_SEND | - HDMI_INFOFRAME_CTRL0_AVI_CONT); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + hdmi_clear_bits(hdmi, REG_HDMI_INFOFRAME_CTRL0, + HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); - val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + hdmi_clear_bits(hdmi, REG_HDMI_INFOFRAME_CTRL1, + HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK); return 0; } @@ -76,18 +73,15 @@ static int msm_hdmi_bridge_clear_audio_infoframe(struct drm_bridge *bridge) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - u32 val; - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); - val &= ~(HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | - HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | - HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | - HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + hdmi_clear_bits(hdmi, REG_HDMI_INFOFRAME_CTRL0, + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); - val &= ~HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK; - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + hdmi_clear_bits(hdmi, REG_HDMI_INFOFRAME_CTRL1, + HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK); return 0; } @@ -96,13 +90,11 @@ static int msm_hdmi_bridge_clear_spd_infoframe(struct drm_bridge *bridge) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - u32 val; - val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); - val &= ~(HDMI_GEN_PKT_CTRL_GENERIC1_SEND | - HDMI_GEN_PKT_CTRL_GENERIC1_CONT | - HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK); - hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + hdmi_clear_bits(hdmi, REG_HDMI_GEN_PKT_CTRL, + HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK); return 0; } @@ -111,14 +103,12 @@ static int msm_hdmi_bridge_clear_hdmi_infoframe(struct drm_bridge *bridge) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - u32 val; - val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); - val &= ~(HDMI_GEN_PKT_CTRL_GENERIC0_SEND | - HDMI_GEN_PKT_CTRL_GENERIC0_CONT | - HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | - HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK); - hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + hdmi_clear_bits(hdmi, REG_HDMI_GEN_PKT_CTRL, + HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK); return 0; } @@ -129,7 +119,6 @@ static int msm_hdmi_bridge_write_avi_infoframe(struct drm_bridge *bridge, struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; u32 buf[4] = {}; - u32 val; int i; if (len != HDMI_INFOFRAME_SIZE(AVI) || len - 3 > sizeof(buf)) { @@ -153,15 +142,13 @@ static int msm_hdmi_bridge_write_avi_infoframe(struct drm_bridge *bridge, for (i = 0; i < ARRAY_SIZE(buf); i++) hdmi_write(hdmi, REG_HDMI_AVI_INFO(i), buf[i]); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); - val |= HDMI_INFOFRAME_CTRL0_AVI_SEND | - HDMI_INFOFRAME_CTRL0_AVI_CONT; - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + hdmi_update_bits(hdmi, REG_HDMI_INFOFRAME_CTRL0, + HDMI_INFOFRAME_CTRL0_AVI_SEND | HDMI_INFOFRAME_CTRL0_AVI_CONT, + HDMI_INFOFRAME_CTRL0_AVI_SEND | HDMI_INFOFRAME_CTRL0_AVI_CONT); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); - val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; - val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + hdmi_update_bits(hdmi, REG_HDMI_INFOFRAME_CTRL1, + HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK, + HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER)); return 0; } @@ -193,12 +180,11 @@ static int msm_hdmi_bridge_write_audio_infoframe(struct drm_bridge *bridge, buffer[9] << 16 | buffer[10] << 24); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); - val |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | - HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | - HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | - HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + val = HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; + hdmi_update_bits(hdmi, REG_HDMI_INFOFRAME_CTRL0, val, val); return 0; } @@ -231,11 +217,10 @@ static int msm_hdmi_bridge_write_spd_infoframe(struct drm_bridge *bridge, for (i = 0; i < ARRAY_SIZE(buf); i++) hdmi_write(hdmi, REG_HDMI_GENERIC1(i), buf[i]); - val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); - val |= HDMI_GEN_PKT_CTRL_GENERIC1_SEND | - HDMI_GEN_PKT_CTRL_GENERIC1_CONT | - HDMI_GEN_PKT_CTRL_GENERIC1_LINE(SPD_IFRAME_LINE_NUMBER); - hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + val = HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE(SPD_IFRAME_LINE_NUMBER); + hdmi_update_bits(hdmi, REG_HDMI_GEN_PKT_CTRL, val, val); return 0; } @@ -269,12 +254,11 @@ static int msm_hdmi_bridge_write_hdmi_infoframe(struct drm_bridge *bridge, for (i = 0; i < ARRAY_SIZE(buf); i++) hdmi_write(hdmi, REG_HDMI_GENERIC0(i), buf[i]); - val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); - val |= HDMI_GEN_PKT_CTRL_GENERIC0_SEND | - HDMI_GEN_PKT_CTRL_GENERIC0_CONT | - HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | - HDMI_GEN_PKT_CTRL_GENERIC0_LINE(VENSPEC_IFRAME_LINE_NUMBER); - hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + val = HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE(VENSPEC_IFRAME_LINE_NUMBER); + hdmi_update_bits(hdmi, REG_HDMI_GEN_PKT_CTRL, val, val); return 0; } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c b/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c index 8fb5497aac9f..7862bd67d154 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c @@ -306,9 +306,9 @@ static int msm_reset_hdcp_ddc_failures(struct hdmi_hdcp_ctrl *hdcp_ctrl) HDMI_HDCP_DDC_CTRL_0_DISABLE); /* ACK the Failure to Clear it */ - reg_val = hdmi_read(hdmi, REG_HDMI_HDCP_DDC_CTRL_1); - reg_val |= HDMI_HDCP_DDC_CTRL_1_FAILED_ACK; - hdmi_write(hdmi, REG_HDMI_HDCP_DDC_CTRL_1, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_HDCP_DDC_CTRL_1, + HDMI_HDCP_DDC_CTRL_1_FAILED_ACK, + HDMI_HDCP_DDC_CTRL_1_FAILED_ACK); /* Check if the FAILURE got Cleared */ reg_val = hdmi_read(hdmi, REG_HDMI_HDCP_DDC_STATUS); @@ -324,28 +324,22 @@ static int msm_reset_hdcp_ddc_failures(struct hdmi_hdcp_ctrl *hdcp_ctrl) DBG("Before: HDMI_DDC_SW_STATUS=0x%08x", hdmi_read(hdmi, REG_HDMI_DDC_SW_STATUS)); /* Reset HDMI DDC software status */ - reg_val = hdmi_read(hdmi, REG_HDMI_DDC_CTRL); - reg_val |= HDMI_DDC_CTRL_SW_STATUS_RESET; - hdmi_write(hdmi, REG_HDMI_DDC_CTRL, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_DDC_CTRL, HDMI_DDC_CTRL_SW_STATUS_RESET, + HDMI_DDC_CTRL_SW_STATUS_RESET); rc = msm_hdmi_hdcp_msleep(hdcp_ctrl, 20, AUTH_ABORT_EV); - reg_val = hdmi_read(hdmi, REG_HDMI_DDC_CTRL); - reg_val &= ~HDMI_DDC_CTRL_SW_STATUS_RESET; - hdmi_write(hdmi, REG_HDMI_DDC_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_DDC_CTRL, HDMI_DDC_CTRL_SW_STATUS_RESET); /* Reset HDMI DDC Controller */ - reg_val = hdmi_read(hdmi, REG_HDMI_DDC_CTRL); - reg_val |= HDMI_DDC_CTRL_SOFT_RESET; - hdmi_write(hdmi, REG_HDMI_DDC_CTRL, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_DDC_CTRL, HDMI_DDC_CTRL_SOFT_RESET, + HDMI_DDC_CTRL_SOFT_RESET); /* If previous msleep is aborted, skip this msleep */ if (!rc) rc = msm_hdmi_hdcp_msleep(hdcp_ctrl, 20, AUTH_ABORT_EV); - reg_val = hdmi_read(hdmi, REG_HDMI_DDC_CTRL); - reg_val &= ~HDMI_DDC_CTRL_SOFT_RESET; - hdmi_write(hdmi, REG_HDMI_DDC_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_DDC_CTRL, HDMI_DDC_CTRL_SOFT_RESET); DBG("After: HDMI_DDC_SW_STATUS=0x%08x", hdmi_read(hdmi, REG_HDMI_DDC_SW_STATUS)); } @@ -399,7 +393,6 @@ static void msm_hdmi_hdcp_reauth_work(struct work_struct *work) struct hdmi_hdcp_ctrl, hdcp_reauth_work); struct hdmi *hdmi = hdcp_ctrl->hdmi; unsigned long flags; - u32 reg_val; DBG("HDCP REAUTH WORK"); /* @@ -409,9 +402,7 @@ static void msm_hdmi_hdcp_reauth_work(struct work_struct *work) * AN1_READY bits in HDMI_HDCP_LINK0_STATUS register */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_HPD_CTRL); - reg_val &= ~HDMI_HPD_CTRL_ENABLE; - hdmi_write(hdmi, REG_HDMI_HPD_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_HPD_CTRL, HDMI_HPD_CTRL_ENABLE); /* Disable HDCP interrupts */ hdmi_write(hdmi, REG_HDMI_HDCP_INT_CTRL, 0); @@ -431,9 +422,8 @@ static void msm_hdmi_hdcp_reauth_work(struct work_struct *work) /* Enable HPD circuitry */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_HPD_CTRL); - reg_val |= HDMI_HPD_CTRL_ENABLE; - hdmi_write(hdmi, REG_HDMI_HPD_CTRL, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_HPD_CTRL, HDMI_HPD_CTRL_ENABLE, + HDMI_HPD_CTRL_ENABLE); spin_unlock_irqrestore(&hdmi->reg_lock, flags); /* @@ -456,7 +446,6 @@ static int msm_hdmi_hdcp_auth_prepare(struct hdmi_hdcp_ctrl *hdcp_ctrl) { struct hdmi *hdmi = hdcp_ctrl->hdmi; u32 link0_status; - u32 reg_val; unsigned long flags; int rc; @@ -472,14 +461,11 @@ static int msm_hdmi_hdcp_auth_prepare(struct hdmi_hdcp_ctrl *hdcp_ctrl) spin_lock_irqsave(&hdmi->reg_lock, flags); /* disable HDMI Encrypt */ - reg_val = hdmi_read(hdmi, REG_HDMI_CTRL); - reg_val &= ~HDMI_CTRL_ENCRYPTED; - hdmi_write(hdmi, REG_HDMI_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_CTRL, HDMI_CTRL_ENCRYPTED); /* Enabling Software DDC */ - reg_val = hdmi_read(hdmi, REG_HDMI_DDC_ARBITRATION); - reg_val &= ~HDMI_DDC_ARBITRATION_HW_ARBITRATION; - hdmi_write(hdmi, REG_HDMI_DDC_ARBITRATION, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_DDC_ARBITRATION, + HDMI_DDC_ARBITRATION_HW_ARBITRATION); spin_unlock_irqrestore(&hdmi->reg_lock, flags); /* @@ -498,9 +484,8 @@ static int msm_hdmi_hdcp_auth_prepare(struct hdmi_hdcp_ctrl *hdcp_ctrl) hdmi_write(hdmi, REG_HDMI_HDCP_ENTROPY_CTRL1, 0xF00DFACE); /* Disable the RngCipher state */ - reg_val = hdmi_read(hdmi, REG_HDMI_HDCP_DEBUG_CTRL); - reg_val &= ~HDMI_HDCP_DEBUG_CTRL_RNG_CIPHER; - hdmi_write(hdmi, REG_HDMI_HDCP_DEBUG_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_HDCP_DEBUG_CTRL, + HDMI_HDCP_DEBUG_CTRL_RNG_CIPHER); DBG("HDCP_DEBUG_CTRL=0x%08x", hdmi_read(hdmi, REG_HDMI_HDCP_DEBUG_CTRL)); @@ -537,15 +522,12 @@ static int msm_hdmi_hdcp_auth_prepare(struct hdmi_hdcp_ctrl *hdcp_ctrl) static void msm_hdmi_hdcp_auth_fail(struct hdmi_hdcp_ctrl *hdcp_ctrl) { struct hdmi *hdmi = hdcp_ctrl->hdmi; - u32 reg_val; unsigned long flags; DBG("hdcp auth failed, queue reauth work"); /* clear HDMI Encrypt */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_CTRL); - reg_val &= ~HDMI_CTRL_ENCRYPTED; - hdmi_write(hdmi, REG_HDMI_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_CTRL, HDMI_CTRL_ENCRYPTED); spin_unlock_irqrestore(&hdmi->reg_lock, flags); hdcp_ctrl->hdcp_state = HDCP_STATE_AUTH_FAILED; @@ -555,7 +537,6 @@ static void msm_hdmi_hdcp_auth_fail(struct hdmi_hdcp_ctrl *hdcp_ctrl) static void msm_hdmi_hdcp_auth_done(struct hdmi_hdcp_ctrl *hdcp_ctrl) { struct hdmi *hdmi = hdcp_ctrl->hdmi; - u32 reg_val; unsigned long flags; /* @@ -563,16 +544,15 @@ static void msm_hdmi_hdcp_auth_done(struct hdmi_hdcp_ctrl *hdcp_ctrl) * there is no Arbitration between software and hardware for DDC */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_DDC_ARBITRATION); - reg_val |= HDMI_DDC_ARBITRATION_HW_ARBITRATION; - hdmi_write(hdmi, REG_HDMI_DDC_ARBITRATION, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_DDC_ARBITRATION, + HDMI_DDC_ARBITRATION_HW_ARBITRATION, + HDMI_DDC_ARBITRATION_HW_ARBITRATION); spin_unlock_irqrestore(&hdmi->reg_lock, flags); /* enable HDMI Encrypt */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_CTRL); - reg_val |= HDMI_CTRL_ENCRYPTED; - hdmi_write(hdmi, REG_HDMI_CTRL, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_CTRL, HDMI_CTRL_ENCRYPTED, + HDMI_CTRL_ENCRYPTED); spin_unlock_irqrestore(&hdmi->reg_lock, flags); hdcp_ctrl->hdcp_state = HDCP_STATE_AUTHENTICATED; @@ -1304,7 +1284,6 @@ static void msm_hdmi_hdcp_auth_work(struct work_struct *work) void msm_hdmi_hdcp_on(struct hdmi_hdcp_ctrl *hdcp_ctrl) { struct hdmi *hdmi = hdcp_ctrl->hdmi; - u32 reg_val; unsigned long flags; if ((HDCP_STATE_INACTIVE != hdcp_ctrl->hdcp_state) || @@ -1315,9 +1294,7 @@ void msm_hdmi_hdcp_on(struct hdmi_hdcp_ctrl *hdcp_ctrl) /* clear HDMI Encrypt */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_CTRL); - reg_val &= ~HDMI_CTRL_ENCRYPTED; - hdmi_write(hdmi, REG_HDMI_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_CTRL, HDMI_CTRL_ENCRYPTED); spin_unlock_irqrestore(&hdmi->reg_lock, flags); hdcp_ctrl->auth_event = 0; @@ -1330,7 +1307,6 @@ void msm_hdmi_hdcp_off(struct hdmi_hdcp_ctrl *hdcp_ctrl) { struct hdmi *hdmi = hdcp_ctrl->hdmi; unsigned long flags; - u32 reg_val; if ((HDCP_STATE_INACTIVE == hdcp_ctrl->hdcp_state) || (HDCP_STATE_NO_AKSV == hdcp_ctrl->hdcp_state)) { @@ -1345,9 +1321,7 @@ void msm_hdmi_hdcp_off(struct hdmi_hdcp_ctrl *hdcp_ctrl) * AN1_READY bits in HDMI_HDCP_LINK0_STATUS register */ spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_HPD_CTRL); - reg_val &= ~HDMI_HPD_CTRL_ENABLE; - hdmi_write(hdmi, REG_HDMI_HPD_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_HPD_CTRL, HDMI_HPD_CTRL_ENABLE); /* * Disable HDCP interrupts. @@ -1375,14 +1349,11 @@ void msm_hdmi_hdcp_off(struct hdmi_hdcp_ctrl *hdcp_ctrl) hdmi_write(hdmi, REG_HDMI_HDCP_CTRL, 0); spin_lock_irqsave(&hdmi->reg_lock, flags); - reg_val = hdmi_read(hdmi, REG_HDMI_CTRL); - reg_val &= ~HDMI_CTRL_ENCRYPTED; - hdmi_write(hdmi, REG_HDMI_CTRL, reg_val); + hdmi_clear_bits(hdmi, REG_HDMI_CTRL, HDMI_CTRL_ENCRYPTED); /* Enable HPD circuitry */ - reg_val = hdmi_read(hdmi, REG_HDMI_HPD_CTRL); - reg_val |= HDMI_HPD_CTRL_ENABLE; - hdmi_write(hdmi, REG_HDMI_HPD_CTRL, reg_val); + hdmi_update_bits(hdmi, REG_HDMI_HPD_CTRL, HDMI_HPD_CTRL_ENABLE, + HDMI_HPD_CTRL_ENABLE); spin_unlock_irqrestore(&hdmi->reg_lock, flags); hdcp_ctrl->hdcp_state = HDCP_STATE_INACTIVE; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ac86b427c0e5..db1b655dd055 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -222,20 +222,21 @@ static void load_gpu(struct drm_device *dev) */ struct drm_gpuvm *msm_context_vm(struct drm_device *dev, struct msm_context *ctx) { - static DEFINE_MUTEX(init_lock); struct msm_drm_private *priv = dev->dev_private; + struct drm_gpuvm *vm = smp_load_acquire(&ctx->vm); /* Once ctx->vm is created it is valid for the lifetime of the context: */ - if (ctx->vm) - return ctx->vm; + if (vm) + return vm; + + guard(rwsem_write)(&ctx->ctxlock); - mutex_lock(&init_lock); if (!ctx->vm) { - ctx->vm = msm_gpu_create_private_vm( + vm = msm_gpu_create_private_vm( priv->gpu, current, !ctx->userspace_managed_vm); - + if (!IS_ERR_OR_NULL(vm)) + smp_store_release(&ctx->vm, vm); } - mutex_unlock(&init_lock); return ctx->vm; } @@ -250,7 +251,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file) return -ENOMEM; INIT_LIST_HEAD(&ctx->submitqueues); - rwlock_init(&ctx->queuelock); + init_rwsem(&ctx->ctxlock); kref_init(&ctx->ref); msm_submitqueue_init(dev, ctx); @@ -422,10 +423,14 @@ static int msm_ioctl_gem_info_iova(struct drm_device *dev, { struct msm_drm_private *priv = dev->dev_private; struct msm_context *ctx = file->driver_priv; + struct drm_gpuvm *vm = msm_context_vm(dev, ctx); if (!priv->gpu) return -EINVAL; + if (!vm) + return UERR(ENOMEM, dev, "no VM"); + if (msm_context_is_vmbind(ctx)) return UERR(EINVAL, dev, "VM_BIND is enabled"); @@ -436,7 +441,7 @@ static int msm_ioctl_gem_info_iova(struct drm_device *dev, * Don't pin the memory here - just get an address so that userspace can * be productive */ - return msm_gem_get_iova(obj, msm_context_vm(dev, ctx), iova); + return msm_gem_get_iova(obj, vm, iova); } static int msm_ioctl_gem_info_set_iova(struct drm_device *dev, @@ -450,6 +455,9 @@ static int msm_ioctl_gem_info_set_iova(struct drm_device *dev, if (!priv->gpu) return -EINVAL; + if (!vm) + return UERR(ENOMEM, dev, "no VM"); + if (msm_context_is_vmbind(ctx)) return UERR(EINVAL, dev, "VM_BIND is enabled"); diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 3787db8770ad..eb4bbae8557b 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -261,8 +261,6 @@ const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb); struct drm_framebuffer *msm_framebuffer_create(struct drm_device *dev, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd); -struct drm_framebuffer * msm_alloc_stolen_fb(struct drm_device *dev, - int w, int h, int p, uint32_t format); #ifdef CONFIG_DRM_MSM_KMS_FBDEV int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, @@ -356,8 +354,6 @@ void __exit msm_dp_unregister(void); int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, struct drm_encoder *encoder, bool yuv_supported); void msm_dp_snapshot(struct msm_disp_state *disp_state, struct msm_dp *dp_display); -bool msm_dp_is_yuv_420_enabled(const struct msm_dp *dp_display, - const struct drm_display_mode *mode); bool msm_dp_needs_periph_flush(const struct msm_dp *dp_display, const struct drm_display_mode *mode); bool msm_dp_wide_bus_available(const struct msm_dp *dp_display); @@ -382,12 +378,6 @@ static inline void msm_dp_snapshot(struct msm_disp_state *disp_state, struct msm { } -static inline bool msm_dp_is_yuv_420_enabled(const struct msm_dp *dp_display, - const struct drm_display_mode *mode) -{ - return false; -} - static inline bool msm_dp_needs_periph_flush(const struct msm_dp *dp_display, const struct drm_display_mode *mode) { @@ -503,13 +493,6 @@ void msm_hrtimer_work_init(struct msm_hrtimer_work *work, #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) -static inline int align_pitch(int width, int bpp) -{ - int bytespp = (bpp + 7) / 8; - /* adreno needs pitch aligned to 32 pixels: */ - return bytespp * ALIGN(width, 32); -} - /* for the generated headers: */ #define INVALID_IDX(idx) ({BUG(); 0;}) #define fui(x) ({BUG(); 0;}) diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index 9b681e144c07..60c108d35d2a 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -6,7 +6,6 @@ #include #include -#include #include #include #include @@ -29,10 +28,6 @@ struct msm_framebuffer { }; #define to_msm_framebuffer(x) container_of(x, struct msm_framebuffer, base) -static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, - const struct drm_format_info *info, - const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos); - static int msm_framebuffer_dirtyfb(struct drm_framebuffer *fb, struct drm_file *file_priv, unsigned int flags, unsigned int color, struct drm_clip_rect *clips, @@ -139,39 +134,10 @@ const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb) return msm_fb->format; } -struct drm_framebuffer *msm_framebuffer_create(struct drm_device *dev, - struct drm_file *file, const struct drm_format_info *info, - const struct drm_mode_fb_cmd2 *mode_cmd) -{ - struct drm_gem_object *bos[4] = {0}; - struct drm_framebuffer *fb; - int ret, i, n = info->num_planes; - - for (i = 0; i < n; i++) { - bos[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]); - if (!bos[i]) { - ret = -ENXIO; - goto out_unref; - } - } - - fb = msm_framebuffer_init(dev, info, mode_cmd, bos); - if (IS_ERR(fb)) { - ret = PTR_ERR(fb); - goto out_unref; - } - - return fb; - -out_unref: - for (i = 0; i < n; i++) - drm_gem_object_put(bos[i]); - return ERR_PTR(ret); -} - -static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, - const struct drm_format_info *info, - const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos) +static struct drm_framebuffer * +msm_framebuffer_init(struct drm_device *dev, const struct drm_format_info *info, + const struct drm_mode_fb_cmd2 *mode_cmd, + struct drm_gem_object **bos) { struct msm_drm_private *priv = dev->dev_private; struct msm_kms *kms = priv->kms; @@ -251,47 +217,33 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, return ERR_PTR(ret); } -struct drm_framebuffer * -msm_alloc_stolen_fb(struct drm_device *dev, int w, int h, int p, uint32_t format) +struct drm_framebuffer *msm_framebuffer_create(struct drm_device *dev, + struct drm_file *file, + const struct drm_format_info *info, + const struct drm_mode_fb_cmd2 *mode_cmd) { - struct drm_mode_fb_cmd2 mode_cmd = { - .pixel_format = format, - .width = w, - .height = h, - .pitches = { p }, - }; - struct drm_gem_object *bo; + struct drm_gem_object *bos[4] = {0}; struct drm_framebuffer *fb; - int size; + int ret, i, n = info->num_planes; - /* allocate backing bo */ - size = mode_cmd.pitches[0] * mode_cmd.height; - DBG("allocating %d bytes for fb %d", size, dev->primary->index); - bo = msm_gem_new(dev, size, MSM_BO_SCANOUT | MSM_BO_WC | MSM_BO_STOLEN); - if (IS_ERR(bo)) { - dev_warn(dev->dev, "could not allocate stolen bo\n"); - /* try regular bo: */ - bo = msm_gem_new(dev, size, MSM_BO_SCANOUT | MSM_BO_WC); - } - if (IS_ERR(bo)) { - DRM_DEV_ERROR(dev->dev, "failed to allocate buffer object\n"); - return ERR_CAST(bo); + for (i = 0; i < n; i++) { + bos[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]); + if (!bos[i]) { + ret = -ENXIO; + goto out_unref; + } } - msm_gem_object_set_name(bo, "stolenfb"); - - fb = msm_framebuffer_init(dev, - drm_get_format_info(dev, mode_cmd.pixel_format, - mode_cmd.modifier[0]), - &mode_cmd, &bo); + fb = msm_framebuffer_init(dev, info, mode_cmd, bos); if (IS_ERR(fb)) { - DRM_DEV_ERROR(dev->dev, "failed to allocate fb\n"); - /* note: if fb creation failed, we can't rely on fb destroy - * to unref the bo: - */ - drm_gem_object_put(bo); - return ERR_CAST(fb); + ret = PTR_ERR(fb); + goto out_unref; } return fb; + +out_unref: + for (i = 0; i < n; i++) + drm_gem_object_put(bos[i]); + return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index fd19995b12b5..89ca9da3e1f2 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -40,17 +41,15 @@ static int msm_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma) static void msm_fbdev_fb_destroy(struct fb_info *info) { struct drm_fb_helper *helper = (struct drm_fb_helper *)info->par; - struct drm_framebuffer *fb = helper->fb; - struct drm_gem_object *bo = msm_framebuffer_bo(fb, 0); + struct drm_gem_object *bo = msm_framebuffer_bo(helper->fb, 0); DBG(); drm_fb_helper_fini(helper); - /* this will free the backing object */ msm_gem_put_vaddr(bo); - drm_framebuffer_remove(fb); + drm_client_buffer_delete(helper->buffer); drm_client_release(&helper->client); } @@ -89,31 +88,54 @@ static const struct drm_fb_helper_funcs msm_fbdev_helper_funcs = { int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct drm_fb_helper_surface_size *sizes) { - struct drm_device *dev = helper->dev; + struct drm_client_dev *client = &helper->client; + struct drm_device *dev = client->dev; + struct drm_file *file = client->file; struct msm_drm_private *priv = dev->dev_private; struct fb_info *fbi = helper->info; - struct drm_framebuffer *fb = NULL; + const struct drm_format_info *format; + u32 fourcc, pitch, handle; + u64 size; struct drm_gem_object *bo; + struct drm_client_buffer *buffer; uint64_t paddr; - uint32_t format; - int ret, pitch; - - format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); + int ret; DBG("create fbdev: %dx%d@%d (%dx%d)", sizes->surface_width, sizes->surface_height, sizes->surface_bpp, sizes->fb_width, sizes->fb_height); - pitch = align_pitch(sizes->surface_width, sizes->surface_bpp); - fb = msm_alloc_stolen_fb(dev, sizes->surface_width, - sizes->surface_height, pitch, format); + fourcc = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); + format = drm_get_format_info(dev, fourcc, DRM_FORMAT_MOD_LINEAR); + /* adreno needs pitch aligned to 32 pixels: */ + pitch = drm_format_info_min_pitch(format, 0, ALIGN(sizes->surface_width, 32)); + size = ALIGN(pitch * sizes->surface_height, PAGE_SIZE); - if (IS_ERR(fb)) { - DRM_DEV_ERROR(dev->dev, "failed to allocate fb\n"); - return PTR_ERR(fb); + /* allocate backing bo */ + DBG("allocating %llu bytes for fb %d", size, dev->primary->index); + bo = msm_gem_new(dev, size, MSM_BO_SCANOUT | MSM_BO_WC | MSM_BO_STOLEN, NULL); + if (IS_ERR(bo)) { + drm_warn(dev, "could not allocate stolen bo\n"); + /* try regular bo: */ + bo = msm_gem_new(dev, size, MSM_BO_SCANOUT | MSM_BO_WC, NULL); + if (IS_ERR(bo)) { + drm_err(dev, "failed to allocate buffer object\n"); + return PTR_ERR(bo); + } } - bo = msm_framebuffer_bo(fb, 0); + msm_gem_object_set_name(bo, "stolenfb"); + + ret = drm_gem_handle_create(file, bo, &handle); + if (ret) + goto err_drm_gem_object_put; + + buffer = drm_client_buffer_create(client, sizes->surface_width, sizes->surface_height, + fourcc, handle, pitch); + if (IS_ERR(buffer)) { + ret = PTR_ERR(buffer); + goto err_drm_gem_handle_delete; + } /* * NOTE: if we can be guaranteed to be able to map buffer @@ -122,14 +144,15 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, */ ret = msm_gem_get_and_pin_iova(bo, priv->kms->vm, &paddr); if (ret) { - DRM_DEV_ERROR(dev->dev, "failed to get buffer obj iova: %d\n", ret); - goto fail; + drm_err(dev, "failed to get buffer obj iova: %d\n", ret); + goto err_drm_client_buffer_delete; } DBG("fbi=%p, dev=%p", fbi, dev); helper->funcs = &msm_fbdev_helper_funcs; - helper->fb = fb; + helper->buffer = buffer; + helper->fb = buffer->fb; fbi->fbops = &msm_fb_ops; @@ -138,18 +161,31 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, fbi->screen_buffer = msm_gem_get_vaddr(bo); if (IS_ERR(fbi->screen_buffer)) { ret = PTR_ERR(fbi->screen_buffer); - goto fail; + goto err_msm_gem_unpin; } fbi->screen_size = bo->size; fbi->fix.smem_start = paddr; fbi->fix.smem_len = bo->size; DBG("par=%p, %dx%d", fbi->par, fbi->var.xres, fbi->var.yres); - DBG("allocated %dx%d fb", fb->width, fb->height); + DBG("allocated %dx%d fb", buffer->fb->width, buffer->fb->height); + + /* The handle is only needed for creating the framebuffer. */ + drm_gem_handle_delete(file, handle); + + /* The framebuffer still holds a reference on the GEM object. */ + drm_gem_object_put(bo); return 0; -fail: - drm_framebuffer_remove(fb); +err_msm_gem_unpin: + msm_gem_unpin_iova(bo, priv->kms->vm); + msm_gem_vma_put(bo); +err_drm_client_buffer_delete: + drm_client_buffer_delete(buffer); +err_drm_gem_handle_delete: + drm_gem_handle_delete(file, handle); +err_drm_gem_object_put: + drm_gem_object_put(bo); return ret; } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 6a78e242de7c..c4cff3d53d81 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1094,7 +1094,9 @@ static void msm_gem_free_object(struct drm_gem_object *obj) */ kvfree(msm_obj->pages); - drm_prime_gem_destroy(obj, msm_obj->sgt); + /* In msm_gem_import() error path, sgt won't be set yet: */ + if (msm_obj->sgt) + drm_prime_gem_destroy(obj, msm_obj->sgt); } else { msm_gem_vunmap(obj); put_pages(obj); @@ -1135,10 +1137,21 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, size_t size, uint32_t flags, uint32_t *handle, char *name) { - struct drm_gem_object *obj; + struct drm_gem_object *obj, *r_obj = NULL; int ret; - obj = msm_gem_new(dev, size, flags); + if (flags & MSM_BO_NO_SHARE) { + struct msm_drm_private *priv = dev->dev_private; + struct msm_context *ctx = file->driver_priv; + struct drm_gpuvm *vm = msm_context_vm(dev, ctx); + + if (!priv->gpu || !vm) + return UERR(EINVAL, dev, "not supported with shared VM"); + + r_obj = drm_gpuvm_resv_obj(vm); + } + + obj = msm_gem_new(dev, size, flags, r_obj); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -1146,15 +1159,6 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, if (name) msm_gem_object_set_name(obj, "%s", name); - if (flags & MSM_BO_NO_SHARE) { - struct msm_context *ctx = file->driver_priv; - struct drm_gem_object *r_obj = drm_gpuvm_resv_obj(ctx->vm); - - drm_gem_object_get(r_obj); - - obj->resv = r_obj->resv; - } - ret = drm_gem_handle_create(file, obj, handle); /* drop reference from allocate - handle holds it now */ @@ -1233,10 +1237,27 @@ static int msm_gem_new_impl(struct drm_device *dev, uint32_t flags, return 0; } -struct drm_gem_object *msm_gem_new(struct drm_device *dev, size_t size, uint32_t flags) +static int msm_gem_init_bookkeeping(struct drm_gem_object *obj) +{ + struct msm_drm_private *priv = obj->dev->dev_private; + + if (drm_gem_is_imported(obj)) { + drm_gem_lru_move_tail(&priv->lru.pinned, obj); + } else { + drm_gem_lru_move_tail(&priv->lru.unbacked, obj); + } + + mutex_lock(&priv->obj_lock); + list_add_tail(&to_msm_bo(obj)->node, &priv->objects); + mutex_unlock(&priv->obj_lock); + + return drm_gem_create_mmap_offset(obj); +} + +struct drm_gem_object * +msm_gem_new(struct drm_device *dev, size_t size, uint32_t flags, + struct drm_gem_object *r_obj) { - struct msm_drm_private *priv = dev->dev_private; - struct msm_gem_object *msm_obj; struct drm_gem_object *obj = NULL; int ret; @@ -1252,7 +1273,10 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, size_t size, uint32_t if (ret) return ERR_PTR(ret); - msm_obj = to_msm_bo(obj); + if (flags & MSM_BO_NO_SHARE) { + drm_gem_object_get(r_obj); + obj->resv = r_obj->resv; + } ret = drm_gem_object_init(dev, obj, size); if (ret) @@ -1265,13 +1289,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, size_t size, uint32_t */ mapping_set_gfp_mask(obj->filp->f_mapping, GFP_HIGHUSER); - drm_gem_lru_move_tail(&priv->lru.unbacked, obj); - - mutex_lock(&priv->obj_lock); - list_add_tail(&msm_obj->node, &priv->objects); - mutex_unlock(&priv->obj_lock); - - ret = drm_gem_create_mmap_offset(obj); + ret = msm_gem_init_bookkeeping(obj); if (ret) goto fail; @@ -1283,11 +1301,12 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, size_t size, uint32_t } struct drm_gem_object *msm_gem_import(struct drm_device *dev, - struct dma_buf *dmabuf, struct sg_table *sgt) + struct dma_buf_attachment *attach, + struct sg_table *sgt) { - struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; struct drm_gem_object *obj; + struct dma_buf *dmabuf = attach->dmabuf; size_t size, npages; int ret; @@ -1297,38 +1316,35 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, if (ret) return ERR_PTR(ret); + /* + * Set import_attach here in case we hit an error path that ends + * up in drm_gem_object_put() -> msm_gem_free_object() + */ + obj->import_attach = attach; + obj->resv = dmabuf->resv; drm_gem_private_object_init(dev, obj, size); npages = size / PAGE_SIZE; msm_obj = to_msm_bo(obj); - msm_gem_lock(obj); - msm_obj->sgt = sgt; msm_obj->pages = kvmalloc_objs(struct page *, npages); if (!msm_obj->pages) { - msm_gem_unlock(obj); ret = -ENOMEM; goto fail; } ret = drm_prime_sg_to_page_array(sgt, msm_obj->pages, npages); if (ret) { - msm_gem_unlock(obj); goto fail; } - msm_gem_unlock(obj); - - drm_gem_lru_move_tail(&priv->lru.pinned, obj); - - mutex_lock(&priv->obj_lock); - list_add_tail(&msm_obj->node, &priv->objects); - mutex_unlock(&priv->obj_lock); - - ret = drm_gem_create_mmap_offset(obj); + ret = msm_gem_init_bookkeeping(obj); if (ret) goto fail; + /* Now that we are past potential failure points, set sgt: */ + msm_obj->sgt = sgt; + return obj; fail: @@ -1341,7 +1357,7 @@ void *msm_gem_kernel_new(struct drm_device *dev, size_t size, uint32_t flags, uint64_t *iova) { void *vaddr; - struct drm_gem_object *obj = msm_gem_new(dev, size, flags); + struct drm_gem_object *obj = msm_gem_new(dev, size, flags, NULL); int ret; if (IS_ERR(obj)) diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 762e546d25ef..dff60cbc9d95 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -296,13 +296,14 @@ int msm_gem_cpu_fini(struct drm_gem_object *obj); int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, size_t size, uint32_t flags, uint32_t *handle, char *name); struct drm_gem_object *msm_gem_new(struct drm_device *dev, - size_t size, uint32_t flags); + size_t size, uint32_t flags, struct drm_gem_object *r_obj); void *msm_gem_kernel_new(struct drm_device *dev, size_t size, uint32_t flags, struct drm_gpuvm *vm, struct drm_gem_object **bo, uint64_t *iova); void msm_gem_kernel_put(struct drm_gem_object *bo, struct drm_gpuvm *vm); struct drm_gem_object *msm_gem_import(struct drm_device *dev, - struct dma_buf *dmabuf, struct sg_table *sgt); + struct dma_buf_attachment *attach, + struct sg_table *sgt); __printf(2, 3) void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...); diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index 036d34c674d9..beb7f22fd694 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -83,7 +83,7 @@ struct drm_gem_object *msm_gem_prime_import(struct drm_device *dev, struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg) { - return msm_gem_import(dev, attach->dmabuf, sg); + return msm_gem_import(dev, attach, sg); } struct dma_buf *msm_gem_prime_export(struct drm_gem_object *obj, int flags) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3c6bc90c3d48..5862db05297a 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -30,20 +30,17 @@ */ static struct msm_gem_submit *submit_create(struct drm_device *dev, - struct msm_gpu *gpu, + struct msm_gpu *gpu, struct drm_gpuvm *vm, struct msm_gpu_submitqueue *queue, uint32_t nr_bos, uint32_t nr_cmds, u64 drm_client_id) { static atomic_t ident = ATOMIC_INIT(0); struct msm_gem_submit *submit; - uint64_t sz; + size_t sz; int ret; - sz = struct_size(submit, bos, nr_bos) + - ((u64)nr_cmds * sizeof(submit->cmd[0])); - - if (sz > SIZE_MAX) - return ERR_PTR(-ENOMEM); + sz = size_add(struct_size(submit, bos, nr_bos), + array_size(sizeof(submit->cmd[0]), nr_cmds)); submit = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN); if (!submit) @@ -66,7 +63,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, kref_init(&submit->ref); submit->dev = dev; - submit->vm = msm_context_vm(dev, queue->ctx); + submit->vm = vm; submit->gpu = gpu; submit->cmd = (void *)&submit->bos[nr_bos]; submit->queue = queue; @@ -250,16 +247,14 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit, sz = array_size(submit_cmd.nr_relocs, sizeof(struct drm_msm_gem_submit_reloc)); - /* check for overflow: */ - if (sz == SIZE_MAX) { - ret = -ENOMEM; - goto out; - } submit->cmd[i].relocs = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN); if (!submit->cmd[i].relocs) { ret = -ENOMEM; goto out; } + + submit->nr_cmds = i + 1; + ret = copy_from_user(submit->cmd[i].relocs, userptr, sz); if (ret) { ret = -EFAULT; @@ -554,6 +549,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_context *ctx = file->driver_priv; + struct drm_gpuvm *vm = msm_context_vm(dev, ctx); struct msm_gem_submit *submit = NULL; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; @@ -569,10 +565,13 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (!gpu) return -ENXIO; + if (!vm) + return UERR(ENOMEM, dev, "no VM"); + if (args->pad) return -EINVAL; - if (to_msm_vm(ctx->vm)->unusable) + if (to_msm_vm(vm)->unusable) return UERR(EPIPE, dev, "context is unusable"); /* for now, we just have 3d pipe.. eventually this would need to @@ -609,7 +608,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, } } - submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds, + submit = submit_create(dev, gpu, vm, queue, args->nr_bos, args->nr_cmds, file->client_id); if (IS_ERR(submit)) { ret = PTR_ERR(submit); @@ -719,8 +718,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, goto out; } - submit->nr_cmds = args->nr_cmds; - idr_preload(GFP_KERNEL); spin_lock(&queue->idr_lock); diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index c4cfe036066b..c11d021581e0 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -458,6 +458,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) return ret; } + drm_gpuvm_bo_evict(vm_bo, false); + return 0; } @@ -955,7 +957,7 @@ msm_gem_vm_close(struct drm_gpuvm *gpuvm) static struct msm_vm_bind_job * -vm_bind_job_create(struct drm_device *dev, struct drm_file *file, +vm_bind_job_create(struct drm_device *dev, struct drm_file *file, struct drm_gpuvm *vm, struct msm_gpu_submitqueue *queue, uint32_t nr_ops) { struct msm_vm_bind_job *job; @@ -972,7 +974,7 @@ vm_bind_job_create(struct drm_device *dev, struct drm_file *file, return ERR_PTR(ret); } - job->vm = msm_context_vm(dev, queue->ctx); + job->vm = vm; job->queue = queue; INIT_LIST_HEAD(&job->vm_ops); @@ -1431,6 +1433,7 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) struct msm_drm_private *priv = dev->dev_private; struct drm_msm_vm_bind *args = data; struct msm_context *ctx = file->driver_priv; + struct drm_gpuvm *vm = msm_context_vm(dev, ctx); struct msm_vm_bind_job *job = NULL; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; @@ -1445,11 +1448,14 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) if (!gpu) return -ENXIO; + if (!vm) + return UERR(ENOMEM, dev, "no VM"); + /* * Maybe we could allow just UNMAP ops? OTOH userspace should just * immediately close the device file and all will be torn down. */ - if (to_msm_vm(msm_context_vm(dev, ctx))->unusable) + if (to_msm_vm(vm)->unusable) return UERR(EPIPE, dev, "context is unusable"); /* @@ -1480,7 +1486,7 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) } } - job = vm_bind_job_create(dev, file, queue, args->nr_ops); + job = vm_bind_job_create(dev, file, vm, queue, args->nr_ops); if (IS_ERR(job)) { ret = PTR_ERR(job); goto out_post_unlock; diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 18ed00e5f143..0c2c35636251 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -505,6 +505,8 @@ static void recover_worker(struct kthread_work *work) */ if (!vm->managed) msm_gem_vm_unusable(submit->vm); + + put_task_struct(task); } noreclaim_flag = memalloc_noreclaim_save(); @@ -552,11 +554,13 @@ static void recover_worker(struct kthread_work *work) msm_update_fence(ring->fctx, fence); } - /* retire completed submits, plus the one that hung: */ - retire_submits(gpu); + priv->disable_err_irq = false; gpu->funcs->recover(gpu); + /* retire completed submits, plus the one that hung: */ + retire_submits(gpu); + /* * Replay all remaining submits starting with highest priority * ring @@ -875,7 +879,7 @@ msm_gpu_create_private_vm(struct msm_gpu *gpu, struct task_struct *task, to_msm_vm(vm)->pid = get_pid(task_pid(task)); } - if (IS_ERR_OR_NULL(vm)) + if (IS_ERR_OR_NULL(vm) && kernel_managed) vm = drm_gpuvm_get(gpu->vm); return vm; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 6c83b8cbbb90..d27d54bdb7a7 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -392,8 +392,8 @@ msm_gpu_sysprof_no_ifpc(struct msm_gpu *gpu) * struct msm_context - per-drm_file context */ struct msm_context { - /** @queuelock: synchronizes access to submitqueues list */ - rwlock_t queuelock; + /** @ctxlock: synchronizes access to submitqueues list, etc */ + struct rw_semaphore ctxlock; /** @submitqueues: list of &msm_gpu_submitqueue created by userspace */ struct list_head submitqueues; /** diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 897e42c8d5c8..da6782fca6bd 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -7,6 +7,15 @@ #include #include #include + +#if defined(CONFIG_ARM_DMA_USE_IOMMU) +#include +#else +#define arm_iommu_detach_device(...) ({ }) +#define arm_iommu_release_mapping(...) ({ }) +#define to_dma_iommu_mapping(dev) NULL +#endif + #include "msm_drv.h" #include "msm_gpu_trace.h" #include "msm_mmu.h" @@ -749,6 +758,19 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) mutex_init(&iommu->init_lock); + /* + * ARM32 attaches a DMA mapping domain to every IOMMU-backed device, + * which would make attaching our own domain fail with -EBUSY. + */ + if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + + if (mapping) { + arm_iommu_detach_device(dev); + arm_iommu_release_mapping(mapping); + } + } + ret = iommu_attach_device(iommu->domain, dev); if (ret) { iommu_domain_free(domain); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 2d6b930b766e..59c69aa75649 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -109,9 +109,9 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->memptrs_iova = memptrs_iova; ret = drm_sched_init(&ring->sched, &args); - if (ret) { + if (ret) goto fail; - } + ring->sched_initialized = true; INIT_LIST_HEAD(&ring->submits); spin_lock_init(&ring->submit_lock); @@ -133,7 +133,8 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring) if (IS_ERR_OR_NULL(ring)) return; - drm_sched_fini(&ring->sched); + if (ring->sched_initialized) + drm_sched_fini(&ring->sched); msm_fence_context_free(ring->fctx); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index 28ca8c9f7463..3631ec283c6e 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -56,6 +56,7 @@ struct msm_ringbuffer { * The job scheduler for this ring. */ struct drm_gpu_scheduler sched; + bool sched_initialized; /* * List of in-flight submits on this ring. Protected by submit_lock. diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 1a5a77b28016..d307cdd17d90 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -9,6 +9,8 @@ int msm_context_set_sysprof(struct msm_context *ctx, struct msm_gpu *gpu, int sysprof) { + guard(rwsem_write)(&ctx->ctxlock); + /* * Since pm_runtime and sysprof_active are both refcounts, we * call apply the new value first, and then unwind the previous @@ -93,18 +95,15 @@ struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_context *ctx, if (!ctx) return NULL; - read_lock(&ctx->queuelock); + guard(rwsem_read)(&ctx->ctxlock); list_for_each_entry(entry, &ctx->submitqueues, node) { if (entry->id == id) { kref_get(&entry->ref); - read_unlock(&ctx->queuelock); - return entry; } } - read_unlock(&ctx->queuelock); return NULL; } @@ -175,6 +174,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, struct msm_drm_private *priv = drm->dev_private; struct msm_gpu_submitqueue *queue; enum drm_sched_priority sched_prio; + struct drm_gpuvm *vm = NULL; unsigned ring_nr; int ret; @@ -187,6 +187,11 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, if (flags & MSM_SUBMITQUEUE_VM_BIND) { unsigned sz; + vm = msm_context_vm(drm, ctx); + + if (!vm) + return UERR(ENOMEM, drm, "no VM"); + /* Not allowed for kernel managed VMs (ie. kernel allocs VA) */ if (!msm_context_is_vmbind(ctx)) return -EINVAL; @@ -218,7 +223,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, queue->flags = flags; if (flags & MSM_SUBMITQUEUE_VM_BIND) { - struct drm_gpu_scheduler *sched = &to_msm_vm(msm_context_vm(drm, ctx))->sched; + struct drm_gpu_scheduler *sched = &to_msm_vm(vm)->sched; queue->entity = &queue->_vm_bind_entity[0]; @@ -237,7 +242,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, return ret; } - write_lock(&ctx->queuelock); + guard(rwsem_write)(&ctx->ctxlock); queue->ctx = msm_context_get(ctx); queue->id = ctx->queueid++; @@ -251,8 +256,6 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, list_add_tail(&queue->node, &ctx->submitqueues); - write_unlock(&ctx->queuelock); - return 0; } @@ -335,19 +338,16 @@ int msm_submitqueue_remove(struct msm_context *ctx, u32 id) if (!id) return -ENOENT; - write_lock(&ctx->queuelock); + guard(rwsem_write)(&ctx->ctxlock); list_for_each_entry(entry, &ctx->submitqueues, node) { if (entry->id == id) { list_del(&entry->node); - write_unlock(&ctx->queuelock); - msm_submitqueue_put(entry); return 0; } } - write_unlock(&ctx->queuelock); return -ENOENT; } diff --git a/drivers/gpu/drm/msm/registers/adreno/a3xx.xml b/drivers/gpu/drm/msm/registers/adreno/a3xx.xml index 09c9606fc3e1..21b00a17ef3e 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a3xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a3xx.xml @@ -1495,6 +1495,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + + diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index 3349c01646e1..69dd0446f8d2 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -1268,7 +1268,7 @@ by a particular renderpass/blit. - + diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 2fc0334e0d6c..075eba2d47f3 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -24,6 +24,8 @@ * Alex Deucher */ +#include + #include #include #include @@ -594,7 +596,8 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, if (((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880)) && !radeon_crtc->ss_enabled) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; - if (ASIC_IS_DCE32(rdev) && mode->clock > 165000) + if ((ASIC_IS_DCE32(rdev) || dmi_match(DMI_PRODUCT_NAME, "iMac11,1")) + && mode->clock > 165000) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; } else { radeon_crtc->pll_flags |= RADEON_PLL_LEGACY; diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 5cfd8fcfa5e8..8b3f8303a967 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1707,7 +1707,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) { /* DP_SET_POWER_D0 is set in radeon_dp_link_train */ radeon_dp_link_train(encoder, connector); - if (ASIC_IS_DCE4(rdev)) + if (ASIC_IS_DCE4(rdev) || dmi_match(DMI_PRODUCT_NAME, "iMac11,1")) atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0); } if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { @@ -2123,17 +2123,20 @@ int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder, int fe_idx) } /* - * On DCE32 any encoder can drive any block so usually just use crtc id, - * but Apple thinks different at least on iMac10,1 and iMac11,2, so there use linkb, - * otherwise the internal eDP panel will stay dark. + * Apple routes the internal eDP panel through Link B of the DIG encoder + * instead of Link A on the iMac10,1, iMac11,1 and iMac11,2. + * Use linkb to avoid a dark display. */ - if (ASIC_IS_DCE32(rdev)) { - if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1") || - dmi_match(DMI_PRODUCT_NAME, "iMac11,2")) - enc_idx = (dig->linkb) ? 1 : 0; - else - enc_idx = radeon_crtc->crtc_id; + if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1") || + dmi_match(DMI_PRODUCT_NAME, "iMac11,1") || + dmi_match(DMI_PRODUCT_NAME, "iMac11,2")) { + enc_idx = (dig->linkb) ? 1 : 0; + goto assigned; + } + /* on DCE32 and encoder can driver any block so just crtc id */ + if (ASIC_IS_DCE32(rdev)) { + enc_idx = radeon_crtc->crtc_id; goto assigned; } diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 67ada1d6c2fb..c92468cb9b89 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -153,7 +153,9 @@ xe-y += xe_bb.o \ xe_wait_user_fence.o \ xe_wopcm.o -xe-$(CONFIG_I2C) += xe_i2c.o +xe-$(CONFIG_I2C) += xe_i2c.o \ + xe_amc.o + xe-$(CONFIG_DRM_XE_GPUSVM) += xe_svm.o xe-$(CONFIG_DRM_GPUSVM) += xe_userptr.o diff --git a/drivers/gpu/drm/xe/regs/xe_i2c_regs.h b/drivers/gpu/drm/xe/regs/xe_i2c_regs.h index f2e455e2bfe4..37550e4a20f8 100644 --- a/drivers/gpu/drm/xe/regs/xe_i2c_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_i2c_regs.h @@ -20,4 +20,6 @@ #define I2C_CONFIG_CMD XE_REG(I2C_CONFIG_SPACE_OFFSET + PCI_COMMAND) #define I2C_CONFIG_PMCSR XE_REG(I2C_CONFIG_SPACE_OFFSET + 0x84) +#define I2C_REG(reg) XE_REG((reg) + I2C_MEM_SPACE_OFFSET) + #endif /* _XE_I2C_REGS_H_ */ diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index 3c1be809be82..f10d9513747b 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -198,8 +198,7 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test, err = xe_bo_vmap(bo); if (err) { - KUNIT_FAIL(test, "Failed to vmap our pagetables: %li\n", - PTR_ERR(bo)); + KUNIT_FAIL(test, "Failed to vmap our pagetables: %d\n", err); return; } diff --git a/drivers/gpu/drm/xe/xe_amc.c b/drivers/gpu/drm/xe/xe_amc.c new file mode 100644 index 000000000000..8ecadee6eea3 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_amc.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 Intel Corporation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "regs/xe_i2c_regs.h" + +#include "xe_amc.h" +#include "xe_device.h" +#include "xe_i2c.h" +#include "xe_mmio.h" + +/** + * DOC: Add-In Management Controller (AMC) + * + * Handler for the SMBus Alerts from the AMC. All the alerts from AMC will cause + * the device to be declared wedged. + */ + +#define AMC_COMMAND 0x0f +#define AMC_GPU_I2C_ADDR 0x8f +#define AMC_VERSION_V1 0x01 +#define AMC_DESTINATION_ID 12 +#define AMC_SOURCE_ID 8 +#define AMC_FLAGS 0xc8 + +#define AMC_MSG_TYPE 0x7e +#define AMC_GET_ALERT_REASON 0x01 + +enum xe_amc_alert { + AMC_ALERT_UNKNOWN, + AMC_ALERT_FW_DOWNLOAD, + AMC_ALERT_THERMAL_TRIP, + AMC_ALERT_OOB_REQUEST, + AMC_ALERT_OOB_RESET, + AMC_ALERT_CATERR, +}; + +static const char * const amc_alert[] = { + [AMC_ALERT_FW_DOWNLOAD] = "Firmware Download", + [AMC_ALERT_THERMAL_TRIP] = "Thermal Trip", + [AMC_ALERT_OOB_REQUEST] = "OOB Request", + [AMC_ALERT_OOB_RESET] = "OOB Reset", + [AMC_ALERT_CATERR] = "Catastrophic", +}; + +struct xe_amc { + struct xe_i2c *i2c; + struct work_struct work; +}; + +struct amc_header { + u8 command; + u8 len; + u8 address; + u8 version; + u8 destination; + u8 source; + u8 flags; +} __packed; + +struct amc_message { + u8 type; + u16 vendor; + u8 command; +} __packed; + +struct amc_request { + struct amc_header header; + struct amc_message message; + u32 reserved; +} __packed; + +struct amc_response { + struct amc_header header; + struct amc_message message; + u8 error; + u8 value; +} __packed; + +static const struct amc_request amc_get_alert_reason = { + .header = { + .command = AMC_COMMAND, + .len = sizeof(struct amc_request) - 2, + .address = AMC_GPU_I2C_ADDR, + .version = AMC_VERSION_V1, + .destination = AMC_DESTINATION_ID, + .source = AMC_SOURCE_ID, + .flags = AMC_FLAGS, + }, + .message = { + .type = AMC_MSG_TYPE, + .vendor = htons(PCI_VENDOR_ID_INTEL), + .command = AMC_GET_ALERT_REASON, + }, +}; + +static void xe_amc_work(struct work_struct *work) +{ + const struct amc_request *request = &amc_get_alert_reason; + struct xe_amc *amc = from_work(amc, work, work); + u8 alert_reason = AMC_ALERT_UNKNOWN; + struct amc_response response; + struct i2c_client *client; + int ret; + + client = amc->i2c->client[XE_I2C_CLIENT_AMC]; + if (IS_ERR_OR_NULL(client)) + goto out_reassert_interrupt; + + ret = i2c_master_send(client, (u8 *)request, sizeof(*request)); + if (ret < 0) { + dev_err(&client->dev, "failed to send request (%d)\n", ret); + goto out_reassert_interrupt; + } + + /* AMC needs 20ms to generate the response. */ + fsleep(20 * USEC_PER_MSEC); + + ret = i2c_master_recv(client, (u8 *)&response, sizeof(response)); + if (ret < 0) { + dev_err(&client->dev, "failed to read response (%d)\n", ret); + goto out_reassert_interrupt; + } + + if (!response.header.len) { + dev_err(&client->dev, "empty response from AMC\n"); + goto out_reassert_interrupt; + } + + if (memcmp(&response.message, &request->message, sizeof(struct amc_message))) { + dev_err(&client->dev, "response does not match the request\n"); + goto out_reassert_interrupt; + } + + if (response.error) { + dev_err(&client->dev, "AMC error 0x%02x\n", response.error); + goto out_reassert_interrupt; + } + + alert_reason = response.value; + dev_dbg(&client->dev, "Alert reason: %d\n", alert_reason); + +out_reassert_interrupt: + xe_mmio_rmw32(amc->i2c->mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); + + switch (alert_reason) { + case AMC_ALERT_FW_DOWNLOAD: + case AMC_ALERT_THERMAL_TRIP: + case AMC_ALERT_OOB_REQUEST: + case AMC_ALERT_OOB_RESET: + case AMC_ALERT_CATERR: + dev_warn(amc->i2c->drm_dev, "AMC Alert: %s\n", amc_alert[alert_reason]); + xe_device_declare_wedged(i2c_client_to_xe_device(client)); + break; + default: + dev_warn(amc->i2c->drm_dev, "unknown AMC alert: %d\n", alert_reason); + break; + } +} + +void xe_amc_handle_alert(struct xe_i2c *i2c) +{ + queue_work(system_long_wq, &i2c->amc->work); +} + +int xe_amc_init(struct xe_i2c *i2c) +{ + struct xe_amc *amc; + + amc = kzalloc(sizeof(*amc), GFP_KERNEL); + if (!amc) + return -ENOMEM; + + INIT_WORK(&amc->work, xe_amc_work); + i2c->amc = amc; + amc->i2c = i2c; + + return 0; +} + +void xe_amc_exit(struct xe_i2c *i2c) +{ + if (i2c->amc) { + cancel_work_sync(&i2c->amc->work); + kfree(i2c->amc); + } +} diff --git a/drivers/gpu/drm/xe/xe_amc.h b/drivers/gpu/drm/xe/xe_amc.h new file mode 100644 index 000000000000..b1d5311fee53 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_amc.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _XE_AMC_H_ +#define _XE_AMC_H_ + +#include + +#include "xe_device.h" + +struct xe_i2c; + +static inline struct xe_device *i2c_adapter_to_xe_device(struct i2c_adapter *adapter) +{ + return kdev_to_xe_device(adapter->dev.parent->parent); +} + +static inline struct xe_device *i2c_client_to_xe_device(struct i2c_client *client) +{ + return i2c_adapter_to_xe_device(client->adapter); +} + +int xe_amc_init(struct xe_i2c *i2c); +void xe_amc_exit(struct xe_i2c *i2c); +void xe_amc_handle_alert(struct xe_i2c *i2c); + +#endif /* _XE_AMC_H_ */ diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index 04b24e1c8b78..7dc9873aef54 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -248,7 +248,8 @@ int xe_gt_idle_pg_print(struct xe_gt *gt, struct drm_printer *p) pg_status = xe_mmio_read32(>->mmio, POWERGATE_DOMAIN_STATUS); } - if (gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK) { + if (gt->info.engine_mask & + (XE_HW_ENGINE_RCS_MASK | XE_HW_ENGINE_CCS_MASK)) { drm_printf(p, "Render Power Gating Enabled: %s\n", str_yes_no(pg_enabled & RENDER_POWERGATE_ENABLE)); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 8aaed4fd13ea..864859bd0ccc 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1559,8 +1559,14 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) if (!skip_timeout_check && !check_timeout(q, job)) goto rearm; + /* + * Killed queues must not newly wedge the device, but preserve an + * already-wedged state to avoid warning on teardown timeouts. + */ if (!exec_queue_killed(q)) wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); + else + wedged = xe_device_wedged(xe); set_exec_queue_banned(q); diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c index 78a38363c8ae..399099ff0dbc 100644 --- a/drivers/gpu/drm/xe/xe_i2c.c +++ b/drivers/gpu/drm/xe/xe_i2c.c @@ -8,12 +8,11 @@ #include #include #include +#include #include #include #include #include -#include -#include #include #include #include @@ -24,9 +23,12 @@ #include #include +#include + #include "regs/xe_i2c_regs.h" #include "regs/xe_irq_regs.h" +#include "xe_amc.h" #include "xe_device.h" #include "xe_i2c.h" #include "xe_mmio.h" @@ -61,16 +63,32 @@ static inline void xe_i2c_read_endpoint(struct xe_mmio *mmio, void *ep) val[1] = xe_mmio_read32(mmio, REG_SG_REMAP_ADDR_POSTFIX); } +static void xe_i2c_handle_smbus_alert(struct xe_i2c *i2c) +{ + u32 stat; + + stat = xe_mmio_read32(i2c->mmio, I2C_REG(DW_IC_SMBUS_INTR_STAT)); + if (!stat) + return; + + xe_mmio_write32(i2c->mmio, I2C_REG(DW_IC_CLR_SMBUS_INTR), stat); + + if (stat & DW_IC_SMBUS_INTR_ALERT && i2c->amc) + xe_amc_handle_alert(i2c); + else + xe_mmio_rmw32(i2c->mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); +} + static void xe_i2c_client_work(struct work_struct *work) { struct xe_i2c *i2c = container_of(work, struct xe_i2c, work); struct i2c_board_info info = { .type = "amc", .flags = I2C_CLIENT_HOST_NOTIFY, - .addr = i2c->ep.addr[1], + .addr = i2c->ep.addr[XE_I2C_CLIENT_AMC], }; - i2c->client[0] = i2c_new_client_device(i2c->adapter, &info); + i2c->client[XE_I2C_CLIENT_AMC] = i2c_new_client_device(i2c->adapter, &info); } static int xe_i2c_notifier(struct notifier_block *nb, unsigned long action, void *data) @@ -114,16 +132,6 @@ static int xe_i2c_register_adapter(struct xe_i2c *i2c) if (ret) goto err_pdev_put; - if (i2c->adapter_irq) { - struct resource res; - - res = DEFINE_RES_IRQ_NAMED(i2c->adapter_irq, "xe_i2c"); - - ret = platform_device_add_resources(pdev, &res, 1); - if (ret) - goto err_pdev_put; - } - pdev->dev.parent = i2c->drm_dev; i2c->pdev = pdev; @@ -160,7 +168,8 @@ bool xe_i2c_present(struct xe_device *xe) static bool xe_i2c_irq_present(struct xe_device *xe) { - return xe->i2c && xe->i2c->adapter_irq; + return xe->i2c && xe->i2c->ep.capabilities & XE_I2C_EP_CAP_IRQ && + !xe_survivability_mode_is_boot_enabled(xe); } /** @@ -173,18 +182,10 @@ static bool xe_i2c_irq_present(struct xe_device *xe) */ void xe_i2c_irq_handler(struct xe_device *xe, u32 master_ctl) { - struct xe_mmio *mmio = xe_root_tile_mmio(xe); - if (!(master_ctl & I2C_IRQ) || !xe_i2c_irq_present(xe)) return; - /* Forward interrupt to I2C adapter */ - generic_handle_irq_safe(xe->i2c->adapter_irq); - - /* Deassert after I2C adapter clears the interrupt */ - xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, 0, PCI_COMMAND_INTX_DISABLE); - /* Reassert to allow subsequent interrupt generation */ - xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); + xe_i2c_handle_smbus_alert(xe->i2c); } void xe_i2c_irq_reset(struct xe_device *xe) @@ -209,50 +210,40 @@ void xe_i2c_irq_postinstall(struct xe_device *xe) xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); } -static int xe_i2c_irq_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw_irq_num) +/* See "Disabling DW_apb_i2c" in the DesignWare DW_abp_i2c databook. */ +static void xe_i2c_disable(struct xe_i2c *i2c) { - irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_simple_irq); - return 0; -} + int timeout = 100; + u32 status; -static const struct irq_domain_ops xe_i2c_irq_ops = { - .map = xe_i2c_irq_map, -}; + xe_mmio_rmw32(i2c->mmio, I2C_REG(DW_IC_ENABLE), DW_IC_ENABLE_ENABLE, 0); -static int xe_i2c_create_irq(struct xe_device *xe) -{ - struct xe_i2c *i2c = xe->i2c; - struct irq_domain *domain; + do { + status = xe_mmio_read32(i2c->mmio, I2C_REG(DW_IC_ENABLE_STATUS)); + if (!(status & DW_IC_ENABLE_ENABLE)) + return; + /* Can't sleep here. */ + udelay(25); + } while (timeout--); - if (!(i2c->ep.capabilities & XE_I2C_EP_CAP_IRQ) || - xe_survivability_mode_is_boot_enabled(xe)) - return 0; - - domain = irq_domain_create_linear(dev_fwnode(i2c->drm_dev), 1, &xe_i2c_irq_ops, NULL); - if (!domain) - return -ENOMEM; - - i2c->adapter_irq = irq_create_mapping(domain, 0); - i2c->irqdomain = domain; - - return 0; -} - -static void xe_i2c_remove_irq(struct xe_i2c *i2c) -{ - if (!i2c->irqdomain) - return; - - irq_dispose_mapping(i2c->adapter_irq); - irq_domain_remove(i2c->irqdomain); + dev_warn(i2c->drm_dev, "timeout in disabling i2c adapter\n"); } static int xe_i2c_read(void *context, unsigned int reg, unsigned int *val) { struct xe_i2c *i2c = context; - *val = xe_mmio_read32(i2c->mmio, XE_REG(reg + I2C_MEM_SPACE_OFFSET)); + *val = xe_mmio_read32(i2c->mmio, I2C_REG(reg)); + + switch (reg) { + case DW_IC_ENABLE: + case DW_IC_ENABLE_STATUS: + FIELD_MODIFY(DW_IC_ENABLE_ENABLE, val, + i2c->ic_enable & DW_IC_ENABLE_ENABLE); + break; + default: + break; + } return 0; } @@ -261,8 +252,33 @@ static int xe_i2c_write(void *context, unsigned int reg, unsigned int val) { struct xe_i2c *i2c = context; - xe_mmio_write32(i2c->mmio, XE_REG(reg + I2C_MEM_SPACE_OFFSET), val); + switch (reg) { + case DW_IC_CON: + case DW_IC_TAR: + case DW_IC_SAR: + /* Disable the controller. */ + xe_i2c_disable(i2c); + /* Write the register. */ + xe_mmio_write32(i2c->mmio, I2C_REG(reg), val); + + /* Enable the controller. */ + xe_mmio_rmw32(i2c->mmio, I2C_REG(DW_IC_ENABLE), 0, DW_IC_ENABLE_ENABLE); + return 0; + case DW_IC_ENABLE: + i2c->ic_enable = val; + /* Other fields can be updated except the enable bit. */ + val |= DW_IC_ENABLE_ENABLE; + break; + case DW_IC_SMBUS_INTR_MASK: + /* Make sure the Alert is never masked. */ + val |= DW_IC_SMBUS_INTR_ALERT; + break; + default: + break; + } + + xe_mmio_write32(i2c->mmio, I2C_REG(reg), val); return 0; } @@ -304,12 +320,15 @@ static void xe_i2c_remove(void *data) struct xe_i2c *i2c = data; unsigned int i; - for (i = 0; i < XE_I2C_MAX_CLIENTS; i++) + xe_amc_exit(i2c); + + for (i = 0; i < XE_I2C_MAX_CLIENTS; i++) { i2c_unregister_device(i2c->client[i]); + i2c->client[i] = NULL; + } bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); xe_i2c_unregister_adapter(i2c); - xe_i2c_remove_irq(i2c); } /** @@ -357,22 +376,18 @@ int xe_i2c_probe(struct xe_device *xe) if (ret) return ret; - ret = xe_i2c_create_irq(xe); - if (ret) - goto err_unregister_notifier; - ret = xe_i2c_register_adapter(i2c); - if (ret) - goto err_remove_irq; + if (ret) { + bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); + return ret; + } + + ret = xe_amc_init(i2c); + if (ret) { + xe_i2c_remove(i2c); + return ret; + } xe_i2c_irq_postinstall(xe); return devm_add_action_or_reset(drm_dev, xe_i2c_remove, i2c); - -err_remove_irq: - xe_i2c_remove_irq(i2c); - -err_unregister_notifier: - bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); - - return ret; } diff --git a/drivers/gpu/drm/xe/xe_i2c.h b/drivers/gpu/drm/xe/xe_i2c.h index b28229f056c5..5969054a6b6b 100644 --- a/drivers/gpu/drm/xe/xe_i2c.h +++ b/drivers/gpu/drm/xe/xe_i2c.h @@ -11,18 +11,21 @@ struct device; struct fwnode_handle; struct i2c_adapter; struct i2c_client; -struct irq_domain; struct platform_device; +struct xe_amc; struct xe_device; struct xe_mmio; -#define XE_I2C_MAX_CLIENTS 3 - #define XE_I2C_EP_COOKIE_DEVICE 0xde /* Endpoint Capabilities */ #define XE_I2C_EP_CAP_IRQ BIT(0) +enum XE_I2C_CLIENT { + XE_I2C_CLIENT_AMC = 1, + XE_I2C_MAX_CLIENTS = 3, +}; + struct xe_i2c_endpoint { u8 cookie; u8 capabilities; @@ -33,17 +36,16 @@ struct xe_i2c { struct platform_device *pdev; struct i2c_adapter *adapter; struct i2c_client *client[XE_I2C_MAX_CLIENTS]; + unsigned int ic_enable; struct notifier_block bus_notifier; struct work_struct work; - struct irq_domain *irqdomain; - int adapter_irq; - struct xe_i2c_endpoint ep; struct device *drm_dev; struct xe_mmio *mmio; + struct xe_amc *amc; }; #if IS_ENABLED(CONFIG_I2C) diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c index dd3c068e1a39..dbf8f71d3328 100644 --- a/drivers/gpu/drm/xe/xe_pagefault.c +++ b/drivers/gpu/drm/xe/xe_pagefault.c @@ -158,7 +158,7 @@ static struct xe_vm *xe_pagefault_asid_to_vm(struct xe_device *xe, u32 asid) down_read(&xe->usm.lock); vm = xa_load(&xe->usm.asid_to_vm, asid); - if (vm && (xe_vm_in_fault_mode(vm) || xe_vm_has_scratch(vm))) + if (vm && xe_vm_in_fault_mode(vm)) xe_vm_get(vm); else vm = ERR_PTR(-EINVAL); diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c index 1db20be8158b..62ccc9be71b4 100644 --- a/drivers/gpu/drm/xe/xe_sysctrl.c +++ b/drivers/gpu/drm/xe/xe_sysctrl.c @@ -85,7 +85,6 @@ int xe_sysctrl_init(struct xe_device *xe) return ret; xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX); - xe_sysctrl_mailbox_init(sc); INIT_WORK(&sc->work, xe_sysctrl_work); return devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe); @@ -114,12 +113,10 @@ void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl) * @xe: xe device instance * * Invoked during system resume (S3/S4 to S0) and runtime resume from D3cold. - * Restores SoC remapper configuration and reinitializes mailbox interface. + * Restores SoC remapper configuration. */ void xe_sysctrl_pm_resume(struct xe_device *xe) { - struct xe_sysctrl *sc = &xe->sc; - if (!xe->info.has_soc_remapper_sysctrl) return; @@ -127,6 +124,4 @@ void xe_sysctrl_pm_resume(struct xe_device *xe) return; xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX); - - xe_sysctrl_mailbox_init(sc); } diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c index e13eebaac1d0..72baf1aa4b3a 100644 --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c @@ -145,6 +145,7 @@ static int sysctrl_send_frames(struct xe_sysctrl *sc, struct xe_device *xe = sc_to_xe(sc); u32 ctrl_reg, total_frames, frame; size_t bytes_sent, frame_size; + bool phase; total_frames = DIV_ROUND_UP(cmd_size, XE_SYSCTRL_MB_FRAME_SIZE); @@ -153,7 +154,8 @@ static int sysctrl_send_frames(struct xe_sysctrl *sc, return -EBUSY; } - sc->phase_bit ^= 1; + ctrl_reg = xe_mmio_read32(sc->mmio, SYSCTRL_MB_CTRL); + phase = !(ctrl_reg & SYSCTRL_FRAME_PHASE); bytes_sent = 0; for (frame = 0; frame < total_frames; frame++) { @@ -161,7 +163,6 @@ static int sysctrl_send_frames(struct xe_sysctrl *sc, if (sysctrl_write_frame(sc, mbox_cmd + bytes_sent, frame_size)) { xe_err(xe, "sysctrl: Failed to write frame %u\n", frame); - sc->phase_bit = 0; return -EIO; } @@ -169,13 +170,12 @@ static int sysctrl_send_frames(struct xe_sysctrl *sc, REG_FIELD_PREP(SYSCTRL_FRAME_CURRENT_MASK, frame) | REG_FIELD_PREP(SYSCTRL_FRAME_TOTAL_MASK, total_frames - 1) | SYSCTRL_MB_CTRL_CMD | - (sc->phase_bit ? SYSCTRL_FRAME_PHASE : 0); + (phase ? SYSCTRL_FRAME_PHASE : 0); xe_mmio_write32(sc->mmio, SYSCTRL_MB_CTRL, ctrl_reg); if (!sysctrl_wait_bit_clear(sc, SYSCTRL_MB_CTRL_RUN_BUSY, timeout_ms)) { xe_err(xe, "sysctrl: Frame %u acknowledgment timeout\n", frame); - sc->phase_bit = 0; return -ETIMEDOUT; } @@ -321,20 +321,6 @@ void xe_sysctrl_create_command(struct xe_sysctrl_mailbox_command *command, u8 gr command->data_out_len = response_len; } -/** - * xe_sysctrl_mailbox_init - Initialize System Controller mailbox interface - * @sc: System controller structure - * - * Initialize system controller mailbox interface for communication. - */ -void xe_sysctrl_mailbox_init(struct xe_sysctrl *sc) -{ - u32 ctrl_reg; - - ctrl_reg = xe_mmio_read32(sc->mmio, SYSCTRL_MB_CTRL); - sc->phase_bit = (ctrl_reg & SYSCTRL_FRAME_PHASE) ? 1 : 0; -} - /** * xe_sysctrl_send_command() - Send mailbox command to System Controller * @sc: System Controller instance diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h index fb434cc165b2..f0d5e3d7f5e3 100644 --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.h @@ -26,7 +26,6 @@ struct xe_sysctrl_mailbox_command; void xe_sysctrl_create_command(struct xe_sysctrl_mailbox_command *command, u8 group_id, u8 cmd_id, void *request, size_t request_len, void *response, size_t response_len); -void xe_sysctrl_mailbox_init(struct xe_sysctrl *sc); int xe_sysctrl_send_command(struct xe_sysctrl *sc, struct xe_sysctrl_mailbox_command *cmd, size_t *rdata_len); diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h b/drivers/gpu/drm/xe/xe_sysctrl_types.h index 66ba24f43017..98c2f473f7c6 100644 --- a/drivers/gpu/drm/xe/xe_sysctrl_types.h +++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h @@ -26,9 +26,6 @@ struct xe_sysctrl { /** @cmd_lock: Mutex protecting mailbox command operations */ struct mutex cmd_lock; - /** @phase_bit: Message boundary phase toggle bit (0 or 1) */ - bool phase_bit; - /** @work: Pending events worker */ struct work_struct work; diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index f02ac9bf7424..dd69ad07f7a9 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -63,7 +63,7 @@ 16026007364 MEDIA_VERSION(3000) 14020316580 MEDIA_VERSION(1301) -14025883347 MEDIA_VERSION_RANGE(1301, 3503) +14025883347 MEDIA_VERSION_RANGE(1301, 3500) GRAPHICS_VERSION_RANGE(2004, 3005) 16029380221 MEDIA_VERSION(3500) 22022079272 MEDIA_VERSION(3503) diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index e4dfa2ec58bb..a1eca6cd4b75 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -33,6 +33,8 @@ #include #include +#include + #include "i2c-designware-core.h" #define DW_IC_DEFAULT_BUS_CAPACITANCE_pF 100 diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index c71aa2dd368d..2c929a6e8da2 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -18,6 +18,8 @@ #include #include +#include + #define DW_IC_DEFAULT_FUNCTIONALITY (I2C_FUNC_I2C | \ I2C_FUNC_SMBUS_BYTE | \ I2C_FUNC_SMBUS_BYTE_DATA | \ @@ -25,23 +27,6 @@ I2C_FUNC_SMBUS_BLOCK_DATA | \ I2C_FUNC_SMBUS_I2C_BLOCK) -#define DW_IC_CON_MASTER BIT(0) -#define DW_IC_CON_SPEED_STD (1 << 1) -#define DW_IC_CON_SPEED_FAST (2 << 1) -#define DW_IC_CON_SPEED_HIGH (3 << 1) -#define DW_IC_CON_SPEED_MASK GENMASK(2, 1) -#define DW_IC_CON_10BITADDR_SLAVE BIT(3) -#define DW_IC_CON_10BITADDR_MASTER BIT(4) -#define DW_IC_CON_RESTART_EN BIT(5) -#define DW_IC_CON_SLAVE_DISABLE BIT(6) -#define DW_IC_CON_STOP_DET_IFADDRESSED BIT(7) -#define DW_IC_CON_TX_EMPTY_CTRL BIT(8) -#define DW_IC_CON_RX_FIFO_FULL_HLD_CTRL BIT(9) -#define DW_IC_CON_BUS_CLEAR_CTRL BIT(11) - -#define DW_IC_DATA_CMD_DAT GENMASK(7, 0) -#define DW_IC_DATA_CMD_FIRST_DATA_BYTE BIT(11) - /* * Register access parameters */ @@ -55,65 +40,9 @@ #define DW_IC_FIFO_RX_FIELD GENMASK(15, 8) #define DW_IC_FIFO_MIN_DEPTH 2 -/* - * Registers offset - */ -#define DW_IC_CON 0x00 -#define DW_IC_TAR 0x04 -#define DW_IC_SAR 0x08 -#define DW_IC_DATA_CMD 0x10 -#define DW_IC_SS_SCL_HCNT 0x14 -#define DW_IC_SS_SCL_LCNT 0x18 -#define DW_IC_FS_SCL_HCNT 0x1c -#define DW_IC_FS_SCL_LCNT 0x20 -#define DW_IC_HS_SCL_HCNT 0x24 -#define DW_IC_HS_SCL_LCNT 0x28 -#define DW_IC_INTR_STAT 0x2c -#define DW_IC_INTR_MASK 0x30 -#define DW_IC_RAW_INTR_STAT 0x34 -#define DW_IC_RX_TL 0x38 -#define DW_IC_TX_TL 0x3c -#define DW_IC_CLR_INTR 0x40 -#define DW_IC_CLR_RX_UNDER 0x44 -#define DW_IC_CLR_RX_OVER 0x48 -#define DW_IC_CLR_TX_OVER 0x4c -#define DW_IC_CLR_RD_REQ 0x50 -#define DW_IC_CLR_TX_ABRT 0x54 -#define DW_IC_CLR_RX_DONE 0x58 -#define DW_IC_CLR_ACTIVITY 0x5c -#define DW_IC_CLR_STOP_DET 0x60 -#define DW_IC_CLR_START_DET 0x64 -#define DW_IC_CLR_GEN_CALL 0x68 -#define DW_IC_ENABLE 0x6c -#define DW_IC_STATUS 0x70 -#define DW_IC_TXFLR 0x74 -#define DW_IC_RXFLR 0x78 -#define DW_IC_SDA_HOLD 0x7c -#define DW_IC_TX_ABRT_SOURCE 0x80 -#define DW_IC_ENABLE_STATUS 0x9c -#define DW_IC_CLR_RESTART_DET 0xa8 -#define DW_IC_SMBUS_INTR_MASK 0xcc -#define DW_IC_COMP_PARAM_1 0xf4 -#define DW_IC_COMP_VERSION 0xf8 #define DW_IC_SDA_HOLD_MIN_VERS 0x3131312A /* "111*" == v1.11* */ -#define DW_IC_COMP_TYPE 0xfc #define DW_IC_COMP_TYPE_VALUE 0x44570140 /* "DW" + 0x0140 */ -#define DW_IC_INTR_RX_UNDER BIT(0) -#define DW_IC_INTR_RX_OVER BIT(1) -#define DW_IC_INTR_RX_FULL BIT(2) -#define DW_IC_INTR_TX_OVER BIT(3) -#define DW_IC_INTR_TX_EMPTY BIT(4) -#define DW_IC_INTR_RD_REQ BIT(5) -#define DW_IC_INTR_TX_ABRT BIT(6) -#define DW_IC_INTR_RX_DONE BIT(7) -#define DW_IC_INTR_ACTIVITY BIT(8) -#define DW_IC_INTR_STOP_DET BIT(9) -#define DW_IC_INTR_START_DET BIT(10) -#define DW_IC_INTR_GEN_CALL BIT(11) -#define DW_IC_INTR_RESTART_DET BIT(12) -#define DW_IC_INTR_MST_ON_HOLD BIT(13) - #define DW_IC_INTR_DEFAULT_MASK (DW_IC_INTR_RX_FULL | \ DW_IC_INTR_TX_ABRT | \ DW_IC_INTR_STOP_DET) @@ -123,16 +52,6 @@ DW_IC_INTR_RX_UNDER | \ DW_IC_INTR_RD_REQ) -#define DW_IC_ENABLE_ENABLE BIT(0) -#define DW_IC_ENABLE_ABORT BIT(1) - -#define DW_IC_STATUS_ACTIVITY BIT(0) -#define DW_IC_STATUS_TFE BIT(2) -#define DW_IC_STATUS_RFNE BIT(3) -#define DW_IC_STATUS_MASTER_ACTIVITY BIT(5) -#define DW_IC_STATUS_SLAVE_ACTIVITY BIT(6) -#define DW_IC_STATUS_MASTER_HOLD_TX_FIFO_EMPTY BIT(7) - #define DW_IC_SDA_HOLD_RX_SHIFT 16 #define DW_IC_SDA_HOLD_RX_MASK GENMASK(23, 16) diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 7a301c8b604e..a1bcc3797e4f 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -25,6 +25,8 @@ #include #include +#include + #include "i2c-designware-core.h" #define AMD_TIMEOUT_MIN_US 25 diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 6d6e81242f74..447af5523c2e 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -272,7 +272,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = { { "HISI02A1", 0 }, { "HISI02A2", 0 }, { "HISI02A3", 0 }, - { "HJMC3001", 0 }, + { "HJMC3001", ACCESS_INTR_MASK }, { "HYGO0010", ACCESS_INTR_MASK }, { "INT33C2", 0 }, { "INT33C3", 0 }, diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index ad0d5fbfa6d5..0abcc7757b23 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -19,6 +19,8 @@ #include #include +#include + #include "i2c-designware-core.h" int i2c_dw_reg_slave(struct i2c_client *slave) diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index e1a4338bc51e..1cfd7a4c8237 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -29,6 +29,7 @@ #define DRIVER_NAME "imx-lpi2c" +#define LPI2C_VERID 0x00 /* i2c version ID */ #define LPI2C_PARAM 0x04 /* i2c RX/TX FIFO size */ #define LPI2C_MCR 0x10 /* i2c contrl register */ #define LPI2C_MSR 0x14 /* i2c status register */ @@ -136,6 +137,9 @@ #define I2C_PM_LONG_TIMEOUT_MS 1000 /* Avoid dead lock caused by big clock prepare lock */ #define I2C_DMA_THRESHOLD 8 /* bytes */ +/* Bit 0 indicates the presence of the target feature */ +#define VERID_FEATURE_TARGET_PRESENT BIT(0) + enum lpi2c_imx_mode { STANDARD, /* 100+Kbps */ FAST, /* 400+Kbps */ @@ -194,6 +198,7 @@ struct lpi2c_imx_struct { bool can_use_dma; struct lpi2c_imx_dma *dma; struct i2c_client *target; + bool target_supported; int irq; const struct imx_lpi2c_hwdata *hwdata; }; @@ -1330,6 +1335,10 @@ static int lpi2c_imx_register_target(struct i2c_client *client) struct lpi2c_imx_struct *lpi2c_imx = i2c_get_adapdata(client->adapter); int ret; + /* Reject target-mode registration on controllers that don't support it. */ + if (!lpi2c_imx->target_supported) + return -EOPNOTSUPP; + if (lpi2c_imx->target) return -EBUSY; @@ -1546,13 +1555,23 @@ static int lpi2c_imx_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); /* - * Reset all internal controller registers of both Master and Target - * to avoid effects of previous status. + * Reset all internal controller registers to avoid effects of any + * state left over from a previous stage (e.g. the bootloader). + * + * The Master block (MCR) is present on every controller, so reset it + * unconditionally. VERID shows whether the target feature is supported. + * Do not touch the Target block (SCR) on a master-only controller to + * avoid an asynchronous SError. */ writel(MCR_RST, lpi2c_imx->base + LPI2C_MCR); - writel(SCR_RST, lpi2c_imx->base + LPI2C_SCR); writel(0, lpi2c_imx->base + LPI2C_MCR); - writel(0, lpi2c_imx->base + LPI2C_SCR); + + lpi2c_imx->target_supported = !!(readl(lpi2c_imx->base + LPI2C_VERID) & + VERID_FEATURE_TARGET_PRESENT); + if (lpi2c_imx->target_supported) { + writel(SCR_RST, lpi2c_imx->base + LPI2C_SCR); + writel(0, lpi2c_imx->base + LPI2C_SCR); + } ret = devm_request_irq(&pdev->dev, lpi2c_imx->irq, lpi2c_imx_isr, IRQF_NO_SUSPEND, pdev->name, lpi2c_imx); diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c index bdeda3979c48..25b6e4e9e3fa 100644 --- a/drivers/i2c/busses/i2c-qcom-cci.c +++ b/drivers/i2c/busses/i2c-qcom-cci.c @@ -595,9 +595,11 @@ static int cci_probe(struct platform_device *pdev) goto disable_clocks; pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); + ret = devm_pm_runtime_set_active_enabled(dev); + if (ret) + goto disable_clocks; + pm_runtime_use_autosuspend(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); for (i = 0; i < cci->data->num_masters; i++) { if (!cci->master[i].cci) @@ -613,8 +615,6 @@ static int cci_probe(struct platform_device *pdev) return 0; error_i2c: - pm_runtime_disable(dev); - pm_runtime_dont_use_autosuspend(dev); for (--i ; i >= 0; i--) { if (cci->master[i].cci) { @@ -640,9 +640,6 @@ static void cci_remove(struct platform_device *pdev) cci_halt(cci, i); } } - - pm_runtime_disable(&pdev->dev); - pm_runtime_set_suspended(&pdev->dev); } static const struct cci_data cci_v1_data = { diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 658636c1ee0e..00013b41a6f5 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -188,8 +188,8 @@ static const struct geni_i2c_clk_fld geni_i2c_clk_map_19p2mhz[] = { /* source_clock = 32 MHz */ static const struct geni_i2c_clk_fld geni_i2c_clk_map_32mhz[] = { - { I2C_MAX_STANDARD_MODE_FREQ, 8, 14, 18, 38 }, - { I2C_MAX_FAST_MODE_FREQ, 4, 3, 9, 19 }, + { I2C_MAX_STANDARD_MODE_FREQ, 12, 9, 10, 26 }, + { I2C_MAX_FAST_MODE_FREQ, 4, 3, 9, 19 }, { I2C_MAX_FAST_MODE_PLUS_FREQ, 2, 3, 5, 15 }, {} }; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index fb25704219c7..ddaacf876dad 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1816,6 +1816,12 @@ void i2c_del_adapter(struct i2c_adapter *adap) return; } + /* + * This drains any in-flight writers, so all + * clients will be caught by i2c_deregister_clients(). + */ + device_remove_file(&adap->dev, &dev_attr_new_device); + i2c_acpi_remove_space_handler(adap); i2c_deregister_clients(adap); diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 681a201c239b..68a4c34b5987 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -408,6 +408,7 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, return 0; err_free_priv: + of_node_put(priv->adap.dev.of_node); kfree(priv); return ret; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 33dbc71b730f..1a5072425c4a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -340,8 +340,6 @@ struct cache { struct list_head invalidation_requests; sector_t migration_threshold; - wait_queue_head_t migration_wait; - atomic_t nr_allocated_migrations; /* * The number of in flight migrations that are performing @@ -397,7 +395,11 @@ struct cache { bool loaded_mappings:1; bool loaded_discards:1; - struct rw_semaphore background_work_lock; + /* background work management */ + bool background_work_allowed; + unsigned background_work_nr; + spinlock_t background_work_lock; + wait_queue_head_t background_work_wait; struct batcher committer; struct work_struct commit_ws; @@ -488,19 +490,13 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache) memset(mg, 0, sizeof(*mg)); mg->cache = cache; - atomic_inc(&cache->nr_allocated_migrations); return mg; } static void free_migration(struct dm_cache_migration *mg) { - struct cache *cache = mg->cache; - - if (atomic_dec_and_test(&cache->nr_allocated_migrations)) - wake_up(&cache->migration_wait); - - mempool_free(mg, &cache->migration_pool); + mempool_free(mg, &mg->cache->migration_pool); } /*----------------------------------------------------------------*/ @@ -1030,34 +1026,39 @@ static void calc_discard_block_range(struct cache *cache, struct bio *bio, static void prevent_background_work(struct cache *cache) { - lockdep_off(); - down_write(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + cache->background_work_allowed = false; + wait_event_lock_irq(cache->background_work_wait, + cache->background_work_nr == 0, + cache->background_work_lock); + spin_unlock_irq(&cache->background_work_lock); } static void allow_background_work(struct cache *cache) { - lockdep_off(); - up_write(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + cache->background_work_allowed = true; + spin_unlock_irq(&cache->background_work_lock); } static bool background_work_begin(struct cache *cache) { bool r; - lockdep_off(); - r = down_read_trylock(&cache->background_work_lock); - lockdep_on(); - + spin_lock_irq(&cache->background_work_lock); + r = cache->background_work_allowed; + if (r) + cache->background_work_nr++; + spin_unlock_irq(&cache->background_work_lock); return r; } static void background_work_end(struct cache *cache) { - lockdep_off(); - up_read(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + if (--cache->background_work_nr == 0) + wake_up(&cache->background_work_wait); + spin_unlock_irq(&cache->background_work_lock); } /*----------------------------------------------------------------*/ @@ -1462,6 +1463,9 @@ static void invalidate_complete(struct dm_cache_migration *mg, bool success) struct bio_list bios; struct cache *cache = mg->cache; + if (success) + atomic_inc(&cache->stats.demotion); + bio_list_init(&bios); if (mg->cell) { if (dm_cell_unlock_v2(cache->prison, mg->cell, &bios)) @@ -1733,7 +1737,6 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, if (passthrough_mode(cache)) { if (bio_data_dir(bio) == WRITE) { bio_drop_shared_lock(cache, bio); - atomic_inc(&cache->stats.demotion); invalidate_start(cache, cblock, block, bio); return DM_MAPIO_SUBMITTED; } else @@ -2507,9 +2510,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) spin_lock_init(&cache->lock); bio_list_init(&cache->deferred_bios); - atomic_set(&cache->nr_allocated_migrations, 0); atomic_set(&cache->nr_io_migrations, 0); - init_waitqueue_head(&cache->migration_wait); r = -ENOMEM; atomic_set(&cache->nr_dirty, 0); @@ -2592,8 +2593,10 @@ static int cache_create(struct cache_args *ca, struct cache **result) issue_op, cache, cache->wq); dm_iot_init(&cache->tracker); - init_rwsem(&cache->background_work_lock); - prevent_background_work(cache); + init_waitqueue_head(&cache->background_work_wait); + spin_lock_init(&cache->background_work_lock); + cache->background_work_allowed = false; + cache->background_work_nr = 0; *result = cache; return 0; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 608b617fb817..9e170de50ad3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1745,7 +1745,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; struct bio *base_bio = io->base_bio; - blk_status_t error = io->error; if (!atomic_dec_and_test(&io->io_pending)) return; @@ -1767,7 +1766,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io) else kfree(io->integrity_metadata); - base_bio->bi_status = error; + base_bio->bi_status = io->error; bio_endio(base_bio); } diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 1e52bde48b91..5d67c6c19d4b 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -265,8 +265,7 @@ static int ebs_ctr(struct dm_target *ti, unsigned int argc, char **argv) r = -EINVAL; if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1 || - tmp != (sector_t)tmp || - (sector_t)tmp >= ti->len) { + tmp != (sector_t)tmp) { ti->error = "Invalid device offset sector"; goto bad; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index c50feaa98bf9..92970e12267a 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1979,8 +1979,8 @@ static void integrity_metadata(struct work_struct *w) if (unlikely(dio->op == REQ_OP_DISCARD)) { unsigned int bi_size = dio->bio_details.bi_iter.bi_size; - unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE; - unsigned int max_blocks = max_size / ic->tag_size; + unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : sizeof(checksums_onstack); + unsigned int max_blocks = (max_size - extra_space) / ic->tag_size; sector_t sector = dio->range.logical_sector; if (!ic->discard_keyed) @@ -3875,6 +3875,10 @@ static void dm_integrity_resume(struct dm_target *ti) r = sync_rw_sb(ic, REQ_OP_READ); if (r) dm_integrity_io_error(ic, "reading superblock", r); + + if (ic->mode == 'R') + goto skip_writes; + if ((ic->sb->flags & flags) != flags) { ic->sb->flags |= flags; r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA); @@ -3984,6 +3988,7 @@ static void dm_integrity_resume(struct dm_target *ti) } } +skip_writes: ic->reboot_notifier.notifier_call = dm_integrity_reboot; ic->reboot_notifier.next = NULL; ic->reboot_notifier.priority = INT_MAX - 1; /* be notified after md and before hardware drivers */ @@ -4130,6 +4135,10 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim limits->dma_alignment = limits->logical_block_size - 1; limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT; + if (ic->internal_hash && + (ic->mode == 'D' || ic->mode == 'B' || ic->mode == 'I')) + limits->features |= BLK_FEAT_STABLE_WRITES; + if (!ic->internal_hash) { struct blk_integrity *bi = &limits->integrity; diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c index 0fa115cbf3ad..0ce7ff7400d3 100644 --- a/drivers/mtd/ubi/attach.c +++ b/drivers/mtd/ubi/attach.c @@ -771,7 +771,7 @@ void ubi_remove_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av) static int early_erase_peb(struct ubi_device *ubi, const struct ubi_attach_info *ai, int pnum, int ec) { - int err; + int err, torture = 0; struct ubi_ec_hdr *ec_hdr; if ((long long)ec >= UBI_MAX_ERASECOUNTER) { @@ -790,7 +790,7 @@ static int early_erase_peb(struct ubi_device *ubi, ec_hdr->ec = cpu_to_be64(ec); - err = ubi_io_sync_erase(ubi, pnum, 0); + err = ubi_io_sync_erase(ubi, pnum, &torture); if (err < 0) goto out_free; diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 674ad87809df..910e6b0ff5e7 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -36,7 +36,7 @@ #define MTD_PARAM_LEN_MAX 64 /* Maximum number of comma-separated items in the 'mtd=' parameter */ -#define MTD_PARAM_MAX_COUNT 6 +#define MTD_PARAM_MAX_COUNT 7 /* Maximum value for the number of bad PEBs per 1024 PEBs */ #define MAX_MTD_UBI_BEB_LIMIT 768 @@ -56,6 +56,7 @@ * @max_beb_per1024: maximum expected number of bad PEBs per 1024 PEBs * @enable_fm: enable fastmap when value is non-zero * @need_resv_pool: reserve pool->max_size pebs when value is none-zero + * @wl_threshold: wear-leveling threshold, 0 means use CONFIG_MTD_UBI_WL_THRESHOLD */ struct mtd_dev_param { char name[MTD_PARAM_LEN_MAX]; @@ -64,6 +65,7 @@ struct mtd_dev_param { int max_beb_per1024; int enable_fm; int need_resv_pool; + int wl_threshold; }; /* Numbers of elements set in the @mtd_dev_param array */ @@ -832,6 +834,8 @@ static int autoresize(struct ubi_device *ubi, int vol_id) * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs * @disable_fm: whether disable fastmap * @need_resv_pool: whether reserve pebs to fill fm_pool + * @wl_threshold: wear-leveling threshold for this UBI device; 0 means use + * %CONFIG_MTD_UBI_WL_THRESHOLD; accepted range is 2-65536 * * This function attaches MTD device @mtd_dev to UBI and assign @ubi_num number * to the newly created UBI device, unless @ubi_num is %UBI_DEV_NUM_AUTO, in @@ -848,7 +852,7 @@ static int autoresize(struct ubi_device *ubi, int vol_id) */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset, int max_beb_per1024, bool disable_fm, - bool need_resv_pool) + bool need_resv_pool, int wl_threshold) { struct ubi_device *ubi; int i, err; @@ -859,6 +863,15 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, if (!max_beb_per1024) max_beb_per1024 = CONFIG_MTD_UBI_BEB_LIMIT; + if (!wl_threshold) + wl_threshold = CONFIG_MTD_UBI_WL_THRESHOLD; + + if (wl_threshold < 2 || wl_threshold > 65536) { + pr_err("ubi: bad wear-leveling threshold %d\n", + wl_threshold); + return -EINVAL; + } + /* * Check if we already have the same MTD device attached. * @@ -944,6 +957,8 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, ubi->ubi_num = ubi_num; ubi->vid_hdr_offset = vid_hdr_offset; ubi->autoresize_vol_id = -1; + ubi->wl_threshold = wl_threshold; + ubi->wl_free_max_diff = wl_threshold * 2; #ifdef CONFIG_MTD_UBI_FASTMAP ubi->fm_pool.used = ubi->fm_pool.size = 0; @@ -1044,7 +1059,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, ubi->vol_count - UBI_INT_VOL_COUNT, UBI_INT_VOL_COUNT, ubi->vtbl_slots); ubi_msg(ubi, "max/mean erase counter: %d/%d, WL threshold: %d, image sequence number: %u", - ubi->max_ec, ubi->mean_ec, CONFIG_MTD_UBI_WL_THRESHOLD, + ubi->max_ec, ubi->mean_ec, ubi->wl_threshold, ubi->image_seq); ubi_msg(ubi, "available PEBs: %d, total reserved PEBs: %d, PEBs reserved for bad PEB handling: %d", ubi->avail_pebs, ubi->rsvd_pebs, ubi->beb_rsvd_pebs); @@ -1105,6 +1120,7 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway) ubi->ref_count -= 1; if (ubi->ref_count) { if (!anyway) { + put_device(&ubi->dev); spin_unlock(&ubi_devices_lock); return -EBUSY; } @@ -1247,7 +1263,7 @@ static void ubi_notify_add(struct mtd_info *mtd) /* called while holding mtd_table_mutex */ mutex_lock_nested(&ubi_devices_mutex, SINGLE_DEPTH_NESTING); - err = ubi_attach_mtd_dev(mtd, UBI_DEV_NUM_AUTO, 0, 0, false, false); + err = ubi_attach_mtd_dev(mtd, UBI_DEV_NUM_AUTO, 0, 0, false, false, 0); mutex_unlock(&ubi_devices_mutex); if (err < 0) __put_mtd_device(mtd); @@ -1289,7 +1305,8 @@ static int __init ubi_init_attach(void) err = ubi_attach_mtd_dev(mtd, p->ubi_num, p->vid_hdr_offs, p->max_beb_per1024, p->enable_fm == 0, - p->need_resv_pool != 0); + p->need_resv_pool != 0, + p->wl_threshold); mutex_unlock(&ubi_devices_mutex); if (err < 0) { pr_err("UBI error: cannot attach mtd%d\n", @@ -1317,10 +1334,10 @@ static int __init ubi_init_attach(void) return 0; out_detach: - for (k = 0; k < i; k++) + for (k = 0; k < UBI_MAX_DEVICES; k++) if (ubi_devices[k]) { mutex_lock(&ubi_devices_mutex); - ubi_detach_mtd_dev(ubi_devices[k]->ubi_num, 1); + ubi_detach_mtd_dev(k, 1); mutex_unlock(&ubi_devices_mutex); } return err; @@ -1569,12 +1586,24 @@ static int ubi_mtd_param_parse(const char *val, const struct kernel_param *kp) } else p->need_resv_pool = 0; + token = tokens[6]; + if (token) { + int err = kstrtoint(token, 10, &p->wl_threshold); + + if (err) { + pr_err("UBI error: bad value for wl_threshold parameter: %s\n", + token); + return -EINVAL; + } + } else + p->wl_threshold = 0; + mtd_devs += 1; return 0; } module_param_call(mtd, ubi_mtd_param_parse, NULL, NULL, 0400); -MODULE_PARM_DESC(mtd, "MTD devices to attach. Parameter format: mtd=[,[,max_beb_per1024[,ubi_num]]].\n" +MODULE_PARM_DESC(mtd, "MTD devices to attach. Parameter format: mtd=[,[,max_beb_per1024[,ubi_num[,enable_fm[,need_resv_pool[,wl_threshold]]]]]].\n" "Multiple \"mtd\" parameters may be specified.\n" "MTD devices may be specified by their number, name, or path to the MTD character device node.\n" "Optional \"vid_hdr_offs\" parameter specifies UBI VID header position to be used by UBI. (default value if 0)\n" @@ -1587,9 +1616,10 @@ MODULE_PARM_DESC(mtd, "MTD devices to attach. Parameter format: mtd=free, WL_FREE_MAX_DIFF, + e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, !can_fill_pools(ubi, left_free)); self_check_in_wl_tree(ubi, e, &ubi->free); rb_erase(&e->u.rb, &ubi->free); @@ -392,18 +392,18 @@ static bool need_wear_leveling(struct ubi_device *ubi) if (!e) { if (!ubi->free.rb_node) return false; - e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF, 0); + e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, 0); ec = e->ec; } else { ec = e->ec; if (ubi->free.rb_node) { - e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF, 0); + e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, 0); ec = max(ec, e->ec); } } e = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb); - return ec - e->ec >= UBI_WL_THRESHOLD; + return ec - e->ec >= ubi->wl_threshold; } /* get_peb_for_wl - returns a PEB to be used internally by the WL sub-system. diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 3bce1b4d8464..3f9fb7c181ff 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -1526,7 +1526,8 @@ int ubi_update_fastmap(struct ubi_device *ubi) if (!tmp_e) { if (old_fm && old_fm->e[i]) { - ret = ubi_sync_erase(ubi, old_fm->e[i], 0); + ret = ubi_sync_erase(ubi, old_fm->e[i], + &old_fm->to_be_tortured[i]); if (ret < 0) { ubi_err(ubi, "could not erase old fastmap PEB"); @@ -1578,7 +1579,8 @@ int ubi_update_fastmap(struct ubi_device *ubi) if (old_fm) { /* no fresh anchor PEB was found, reuse the old one */ if (!tmp_e) { - ret = ubi_sync_erase(ubi, old_fm->e[0], 0); + ret = ubi_sync_erase(ubi, old_fm->e[0], + &old_fm->to_be_tortured[0]); if (ret < 0) { ubi_err(ubi, "could not erase old anchor PEB"); diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index 915eb64cb001..d70d1313ad4e 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -519,8 +519,10 @@ static int nor_erase_prepare(struct ubi_device *ubi, int pnum) /** * ubi_io_sync_erase - synchronously erase a physical eraseblock. * @ubi: UBI device description object - * @pnum: physical eraseblock number to erase - * @torture: if this physical eraseblock has to be tortured + * @pnum: the physical eraseblock number to erase + * @torture: if this physical eraseblock has to be tortured; cleared to zero + * once the torture test has completed successfully so that a retry + * of the erase does not torture the physical eraseblock again * * This function synchronously erases physical eraseblock @pnum. If @torture * flag is not zero, the physical eraseblock is checked by means of writing @@ -532,7 +534,7 @@ static int nor_erase_prepare(struct ubi_device *ubi, int pnum) * codes in case of other errors. Note, %-EIO means that the physical * eraseblock is bad. */ -int ubi_io_sync_erase(struct ubi_device *ubi, int pnum, int torture) +int ubi_io_sync_erase(struct ubi_device *ubi, int pnum, int *torture) { int err, ret = 0; @@ -560,10 +562,11 @@ int ubi_io_sync_erase(struct ubi_device *ubi, int pnum, int torture) return err; } - if (torture) { + if (*torture) { ret = torture_peb(ubi, pnum); if (ret < 0) return ret; + *torture = 0; } err = do_sync_erase(ubi, pnum); diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index af466cd83ae0..8a9ac60ff2f4 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -516,6 +516,22 @@ struct ubi_debug_info { * @bgt_thread: background thread description object * @thread_enabled: if the background thread is enabled * @bgt_name: background thread name + * @wl_threshold: Maximum difference between two erase counters. If this + * threshold is exceeded, the WL sub-system starts moving + * data from used physical eraseblocks with low erase + * counter to free physical eraseblocks with high erase counter. + * @wl_free_max_diff: When a physical eraseblock is moved, the WL sub-system + * has to pick the target physical eraseblock to move to. + * The simplest way would be just to pick the one with the + * highest erase counter. But in certain workloads this + * could lead to an unlimited wear of one or few physical + * eraseblock. Indeed, imagine a situation when the picked + * physical eraseblock is constantly erased after the + * data is written to it. So, we have a constant which + * limits the highest erase counter of the free physical + * eraseblock to pick. Namely, the WL sub-system does not + * pick eraseblocks with erase counter greater than the + * lowest erase counter plus @wl_free_max_diff. * * @flash_size: underlying MTD device size (in bytes) * @peb_count: count of physical eraseblocks on the MTD device @@ -623,6 +639,8 @@ struct ubi_device { struct task_struct *bgt_thread; int thread_enabled; char bgt_name[sizeof(UBI_BGT_NAME_PATTERN)+2]; + int wl_threshold; + int wl_free_max_diff; /* I/O sub-system's stuff */ long long flash_size; @@ -901,7 +919,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap, struct ubi_attach_info *ai_scan); /* wl.c */ -int ubi_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int torture); +int ubi_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int *torture); int ubi_wl_get_peb(struct ubi_device *ubi); int ubi_wl_put_peb(struct ubi_device *ubi, int vol_id, int lnum, int pnum, int torture); @@ -923,7 +941,7 @@ int ubi_io_read(const struct ubi_device *ubi, void *buf, int pnum, int offset, int len); int ubi_io_write(struct ubi_device *ubi, const void *buf, int pnum, int offset, int len); -int ubi_io_sync_erase(struct ubi_device *ubi, int pnum, int torture); +int ubi_io_sync_erase(struct ubi_device *ubi, int pnum, int *torture); int ubi_io_is_bad(const struct ubi_device *ubi, int pnum); int ubi_io_mark_bad(const struct ubi_device *ubi, int pnum); int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum, @@ -938,7 +956,8 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum, /* build.c */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset, int max_beb_per1024, - bool disable_fm, bool need_resv_pool); + bool disable_fm, bool need_resv_pool, + int wl_threshold); int ubi_detach_mtd_dev(int ubi_num, int anyway); struct ubi_device *ubi_get_device(int ubi_num); void ubi_put_device(struct ubi_device *ubi); diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index e3705db8e570..5a0db928a90e 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -95,27 +95,6 @@ /* Number of physical eraseblocks reserved for wear-leveling purposes */ #define WL_RESERVED_PEBS 1 -/* - * Maximum difference between two erase counters. If this threshold is - * exceeded, the WL sub-system starts moving data from used physical - * eraseblocks with low erase counter to free physical eraseblocks with high - * erase counter. - */ -#define UBI_WL_THRESHOLD CONFIG_MTD_UBI_WL_THRESHOLD - -/* - * When a physical eraseblock is moved, the WL sub-system has to pick the target - * physical eraseblock to move to. The simplest way would be just to pick the - * one with the highest erase counter. But in certain workloads this could lead - * to an unlimited wear of one or few physical eraseblock. Indeed, imagine a - * situation when the picked physical eraseblock is constantly erased after the - * data is written to it. So, we have a constant which limits the highest erase - * counter of the free physical eraseblock to pick. Namely, the WL sub-system - * does not pick eraseblocks with erase counter greater than the lowest erase - * counter plus %WL_FREE_MAX_DIFF. - */ -#define WL_FREE_MAX_DIFF (2*UBI_WL_THRESHOLD) - /* * Maximum number of consecutive background thread failures which is enough to * switch to read-only mode. @@ -358,7 +337,7 @@ static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi, * * This function looks for a wear leveling entry with medium erase counter, * but not greater or equivalent than the lowest erase counter plus - * %WL_FREE_MAX_DIFF/2. + * @ubi->wl_free_max_diff/2. */ static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, struct rb_root *root) @@ -368,7 +347,7 @@ static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, first = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb); last = rb_entry(rb_last(root), struct ubi_wl_entry, u.rb); - if (last->ec - first->ec < WL_FREE_MAX_DIFF) { + if (last->ec - first->ec < ubi->wl_free_max_diff) { e = rb_entry(root->rb_node, struct ubi_wl_entry, u.rb); /* @@ -379,7 +358,7 @@ static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, */ e = may_reserve_for_fm(ubi, e, root); } else - e = find_wl_entry(ubi, root, WL_FREE_MAX_DIFF/2, 0); + e = find_wl_entry(ubi, root, ubi->wl_free_max_diff/2, 0); return e; } @@ -443,12 +422,14 @@ static int prot_queue_del(struct ubi_device *ubi, int pnum) * ubi_sync_erase - synchronously erase a physical eraseblock. * @ubi: UBI device description object * @e: the physical eraseblock to erase - * @torture: if the physical eraseblock has to be tortured + * @torture: if the physical eraseblock has to be tortured; cleared to zero + * once the torture test has completed successfully so that a retry + * of the erase does not torture the physical eraseblock again * * This function returns zero in case of success and a negative error code in * case of failure. */ -int ubi_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int torture) +int ubi_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int *torture) { int err; struct ubi_ec_hdr *ec_hdr; @@ -706,7 +687,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, #ifdef CONFIG_MTD_UBI_FASTMAP e1 = find_anchor_wl_entry(&ubi->used); if (e1 && ubi->fm_anchor && - (ubi->fm_anchor->ec - e1->ec >= UBI_WL_THRESHOLD)) { + (ubi->fm_anchor->ec - e1->ec >= ubi->wl_threshold)) { ubi->fm_do_produce_anchor = 1; /* * fm_anchor is no longer considered a good anchor. @@ -743,7 +724,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, if (!e2) goto out_cancel; - if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) { + if (!(e2->ec - e1->ec >= ubi->wl_threshold)) { dbg_wl("no WL needed: min used EC %d, max free EC %d", e1->ec, e2->ec); @@ -1056,12 +1037,12 @@ static int ensure_wear_leveling(struct ubi_device *ubi, int nested) * We schedule wear-leveling only if the difference between the * lowest erase counter of used physical eraseblocks and a high * erase counter of free physical eraseblocks is greater than - * %UBI_WL_THRESHOLD. + * @ubi->wl_threshold. */ e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb); - e2 = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF, 0); + e2 = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, 0); - if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) + if (!(e2->ec - e1->ec >= ubi->wl_threshold)) goto out_unlock; #endif dbg_wl("schedule wear-leveling"); @@ -1113,7 +1094,7 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) dbg_wl("erase PEB %d EC %d LEB %d:%d", pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum); - err = ubi_sync_erase(ubi, e, wl_wrk->torture); + err = ubi_sync_erase(ubi, e, &wl_wrk->torture); if (!err) { spin_lock(&ubi->wl_lock); @@ -1150,7 +1131,8 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) int err1; /* Re-schedule the LEB for erasure */ - err1 = schedule_erase(ubi, e, vol_id, lnum, 0, true); + err1 = schedule_erase(ubi, e, vol_id, lnum, wl_wrk->torture, + true); if (err1) { spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); @@ -1757,7 +1739,7 @@ static void shutdown_work(struct ubi_device *ubi) static int erase_aeb(struct ubi_device *ubi, struct ubi_ainf_peb *aeb, bool sync) { struct ubi_wl_entry *e; - int err; + int err, torture = 0; e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL); if (!e) @@ -1768,7 +1750,7 @@ static int erase_aeb(struct ubi_device *ubi, struct ubi_ainf_peb *aeb, bool sync ubi->lookuptbl[e->pnum] = e; if (sync) { - err = ubi_sync_erase(ubi, e, false); + err = ubi_sync_erase(ubi, e, &torture); if (err) goto out_free; @@ -2090,7 +2072,7 @@ static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi) { struct ubi_wl_entry *e; - e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF, 0); + e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, 0); self_check_in_wl_tree(ubi, e, &ubi->free); ubi->free_count--; ubi_assert(ubi->free_count >= 0); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index bbe9a6985f90..810563259a65 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -888,7 +888,7 @@ static int rlb_initialize(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); /* register to receive ARPs */ - bond->recv_probe = rlb_arp_recv; + WRITE_ONCE(bond->recv_probe, rlb_arp_recv); return 0; } @@ -1294,10 +1294,10 @@ static int alb_set_mac_address(struct bonding *bond, void *addr) } /* determine if the packet is NA or NS */ -static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) +static bool alb_determine_nd(struct sk_buff *skb) { - struct ipv6hdr *ip6hdr; - struct icmp6hdr *hdr; + const struct ipv6hdr *ip6hdr; + const struct icmp6hdr *hdr; if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) return true; @@ -1309,7 +1309,8 @@ static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr))) return true; - hdr = icmp6_hdr(skb); + ip6hdr = ipv6_hdr(skb); + hdr = (const struct icmp6hdr *)(ip6hdr + 1); return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT || hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION; } @@ -1400,7 +1401,7 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { case htons(ETH_P_IPV6): - if (alb_determine_nd(skb, bond)) + if (alb_determine_nd(skb)) break; fallthrough; case htons(ETH_P_IP): @@ -1486,7 +1487,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, break; } - if (alb_determine_nd(skb, bond)) { + if (alb_determine_nd(skb)) { do_tx_balance = false; break; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ef9eb0c53c66..a9bff7663eec 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1245,7 +1245,7 @@ static void bond_peer_notify_may_events(struct bonding *bond, bool force) } if (notified || force) - bond->send_peer_notif--; + WRITE_ONCE(bond->send_peer_notif, bond->send_peer_notif - 1); } /** @@ -2284,7 +2284,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } } - bond->slave_cnt++; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt + 1); netdev_compute_master_upper_features(bond->dev, true); bond_set_carrier(bond); @@ -2517,9 +2517,7 @@ static int __bond_release_one(struct net_device *bond_dev, bond_alb_deinit_slave(bond, slave); } - if (all) { - RCU_INIT_POINTER(bond->curr_active_slave, NULL); - } else if (oldcurrent == slave) { + if (!all && oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. @@ -2533,7 +2531,7 @@ static int __bond_release_one(struct net_device *bond_dev, unblock_netpoll_tx(); synchronize_rcu(); - bond->slave_cnt--; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt - 1); if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); @@ -4385,13 +4383,13 @@ static int bond_open(struct net_device *bond_dev) if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ - bond->recv_probe = bond_3ad_lacpdu_recv; + WRITE_ONCE(bond->recv_probe, bond_3ad_lacpdu_recv); bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) @@ -4413,7 +4411,7 @@ static int bond_close(struct net_device *bond_dev) struct slave *slave; bond_work_cancel_all(bond); - bond->send_peer_notif = 0; + WRITE_ONCE(bond->send_peer_notif, 0); WRITE_ONCE(bond->recv_probe, NULL); /* Wait for any in-flight RX handlers */ @@ -5118,7 +5116,7 @@ static void bond_skip_slave(struct bond_up_slave *slaves, if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; - slaves->count--; + WRITE_ONCE(slaves->count, slaves->count - 1); break; } } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 36b8d89387ee..9efadeff6a22 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1147,11 +1147,11 @@ static int bond_option_arp_interval_set(struct bonding *bond, */ if (!newval->value) { if (bond->params.arp_validate) - bond->recv_probe = NULL; + WRITE_ONCE(bond->recv_probe, NULL); cancel_delayed_work_sync(&bond->arp_work); } else { /* arp_validate can be set only in active-backup mode */ - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); cancel_delayed_work_sync(&bond->mii_work); queue_delayed_work(bond->wq, &bond->arp_work, 0); } diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index fa9a8edce22f..8277c1c87bb3 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -538,7 +538,7 @@ struct airoha_wdma_info { /* RX queue to IRQ mapping: BIT(q) in IRQ(n) */ #define RX_IRQ0_BANK_PIN_MASK 0x839f -#define RX_IRQ1_BANK_PIN_MASK 0x7fe00000 +#define RX_IRQ1_BANK_PIN_MASK 0xffe00000 #define RX_IRQ2_BANK_PIN_MASK 0x20 #define RX_IRQ3_BANK_PIN_MASK 0x40 #define RX_IRQ_BANK_PIN_MASK(_n) \ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 2de974213090..e2e850c1b90b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -3400,7 +3400,7 @@ static void xgbe_enable_rx(struct xgbe_prv_data *pdata) XGMAC_IOWRITE(pdata, MAC_RQC0R, reg_val); /* Enable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 1); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 1); @@ -3411,7 +3411,6 @@ static void xgbe_disable_rx(struct xgbe_prv_data *pdata) unsigned int i; /* Disable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 0); diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 1e1f52285a39..d6931c41f39d 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -968,6 +968,8 @@ struct macb_dma_desc_ptp { * of the frame * @mapping: DMA address of the skb's fragment buffer * @size: size of the DMA mapped buffer + * @fcs_len: FCS bytes appended in software, 0 or ETH_FCS_LEN, only + * set for the last buffer of the frame * @mapped_as_page: true when buffer was mapped with skb_frag_dma_map(), * false when buffer was mapped with dma_map_single() */ @@ -975,6 +977,7 @@ struct macb_tx_skb { struct sk_buff *skb; dma_addr_t mapping; size_t size; + u8 fcs_len; bool mapped_as_page; }; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 76ee4f506033..b1939da4c95a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1322,8 +1322,8 @@ static void macb_tx_error_task(struct work_struct *work) bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; packets++; - bp->netdev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; bytes += skb->len; } } else { @@ -1450,8 +1450,8 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) skb->data); bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; - bp->netdev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; packets++; bytes += skb->len; } @@ -2199,7 +2199,8 @@ static void macb_poll_controller(struct net_device *netdev) static unsigned int macb_tx_map(struct macb *bp, struct macb_queue *queue, struct sk_buff *skb, - unsigned int hdrlen) + unsigned int hdrlen, + u8 fcs_len) { unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags; unsigned int len, i, tx_head = queue->tx_head; @@ -2284,6 +2285,7 @@ static unsigned int macb_tx_map(struct macb *bp, /* This is the last buffer of the frame: save socket buffer */ tx_skb->skb = skb; + tx_skb->fcs_len = fcs_len; /* Update TX ring: update buffer descriptors in reverse order * to avoid race condition @@ -2417,6 +2419,7 @@ static inline int macb_clear_csum(struct sk_buff *skb) return 0; } +/* Returns a negative errno, or the FCS bytes appended (0 or ETH_FCS_LEN). */ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev) { bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || @@ -2465,7 +2468,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev) skb_put_u8(*skb, (fcs >> 16) & 0xff); skb_put_u8(*skb, (fcs >> 24) & 0xff); - return 0; + return ETH_FCS_LEN; } static netdev_tx_t macb_start_xmit(struct sk_buff *skb, @@ -2478,6 +2481,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, netdev_tx_t ret = NETDEV_TX_OK; unsigned int hdrlen; unsigned long flags; + int fcs_len; bool is_lso; if (macb_clear_csum(skb)) { @@ -2485,7 +2489,8 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, return ret; } - if (macb_pad_and_fcs(&skb, netdev)) { + fcs_len = macb_pad_and_fcs(&skb, netdev); + if (fcs_len < 0) { dev_kfree_skb_any(skb); return ret; } @@ -2548,7 +2553,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, } /* Map socket buffer for DMA transfer */ - if (macb_tx_map(bp, queue, skb, hdrlen)) { + if (macb_tx_map(bp, queue, skb, hdrlen, fcs_len)) { dev_kfree_skb_any(skb); goto unlock; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 74c041ab5280..937b085582b5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -3468,6 +3468,8 @@ int rvu_get_num_lbk_chans(void) return ret; } +#define PCI_DEVID_OCTEONTX2_RVU_AFVF 0xA0F8 + static int rvu_enable_sriov(struct rvu *rvu) { struct pci_dev *pdev = rvu->pdev; @@ -3486,24 +3488,27 @@ static int rvu_enable_sriov(struct rvu *rvu) return 0; pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &rvu->vf_devid); - chans = rvu_get_num_lbk_chans(); - if (chans < 0) - return chans; - vfs = pci_sriov_get_totalvfs(pdev); - - /* Limit VFs in case we have more VFs than LBK channels available. */ - if (vfs > chans) - vfs = chans; - if (!vfs) return 0; - /* LBK channel number 63 is used for switching packets between - * CGX mapped VFs. Hence limit LBK pairs till 62 only. - */ - if (vfs > 62) - vfs = 62; + if (rvu->vf_devid == PCI_DEVID_OCTEONTX2_RVU_AFVF) { + chans = rvu_get_num_lbk_chans(); + if (chans < 0) + return chans; + + /* The last LBK channel is reserved for switching packets between + * CGX mapped VFs. Also, since LBK VFs work in pairs, limit VF + * count to available LBK channels minus 2. + */ + vfs = min(vfs, chans - 2); + + if (vfs <= 0) { + dev_warn(&pdev->dev, + "Skipping SRIOV enablement, not enough LBK channels available\n"); + return 0; + } + } /* Save VFs number for reference in VF interrupts handlers. * Since interrupts might start arriving during SRIOV enablement diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 60922944675b..c34f8d86cc8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2957,10 +2957,9 @@ static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, } } - /* Disable the entry */ - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); - if (!cn20k_dft_rl) { + /* Disable the entry */ + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP; /* Free the entry in bitmap */ npc_mcam_clear_bit(mcam, index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 4f984f6a2cb9..55ec6387ab28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -3,6 +3,7 @@ #include "rx.h" #include "en/xdp.h" +#include #include #include @@ -156,6 +157,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) xsk_buff_free(xsk_buffs[batch]); err: + bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe); rq->stats->buff_alloc_err++; return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 206cf9db3466..7bd0606a5253 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -410,8 +410,11 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, static void mlx5e_xsk_free_rx_wqe(struct mlx5e_wqe_frag_info *wi) { - if (!(wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE))) - xsk_buff_free(*wi->xskp); + if (wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE)) + return; + + xsk_buff_free(*wi->xskp); + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); } static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 417c15d1ff42..6fcc5f561d56 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -83,7 +83,7 @@ struct oa_tc6 { u16 spi_data_tx_buf_offset; u16 tx_credits; u8 rx_chunks_available; - bool rx_buf_overflow; + bool wait_until_start_valid; bool int_flag; bool disable_traffic; bool prot_ctrl; @@ -455,7 +455,7 @@ static int oa_tc6_mdiobus_read(struct mii_bus *bus, int addr, int regnum) { struct oa_tc6 *tc6 = bus->priv; u32 regval; - bool ret; + int ret; ret = oa_tc6_read_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE | (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK), @@ -693,6 +693,26 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6) return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value); } +/* Called when a frame that is meant to be transmitted, is dropped. */ +static void oa_tc6_drop_tx_skb(struct oa_tc6 *tc6, struct sk_buff *skb) +{ + if (skb) { + tc6->netdev->stats.tx_dropped++; + dev_kfree_skb_any(skb); + } +} + +static struct sk_buff *oa_tc6_detach_waiting_tx_skb(struct oa_tc6 *tc6) +{ + struct sk_buff *skb; + + lockdep_assert_held(&tc6->tx_skb_lock); + skb = tc6->waiting_tx_skb; + tc6->waiting_tx_skb = NULL; + + return skb; +} + static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) { if (tc6->rx_skb) { @@ -704,29 +724,39 @@ static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6) { - if (tc6->ongoing_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->ongoing_tx_skb); - tc6->ongoing_tx_skb = NULL; - } + oa_tc6_drop_tx_skb(tc6, tc6->ongoing_tx_skb); + tc6->ongoing_tx_skb = NULL; } static void oa_tc6_cleanup_waiting_tx_skb(struct oa_tc6 *tc6) { - if (tc6->waiting_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->waiting_tx_skb); - tc6->waiting_tx_skb = NULL; - } + struct sk_buff *skb; + + spin_lock_bh(&tc6->tx_skb_lock); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + oa_tc6_drop_tx_skb(tc6, skb); +} + +static void oa_tc6_free_ongoing_skbs(struct oa_tc6 *tc6) +{ + oa_tc6_cleanup_ongoing_tx_skb(tc6); + oa_tc6_cleanup_ongoing_rx_skb(tc6); } static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) { - oa_tc6_cleanup_ongoing_tx_skb(tc6); - oa_tc6_cleanup_ongoing_rx_skb(tc6); + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_cleanup_waiting_tx_skb(tc6); } +static void oa_tc6_look_for_new_frame(struct oa_tc6 *tc6) +{ + tc6->wait_until_start_valid = true; + oa_tc6_cleanup_ongoing_rx_skb(tc6); +} + /* If the failure is at SPI interface level, masking and clearing * the interrupt of the device won't work. Since SPI interrupt is * disabled, it should stop the repeated interrupts. @@ -734,9 +764,19 @@ static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) static void oa_tc6_disable_traffic(struct oa_tc6 *tc6) { u32 regval = OA_TC6_INT_MASK0_ALL_INTERRUPTS; + struct sk_buff *skb; + spin_lock_bh(&tc6->tx_skb_lock); tc6->disable_traffic = true; - oa_tc6_free_pending_skbs(tc6); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + /* disable_traffic, when set, is a point of no return to + * working state. Keeping the TX queues disabled. + */ + netif_tx_disable(tc6->netdev); + oa_tc6_drop_tx_skb(tc6, skb); + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval); oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, ®val); oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, regval); @@ -755,6 +795,13 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) return ret; } + /* This function is called for each chunk received in a given SPI + * transaction. In case, extended status bit is set in more than + * one chunk, skip the write, if status0 is already cleared. + */ + if (!value) + return 0; + /* Clear the error interrupts status */ ret = oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, value); if (ret) { @@ -764,8 +811,7 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) } if (FIELD_GET(OA_TC6_STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) { - tc6->rx_buf_overflow = true; - oa_tc6_cleanup_ongoing_rx_skb(tc6); + oa_tc6_look_for_new_frame(tc6); net_err_ratelimited("%s: Receive buffer overflow error\n", tc6->netdev->name); return -EAGAIN; @@ -791,6 +837,8 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) { + int ret = 0; + /* Process rx chunk footer for the following, * 1. tx credits * 2. errors if any from MAC-PHY @@ -801,9 +849,11 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) footer); if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) { - int ret = oa_tc6_process_extended_status(tc6); - - if (ret) + ret = oa_tc6_process_extended_status(tc6); + /* EAGAIN error is recoverable. Move on to check + * HEADER and SYNC errors before returning. + */ + if (ret && ret != -EAGAIN) return ret; } @@ -821,7 +871,7 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) return -ENODEV; } - return 0; + return ret; } static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) @@ -846,13 +896,35 @@ static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) tc6->rx_skb = NULL; } -static void oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) +/* On oversubscribed traffic condition, particularly with overwhelming rx + * buffer overflow errors, there could be data chunk loss. If tail + length + * goes beyond end pointer, that is an indication that the data chunk with + * end_valid bit is lost. Time to look for a data chunk with start_valid bit. + * + * If rx_skb is NULL, it is time to start looking for data chunk with + * start_bit. + */ +static int oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) { + if (!tc6->rx_skb || + skb_tailroom(tc6->rx_skb) < length) { + oa_tc6_look_for_new_frame(tc6); + return -EAGAIN; + } + memcpy(skb_put(tc6->rx_skb, length), payload, length); + return 0; } +/* On overwhelming rx buffer overflow errors, due to data chunk loss, it is + * possible that we get two data chunks with start_valid bit set, without + * end_valid bit set in between. In this case, rx_skb would have a valid + * buffer pointer. We should release, if a valid pointer is found before + * allocating a new one. + */ static int oa_tc6_allocate_rx_skb(struct oa_tc6 *tc6) { + oa_tc6_cleanup_ongoing_rx_skb(tc6); tc6->rx_skb = netdev_alloc_skb_ip_align(tc6->netdev, tc6->netdev->mtu + ETH_HLEN + ETH_FCS_LEN); if (!tc6->rx_skb) { @@ -872,7 +944,9 @@ static int oa_tc6_prcs_complete_rx_frame(struct oa_tc6 *tc6, u8 *payload, if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (ret) + return ret; oa_tc6_submit_rx_skb(tc6); @@ -887,22 +961,24 @@ static int oa_tc6_prcs_rx_frame_start(struct oa_tc6 *tc6, u8 *payload, u16 size) if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); - - return 0; + return oa_tc6_update_rx_skb(tc6, payload, size); } -static void oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) +static int oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) { - oa_tc6_update_rx_skb(tc6, payload, size); + int ret; - oa_tc6_submit_rx_skb(tc6); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (!ret) + oa_tc6_submit_rx_skb(tc6); + return ret; } -static void oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, - u32 footer) +static int oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, + u32 footer) { - oa_tc6_update_rx_skb(tc6, payload, OA_TC6_CHUNK_PAYLOAD_SIZE); + return oa_tc6_update_rx_skb(tc6, payload, + OA_TC6_CHUNK_PAYLOAD_SIZE); } static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, @@ -917,10 +993,10 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, u16 size; /* Restart the new rx frame after receiving rx buffer overflow error */ - if (start_valid && tc6->rx_buf_overflow) - tc6->rx_buf_overflow = false; + if (start_valid && tc6->wait_until_start_valid) + tc6->wait_until_start_valid = false; - if (tc6->rx_buf_overflow) + if (tc6->wait_until_start_valid) return 0; /* Process the chunk with complete rx frame */ @@ -942,8 +1018,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, /* Process the chunk with only rx frame end */ if (end_valid && !start_valid) { size = end_byte_offset + 1; - oa_tc6_prcs_rx_frame_end(tc6, data, size); - return 0; + return oa_tc6_prcs_rx_frame_end(tc6, data, size); } /* Process the chunk with previous rx frame end and next rx frame @@ -957,6 +1032,15 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, if (tc6->rx_skb) { size = end_byte_offset + 1; oa_tc6_prcs_rx_frame_end(tc6, data, size); + + /* Return value from oa_tc6_prcs_rx_frame_end is not + * checked. If it returned an error, it is to make + * the code to look for new frame. At this stage, + * code below is going to process a new frame. So, + * error condition is set to false, in case it is + * set before proceeding. + */ + tc6->wait_until_start_valid = false; } size = OA_TC6_CHUNK_PAYLOAD_SIZE - start_byte_offset; return oa_tc6_prcs_rx_frame_start(tc6, @@ -965,9 +1049,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, } /* Process the chunk with ongoing rx frame data */ - oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); - - return 0; + return oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); } static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) @@ -983,8 +1065,9 @@ static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) { u16 no_of_rx_chunks = length / OA_TC6_CHUNK_SIZE; + bool retry = false; + int ret = 0; u32 footer; - int ret; /* All the rx chunks in the receive SPI data buffer are examined here */ for (int i = 0; i < no_of_rx_chunks; i++) { @@ -993,8 +1076,11 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) OA_TC6_CHUNK_PAYLOAD_SIZE); ret = oa_tc6_process_rx_chunk_footer(tc6, footer); - if (ret) - return ret; + if (ret) { + if (ret != -EAGAIN) + return ret; + retry = true; + } /* If there is a data valid chunks then process it for the * information needed to determine the validity and the location @@ -1006,12 +1092,35 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) ret = oa_tc6_prcs_rx_chunk_payload(tc6, payload, footer); - if (ret) - return ret; + if (ret) { + if (ret != -ENOMEM && ret != -EAGAIN) + return ret; + retry = true; + } } } - return 0; + /* Not bailing out on recoverable error codes, -EAGAIN and + * -ENOMEM. If subsequent loop iterations, if any, succeeds, + * error code would be overwritten. retry flag helps to + * make the caller to continue and retry. Since recovery + * action for -ENOMEM and -EAGAIN are same, we are returning + * one of the error codes, that is -EAGAIN. + * + * Successful recovery depends on how small the frames are, + * how many chunks, among the received chunks triggered the + * error, whether data is intact even with error conditions. + * As a result, there is no single, best method to recover + * most data when error conditions hit. We do our best by + * processing all the chunks with good "footer header" and + * "data valid" bit set. + */ + if (retry) { + ret = -EAGAIN; + oa_tc6_look_for_new_frame(tc6); + } + + return ret; } static __be32 oa_tc6_prepare_data_header(bool data_valid, bool start_valid, @@ -1173,12 +1282,9 @@ static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6) } ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_len); - if (ret) { - if (ret == -EAGAIN) - continue; - oa_tc6_cleanup_ongoing_tx_skb(tc6); - oa_tc6_cleanup_ongoing_rx_skb(tc6); + if (ret && ret != -EAGAIN) { + oa_tc6_free_ongoing_skbs(tc6); netdev_err(tc6->netdev, "Device error: %d\n", ret); return ret; } @@ -1200,15 +1306,20 @@ static irqreturn_t oa_tc6_macphy_threaded_irq(int irq, void *data) * no need to attempt spi transfer, once it fails. Pending skbs * are already freed. */ - if (!tc6->disable_traffic) { - while (tc6->int_flag || - (tc6->waiting_tx_skb && tc6->tx_credits)) { - ret = oa_tc6_try_spi_transfer(tc6); - if (ret) { - disable_irq_nosync(tc6->spi->irq); - oa_tc6_disable_traffic(tc6); - break; - } + spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + return IRQ_HANDLED; + } + spin_unlock_bh(&tc6->tx_skb_lock); + + while (tc6->int_flag || + (tc6->waiting_tx_skb && tc6->tx_credits)) { + ret = oa_tc6_try_spi_transfer(tc6); + if (ret) { + disable_irq_nosync(tc6->spi->irq); + oa_tc6_disable_traffic(tc6); + break; } } @@ -1287,23 +1398,30 @@ EXPORT_SYMBOL_GPL(oa_tc6_zero_align_receive_frame_enable); * @tc6: oa_tc6 struct. * @skb: socket buffer in which the ethernet frame is stored. * - * Return: NETDEV_TX_OK if the transmit ethernet frame skb added in the tx_skb_q - * otherwise returns NETDEV_TX_BUSY. + * Return: NETDEV_TX_OK either on successful queueing of the packet for + * transmission, or on packet getting dropped. Packet can be dropped due to + * failure in linearizing the buffer or disable_traffic is set due to + * earlier fatal error. Returns NETDEV_TX_BUSY when there is no room + * to queue the packet. */ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) { - if (tc6->disable_traffic || tc6->waiting_tx_skb) { - netif_stop_queue(tc6->netdev); - return NETDEV_TX_BUSY; - } - if (skb_linearize(skb)) { - dev_kfree_skb_any(skb); - tc6->netdev->stats.tx_dropped++; + oa_tc6_drop_tx_skb(tc6, skb); return NETDEV_TX_OK; } spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->waiting_tx_skb) { + netif_stop_queue(tc6->netdev); + spin_unlock_bh(&tc6->tx_skb_lock); + return NETDEV_TX_BUSY; + } + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + oa_tc6_drop_tx_skb(tc6, skb); + return NETDEV_TX_OK; + } tc6->waiting_tx_skb = skb; spin_unlock_bh(&tc6->tx_skb_lock); @@ -1462,8 +1580,10 @@ EXPORT_SYMBOL_GPL(oa_tc6_init); */ void oa_tc6_exit(struct oa_tc6 *tc6) { - tc6->disable_traffic = true; disable_irq(tc6->spi->irq); + spin_lock_bh(&tc6->tx_skb_lock); + tc6->disable_traffic = true; + spin_unlock_bh(&tc6->tx_skb_lock); oa_tc6_phy_exit(tc6); oa_tc6_free_pending_skbs(tc6); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5603d2cdc5c0..07a6fab6460e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3676,6 +3676,14 @@ static int stmmac_hw_setup(struct net_device *dev) /* Initialize MTL*/ stmmac_mtl_configuration(priv); + /* Apply the RX packet parser table */ + if (priv->tc_entries) { + ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries, + priv->tc_entries_max); + if (ret) + return ret; + } + /* Initialize Safety Features */ stmmac_safety_feat_configuration(priv); @@ -4321,6 +4329,7 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, /** * stmmac_tso_allocator - close entry point of the driver * @priv: driver private structure + * @entry: TX queue buffer index * @des: buffer start address * @total_len: total length to fill in descriptors * @last_segment: condition for the last descriptor @@ -4329,8 +4338,9 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, * This function fills descriptor and request new descriptors according to * buffer length to fill */ -static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, - int total_len, bool last_segment, u32 queue) +static void stmmac_tso_allocator(struct stmmac_priv *priv, u32 *entry, + dma_addr_t des, int total_len, + bool last_segment, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; struct dma_desc *desc; @@ -4342,14 +4352,13 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, while (tmp_len > 0) { dma_addr_t curr_addr; - tx_q->cur_tx = STMMAC_NEXT_ENTRY(tx_q->cur_tx, - priv->dma_conf.dma_tx_size); - WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); + *entry = STMMAC_NEXT_ENTRY(*entry, priv->dma_conf.dma_tx_size); + WARN_ON(tx_q->tx_skbuff[*entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[tx_q->cur_tx].basic; + desc = &tx_q->dma_entx[*entry].basic; else - desc = &tx_q->dma_tx[tx_q->cur_tx]; + desc = &tx_q->dma_tx[*entry]; curr_addr = des + (total_len - tmp_len); stmmac_set_desc_addr(priv, desc, curr_addr); @@ -4488,7 +4497,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); - unsigned int first_entry, tx_packets; + unsigned int first_entry, entry, tx_packets; struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; bool set_ic, is_last_segment; @@ -4551,22 +4560,24 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } first_entry = tx_q->cur_tx; - WARN_ON(tx_q->tx_skbuff[first_entry]); + entry = first_entry; + + WARN_ON(tx_q->tx_skbuff[entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[first_entry].basic; + desc = &tx_q->dma_entx[entry].basic; else - desc = &tx_q->dma_tx[first_entry]; + desc = &tx_q->dma_tx[entry]; first = desc; /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error; stmmac_set_desc_addr(priv, first, des); - stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len, + stmmac_tso_allocator(priv, &entry, des + proto_hdr_len, pay_len, (nfrags == 0), queue); /* In case two or more DMA transmit descriptors are allocated for this @@ -4581,8 +4592,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) * this DMA buffer right after the DMA engine completely finishes the * full buffer transmission. */ - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, skb_headlen(skb), - false); + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_headlen(skb), false); /* Prepare fragments */ for (i = 0; i < nfrags; i++) { @@ -4592,14 +4602,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_size(frag), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error_dma_unmap; - stmmac_tso_allocator(priv, des, skb_frag_size(frag), + stmmac_tso_allocator(priv, &entry, des, skb_frag_size(frag), (i == nfrags - 1), queue); - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_frag_size(frag), true); } + tx_q->cur_tx = entry; stmmac_set_tx_dma_last_segment(tx_q, tx_q->cur_tx); @@ -4704,7 +4715,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; -dma_map_err: +error_dma_unmap: + for (;;) { + desc = stmmac_get_tx_desc(priv, tx_q, first_entry); + stmmac_release_tx_desc(priv, desc, priv->descriptor_mode); + stmmac_free_tx_buffer(priv, &priv->dma_conf, queue, + first_entry); + if (first_entry == entry) + break; + + first_entry = STMMAC_NEXT_ENTRY(first_entry, + priv->dma_conf.dma_tx_size); + } +error: dev_err(priv->device, "Tx dma map failed\n"); dev_kfree_skb(skb); priv->xstats.tx_dropped++; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 298efc76a56b..69fe5717846b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -318,6 +318,11 @@ static int gtp_inner_proto(struct sk_buff *skb, unsigned int hdrlen, static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, unsigned int role, __u16 inner_proto) { + if (skb_is_gso(skb)) { + netdev_dbg(pctx->dev, "GSO is not supported in GTP\n"); + goto err; + } + if (!gtp_check_ms(skb, pctx, hdrlen, role, inner_proto)) { netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); return 1; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4939cf67b336..f29864db662a 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -848,7 +848,6 @@ static int ipvlan_device_event(struct notifier_block *unused, __ipvlan_link_delete(net, ipvlan->dev, &lst_kill); } - unregister_netdevice_many(&lst_kill); break; } case NETDEV_FEAT_CHANGE: @@ -899,6 +898,9 @@ static int ipvlan_device_event(struct notifier_block *unused, mutex_unlock(&port->pnodes_lock); + /* Avoid invoking nested netdevice notifiers under pnodes_lock. */ + unregister_netdevice_many(&lst_kill); + ipvlan_port_put(port); return ret; diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 9c171697e762..2c04be6d61a8 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -127,8 +127,10 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct pcpu_sw_netstats *tstats; struct sk_buff *skb, *new_skb; struct net_device *ndev; + unsigned long flags; int rc; ndev = dev->ndev; @@ -139,17 +141,20 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, netdev_dbg(ndev, "%s: %d byte payload received\n", __func__, len); if (len < 0) { - ndev->stats.rx_errors++; - ndev->stats.rx_length_errors++; + DEV_STATS_INC(ndev, rx_errors); + DEV_STATS_INC(ndev, rx_length_errors); goto enqueue_again; } - ndev->stats.rx_packets++; - ndev->stats.rx_bytes += len; + tstats = this_cpu_ptr(ndev->tstats); + flags = u64_stats_update_begin_irqsave(&tstats->syncp); + u64_stats_inc(&tstats->rx_packets); + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_update_end_irqrestore(&tstats->syncp, flags); new_skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); if (!new_skb) { - ndev->stats.rx_dropped++; + DEV_STATS_INC(ndev, rx_dropped); goto enqueue_again; } @@ -166,8 +171,8 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN); if (rc) { dev_kfree_skb_any(skb); - ndev->stats.rx_errors++; - ndev->stats.rx_fifo_errors++; + DEV_STATS_INC(ndev, rx_errors); + DEV_STATS_INC(ndev, rx_fifo_errors); } } @@ -210,25 +215,39 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct pcpu_sw_netstats *tstats; struct net_device *ndev; struct sk_buff *skb; + unsigned long flags; + bool registered; ndev = dev->ndev; skb = data; if (!skb || !ndev) return; + rcu_read_lock(); + registered = READ_ONCE(ndev->reg_state) == NETREG_REGISTERED; + if (!registered) + goto free_skb; + if (len > 0) { - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += skb->len; + /* The memcpy kthread can migrate, so pin the per-CPU update. */ + tstats = get_cpu_ptr(ndev->tstats); + flags = u64_stats_update_begin_irqsave(&tstats->syncp); + u64_stats_inc(&tstats->tx_packets); + u64_stats_add(&tstats->tx_bytes, skb->len); + u64_stats_update_end_irqrestore(&tstats->syncp, flags); + put_cpu_ptr(ndev->tstats); } else { - ndev->stats.tx_errors++; - ndev->stats.tx_aborted_errors++; + DEV_STATS_INC(ndev, tx_errors); + DEV_STATS_INC(ndev, tx_aborted_errors); } +free_skb: dev_kfree_skb_any(skb); - if (ntb_transport_tx_free_entry(qp) >= tx_start) { + if (registered && ntb_transport_tx_free_entry(qp) >= tx_start) { /* Make sure anybody stopping the queue after this sees the new * value of ntb_transport_tx_free_entry() */ @@ -237,6 +256,7 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, ntb_transport_link_query(q->qp)) netif_wake_subqueue(ndev, q->qid); } + rcu_read_unlock(); } static const struct ntb_queue_handlers ntb_netdev_handlers = { @@ -277,7 +297,7 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb, drop: dev_kfree_skb_any(skb); - ndev->stats.tx_dropped++; + DEV_STATS_INC(ndev, tx_dropped); return NETDEV_TX_OK; } @@ -647,6 +667,7 @@ static int ntb_netdev_probe(struct device *client_dev) } ndev->features = NETIF_F_HIGHDMA; + ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 583426d06381..ea7fe9608ffd 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -63,8 +63,6 @@ struct asyncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead; struct ppp_channel chan; /* interface to generic ppp layer */ unsigned char obuf[OBUFSIZE]; }; @@ -114,38 +112,6 @@ static const struct ppp_channel_ops async_ops = { * Routines implementing the PPP line discipline. */ -/* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_asynctty_receive while another - * calls ppp_asynctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_asynctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: this is no longer true. The _close path for the ldisc is - * now guaranteed to be sane. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct asyncppp *ap_get(struct tty_struct *tty) -{ - struct asyncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void ap_put(struct asyncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead); -} - /* * Called when a tty is put into PPP line discipline. Called in process * context. @@ -180,9 +146,6 @@ ppp_asynctty_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_async_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead); - ap->chan.private = ap; ap->chan.ops = &async_ops; ap->chan.mtu = PPP_MRU; @@ -203,34 +166,18 @@ ppp_asynctty_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_asynctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the asyncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_asynctty_close(struct tty_struct *tty) { - struct asyncppp *ap; + struct asyncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_async_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -240,17 +187,6 @@ ppp_asynctty_close(struct tty_struct *tty) kfree(ap); } -/* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_asynctty_hangup(struct tty_struct *tty) -{ - ppp_asynctty_close(tty); -} - /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. @@ -281,7 +217,7 @@ ppp_asynctty_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; int err, val; int __user *p = (int __user *)arg; @@ -322,7 +258,6 @@ ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) err = tty_mode_ioctl(tty, cmd, arg); } - ap_put(ap); return err; } @@ -331,7 +266,7 @@ static void ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -341,21 +276,19 @@ ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - ap_put(ap); tty_unthrottle(tty); } static void ppp_asynctty_wakeup(struct tty_struct *tty) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - ap_put(ap); } @@ -365,7 +298,6 @@ static struct tty_ldisc_ops ppp_ldisc = { .name = "ppp", .open = ppp_asynctty_open, .close = ppp_asynctty_close, - .hangup = ppp_asynctty_hangup, .read = ppp_asynctty_read, .write = ppp_asynctty_write, .ioctl = ppp_asynctty_ioctl, diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 0b1bd1635c39..f87d43faeeab 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -38,11 +38,9 @@ #include #include #include -#include #include #include #include -#include #include #include @@ -67,8 +65,6 @@ struct syncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead_cmp; struct ppp_channel chan; /* interface to generic ppp layer */ }; @@ -116,37 +112,6 @@ ppp_print_buffer (const char *name, const __u8 *buf, int count) * Routines implementing the synchronous PPP line discipline. */ -/* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_synctty_receive while another - * calls ppp_synctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_synctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: Fixed in tty_io nowadays. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct syncppp *sp_get(struct tty_struct *tty) -{ - struct syncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void sp_put(struct syncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead_cmp); -} - /* * Called when a tty is put into sync-PPP line discipline. */ @@ -177,9 +142,6 @@ ppp_sync_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_sync_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead_cmp); - ap->chan.private = ap; ap->chan.ops = &sync_ops; ap->chan.mtu = PPP_MRU; @@ -201,34 +163,18 @@ ppp_sync_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_synctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the syncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_sync_close(struct tty_struct *tty) { - struct syncppp *ap; + struct syncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_sync_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead_cmp); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -237,17 +183,6 @@ ppp_sync_close(struct tty_struct *tty) kfree(ap); } -/* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_sync_hangup(struct tty_struct *tty) -{ - ppp_sync_close(tty); -} - /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. @@ -273,7 +208,7 @@ ppp_sync_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; int __user *p = (int __user *)arg; int err, val; @@ -314,7 +249,6 @@ ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) break; } - sp_put(ap); return err; } @@ -323,7 +257,7 @@ static void ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -333,21 +267,19 @@ ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - sp_put(ap); tty_unthrottle(tty); } static void ppp_sync_wakeup(struct tty_struct *tty) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - sp_put(ap); } @@ -357,7 +289,6 @@ static struct tty_ldisc_ops ppp_sync_ldisc = { .name = "pppsync", .open = ppp_sync_open, .close = ppp_sync_close, - .hangup = ppp_sync_hangup, .read = ppp_sync_read, .write = ppp_sync_write, .ioctl = ppp_synctty_ioctl, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8178a8758cd3..fdfdcf24ddcf 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1446,6 +1446,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ + {QMI_QUIRK_SET_DTR(0x04b7, 0x8217, 8)}, /* Compal EXM-G1x */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index d71e1925ecfd..841f42ffecb9 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -354,6 +354,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } + if (ipv4_is_zeronet(nla_get_in_addr(attr))) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 all-zeros source address is not allowed"); + return false; + } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { @@ -368,6 +372,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } + if (ipv6_addr_any(&src)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 all-zeros source address is not allowed"); + return false; + } break; } #endif diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c index 0f7cd6dab0b0..d77dacdd4f56 100644 --- a/drivers/ras/amd/atl/core.c +++ b/drivers/ras/amd/atl/core.c @@ -190,7 +190,6 @@ static const struct x86_cpu_id amd_atl_cpuids[] = { X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL), { } }; -MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids); static int __init amd_atl_init(void) { diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c index 24a05af747d5..4ec9333ef745 100644 --- a/drivers/ras/amd/atl/map.c +++ b/drivers/ras/amd/atl/map.c @@ -771,9 +771,5 @@ int get_address_map(struct addr_ctx *ctx) dump_address_map(&ctx->map); - ret = validate_address_map(ctx); - if (ret) - return ret; - - return ret; + return validate_address_map(ctx); } diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 01def8231873..05b9233b9418 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1635,10 +1635,11 @@ config RTC_DRV_RS5C313 config RTC_DRV_RZN1 tristate "Renesas RZ/N1 RTC" - depends on ARCH_RZN1 || COMPILE_TEST + depends on ARCH_RENESAS || COMPILE_TEST depends on OF && HAS_IOMEM help - If you say yes here you get support for the Renesas RZ/N1 RTC. + If you say yes here you get support for the RTC initially found on + Renesas RZ/N1 SoCs. config RTC_DRV_GENERIC tristate "Generic RTC support" @@ -2106,7 +2107,8 @@ config RTC_DRV_MACSMC config RTC_DRV_MSC313 tristate "MStar MSC313 RTC" - depends on ARCH_MSTARV7 || COMPILE_TEST + depends on ARCH_MSTARV7 || COMPILE_TEST + default ARCH_MSTARV7 help If you say yes here you get support for the Mstar MSC313e On-Chip Real Time Clock. diff --git a/drivers/rtc/rtc-ab-eoz9.c b/drivers/rtc/rtc-ab-eoz9.c index b75f4f665076..eb6d267c2ec3 100644 --- a/drivers/rtc/rtc-ab-eoz9.c +++ b/drivers/rtc/rtc-ab-eoz9.c @@ -549,6 +549,7 @@ static const struct i2c_device_id abeoz9_id[] = { { .name = "abeoz9" }, { } }; +MODULE_DEVICE_TABLE(i2c, abeoz9_id); static struct i2c_driver abeoz9_driver = { .driver = { diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c index fb47c32ab5ff..55c15aad42cf 100644 --- a/drivers/rtc/rtc-brcmstb-waketimer.c +++ b/drivers/rtc/rtc-brcmstb-waketimer.c @@ -413,6 +413,7 @@ static const __maybe_unused struct of_device_id brcmstb_waketmr_of_match[] = { { .compatible = "brcm,brcmstb-waketimer" }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, brcmstb_waketmr_of_match); static struct platform_driver brcmstb_waketmr_driver = { .probe = brcmstb_waketmr_probe, diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index fd3858b6569e..522f7eef3b4a 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -661,7 +661,7 @@ static int rx8130_set_alarm(struct device *dev, struct rtc_wkalrm *t) if (ret < 0) return ret; - ctl[0] &= RX8130_REG_EXTENSION_WADA; + ctl[0] |= RX8130_REG_EXTENSION_WADA; ctl[1] &= ~RX8130_REG_FLAG_AF; ctl[2] &= ~RX8130_REG_CONTROL0_AIE; diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c index aa9500791b7e..54f6af7886a8 100644 --- a/drivers/rtc/rtc-ds1343.c +++ b/drivers/rtc/rtc-ds1343.c @@ -120,7 +120,7 @@ static ssize_t ds1343_store_glitchfilter(struct device *dev, return count; } -static DEVICE_ATTR(glitch_filter, S_IRUGO | S_IWUSR, ds1343_show_glitchfilter, +static DEVICE_ATTR(glitch_filter, 0644, ds1343_show_glitchfilter, ds1343_store_glitchfilter); static int ds1343_nvram_write(void *priv, unsigned int off, void *val, @@ -183,7 +183,7 @@ static ssize_t ds1343_show_tricklecharger(struct device *dev, return sprintf(buf, "%s %s\n", diodes, resistors); } -static DEVICE_ATTR(trickle_charger, S_IRUGO, ds1343_show_tricklecharger, NULL); +static DEVICE_ATTR(trickle_charger, 0444, ds1343_show_tricklecharger, NULL); static struct attribute *ds1343_attrs[] = { &dev_attr_glitch_filter.attr, diff --git a/drivers/rtc/rtc-gamecube.c b/drivers/rtc/rtc-gamecube.c index 045d5d45ab4b..889028cecf4a 100644 --- a/drivers/rtc/rtc-gamecube.c +++ b/drivers/rtc/rtc-gamecube.c @@ -355,9 +355,7 @@ static int gamecube_rtc_probe(struct platform_device *pdev) rtc->range_max = U32_MAX; rtc->ops = &gamecube_rtc_ops; - devm_rtc_register_device(rtc); - - return 0; + return devm_rtc_register_device(rtc); } static const struct of_device_id gamecube_rtc_of_match[] = { diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c index 3156aa5f2d9f..1d52cc3def02 100644 --- a/drivers/rtc/rtc-hym8563.c +++ b/drivers/rtc/rtc-hym8563.c @@ -376,8 +376,8 @@ static struct clk *hym8563_clkout_register_clk(struct hym8563 *hym8563) { struct i2c_client *client = hym8563->client; struct device_node *node = client->dev.of_node; + struct clk_init_data init = {}; struct clk *clk; - struct clk_init_data init; int ret; ret = i2c_smbus_write_byte_data(client, HYM8563_CLKOUT, diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 3c8c379392c1..ec86ca3f2c4c 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -574,8 +574,8 @@ static struct clk *m41t80_sqw_register_clk(struct m41t80_data *m41t80) struct i2c_client *client = m41t80->client; struct device_node *node = client->dev.of_node; struct device_node *fixed_clock; + struct clk_init_data init = {}; struct clk *clk; - struct clk_init_data init; int ret; fixed_clock = of_get_child_by_name(node, "clock"); diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c index f88976fd6d5d..db64c459ee19 100644 --- a/drivers/rtc/rtc-mv.c +++ b/drivers/rtc/rtc-mv.c @@ -219,17 +219,15 @@ static int __init mv_rtc_probe(struct platform_device *pdev) if (IS_ERR(pdata->ioaddr)) return PTR_ERR(pdata->ioaddr); - pdata->clk = devm_clk_get(&pdev->dev, NULL); - /* Not all SoCs require a clock.*/ - if (!IS_ERR(pdata->clk)) - clk_prepare_enable(pdata->clk); + pdata->clk = devm_clk_get_optional_prepared(&pdev->dev, NULL); + if (IS_ERR(pdata->clk)) + return PTR_ERR(pdata->clk); /* make sure the 24 hour mode is enabled */ rtc_time = readl(pdata->ioaddr + RTC_TIME_REG_OFFS); if (rtc_time & RTC_HOURS_12H_MODE) { dev_err(&pdev->dev, "12 Hour mode is enabled but not supported.\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } /* make sure it is actually functional */ @@ -238,8 +236,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev) rtc_time = readl(pdata->ioaddr + RTC_TIME_REG_OFFS); if (rtc_time == 0x01000000) { dev_err(&pdev->dev, "internal RTC not ticking\n"); - ret = -ENODEV; - goto out; + return -ENODEV; } } @@ -249,8 +246,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev) pdata->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(pdata->rtc)) { - ret = PTR_ERR(pdata->rtc); - goto out; + return PTR_ERR(pdata->rtc); } if (pdata->irq >= 0) { @@ -264,7 +260,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev) } if (pdata->irq >= 0) - device_init_wakeup(&pdev->dev, true); + devm_device_init_wakeup(&pdev->dev); else clear_bit(RTC_FEATURE_ALARM, pdata->rtc->features); @@ -275,24 +271,10 @@ static int __init mv_rtc_probe(struct platform_device *pdev) ret = devm_rtc_register_device(pdata->rtc); if (!ret) return 0; -out: - if (!IS_ERR(pdata->clk)) - clk_disable_unprepare(pdata->clk); return ret; } -static void __exit mv_rtc_remove(struct platform_device *pdev) -{ - struct rtc_plat_data *pdata = platform_get_drvdata(pdev); - - if (pdata->irq >= 0) - device_init_wakeup(&pdev->dev, false); - - if (!IS_ERR(pdata->clk)) - clk_disable_unprepare(pdata->clk); -} - #ifdef CONFIG_OF static const struct of_device_id rtc_mv_of_match_table[] = { { .compatible = "marvell,orion-rtc", }, @@ -323,14 +305,7 @@ static int mv_rtc_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(mv_rtc_pm_ops, mv_rtc_suspend, mv_rtc_resume); -/* - * mv_rtc_remove() lives in .exit.text. For drivers registered via - * module_platform_driver_probe() this is ok because they cannot get unbound at - * runtime. So mark the driver struct with __refdata to prevent modpost - * triggering a section mismatch warning. - */ -static struct platform_driver mv_rtc_driver __refdata = { - .remove = __exit_p(mv_rtc_remove), +static struct platform_driver mv_rtc_driver = { .driver = { .name = "rtc-mv", .of_match_table = of_match_ptr(rtc_mv_of_match_table), diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c index 700a395fad3a..2f7ad57057a4 100644 --- a/drivers/rtc/rtc-nct3018y.c +++ b/drivers/rtc/rtc-nct3018y.c @@ -459,8 +459,8 @@ static struct clk *nct3018y_clkout_register_clk(struct nct3018y *nct3018y) { struct i2c_client *client = nct3018y->client; struct device_node *node = client->dev.of_node; + struct clk_init_data init = {}; struct clk *clk; - struct clk_init_data init; init.name = "nct3018y-clkout"; init.ops = &nct3018y_clkout_ops; diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 1995e9f2756d..ff2023908f5a 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -1184,12 +1184,7 @@ static int pcf2127_configure_interrupt_pins(struct device *dev) if (ret) return ret; - ret = regmap_write(pcf2127->regmap, - PCF2131_REG_INT_A_MASK2, 0); - if (ret) - return ret; - - return ret; + return regmap_write(pcf2127->regmap, PCF2131_REG_INT_A_MASK2, 0); } static int pcf2127_probe(struct device *dev, struct regmap *regmap, diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index 01e209d88f5f..8cb9ffc73f6d 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -498,7 +498,7 @@ static const struct clk_ops pcf85063_clkout_ops = { static struct clk *pcf85063_clkout_register_clk(struct pcf85063 *pcf85063) { struct clk *clk; - struct clk_init_data init; + struct clk_init_data init = {}; struct device_node *node = pcf85063->rtc->dev.parent->of_node; struct device_node *fixed_clock; diff --git a/drivers/rtc/rtc-pcf85363.c b/drivers/rtc/rtc-pcf85363.c index 540042b9eec8..ccc7834e5759 100644 --- a/drivers/rtc/rtc-pcf85363.c +++ b/drivers/rtc/rtc-pcf85363.c @@ -426,8 +426,8 @@ static int pcf85363_probe(struct i2c_client *client) err = pcf85363_load_capacitance(pcf85363, client->dev.of_node); if (err < 0) - dev_warn(&client->dev, "failed to set xtal load capacitance: %d", - err); + return dev_err_probe(&client->dev, err, + "failed to set xtal load capacitance\n"); pcf85363->rtc->ops = &rtc_ops; pcf85363->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; @@ -436,9 +436,16 @@ static int pcf85363_probe(struct i2c_client *client) wakeup_source = device_property_read_bool(&client->dev, "wakeup-source"); if (client->irq > 0 || wakeup_source) { - regmap_write(pcf85363->regmap, CTRL_FLAGS, 0); - regmap_update_bits(pcf85363->regmap, CTRL_PIN_IO, - PIN_IO_INTAPM, PIN_IO_INTA_OUT); + err = regmap_write(pcf85363->regmap, CTRL_FLAGS, 0); + if (err) + return dev_err_probe(&client->dev, err, + "failed to clear flags\n"); + + err = regmap_update_bits(pcf85363->regmap, CTRL_PIN_IO, + PIN_IO_INTAPM, PIN_IO_INTA_OUT); + if (err) + return dev_err_probe(&client->dev, err, + "failed to set interrupt pin mode\n"); } if (client->irq > 0) { diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index 81d13733b1e9..7eebdb058067 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -425,7 +425,7 @@ static const struct clk_ops pcf8563_clkout_ops = { static struct clk *pcf8563_clkout_register_clk(struct pcf8563 *pcf8563) { struct device_node *node = pcf8563->rtc->dev.parent->of_node; - struct clk_init_data init; + struct clk_init_data init = {}; struct clk *clk; int ret; @@ -449,7 +449,9 @@ static struct clk *pcf8563_clkout_register_clk(struct pcf8563 *pcf8563) clk = devm_clk_register(&pcf8563->rtc->dev, &pcf8563->clkout_hw); if (!IS_ERR(clk)) - of_clk_add_provider(node, of_clk_src_simple_get, clk); + devm_of_clk_add_hw_provider(pcf8563->rtc->dev.parent, + of_clk_hw_simple_get, + &pcf8563->clkout_hw); return clk; } diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c index d96f6bb68850..d25e33d0835e 100644 --- a/drivers/rtc/rtc-rv3028.c +++ b/drivers/rtc/rtc-rv3028.c @@ -816,7 +816,7 @@ static int rv3028_clkout_register_clk(struct rv3028_data *rv3028, { int ret; struct clk *clk; - struct clk_init_data init; + struct clk_init_data init = {}; struct device_node *node = client->dev.of_node; ret = regmap_update_bits(rv3028->regmap, RV3028_STATUS, diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c index 6bafdec637ae..687faaef42b2 100644 --- a/drivers/rtc/rtc-rv3032.c +++ b/drivers/rtc/rtc-rv3032.c @@ -752,7 +752,7 @@ static int rv3032_clkout_register_clk(struct rv3032_data *rv3032, { int ret; struct clk *clk; - struct clk_init_data init; + struct clk_init_data init = {}; struct device_node *node = client->dev.of_node; ret = regmap_update_bits(rv3032->regmap, RV3032_TLSB, RV3032_TLSB_CLKF, 0); diff --git a/drivers/rtc/rtc-rzn1.c b/drivers/rtc/rtc-rzn1.c index 305f10a8a85b..b9d69ebdd224 100644 --- a/drivers/rtc/rtc-rzn1.c +++ b/drivers/rtc/rtc-rzn1.c @@ -12,10 +12,13 @@ */ #include +#include +#include #include #include #include #include +#include #include #include #include @@ -38,14 +41,18 @@ #define RZN1_RTC_CTL2_STOPPED (RZN1_RTC_CTL2_WAIT | RZN1_RTC_CTL2_WST) #define RZN1_RTC_TIME 0x30 -#define RZN1_RTC_TIME_MIN_SHIFT 8 -#define RZN1_RTC_TIME_HOUR_SHIFT 16 +#define RZN1_RTC_TIME_SEC GENMASK(7, 0) +#define RZN1_RTC_TIME_MIN GENMASK(15, 8) +#define RZN1_RTC_TIME_HOUR GENMASK(23, 16) + #define RZN1_RTC_CAL 0x34 -#define RZN1_RTC_CAL_DAY_SHIFT 8 -#define RZN1_RTC_CAL_MON_SHIFT 16 -#define RZN1_RTC_CAL_YEAR_SHIFT 24 +#define RZN1_RTC_CAL_WDAY GENMASK(7, 0) +#define RZN1_RTC_CAL_DAY GENMASK(15, 8) +#define RZN1_RTC_CAL_MON GENMASK(23, 16) +#define RZN1_RTC_CAL_YEAR GENMASK(31, 24) #define RZN1_RTC_SUBU 0x38 +#define RZN1_RTC_SUBU_RTCA0FX GENMASK(5, 0) #define RZN1_RTC_SUBU_DEV BIT(7) #define RZN1_RTC_SUBU_DECR BIT(6) @@ -59,6 +66,10 @@ #define RZN1_RTC_TIMEC 0x68 #define RZN1_RTC_CALC 0x6c +struct rzn1_rtc_data { + bool has_subu; +}; + struct rzn1_rtc { struct rtc_device *rtcdev; void __iomem *base; @@ -69,6 +80,7 @@ struct rzn1_rtc { */ spinlock_t ctl1_access_lock; struct rtc_time tm_alarm; + unsigned long sync_time; }; static void rzn1_rtc_get_time_snapshot(struct rzn1_rtc *rtc, struct rtc_time *tm) @@ -76,15 +88,15 @@ static void rzn1_rtc_get_time_snapshot(struct rzn1_rtc *rtc, struct rtc_time *tm u32 val; val = readl(rtc->base + RZN1_RTC_TIMEC); - tm->tm_sec = bcd2bin(val); - tm->tm_min = bcd2bin(val >> RZN1_RTC_TIME_MIN_SHIFT); - tm->tm_hour = bcd2bin(val >> RZN1_RTC_TIME_HOUR_SHIFT); + tm->tm_sec = bcd2bin(FIELD_GET(RZN1_RTC_TIME_SEC, val)); + tm->tm_min = bcd2bin(FIELD_GET(RZN1_RTC_TIME_MIN, val)); + tm->tm_hour = bcd2bin(FIELD_GET(RZN1_RTC_TIME_HOUR, val)); val = readl(rtc->base + RZN1_RTC_CALC); - tm->tm_wday = val & 0x0f; - tm->tm_mday = bcd2bin(val >> RZN1_RTC_CAL_DAY_SHIFT); - tm->tm_mon = bcd2bin(val >> RZN1_RTC_CAL_MON_SHIFT) - 1; - tm->tm_year = bcd2bin(val >> RZN1_RTC_CAL_YEAR_SHIFT) + 100; + tm->tm_wday = FIELD_GET(RZN1_RTC_CAL_WDAY, val); + tm->tm_mday = bcd2bin(FIELD_GET(RZN1_RTC_CAL_DAY, val)); + tm->tm_mon = bcd2bin(FIELD_GET(RZN1_RTC_CAL_MON, val)) - 1; + tm->tm_year = bcd2bin(FIELD_GET(RZN1_RTC_CAL_YEAR, val)) + 100; } static int rzn1_rtc_read_time(struct device *dev, struct rtc_time *tm) @@ -119,23 +131,23 @@ static int rzn1_rtc_set_time(struct device *dev, struct rtc_time *tm) /* Hold the counter if it was counting up */ writel(RZN1_RTC_CTL2_WAIT, rtc->base + RZN1_RTC_CTL2); - /* Wait for the counter to stop: two 32k clock cycles */ - usleep_range(61, 100); + /* Wait 2-4 RTC_PCLK clock cycles for the counter to stop */ + usleep_range(rtc->sync_time, rtc->sync_time * 2); ret = readl_poll_timeout(rtc->base + RZN1_RTC_CTL2, val, val & RZN1_RTC_CTL2_WST, 0, 100); if (ret) return ret; } - val = bin2bcd(tm->tm_sec); - val |= bin2bcd(tm->tm_min) << RZN1_RTC_TIME_MIN_SHIFT; - val |= bin2bcd(tm->tm_hour) << RZN1_RTC_TIME_HOUR_SHIFT; + val = FIELD_PREP(RZN1_RTC_TIME_SEC, bin2bcd(tm->tm_sec)) | + FIELD_PREP(RZN1_RTC_TIME_MIN, bin2bcd(tm->tm_min)) | + FIELD_PREP(RZN1_RTC_TIME_HOUR, bin2bcd(tm->tm_hour)); writel(val, rtc->base + RZN1_RTC_TIME); - val = tm->tm_wday; - val |= bin2bcd(tm->tm_mday) << RZN1_RTC_CAL_DAY_SHIFT; - val |= bin2bcd(tm->tm_mon + 1) << RZN1_RTC_CAL_MON_SHIFT; - val |= bin2bcd(tm->tm_year - 100) << RZN1_RTC_CAL_YEAR_SHIFT; + val = FIELD_PREP(RZN1_RTC_CAL_WDAY, tm->tm_wday) | + FIELD_PREP(RZN1_RTC_CAL_DAY, bin2bcd(tm->tm_mday)) | + FIELD_PREP(RZN1_RTC_CAL_MON, bin2bcd(tm->tm_mon + 1)) | + FIELD_PREP(RZN1_RTC_CAL_YEAR, bin2bcd(tm->tm_year - 100)); writel(val, rtc->base + RZN1_RTC_CAL); writel(0, rtc->base + RZN1_RTC_CTL2); @@ -234,13 +246,24 @@ static int rzn1_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) if (ret) return ret; + ctl1 = readl(rtc->base + RZN1_RTC_CTL1); + alrm->enabled = !!(ctl1 & (RZN1_RTC_CTL1_ALME | RZN1_RTC_CTL1_1SE)); + min = readl(rtc->base + RZN1_RTC_ALM); hour = readl(rtc->base + RZN1_RTC_ALH); - wday = readl(rtc->base + RZN1_RTC_ALW); tm->tm_sec = 0; tm->tm_min = bcd2bin(min); tm->tm_hour = bcd2bin(hour); + + /* + * If wday is zero, no bit is set in RZN1_RTC_ALW. This is the + * register's power-on reset value. + */ + wday = readl(rtc->base + RZN1_RTC_ALW); + if (!wday) + return 0; + delta_days = ((fls(wday) - 1) - tm->tm_wday + 7) % 7; tm->tm_wday = fls(wday) - 1; @@ -249,9 +272,6 @@ static int rzn1_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) rtc_time64_to_tm(alarm, tm); } - ctl1 = readl(rtc->base + RZN1_RTC_CTL1); - alrm->enabled = !!(ctl1 & (RZN1_RTC_CTL1_ALME | RZN1_RTC_CTL1_1SE)); - return 0; } @@ -259,8 +279,7 @@ static int rzn1_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) { struct rzn1_rtc *rtc = dev_get_drvdata(dev); struct rtc_time *tm = &alrm->time, tm_now; - unsigned long alarm, farest; - unsigned int days_ahead, wday; + time64_t alarm, farest; int ret; ret = rzn1_rtc_read_time(dev, &tm_now); @@ -270,16 +289,17 @@ static int rzn1_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) /* We cannot set alarms more than one week ahead */ farest = rtc_tm_to_time64(&tm_now) + rtc->rtcdev->alarm_offset_max; alarm = rtc_tm_to_time64(tm); - if (time_after(alarm, farest)) + if (alarm > farest) return -ERANGE; - /* Convert alarm day into week day */ - days_ahead = tm->tm_mday - tm_now.tm_mday; - wday = (tm_now.tm_wday + days_ahead) % 7; + /* Disable alarm interrupts before reprogramming the alarm. */ + ret = rzn1_rtc_alarm_irq_enable(dev, 0); + if (ret) + return ret; writel(bin2bcd(tm->tm_min), rtc->base + RZN1_RTC_ALM); writel(bin2bcd(tm->tm_hour), rtc->base + RZN1_RTC_ALH); - writel(BIT(wday), rtc->base + RZN1_RTC_ALW); + writel(BIT(tm->tm_wday), rtc->base + RZN1_RTC_ALW); rtc->tm_alarm = alrm->time; @@ -298,12 +318,12 @@ static int rzn1_rtc_read_offset(struct device *dev, long *offset) val = readl(rtc->base + RZN1_RTC_SUBU); ppb_per_step = val & RZN1_RTC_SUBU_DEV ? 1017 : 3051; subtract = val & RZN1_RTC_SUBU_DECR; - val &= 0x3F; + val = FIELD_GET(RZN1_RTC_SUBU_RTCA0FX, val); if (!val) *offset = 0; else if (subtract) - *offset = -(((~val) & 0x3F) + 1) * ppb_per_step; + *offset = -(((~val) & RZN1_RTC_SUBU_RTCA0FX) + 1) * ppb_per_step; else *offset = (val - 1) * ppb_per_step; @@ -345,7 +365,7 @@ static int rzn1_rtc_set_offset(struct device *dev, long offset) subu |= steps + 1; } else { subu |= RZN1_RTC_SUBU_DECR; - subu |= (~(-steps - 1)) & 0x3F; + subu |= (~(-steps - 1)) & RZN1_RTC_SUBU_RTCA0FX; } ret = readl_poll_timeout(rtc->base + RZN1_RTC_CTL2, ctl2, @@ -376,15 +396,32 @@ static const struct rtc_class_ops rzn1_rtc_ops_scmp = { .alarm_irq_enable = rzn1_rtc_alarm_irq_enable, }; +static void rzn1_rtc_disable_hardware(void *data) +{ + struct device *dev = data; + struct rzn1_rtc *rtc = dev_get_drvdata(dev); + + /* Disable all interrupts */ + writel(0, rtc->base + RZN1_RTC_CTL1); + + pm_runtime_put_sync(dev); +} + static int rzn1_rtc_probe(struct platform_device *pdev) { + const struct rzn1_rtc_data *data; + struct device *dev = &pdev->dev; + unsigned long rate = 32768; struct rzn1_rtc *rtc; u32 val, scmp_val = 0; struct clk *xtal; - unsigned long rate; int irq, ret; - rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); + data = of_device_get_match_data(dev); + if (!data) + return -ENODEV; + + rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL); if (!rtc) return -ENOMEM; @@ -392,13 +429,13 @@ static int rzn1_rtc_probe(struct platform_device *pdev) rtc->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rtc->base)) - return dev_err_probe(&pdev->dev, PTR_ERR(rtc->base), "Missing reg\n"); + return dev_err_probe(dev, PTR_ERR(rtc->base), "Missing reg\n"); irq = platform_get_irq_byname(pdev, "alarm"); if (irq < 0) return irq; - rtc->rtcdev = devm_rtc_allocate_device(&pdev->dev); + rtc->rtcdev = devm_rtc_allocate_device(dev); if (IS_ERR(rtc->rtcdev)) return PTR_ERR(rtc->rtcdev); @@ -406,38 +443,47 @@ static int rzn1_rtc_probe(struct platform_device *pdev) rtc->rtcdev->range_max = RTC_TIMESTAMP_END_2099; rtc->rtcdev->alarm_offset_max = 7 * 86400; - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret < 0) return ret; - ret = pm_runtime_resume_and_get(&pdev->dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; + ret = devm_add_action_or_reset(dev, rzn1_rtc_disable_hardware, dev); + if (ret) + return ret; + /* Only switch to scmp if we have an xtal clock with a valid rate and != 32768 */ - xtal = devm_clk_get_optional(&pdev->dev, "xtal"); + xtal = devm_clk_get_optional(dev, "xtal"); if (IS_ERR(xtal)) { - ret = PTR_ERR(xtal); - goto dis_runtime_pm; + return PTR_ERR(xtal); } else if (xtal) { rate = clk_get_rate(xtal); - if (rate < 32000 || rate > BIT(22)) { - ret = -EOPNOTSUPP; - goto dis_runtime_pm; - } + if (rate < 32000 || rate > BIT(22)) + return -EOPNOTSUPP; - if (rate != 32768) + if (rate != 32768 || !data->has_subu) scmp_val = RZN1_RTC_CTL0_SLSB_SCMP; + } else if (!data->has_subu) { + /* xtal is NULL here */ + return dev_err_probe(dev, -EOPNOTSUPP, + "No valid XTAL provided and SUBU mode not supported\n"); } + /* Calculate the duration of two RTC_PCLK clock cycles */ + rtc->sync_time = DIV_ROUND_UP(2 * USEC_PER_SEC, rate); + /* Disable controller during SUBU/SCMP setup */ val = readl(rtc->base + RZN1_RTC_CTL0) & ~RZN1_RTC_CTL0_CE; writel(val, rtc->base + RZN1_RTC_CTL0); - /* Wait 2-4 32k clock cycles for the disabled controller */ + /* Wait 2-4 RTC_PCLK clock cycles for the disabled controller to stop */ ret = readl_poll_timeout(rtc->base + RZN1_RTC_CTL0, val, - !(val & RZN1_RTC_CTL0_CEST), 62, 123); + !(val & RZN1_RTC_CTL0_CEST), rtc->sync_time, + rtc->sync_time * 2); if (ret) - goto dis_runtime_pm; + return ret; /* Set desired modes leaving the controller disabled */ writel(RZN1_RTC_CTL0_AMPM | scmp_val, rtc->base + RZN1_RTC_CTL0); @@ -457,53 +503,42 @@ static int rzn1_rtc_probe(struct platform_device *pdev) spin_lock_init(&rtc->ctl1_access_lock); - ret = devm_request_irq(&pdev->dev, irq, rzn1_rtc_alarm_irq, 0, "RZN1 RTC Alarm", rtc); - if (ret) { - dev_err(&pdev->dev, "RTC alarm interrupt not available\n"); - goto dis_runtime_pm; - } + ret = devm_request_irq(dev, irq, rzn1_rtc_alarm_irq, 0, "RZN1 RTC Alarm", rtc); + if (ret) + return dev_err_probe(dev, ret, "RTC alarm interrupt not available\n"); irq = platform_get_irq_byname_optional(pdev, "pps"); + if (irq == -EPROBE_DEFER) + return irq; if (irq >= 0) - ret = devm_request_irq(&pdev->dev, irq, rzn1_rtc_1s_irq, 0, "RZN1 RTC 1s", rtc); + ret = devm_request_irq(dev, irq, rzn1_rtc_1s_irq, 0, "RZN1 RTC 1s", rtc); if (irq < 0 || ret) { set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->rtcdev->features); clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtcdev->features); - dev_warn(&pdev->dev, "RTC pps interrupt not available. Alarm has only minute accuracy\n"); + dev_warn(dev, "RTC pps interrupt not available. Alarm has only minute accuracy\n"); } - ret = devm_rtc_register_device(rtc->rtcdev); - if (ret) - goto dis_runtime_pm; - - return 0; - -dis_runtime_pm: - pm_runtime_put(&pdev->dev); - - return ret; + return devm_rtc_register_device(rtc->rtcdev); } -static void rzn1_rtc_remove(struct platform_device *pdev) -{ - struct rzn1_rtc *rtc = platform_get_drvdata(pdev); +static const struct rzn1_rtc_data rzn1_rtc_rzt2h_data = { + .has_subu = false, +}; - /* Disable all interrupts */ - writel(0, rtc->base + RZN1_RTC_CTL1); - - pm_runtime_put(&pdev->dev); -} +static const struct rzn1_rtc_data rzn1_rtc_rzn1_data = { + .has_subu = true, +}; static const struct of_device_id rzn1_rtc_of_match[] = { - { .compatible = "renesas,rzn1-rtc" }, - {}, + { .compatible = "renesas,r9a09g077-rtc", .data = &rzn1_rtc_rzt2h_data }, + { .compatible = "renesas,rzn1-rtc", .data = &rzn1_rtc_rzn1_data }, + { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, rzn1_rtc_of_match); static struct platform_driver rzn1_rtc_driver = { .probe = rzn1_rtc_probe, - .remove = rzn1_rtc_remove, .driver = { .name = "rzn1-rtc", .of_match_table = rzn1_rtc_of_match, @@ -512,6 +547,6 @@ static struct platform_driver rzn1_rtc_driver = { module_platform_driver(rzn1_rtc_driver); MODULE_AUTHOR("Michel Pollet "); -MODULE_AUTHOR("Miquel Raynal "); MODULE_DESCRIPTION("RZ/N1 RTC driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-s32g.c b/drivers/rtc/rtc-s32g.c index 3a0818e972eb..86716192d10f 100644 --- a/drivers/rtc/rtc-s32g.c +++ b/drivers/rtc/rtc-s32g.c @@ -366,6 +366,7 @@ static const struct of_device_id rtc_dt_ids[] = { { .compatible = "nxp,s32g2-rtc", .data = &rtc_s32g2_data }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, rtc_dt_ids); static DEFINE_SIMPLE_DEV_PM_OPS(s32g_rtc_pm_ops, s32g_rtc_suspend, s32g_rtc_resume); diff --git a/drivers/rtc/rtc-spacemit-p1.c b/drivers/rtc/rtc-spacemit-p1.c index 43ab62494bb4..1de7bd995d29 100644 --- a/drivers/rtc/rtc-spacemit-p1.c +++ b/drivers/rtc/rtc-spacemit-p1.c @@ -57,8 +57,9 @@ static int p1_rtc_read_time(struct device *dev, struct rtc_time *t) u8 time[6]; int ret; - if (!regmap_test_bits(regmap, RTC_CTRL, RTC_EN)) - return -EINVAL; /* RTC is disabled */ + ret = regmap_test_bits(regmap, RTC_CTRL, RTC_EN); + if (ret <= 0) + return ret ?: -EINVAL; /* RTC is disabled or error */ ret = regmap_bulk_read(regmap, RTC_TIME, time, sizeof(time)); if (ret) diff --git a/drivers/rtc/rtc-st-lpc.c b/drivers/rtc/rtc-st-lpc.c index c6d4522411b3..ae79ddf24f37 100644 --- a/drivers/rtc/rtc-st-lpc.c +++ b/drivers/rtc/rtc-st-lpc.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include @@ -212,11 +211,9 @@ static int st_rtc_probe(struct platform_device *pdev) if (IS_ERR(rtc->ioaddr)) return PTR_ERR(rtc->ioaddr); - rtc->irq = irq_of_parse_and_map(np, 0); - if (!rtc->irq) { - dev_err(&pdev->dev, "IRQ missing or invalid\n"); - return -EINVAL; - } + rtc->irq = platform_get_irq(pdev, 0); + if (rtc->irq < 0) + return rtc->irq; ret = devm_request_irq(&pdev->dev, rtc->irq, st_rtc_handler, IRQF_NO_AUTOEN, pdev->name, rtc); diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c index 2ae54804b87a..5bcb7536e973 100644 --- a/drivers/rtc/rtc-zynqmp.c +++ b/drivers/rtc/rtc-zynqmp.c @@ -334,10 +334,9 @@ static int xlnx_rtc_probe(struct platform_device *pdev) /* Getting the rtc info */ xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc"); - if (IS_ERR(xrtcdev->rtc_clk)) { - if (PTR_ERR(xrtcdev->rtc_clk) != -EPROBE_DEFER) - dev_warn(&pdev->dev, "Device clock not found.\n"); - } + if (IS_ERR(xrtcdev->rtc_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(xrtcdev->rtc_clk), + "Failed to get rtc clock\n"); xrtcdev->freq = clk_get_rate(xrtcdev->rtc_clk); if (!xrtcdev->freq) { ret = of_property_read_u32(pdev->dev.of_node, "calibration", diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 08e36685e578..61c88fe853c5 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -826,7 +826,7 @@ static void mpc_action_go_ready(fsm_instance *fsm, int event, void *arg) fsm_deltimer(&grp->timer); - if (grp->saved_xid2->xid2_flag2 == 0x40) { + if (priv->xid->xid2_flag2 == 0x40) { priv->xid->xid2_flag2 = 0x00; if (grp->estconnfunc) { grp->estconnfunc(grp->port_num, 1, @@ -1636,7 +1636,6 @@ static int mpc_validate_xid(struct mpcg_info *mpcginfo) "The XID used in the MPC protocol is not valid, " "rc = %d\n", rc); priv->xid->xid2_flag2 = 0x40; - grp->saved_xid2->xid2_flag2 = 0x40; } return rc; diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 098f35219e7d..533623382eca 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -14,6 +14,29 @@ # satisfy certain initialization assumptions in the SCSI layer. # *!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*!*! +CONTEXT_ANALYSIS_constants.o := y +CONTEXT_ANALYSIS_hosts.o := y +CONTEXT_ANALYSIS_scsi.o := y +CONTEXT_ANALYSIS_scsi_common.o := y +CONTEXT_ANALYSIS_scsi_devinfo.o := y +CONTEXT_ANALYSIS_scsi_dh.o := y +CONTEXT_ANALYSIS_scsi_error.o := y +CONTEXT_ANALYSIS_scsi_ioctl.o := y +CONTEXT_ANALYSIS_scsi_lib.o := y +CONTEXT_ANALYSIS_scsi_lib_dma.o := y +CONTEXT_ANALYSIS_scsi_logging.o := y +CONTEXT_ANALYSIS_scsi_netlink.o := y +CONTEXT_ANALYSIS_scsi_pm.o := y +CONTEXT_ANALYSIS_scsi_proc.o := y +CONTEXT_ANALYSIS_scsi_scan.o := y +CONTEXT_ANALYSIS_scsi_sysfs.o := y +CONTEXT_ANALYSIS_scsi_trace.o := y +CONTEXT_ANALYSIS_scsicam.o := y +CONTEXT_ANALYSIS_sd.o := y +CONTEXT_ANALYSIS_sd_dif.o := y +CONTEXT_ANALYSIS_sd_zbc.o := y +CONTEXT_ANALYSIS_sr.o := y +CONTEXT_ANALYSIS_sr_ioctl.o := y CFLAGS_aha152x.o = -DAHA152X_STAT -DAUTOCONF diff --git a/drivers/scsi/device_handler/Makefile b/drivers/scsi/device_handler/Makefile index 0a603aefd2bb..5aa282a63e24 100644 --- a/drivers/scsi/device_handler/Makefile +++ b/drivers/scsi/device_handler/Makefile @@ -2,6 +2,9 @@ # # SCSI Device Handler # + +CONTEXT_ANALYSIS := y + obj-$(CONFIG_SCSI_DH_RDAC) += scsi_dh_rdac.o obj-$(CONFIG_SCSI_DH_HP_SW) += scsi_dh_hp_sw.o obj-$(CONFIG_SCSI_DH_EMC) += scsi_dh_emc.o diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 08ec144f7bf7..e72055c1ebbb 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -73,8 +73,9 @@ static struct class shost_class = { * transition is illegal. **/ int scsi_host_set_state(struct Scsi_Host *shost, enum scsi_host_state state) + __must_hold(shost->host_lock) { - enum scsi_host_state oldstate = shost->shost_state; + enum scsi_host_state oldstate = READ_ONCE(shost->shost_state); if (state == oldstate) return 0; @@ -145,7 +146,7 @@ int scsi_host_set_state(struct Scsi_Host *shost, enum scsi_host_state state) } break; } - shost->shost_state = state; + WRITE_ONCE(shost->shost_state, state); return 0; illegal: @@ -276,7 +277,8 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, if (error) goto out_disable_runtime_pm; - scsi_host_set_state(shost, SHOST_RUNNING); + scoped_guard(spinlock_irq, shost->host_lock) + scsi_host_set_state(shost, SHOST_RUNNING); get_device(shost->shost_gendev.parent); device_enable_async_suspend(&shost->shost_dev); @@ -350,6 +352,7 @@ EXPORT_SYMBOL(scsi_add_host_with_dma); static void scsi_host_dev_release(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev); + enum scsi_host_state state = scsi_get_host_state(shost); struct device *parent = dev->parent; /* Wait for functions invoked through call_rcu(&scmd->rcu, ...) */ @@ -363,7 +366,7 @@ static void scsi_host_dev_release(struct device *dev) if (shost->work_q) destroy_workqueue(shost->work_q); - if (shost->shost_state == SHOST_CREATED) { + if (state == SHOST_CREATED) { /* * Free the shost_dev device name and remove the proc host dir * here if scsi_host_{alloc,put}() have been called but neither @@ -379,7 +382,7 @@ static void scsi_host_dev_release(struct device *dev) ida_free(&host_index_ida, shost->host_no); - if (shost->shost_state != SHOST_CREATED) + if (state != SHOST_CREATED) put_device(parent); kfree(shost); } @@ -412,8 +415,8 @@ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int priv return NULL; shost->host_lock = &shost->default_lock; - spin_lock_init(shost->host_lock); - shost->shost_state = SHOST_CREATED; + scoped_guard(spinlock_init, shost->host_lock) + shost->shost_state = SHOST_CREATED; INIT_LIST_HEAD(&shost->__devices); INIT_LIST_HEAD(&shost->__targets); INIT_LIST_HEAD(&shost->eh_abort_list); @@ -600,7 +603,7 @@ EXPORT_SYMBOL(scsi_host_lookup); **/ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) { - if ((shost->shost_state == SHOST_DEL) || + if (scsi_get_host_state(shost) == SHOST_DEL || !get_device(&shost->shost_gendev)) return NULL; return shost; diff --git a/drivers/scsi/ibmvscsi/ibmvfc-core.c b/drivers/scsi/ibmvscsi/ibmvfc-core.c index 93b9f699c2e5..b3bc3ce872d6 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc-core.c +++ b/drivers/scsi/ibmvscsi/ibmvfc-core.c @@ -6151,7 +6151,7 @@ static void ibmvfc_do_work(struct ibmvfc_host *vhost) timer_delete_sync(&tgt->timer); kref_put(&tgt->kref, ibmvfc_release_tgt); return; - } else if (rport && tgt->action == IBMVFC_TGT_ACTION_DEL_AND_LOGOUT_RPORT) { + } else if (tgt->action == IBMVFC_TGT_ACTION_DEL_AND_LOGOUT_RPORT) { tgt_dbg(tgt, "Deleting NVMe rport with outstanding I/O\n"); nvme_rport = tgt->nvme_remote_port; ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_LOGOUT_DELETED_RPORT); diff --git a/drivers/scsi/leapraid/leapraid_app.c b/drivers/scsi/leapraid/leapraid_app.c index 742f19c07fcb..84eef50947ae 100644 --- a/drivers/scsi/leapraid/leapraid_app.c +++ b/drivers/scsi/leapraid/leapraid_app.c @@ -171,7 +171,8 @@ static int leapraid_ctl_validate_sge_offset(struct leapraid_adapter *adapter, return 0; } -static struct leapraid_adapter *leapraid_ctl_lookup_adapter(int adapter_id) +static struct leapraid_adapter *leapraid_ctl_lookup_adapter(int adapter_id, + bool track_mmap) { struct leapraid_adapter *adapter; struct Scsi_Host *shost; @@ -184,6 +185,8 @@ static struct leapraid_adapter *leapraid_ctl_lookup_adapter(int adapter_id) shost = adapter->shost; if (!shost || !scsi_host_get(shost)) break; + if (track_mmap) + atomic_inc(&adapter->fw_log_desc.mmap_refcnt); spin_unlock(&leapraid_adapter_lock); return adapter; } @@ -589,7 +592,7 @@ static int leapraid_ctl_ioctl_main(struct file *file, unsigned int cmd, return -EFAULT; } - adapter = leapraid_ctl_lookup_adapter(ioctl_header.adapter_id); + adapter = leapraid_ctl_lookup_adapter(ioctl_header.adapter_id, false); if (!adapter) return -EFAULT; @@ -697,6 +700,7 @@ static void leapraid_fw_mmap_open(struct vm_area_struct *vma) if (!adapter) return; + get_device(&adapter->shost->shost_gendev); atomic_inc(&adapter->fw_log_desc.mmap_refcnt); } @@ -727,7 +731,7 @@ static int leapraid_fw_mmap(struct file *filp, struct vm_area_struct *vma) length = vma->vm_end - vma->vm_start; - adapter = leapraid_ctl_lookup_adapter(adapter_id); + adapter = leapraid_ctl_lookup_adapter(adapter_id, true); if (!adapter) { pr_err("%s: No adapter found!\n", __func__); return -EINVAL; @@ -767,10 +771,12 @@ static int leapraid_fw_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_private_data = adapter; vma->vm_ops = &leapraid_fw_mmap_vm_ops; leapraid_fw_mmap_open(vma); - adapter = NULL; rc = 0; out_put: + if (adapter && + atomic_dec_and_test(&adapter->fw_log_desc.mmap_refcnt)) + wake_up(&adapter->fw_log_desc.mmap_waitq); leapraid_ctl_put_adapter(adapter); return rc; } diff --git a/drivers/scsi/leapraid/leapraid_func.c b/drivers/scsi/leapraid/leapraid_func.c index 3e1aeceab994..089d0810bd13 100644 --- a/drivers/scsi/leapraid/leapraid_func.c +++ b/drivers/scsi/leapraid/leapraid_func.c @@ -37,7 +37,7 @@ static noinline bool leapraid_shost_in_recovery(struct Scsi_Host *shost) { enum scsi_host_state state; - state = READ_ONCE(shost->shost_state); + state = scsi_get_host_state(shost); return state == SHOST_RECOVERY || state == SHOST_CANCEL_RECOVERY || state == SHOST_DEL_RECOVERY || diff --git a/drivers/scsi/leapraid/leapraid_func.h b/drivers/scsi/leapraid/leapraid_func.h index 923596211aa1..4c0b9ca728d8 100644 --- a/drivers/scsi/leapraid/leapraid_func.h +++ b/drivers/scsi/leapraid/leapraid_func.h @@ -1064,7 +1064,7 @@ struct leapraid_starget_priv { * @starget_priv: Associated target private data. * @lun: Logical Unit Number. * @flg: Flags. - * @ncq_cmd_prio_enable: Enables NCQ command priority for RT I/O. + * @ncq_prio_enable: Enables NCQ command priority for RT I/O. * @block: Block flag. * @deleted: Deletion flag. * @sep: SEP flag. @@ -1073,7 +1073,7 @@ struct leapraid_sdev_priv { struct leapraid_starget_priv *starget_priv; unsigned int lun; u32 flg; - u8 ncq_cmd_prio_enable; + u8 ncq_prio_enable; u8 block; u8 deleted; u8 sep; diff --git a/drivers/scsi/leapraid/leapraid_os.c b/drivers/scsi/leapraid/leapraid_os.c index 2f3d4ac7490c..ee3242779dfd 100644 --- a/drivers/scsi/leapraid/leapraid_os.c +++ b/drivers/scsi/leapraid/leapraid_os.c @@ -808,7 +808,7 @@ static bool leapraid_should_queuecommand(struct leapraid_adapter *adapter, goto no_connect; if (sdev_priv->block && - scmd->device->host->shost_state == SHOST_RECOVERY && + scsi_get_host_state(scmd->device->host) == SHOST_RECOVERY && scmd->cmnd[0] == TEST_UNIT_READY) { scsi_build_sense(scmd, 0, UNIT_ATTENTION, LEAPRAID_SCSI_ASC_POWER_ON_RESET, @@ -859,7 +859,7 @@ static u32 build_scsiio_req_control(struct scsi_cmnd *scmd, control |= LEAPRAID_SCSIIO_CTRL_SIMPLEQ; - if (sdev_priv->ncq_cmd_prio_enable && + if (sdev_priv->ncq_prio_enable && (IOPRIO_PRIO_CLASS(req_get_ioprio(scsi_cmd_to_rq(scmd))) == IOPRIO_CLASS_RT)) control |= LEAPRAID_SCSIIO_CTRL_CMDPRI; @@ -1854,7 +1854,16 @@ static ssize_t sas_device_handle_show(struct device *dev, sas_device_priv_data->starget_priv->hdl); } -static ssize_t ncq_cmd_prio_enable_show(struct device *dev, +static ssize_t sas_ncq_prio_supported_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); +} + +static ssize_t sas_ncq_prio_enable_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1867,19 +1876,16 @@ static ssize_t ncq_cmd_prio_enable_show(struct device *dev, return -EINVAL; } - return sysfs_emit(buf, "%d\n", - sas_device_priv_data->ncq_cmd_prio_enable); + return sysfs_emit(buf, "%d\n", sas_device_priv_data->ncq_prio_enable); } -static ssize_t ncq_cmd_prio_enable_store(struct device *dev, +static ssize_t sas_ncq_prio_enable_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_device *sdev = to_scsi_device(dev); struct leapraid_sdev_priv *sas_device_priv_data = sdev->hostdata; - struct scsi_vpd *vpd_pg89; - int ncq_cmd_prio_enable; - bool ncq_supported; + bool enable; if (!sas_device_priv_data) { dev_err(&sdev->sdev_gendev, @@ -1887,44 +1893,63 @@ static ssize_t ncq_cmd_prio_enable_store(struct device *dev, return -EINVAL; } - if (kstrtoint(buf, 0, &ncq_cmd_prio_enable)) + if (kstrtobool(buf, &enable)) return -EINVAL; - if (ncq_cmd_prio_enable != 0 && ncq_cmd_prio_enable != 1) { - dev_err(&sdev->sdev_gendev, - "%s: Invalid NCQ cmd prio %d (0/1 only)\n", - __func__, ncq_cmd_prio_enable); + if (!sas_ata_ncq_prio_supported(sdev)) return -EINVAL; - } - rcu_read_lock(); - vpd_pg89 = rcu_dereference(sdev->vpd_pg89); - if (!vpd_pg89 || vpd_pg89->len < LEAPRAID_VPD_PG89_MIN_LEN) { - rcu_read_unlock(); - return -EINVAL; - } - - ncq_supported = (vpd_pg89->data[LEAPRAID_VPD_PG89_NCQ_BYTE_IDX] >> - LEAPRAID_VPD_PG89_NCQ_BIT_SHIFT) & - LEAPRAID_VPD_PG89_NCQ_BIT_MASK; - rcu_read_unlock(); - if (ncq_supported) - sas_device_priv_data->ncq_cmd_prio_enable = - ncq_cmd_prio_enable; + sas_device_priv_data->ncq_prio_enable = enable; return count; } static DEVICE_ATTR_RO(sas_device_handle); +static DEVICE_ATTR_RO(sas_ncq_prio_supported); +static DEVICE_ATTR_RW(sas_ncq_prio_enable); -static DEVICE_ATTR_RW(ncq_cmd_prio_enable); +static bool leapraid_sdev_is_sata(struct scsi_device *sdev) +{ + struct scsi_target *starget = sdev->sdev_target; + struct leapraid_starget_priv *starget_priv = starget->hostdata; + struct leapraid_sas_dev *sas_dev; + + if (!starget_priv) + return false; + + sas_dev = starget_priv->sas_dev; + return sas_dev && (sas_dev->dev_info & LEAPRAID_DEVTYP_SATA_DEV); +} static struct attribute *leapraid_sdev_attrs[] = { &dev_attr_sas_device_handle.attr, - &dev_attr_ncq_cmd_prio_enable.attr, + &dev_attr_sas_ncq_prio_supported.attr, + &dev_attr_sas_ncq_prio_enable.attr, NULL, }; -ATTRIBUTE_GROUPS(leapraid_sdev); +static umode_t leapraid_sdev_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int i) +{ + struct device *dev = kobj_to_dev(kobj); + struct scsi_device *sdev = to_scsi_device(dev); + + if (attr == &dev_attr_sas_ncq_prio_supported.attr || + attr == &dev_attr_sas_ncq_prio_enable.attr) + if (!leapraid_sdev_is_sata(sdev)) + return 0; + + return attr->mode; +} + +static const struct attribute_group leapraid_sdev_attr_group = { + .attrs = leapraid_sdev_attrs, + .is_visible = leapraid_sdev_attr_is_visible, +}; + +static const struct attribute_group *leapraid_sdev_groups[] = { + &leapraid_sdev_attr_group, + NULL, +}; static struct scsi_host_template leapraid_driver_template = { .module = THIS_MODULE, diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index f471ab464a78..811c9eb4fef1 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -345,11 +345,10 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id, SAS_ADDR(phy->attached_sas_addr), type); } -/* check if we have an existing attached ata device on this expander phy */ -struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id) +/* Return the domain device attached to an expander phy */ +struct domain_device *sas_ex_phy_to_dev(struct domain_device *ex_dev, int phy_id) { struct ex_phy *ex_phy = &ex_dev->ex_dev.ex_phy[phy_id]; - struct domain_device *dev; struct sas_rphy *rphy; if (!ex_phy->port) @@ -359,7 +358,13 @@ struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id) if (!rphy) return NULL; - dev = sas_find_dev_by_rphy(rphy); + return sas_find_dev_by_rphy(rphy); +} + +/* Check if we have an existing attached ata device on this expander phy */ +struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id) +{ + struct domain_device *dev = sas_ex_phy_to_dev(ex_dev, phy_id); if (dev && dev_is_sata(dev)) return dev; @@ -1958,6 +1963,72 @@ static bool dev_type_flutter(enum sas_device_type new, enum sas_device_type old) return false; } +static void sas_rediscover_ex_phy(struct domain_device *dev, int phy_id, + bool last) +{ + struct expander_device *ex = &dev->ex_dev; + struct ex_phy *phy = &ex->ex_phy[phy_id]; + + phy->phy_change_count = -1; + ex->ex_change_count = -1; + sas_unregister_devs_sas_addr(dev, phy_id, last); + sas_discover_event(dev->port, DISCE_REVALIDATE_DOMAIN); +} + +static bool sas_dev_is_flutter(struct domain_device *dev, int phy_id, + u8 *sas_addr, enum sas_device_type type) +{ + struct expander_device *ex = &dev->ex_dev; + struct ex_phy *phy = &ex->ex_phy[phy_id]; + struct domain_device *child_dev; + char *action = ""; + int res; + + if (SAS_ADDR(sas_addr) != SAS_ADDR(phy->attached_sas_addr) || + !dev_type_flutter(type, phy->attached_dev_type)) + return false; + + res = sas_ex_phy_discover(dev, phy_id); + if (res) + return false; + + child_dev = sas_ex_phy_to_dev(dev, phy_id); + if (!child_dev) + goto out; + + if (dev_is_sata(child_dev) && + phy->attached_dev_type == SAS_SATA_PENDING) { + action = ", needs recovery"; + goto out; + } + + if (SAS_ADDR(child_dev->sas_addr) != SAS_ADDR(phy->attached_sas_addr)) { + pr_info("ex %016llx phy%02d sas_addr changed from %016llx to %016llx\n", + SAS_ADDR(dev->sas_addr), phy_id, + SAS_ADDR(child_dev->sas_addr), + SAS_ADDR(phy->attached_sas_addr)); + /* + * Device unregistering relies on address matching. Restore + * attached_sas_addr back to the original address so that the old + * device can be unregistered later + */ + memcpy(phy->attached_sas_addr, child_dev->sas_addr, SAS_ADDR_SIZE); + return false; + } + + if (child_dev->linkrate != phy->linkrate) { + pr_info("ex %016llx phy%02d linkrate changed from %d to %d\n", + SAS_ADDR(dev->sas_addr), phy_id, + child_dev->linkrate, phy->linkrate); + return false; + } + +out: + pr_debug("ex %016llx phy%02d broadcast flutter%s\n", + SAS_ADDR(dev->sas_addr), phy_id, action); + return true; +} + static int sas_rediscover_dev(struct domain_device *dev, int phy_id, bool last, int sibling) { @@ -2011,27 +2082,16 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, if (res == 0) sas_set_ex_phy(dev, phy_id, disc_resp); goto out_free_resp; - } else if (SAS_ADDR(sas_addr) == SAS_ADDR(phy->attached_sas_addr) && - dev_type_flutter(type, phy->attached_dev_type)) { - struct domain_device *ata_dev = sas_ex_to_ata(dev, phy_id); - char *action = ""; - - sas_ex_phy_discover(dev, phy_id); - - if (ata_dev && phy->attached_dev_type == SAS_SATA_PENDING) - action = ", needs recovery"; - pr_debug("ex %016llx phy%02d broadcast flutter%s\n", - SAS_ADDR(dev->sas_addr), phy_id, action); - goto out_free_resp; } + if (sas_dev_is_flutter(dev, phy_id, sas_addr, type)) + goto out_free_resp; + /* we always have to delete the old device when we went here */ pr_info("ex %016llx phy%02d replace %016llx\n", SAS_ADDR(dev->sas_addr), phy_id, SAS_ADDR(phy->attached_sas_addr)); - sas_unregister_devs_sas_addr(dev, phy_id, last); - - res = sas_discover_new(dev, phy_id); + sas_rediscover_ex_phy(dev, phy_id, last); out_free_resp: kfree(disc_resp); return res; diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 7dce0f587149..f5c75ab10dc4 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -91,6 +91,7 @@ int sas_smp_get_phy_events(struct sas_phy *phy); void sas_device_set_phy(struct domain_device *dev, struct sas_port *port); struct domain_device *sas_find_dev_by_rphy(struct sas_rphy *rphy); +struct domain_device *sas_ex_phy_to_dev(struct domain_device *ex_dev, int phy_id); struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id); int sas_ex_phy_discover(struct domain_device *dev, int single); int sas_get_report_phy_sata(struct domain_device *dev, int phy_id, diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index f4e8164b94ab..bb5c84f0b787 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -57,7 +57,6 @@ #define LPFC_MIN_DEVLOSS_TMO 1 #define LPFC_MAX_DEVLOSS_TMO 255 -#define LPFC_MAX_INFO_TMP_LEN 100 #define LPFC_INFO_MORE_STR "\nCould be more info...\n" /* * Write key size should be multiple of 4. If write key is changed @@ -126,133 +125,121 @@ lpfc_cmf_info_show(struct device *dev, struct device_attribute *attr, int len = 0; int cpu; u64 rcv, total; - char tmp[LPFC_MAX_INFO_TMP_LEN] = {0}; if (phba->cgn_i) cp = (struct lpfc_cgn_info *)phba->cgn_i->virt; - scnprintf(tmp, sizeof(tmp), - "Congestion Mgmt Info: E2Eattr %d Ver %d " - "CMF %d cnt %d\n", - phba->sli4_hba.pc_sli4_params.mi_cap, - cp ? cp->cgn_info_version : 0, - phba->sli4_hba.pc_sli4_params.cmf, phba->cmf_timer_cnt); - - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len = strnlen(buf, PAGE_SIZE); + len += sysfs_emit_at(buf, len, + "Congestion Mgmt Info: E2Eattr %d Ver %d CMF %d cnt %d\n", + phba->sli4_hba.pc_sli4_params.mi_cap, + cp ? cp->cgn_info_version : 0, + phba->sli4_hba.pc_sli4_params.cmf, + phba->cmf_timer_cnt); if (!phba->sli4_hba.pc_sli4_params.cmf) goto buffer_done; switch (phba->cgn_init_reg_signal) { case EDC_CG_SIG_WARN_ONLY: - scnprintf(tmp, sizeof(tmp), - "Register: Init: Signal:WARN "); + len += sysfs_emit_at(buf, len, + "Register: Init: Signal:WARN "); break; case EDC_CG_SIG_WARN_ALARM: - scnprintf(tmp, sizeof(tmp), - "Register: Init: Signal:WARN|ALARM "); + len += sysfs_emit_at(buf, len, + "Register: Init: Signal:WARN|ALARM "); break; default: - scnprintf(tmp, sizeof(tmp), - "Register: Init: Signal:NONE "); + len += sysfs_emit_at(buf, len, + "Register: Init: Signal:NONE "); break; } - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; switch (phba->cgn_init_reg_fpin) { case LPFC_CGN_FPIN_WARN: - scnprintf(tmp, sizeof(tmp), - "FPIN:WARN\n"); + len += sysfs_emit_at(buf, len, "FPIN:WARN\n"); break; case LPFC_CGN_FPIN_ALARM: - scnprintf(tmp, sizeof(tmp), - "FPIN:ALARM\n"); + len += sysfs_emit_at(buf, len, "FPIN:ALARM\n"); break; case LPFC_CGN_FPIN_BOTH: - scnprintf(tmp, sizeof(tmp), - "FPIN:WARN|ALARM\n"); + len += sysfs_emit_at(buf, len, "FPIN:WARN|ALARM\n"); break; default: - scnprintf(tmp, sizeof(tmp), - "FPIN:NONE\n"); + len += sysfs_emit_at(buf, len, "FPIN:NONE\n"); break; } - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; switch (phba->cgn_reg_signal) { case EDC_CG_SIG_WARN_ONLY: - scnprintf(tmp, sizeof(tmp), - " Current: Signal:WARN "); + len += sysfs_emit_at(buf, len, + " Current: Signal:WARN "); break; case EDC_CG_SIG_WARN_ALARM: - scnprintf(tmp, sizeof(tmp), - " Current: Signal:WARN|ALARM "); + len += sysfs_emit_at(buf, len, + " Current: Signal:WARN|ALARM "); break; default: - scnprintf(tmp, sizeof(tmp), - " Current: Signal:NONE "); + len += sysfs_emit_at(buf, len, + " Current: Signal:NONE "); break; } - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; switch (phba->cgn_reg_fpin) { case LPFC_CGN_FPIN_WARN: - scnprintf(tmp, sizeof(tmp), - "FPIN:WARN ACQEcnt:%d\n", phba->cgn_acqe_cnt); + len += sysfs_emit_at(buf, len, + "FPIN:WARN ACQEcnt:%d\n", + phba->cgn_acqe_cnt); break; case LPFC_CGN_FPIN_ALARM: - scnprintf(tmp, sizeof(tmp), - "FPIN:ALARM ACQEcnt:%d\n", phba->cgn_acqe_cnt); + len += sysfs_emit_at(buf, len, + "FPIN:ALARM ACQEcnt:%d\n", + phba->cgn_acqe_cnt); break; case LPFC_CGN_FPIN_BOTH: - scnprintf(tmp, sizeof(tmp), - "FPIN:WARN|ALARM ACQEcnt:%d\n", phba->cgn_acqe_cnt); + len += sysfs_emit_at(buf, len, + "FPIN:WARN|ALARM ACQEcnt:%d\n", + phba->cgn_acqe_cnt); break; default: - scnprintf(tmp, sizeof(tmp), - "FPIN:NONE ACQEcnt:%d\n", phba->cgn_acqe_cnt); + len += sysfs_emit_at(buf, len, + "FPIN:NONE ACQEcnt:%d\n", + phba->cgn_acqe_cnt); break; } - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; if (phba->cmf_active_mode != phba->cgn_p.cgn_param_mode) { switch (phba->cmf_active_mode) { case LPFC_CFG_OFF: - scnprintf(tmp, sizeof(tmp), "Active: Mode:Off\n"); + len += sysfs_emit_at(buf, len, "Active: Mode:Off\n"); break; case LPFC_CFG_MANAGED: - scnprintf(tmp, sizeof(tmp), "Active: Mode:Managed\n"); + len += sysfs_emit_at(buf, len, + "Active: Mode:Managed\n"); break; case LPFC_CFG_MONITOR: - scnprintf(tmp, sizeof(tmp), "Active: Mode:Monitor\n"); + len += sysfs_emit_at(buf, len, + "Active: Mode:Monitor\n"); break; default: - scnprintf(tmp, sizeof(tmp), "Active: Mode:Unknown\n"); + len += sysfs_emit_at(buf, len, + "Active: Mode:Unknown\n"); } - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; } switch (phba->cgn_p.cgn_param_mode) { case LPFC_CFG_OFF: - scnprintf(tmp, sizeof(tmp), "Config: Mode:Off "); + len += sysfs_emit_at(buf, len, "Config: Mode:Off "); break; case LPFC_CFG_MANAGED: - scnprintf(tmp, sizeof(tmp), "Config: Mode:Managed "); + len += sysfs_emit_at(buf, len, "Config: Mode:Managed "); break; case LPFC_CFG_MONITOR: - scnprintf(tmp, sizeof(tmp), "Config: Mode:Monitor "); + len += sysfs_emit_at(buf, len, "Config: Mode:Monitor "); break; default: - scnprintf(tmp, sizeof(tmp), "Config: Mode:Unknown "); + len += sysfs_emit_at(buf, len, "Config: Mode:Unknown "); } - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; total = 0; rcv = 0; @@ -262,24 +249,18 @@ lpfc_cmf_info_show(struct device *dev, struct device_attribute *attr, rcv += atomic64_read(&cgs->rcv_bytes); } - scnprintf(tmp, sizeof(tmp), - "IObusy:%d Info:%d Bytes: Rcv:x%llx Total:x%llx\n", - atomic_read(&phba->cmf_busy), - phba->cmf_active_info, rcv, total); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "IObusy:%d Info:%d Bytes: Rcv:x%llx Total:x%llx\n", + atomic_read(&phba->cmf_busy), + phba->cmf_active_info, rcv, total); - scnprintf(tmp, sizeof(tmp), - "Port_speed:%d Link_byte_cnt:%ld " - "Max_byte_per_interval:%ld\n", - lpfc_sli_port_speed_get(phba), - (unsigned long)phba->cmf_link_byte_count, - (unsigned long)phba->cmf_max_bytes_per_interval); - strlcat(buf, tmp, PAGE_SIZE); + len += sysfs_emit_at(buf, len, + "Port_speed:%d Link_byte_cnt:%ld Max_byte_per_interval:%ld\n", + lpfc_sli_port_speed_get(phba), + (unsigned long)phba->cmf_link_byte_count, + (unsigned long)phba->cmf_max_bytes_per_interval); buffer_done: - len = strnlen(buf, PAGE_SIZE); - if (unlikely(len >= (PAGE_SIZE - 1))) { lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT, "6312 Catching potential buffer " @@ -480,17 +461,19 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, char *statep; int i; int len = 0; - char tmp[LPFC_MAX_INFO_TMP_LEN] = {0}; if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) { - len = scnprintf(buf, PAGE_SIZE, "NVME Disabled\n"); + len = sysfs_emit(buf, "NVME Disabled\n"); return len; } + + len = strnlen(buf, PAGE_SIZE); + if (phba->nvmet_support) { if (!phba->targetport) { - len = scnprintf(buf, PAGE_SIZE, - "NVME Target: x%llx is not allocated\n", - wwn_to_u64(vport->fc_portname.u.wwn)); + len = sysfs_emit(buf, + "NVME Target: x%llx is not allocated\n", + wwn_to_u64(vport->fc_portname.u.wwn)); return len; } /* Port state is only one of two values for now. */ @@ -498,167 +481,131 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, statep = "REGISTERED"; else statep = "INIT"; - scnprintf(tmp, sizeof(tmp), - "NVME Target Enabled State %s\n", - statep); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "NVME Target Enabled State %s\n", + statep); - scnprintf(tmp, sizeof(tmp), - "%s%d WWPN x%llx WWNN x%llx DID x%06x\n", - "NVME Target: lpfc", - phba->brd_no, - wwn_to_u64(vport->fc_portname.u.wwn), - wwn_to_u64(vport->fc_nodename.u.wwn), - phba->targetport->port_id); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "%s%d WWPN x%llx WWNN x%llx DID x%06x\n", + "NVME Target: lpfc", + phba->brd_no, + wwn_to_u64(vport->fc_portname.u.wwn), + wwn_to_u64(vport->fc_nodename.u.wwn), + phba->targetport->port_id); - if (strlcat(buf, "\nNVME Target: Statistics\n", PAGE_SIZE) - >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, "\nNVME Target: Statistics\n"); tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private; - scnprintf(tmp, sizeof(tmp), - "LS: Rcv %08x Drop %08x Abort %08x\n", - atomic_read(&tgtp->rcv_ls_req_in), - atomic_read(&tgtp->rcv_ls_req_drop), - atomic_read(&tgtp->xmt_ls_abort)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "LS: Rcv %08x Drop %08x Abort %08x\n", + atomic_read(&tgtp->rcv_ls_req_in), + atomic_read(&tgtp->rcv_ls_req_drop), + atomic_read(&tgtp->xmt_ls_abort)); if (atomic_read(&tgtp->rcv_ls_req_in) != atomic_read(&tgtp->rcv_ls_req_out)) { - scnprintf(tmp, sizeof(tmp), - "Rcv LS: in %08x != out %08x\n", - atomic_read(&tgtp->rcv_ls_req_in), - atomic_read(&tgtp->rcv_ls_req_out)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "Rcv LS: in %08x != out %08x\n", + atomic_read(&tgtp->rcv_ls_req_in), + atomic_read(&tgtp->rcv_ls_req_out)); } - scnprintf(tmp, sizeof(tmp), - "LS: Xmt %08x Drop %08x Cmpl %08x\n", - atomic_read(&tgtp->xmt_ls_rsp), - atomic_read(&tgtp->xmt_ls_drop), - atomic_read(&tgtp->xmt_ls_rsp_cmpl)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "LS: Xmt %08x Drop %08x Cmpl %08x\n", + atomic_read(&tgtp->xmt_ls_rsp), + atomic_read(&tgtp->xmt_ls_drop), + atomic_read(&tgtp->xmt_ls_rsp_cmpl)); - scnprintf(tmp, sizeof(tmp), - "LS: RSP Abort %08x xb %08x Err %08x\n", - atomic_read(&tgtp->xmt_ls_rsp_aborted), - atomic_read(&tgtp->xmt_ls_rsp_xb_set), - atomic_read(&tgtp->xmt_ls_rsp_error)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "LS: RSP Abort %08x xb %08x Err %08x\n", + atomic_read(&tgtp->xmt_ls_rsp_aborted), + atomic_read(&tgtp->xmt_ls_rsp_xb_set), + atomic_read(&tgtp->xmt_ls_rsp_error)); - scnprintf(tmp, sizeof(tmp), - "FCP: Rcv %08x Defer %08x Release %08x " - "Drop %08x\n", - atomic_read(&tgtp->rcv_fcp_cmd_in), - atomic_read(&tgtp->rcv_fcp_cmd_defer), - atomic_read(&tgtp->xmt_fcp_release), - atomic_read(&tgtp->rcv_fcp_cmd_drop)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "FCP: Rcv %08x Defer %08x Release %08x Drop %08x\n", + atomic_read(&tgtp->rcv_fcp_cmd_in), + atomic_read(&tgtp->rcv_fcp_cmd_defer), + atomic_read(&tgtp->xmt_fcp_release), + atomic_read(&tgtp->rcv_fcp_cmd_drop)); if (atomic_read(&tgtp->rcv_fcp_cmd_in) != atomic_read(&tgtp->rcv_fcp_cmd_out)) { - scnprintf(tmp, sizeof(tmp), - "Rcv FCP: in %08x != out %08x\n", - atomic_read(&tgtp->rcv_fcp_cmd_in), - atomic_read(&tgtp->rcv_fcp_cmd_out)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "Rcv FCP: in %08x != out %08x\n", + atomic_read(&tgtp->rcv_fcp_cmd_in), + atomic_read(&tgtp->rcv_fcp_cmd_out)); } - scnprintf(tmp, sizeof(tmp), - "FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x " - "drop %08x\n", - atomic_read(&tgtp->xmt_fcp_read), - atomic_read(&tgtp->xmt_fcp_read_rsp), - atomic_read(&tgtp->xmt_fcp_write), - atomic_read(&tgtp->xmt_fcp_rsp), - atomic_read(&tgtp->xmt_fcp_drop)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x drop %08x\n", + atomic_read(&tgtp->xmt_fcp_read), + atomic_read(&tgtp->xmt_fcp_read_rsp), + atomic_read(&tgtp->xmt_fcp_write), + atomic_read(&tgtp->xmt_fcp_rsp), + atomic_read(&tgtp->xmt_fcp_drop)); - scnprintf(tmp, sizeof(tmp), - "FCP Rsp Cmpl: %08x err %08x drop %08x\n", - atomic_read(&tgtp->xmt_fcp_rsp_cmpl), - atomic_read(&tgtp->xmt_fcp_rsp_error), - atomic_read(&tgtp->xmt_fcp_rsp_drop)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "FCP Rsp Cmpl: %08x err %08x drop %08x\n", + atomic_read(&tgtp->xmt_fcp_rsp_cmpl), + atomic_read(&tgtp->xmt_fcp_rsp_error), + atomic_read(&tgtp->xmt_fcp_rsp_drop)); - scnprintf(tmp, sizeof(tmp), - "FCP Rsp Abort: %08x xb %08x xricqe %08x\n", - atomic_read(&tgtp->xmt_fcp_rsp_aborted), - atomic_read(&tgtp->xmt_fcp_rsp_xb_set), - atomic_read(&tgtp->xmt_fcp_xri_abort_cqe)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "FCP Rsp Abort: %08x xb %08x xricqe %08x\n", + atomic_read(&tgtp->xmt_fcp_rsp_aborted), + atomic_read(&tgtp->xmt_fcp_rsp_xb_set), + atomic_read(&tgtp->xmt_fcp_xri_abort_cqe)); - scnprintf(tmp, sizeof(tmp), - "ABORT: Xmt %08x Cmpl %08x\n", - atomic_read(&tgtp->xmt_fcp_abort), - atomic_read(&tgtp->xmt_fcp_abort_cmpl)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "ABORT: Xmt %08x Cmpl %08x\n", + atomic_read(&tgtp->xmt_fcp_abort), + atomic_read(&tgtp->xmt_fcp_abort_cmpl)); - scnprintf(tmp, sizeof(tmp), - "ABORT: Sol %08x Usol %08x Err %08x Cmpl %08x\n", - atomic_read(&tgtp->xmt_abort_sol), - atomic_read(&tgtp->xmt_abort_unsol), - atomic_read(&tgtp->xmt_abort_rsp), - atomic_read(&tgtp->xmt_abort_rsp_error)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "ABORT: Sol %08x Usol %08x Err %08x Cmpl %08x\n", + atomic_read(&tgtp->xmt_abort_sol), + atomic_read(&tgtp->xmt_abort_unsol), + atomic_read(&tgtp->xmt_abort_rsp), + atomic_read(&tgtp->xmt_abort_rsp_error)); - scnprintf(tmp, sizeof(tmp), - "DELAY: ctx %08x fod %08x wqfull %08x\n", - atomic_read(&tgtp->defer_ctx), - atomic_read(&tgtp->defer_fod), - atomic_read(&tgtp->defer_wqfull)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "DELAY: ctx %08x fod %08x wqfull %08x\n", + atomic_read(&tgtp->defer_ctx), + atomic_read(&tgtp->defer_fod), + atomic_read(&tgtp->defer_wqfull)); /* Calculate outstanding IOs */ tot = atomic_read(&tgtp->rcv_fcp_cmd_drop); tot += atomic_read(&tgtp->xmt_fcp_release); tot = atomic_read(&tgtp->rcv_fcp_cmd_in) - tot; - scnprintf(tmp, sizeof(tmp), - "IO_CTX: %08x WAIT: cur %08x tot %08x\n" - "CTX Outstanding %08llx\n\n", - phba->sli4_hba.nvmet_xri_cnt, - phba->sli4_hba.nvmet_io_wait_cnt, - phba->sli4_hba.nvmet_io_wait_total, - tot); - strlcat(buf, tmp, PAGE_SIZE); + len += sysfs_emit_at(buf, len, + "IO_CTX: %08x WAIT: cur %08x tot %08x\n" + "CTX Outstanding %08llx\n\n", + phba->sli4_hba.nvmet_xri_cnt, + phba->sli4_hba.nvmet_io_wait_cnt, + phba->sli4_hba.nvmet_io_wait_total, + tot); goto buffer_done; } localport = vport->localport; if (!localport) { - len = scnprintf(buf, PAGE_SIZE, - "NVME Initiator x%llx is not allocated\n", - wwn_to_u64(vport->fc_portname.u.wwn)); + len = sysfs_emit(buf, + "NVME Initiator x%llx is not allocated\n", + wwn_to_u64(vport->fc_portname.u.wwn)); return len; } lport = (struct lpfc_nvme_lport *)localport->private; - if (strlcat(buf, "\nNVME Initiator Enabled\n", PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, "\nNVME Initiator Enabled\n"); - scnprintf(tmp, sizeof(tmp), - "XRI Dist lpfc%d Total %d IO %d ELS %d\n", - phba->brd_no, - phba->sli4_hba.max_cfg_param.max_xri, - phba->sli4_hba.io_xri_max, - lpfc_sli4_get_els_iocb_cnt(phba)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "XRI Dist lpfc%d Total %d IO %d ELS %d\n", + phba->brd_no, + phba->sli4_hba.max_cfg_param.max_xri, + phba->sli4_hba.io_xri_max, + lpfc_sli4_get_els_iocb_cnt(phba)); /* Port state is only one of two values for now. */ if (localport->port_id) @@ -666,15 +613,13 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, else statep = "UNKNOWN "; - scnprintf(tmp, sizeof(tmp), - "%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n", - "NVME LPORT lpfc", - phba->brd_no, - wwn_to_u64(vport->fc_portname.u.wwn), - wwn_to_u64(vport->fc_nodename.u.wwn), - localport->port_id, statep); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n", + "NVME LPORT lpfc", + phba->brd_no, + wwn_to_u64(vport->fc_portname.u.wwn), + wwn_to_u64(vport->fc_nodename.u.wwn), + localport->port_id, statep); spin_lock_irqsave(&vport->fc_nodes_list_lock, iflags); @@ -702,77 +647,55 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, } /* Tab in to show lport ownership. */ - if (strlcat(buf, "NVME RPORT ", PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; - if (phba->brd_no >= 10) { - if (strlcat(buf, " ", PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; - } + len += sysfs_emit_at(buf, len, "NVME RPORT "); + if (phba->brd_no >= 10) + len += sysfs_emit_at(buf, len, " "); - scnprintf(tmp, sizeof(tmp), "WWPN x%llx ", - nrport->port_name); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; + len += sysfs_emit_at(buf, len, "WWPN x%llx ", + nrport->port_name); - scnprintf(tmp, sizeof(tmp), "WWNN x%llx ", - nrport->node_name); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; + len += sysfs_emit_at(buf, len, "WWNN x%llx ", + nrport->node_name); - scnprintf(tmp, sizeof(tmp), "DID x%06x ", - nrport->port_id); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; + len += sysfs_emit_at(buf, len, "DID x%06x ", + nrport->port_id); /* An NVME rport can have multiple roles. */ - if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) { - if (strlcat(buf, "INITIATOR ", PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; - } - if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) { - if (strlcat(buf, "TARGET ", PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; - } - if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) { - if (strlcat(buf, "DISCSRVC ", PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; - } + if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) + len += sysfs_emit_at(buf, len, "INITIATOR "); + if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) + len += sysfs_emit_at(buf, len, "TARGET "); + if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) + len += sysfs_emit_at(buf, len, "DISCSRVC "); if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR | FC_PORT_ROLE_NVME_TARGET | - FC_PORT_ROLE_NVME_DISCOVERY)) { - scnprintf(tmp, sizeof(tmp), "UNKNOWN ROLE x%x", - nrport->port_role); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; - } + FC_PORT_ROLE_NVME_DISCOVERY)) + len += sysfs_emit_at(buf, len, "UNKNOWN ROLE x%x", + nrport->port_role); - scnprintf(tmp, sizeof(tmp), "%s\n", statep); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto unlock_buf_done; + len += sysfs_emit_at(buf, len, "%s\n", statep); + + if (len >= PAGE_SIZE - 1) + break; } spin_unlock_irqrestore(&vport->fc_nodes_list_lock, iflags); if (!lport) goto buffer_done; - if (strlcat(buf, "\nNVME Statistics\n", PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, "\nNVME Statistics\n"); - scnprintf(tmp, sizeof(tmp), - "LS: Xmt %010x Cmpl %010x Abort %08x\n", - atomic_read(&lport->fc4NvmeLsRequests), - atomic_read(&lport->fc4NvmeLsCmpls), - atomic_read(&lport->xmt_ls_abort)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "LS: Xmt %010x Cmpl %010x Abort %08x\n", + atomic_read(&lport->fc4NvmeLsRequests), + atomic_read(&lport->fc4NvmeLsCmpls), + atomic_read(&lport->xmt_ls_abort)); - scnprintf(tmp, sizeof(tmp), - "LS XMIT: Err %08x CMPL: xb %08x Err %08x\n", - atomic_read(&lport->xmt_ls_err), - atomic_read(&lport->cmpl_ls_xb), - atomic_read(&lport->cmpl_ls_err)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "LS XMIT: Err %08x CMPL: xb %08x Err %08x\n", + atomic_read(&lport->xmt_ls_err), + atomic_read(&lport->cmpl_ls_xb), + atomic_read(&lport->cmpl_ls_err)); totin = 0; totout = 0; @@ -785,40 +708,25 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, data3 = cstat->control_requests; totout += (data1 + data2 + data3); } - scnprintf(tmp, sizeof(tmp), - "Total FCP Cmpl %016llx Issue %016llx " - "OutIO %016llx\n", - totin, totout, totout - totin); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "Total FCP Cmpl %016llx Issue %016llx OutIO %016llx\n", + totin, totout, totout - totin); - scnprintf(tmp, sizeof(tmp), - "\tabort %08x noxri %08x nondlp %08x qdepth %08x " - "wqerr %08x err %08x\n", - atomic_read(&lport->xmt_fcp_abort), - atomic_read(&lport->xmt_fcp_noxri), - atomic_read(&lport->xmt_fcp_bad_ndlp), - atomic_read(&lport->xmt_fcp_qdepth), - atomic_read(&lport->xmt_fcp_wqerr), - atomic_read(&lport->xmt_fcp_err)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "\tabort %08x noxri %08x nondlp %08x qdepth %08x wqerr %08x err %08x\n", + atomic_read(&lport->xmt_fcp_abort), + atomic_read(&lport->xmt_fcp_noxri), + atomic_read(&lport->xmt_fcp_bad_ndlp), + atomic_read(&lport->xmt_fcp_qdepth), + atomic_read(&lport->xmt_fcp_wqerr), + atomic_read(&lport->xmt_fcp_err)); - scnprintf(tmp, sizeof(tmp), - "FCP CMPL: xb %08x Err %08x\n", - atomic_read(&lport->cmpl_fcp_xb), - atomic_read(&lport->cmpl_fcp_err)); - strlcat(buf, tmp, PAGE_SIZE); - - /* host_lock is already unlocked. */ - goto buffer_done; - - unlock_buf_done: - spin_unlock_irqrestore(&vport->fc_nodes_list_lock, iflags); + len += sysfs_emit_at(buf, len, + "FCP CMPL: xb %08x Err %08x\n", + atomic_read(&lport->cmpl_fcp_xb), + atomic_read(&lport->cmpl_fcp_err)); buffer_done: - len = strnlen(buf, PAGE_SIZE); - if (unlikely(len >= (PAGE_SIZE - 1))) { lpfc_printf_log(phba, KERN_INFO, LOG_NVME, "6314 Catching potential buffer " @@ -844,13 +752,12 @@ lpfc_scsi_stat_show(struct device *dev, struct device_attribute *attr, u64 data1, data2, data3; u64 tot, totin, totout; int i; - char tmp[LPFC_MAX_SCSI_INFO_TMP_LEN] = {0}; if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_FCP) || (phba->sli_rev != LPFC_SLI_REV4)) return 0; - scnprintf(buf, PAGE_SIZE, "SCSI HDWQ Statistics\n"); + len = sysfs_emit(buf, "SCSI HDWQ Statistics\n"); totin = 0; totout = 0; @@ -863,22 +770,20 @@ lpfc_scsi_stat_show(struct device *dev, struct device_attribute *attr, data3 = cstat->control_requests; totout += (data1 + data2 + data3); - scnprintf(tmp, sizeof(tmp), "HDWQ (%d): Rd %016llx Wr %016llx " - "IO %016llx ", i, data1, data2, data3); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "HDWQ (%d): Rd %016llx Wr %016llx IO %016llx ", + i, data1, data2, data3); - scnprintf(tmp, sizeof(tmp), "Cmpl %016llx OutIO %016llx\n", - tot, ((data1 + data2 + data3) - tot)); - if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto buffer_done; + len += sysfs_emit_at(buf, len, + "Cmpl %016llx OutIO %016llx\n", + tot, ((data1 + data2 + data3) - tot)); + + if (len >= PAGE_SIZE - 1) + break; } - scnprintf(tmp, sizeof(tmp), "Total FCP Cmpl %016llx Issue %016llx " - "OutIO %016llx\n", totin, totout, totout - totin); - strlcat(buf, tmp, PAGE_SIZE); - -buffer_done: - len = strnlen(buf, PAGE_SIZE); + len += sysfs_emit_at(buf, len, + "Total FCP Cmpl %016llx Issue %016llx OutIO %016llx\n", + totin, totout, totout - totin); return len; } diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index c95165905483..7354ae9ba8e5 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -1329,10 +1329,8 @@ lpfc_bsg_hba_get_event(struct bsg_job *job) else bsg_reply->reply_payload_rcv_len = 0; - if (evt_dat) { - kfree(evt_dat->data); - kfree(evt_dat); - } + kfree(evt_dat->data); + kfree(evt_dat); spin_lock_irqsave(&phba->ct_ev_lock, flags); lpfc_bsg_event_unref(evt); diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index c7853e7fe071..0734ab3be3e3 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1823,34 +1823,15 @@ lpfc_vport_symbolic_node_name(struct lpfc_vport *vport, char *symbol, size_t size) { char fwrev[FW_REV_STR_SIZE] = {0}; - char tmp[MAXHOSTNAMELEN] = {0}; - - memset(symbol, 0, size); - - scnprintf(tmp, sizeof(tmp), "Emulex %s", vport->phba->ModelName); - if (strlcat(symbol, tmp, size) >= size) - goto buffer_done; lpfc_decode_firmware_rev(vport->phba, fwrev, 0); - scnprintf(tmp, sizeof(tmp), " FV%s", fwrev); - if (strlcat(symbol, tmp, size) >= size) - goto buffer_done; - - scnprintf(tmp, sizeof(tmp), " DV%s", lpfc_release_version); - if (strlcat(symbol, tmp, size) >= size) - goto buffer_done; - - scnprintf(tmp, sizeof(tmp), " HN:%s", vport->phba->os_host_name); - if (strlcat(symbol, tmp, size) >= size) - goto buffer_done; + memset(symbol, 0, size); /* Note :- OS name is "Linux" */ - scnprintf(tmp, sizeof(tmp), " OS:%s", init_utsname()->sysname); - strlcat(symbol, tmp, size); - -buffer_done: - return strnlen(symbol, size); - + return scnprintf(symbol, size, "Emulex %s FV%s DV%s HN:%s OS:%s", + vport->phba->ModelName, fwrev, + lpfc_release_version, vport->phba->os_host_name, + init_utsname()->sysname); } static uint32_t diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 052023fc1733..30e3cc050aaa 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -462,7 +463,8 @@ lpfc_debugfs_multixripools_data(struct lpfc_hba *phba, char *buf, int size) struct lpfc_pvt_pool *pvt_pool; struct lpfc_pbl_pool *pbl_pool; u32 txcmplq_cnt; - char tmp[LPFC_DEBUG_OUT_LINE_SZ] = {0}; + size_t used; + struct seq_buf s; if (phba->sli_rev != LPFC_SLI_REV4) return 0; @@ -475,6 +477,9 @@ lpfc_debugfs_multixripools_data(struct lpfc_hba *phba, char *buf, int size) return i; } + used = strnlen(buf, size); + seq_buf_init(&s, buf + used, size - used); + /* * Pbl: Current number of free XRIs in public pool * Pvt: Current number of free XRIs in private pool @@ -484,10 +489,8 @@ lpfc_debugfs_multixripools_data(struct lpfc_hba *phba, char *buf, int size) * pbl_empty: Incremented by 1 when all pbl_pool are empty during * IO submission */ - scnprintf(tmp, sizeof(tmp), - "HWQ: Pbl Pvt Busy HWM | pvt_empty pbl_empty "); - if (strlcat(buf, tmp, size) >= size) - return strnlen(buf, size); + seq_buf_printf(&s, + "HWQ: Pbl Pvt Busy HWM | pvt_empty pbl_empty "); #ifdef LPFC_MXP_STAT /* @@ -501,25 +504,17 @@ lpfc_debugfs_multixripools_data(struct lpfc_hba *phba, char *buf, int size) * othPbl_hit: Incremented by 1 if successfully get a batch of XRI from * other pbl_pool */ - scnprintf(tmp, sizeof(tmp), - "MAXH above_lmt below_lmt locPbl_hit othPbl_hit"); - if (strlcat(buf, tmp, size) >= size) - return strnlen(buf, size); + seq_buf_printf(&s, "MAXH above_lmt below_lmt locPbl_hit othPbl_hit"); /* * sPbl: snapshot of Pbl 15 sec after stat gets cleared * sPvt: snapshot of Pvt 15 sec after stat gets cleared * sBusy: snapshot of Busy 15 sec after stat gets cleared */ - scnprintf(tmp, sizeof(tmp), - " | sPbl sPvt sBusy"); - if (strlcat(buf, tmp, size) >= size) - return strnlen(buf, size); + seq_buf_printf(&s, " | sPbl sPvt sBusy"); #endif - scnprintf(tmp, sizeof(tmp), "\n"); - if (strlcat(buf, tmp, size) >= size) - return strnlen(buf, size); + seq_buf_printf(&s, "\n"); hwq_count = phba->cfg_hdw_queue; for (i = 0; i < hwq_count; i++) { @@ -531,36 +526,32 @@ lpfc_debugfs_multixripools_data(struct lpfc_hba *phba, char *buf, int size) pvt_pool = &multixri_pool->pvt_pool; txcmplq_cnt = qp->io_wq->pring->txcmplq_cnt; - scnprintf(tmp, sizeof(tmp), - "%03d: %4d %4d %4d %4d | %10d %10d ", - i, pbl_pool->count, pvt_pool->count, - txcmplq_cnt, pvt_pool->high_watermark, - qp->empty_io_bufs, multixri_pool->pbl_empty_count); - if (strlcat(buf, tmp, size) >= size) - break; + seq_buf_printf(&s, + "%03d: %4d %4d %4d %4d | %10d %10d ", + i, pbl_pool->count, pvt_pool->count, + txcmplq_cnt, pvt_pool->high_watermark, + qp->empty_io_bufs, + multixri_pool->pbl_empty_count); #ifdef LPFC_MXP_STAT - scnprintf(tmp, sizeof(tmp), - "%4d %10d %10d %10d %10d", - multixri_pool->stat_max_hwm, - multixri_pool->above_limit_count, - multixri_pool->below_limit_count, - multixri_pool->local_pbl_hit_count, - multixri_pool->other_pbl_hit_count); - if (strlcat(buf, tmp, size) >= size) - break; + seq_buf_printf(&s, + "%4d %10d %10d %10d %10d", + multixri_pool->stat_max_hwm, + multixri_pool->above_limit_count, + multixri_pool->below_limit_count, + multixri_pool->local_pbl_hit_count, + multixri_pool->other_pbl_hit_count); - scnprintf(tmp, sizeof(tmp), - " | %4d %4d %5d", - multixri_pool->stat_pbl_count, - multixri_pool->stat_pvt_count, - multixri_pool->stat_busy_count); - if (strlcat(buf, tmp, size) >= size) - break; + seq_buf_printf(&s, + " | %4d %4d %5d", + multixri_pool->stat_pbl_count, + multixri_pool->stat_pvt_count, + multixri_pool->stat_busy_count); #endif - scnprintf(tmp, sizeof(tmp), "\n"); - if (strlcat(buf, tmp, size) >= size) + seq_buf_printf(&s, "\n"); + + if (seq_buf_has_overflowed(&s)) break; } return strnlen(buf, size); @@ -1261,13 +1252,14 @@ lpfc_debugfs_scsistat_data(struct lpfc_vport *vport, char *buf, int size) u64 data1, data2, data3; u64 tot, totin, totout; int i; - char tmp[LPFC_MAX_SCSI_INFO_TMP_LEN] = {0}; + struct seq_buf s; if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_FCP) || (phba->sli_rev != LPFC_SLI_REV4)) return 0; - scnprintf(buf, size, "SCSI HDWQ Statistics\n"); + seq_buf_init(&s, buf, size); + seq_buf_printf(&s, "SCSI HDWQ Statistics\n"); totin = 0; totout = 0; @@ -1280,21 +1272,18 @@ lpfc_debugfs_scsistat_data(struct lpfc_vport *vport, char *buf, int size) data3 = cstat->control_requests; totout += (data1 + data2 + data3); - scnprintf(tmp, sizeof(tmp), "HDWQ (%d): Rd %016llx Wr %016llx " - "IO %016llx ", i, data1, data2, data3); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "HDWQ (%d): Rd %016llx Wr %016llx IO %016llx ", + i, data1, data2, data3); - scnprintf(tmp, sizeof(tmp), "Cmpl %016llx OutIO %016llx\n", - tot, ((data1 + data2 + data3) - tot)); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "Cmpl %016llx OutIO %016llx\n", + tot, ((data1 + data2 + data3) - tot)); + + if (seq_buf_has_overflowed(&s)) + break; } - scnprintf(tmp, sizeof(tmp), "Total FCP Cmpl %016llx Issue %016llx " - "OutIO %016llx\n", totin, totout, totout - totin); - strlcat(buf, tmp, size); + seq_buf_printf(&s, "Total FCP Cmpl %016llx Issue %016llx OutIO %016llx\n", + totin, totout, totout - totin); -buffer_done: len = strnlen(buf, size); return len; @@ -1704,28 +1693,23 @@ lpfc_debugfs_hdwqstat_data(struct lpfc_vport *vport, char *buf, int size) uint32_t tot_xmt; uint32_t tot_rcv; uint32_t tot_cmpl; - char tmp[LPFC_MAX_SCSI_INFO_TMP_LEN] = {0}; + size_t used = strnlen(buf, size); + struct seq_buf s; - scnprintf(tmp, sizeof(tmp), "HDWQ Stats:\n\n"); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_init(&s, buf + used, size - used); - scnprintf(tmp, sizeof(tmp), "(NVME Accounting: %s) ", - (phba->hdwqstat_on & - (LPFC_CHECK_NVME_IO | LPFC_CHECK_NVMET_IO) ? - "Enabled" : "Disabled")); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "HDWQ Stats:\n\n"); - scnprintf(tmp, sizeof(tmp), "(SCSI Accounting: %s) ", - (phba->hdwqstat_on & LPFC_CHECK_SCSI_IO ? - "Enabled" : "Disabled")); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "(NVME Accounting: %s) ", + (phba->hdwqstat_on & + (LPFC_CHECK_NVME_IO | LPFC_CHECK_NVMET_IO) ? + "Enabled" : "Disabled")); - scnprintf(tmp, sizeof(tmp), "\n\n"); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "(SCSI Accounting: %s) ", + (phba->hdwqstat_on & LPFC_CHECK_SCSI_IO ? + "Enabled" : "Disabled")); + + seq_buf_printf(&s, "\n\n"); for (i = 0; i < phba->cfg_hdw_queue; i++) { tot_rcv = 0; @@ -1744,62 +1728,50 @@ lpfc_debugfs_hdwqstat_data(struct lpfc_vport *vport, char *buf, int size) !c_stat->rcv_io) continue; - if (!tot_xmt && !tot_cmpl && !tot_rcv) { - /* Print HDWQ string only the first time */ - scnprintf(tmp, sizeof(tmp), "[HDWQ %d]:\t", i); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; - } + /* Print HDWQ string only the first time */ + if (!tot_xmt && !tot_cmpl && !tot_rcv) + seq_buf_printf(&s, "[HDWQ %d]:\t", i); tot_xmt += c_stat->xmt_io; tot_cmpl += c_stat->cmpl_io; if (phba->nvmet_support) tot_rcv += c_stat->rcv_io; - scnprintf(tmp, sizeof(tmp), "| [CPU %d]: ", j); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "| [CPU %d]: ", j); - if (phba->nvmet_support) { - scnprintf(tmp, sizeof(tmp), - "XMT 0x%x CMPL 0x%x RCV 0x%x |", - c_stat->xmt_io, c_stat->cmpl_io, - c_stat->rcv_io); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; - } else { - scnprintf(tmp, sizeof(tmp), - "XMT 0x%x CMPL 0x%x |", - c_stat->xmt_io, c_stat->cmpl_io); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; - } + if (phba->nvmet_support) + seq_buf_printf(&s, + "XMT 0x%x CMPL 0x%x RCV 0x%x |", + c_stat->xmt_io, c_stat->cmpl_io, + c_stat->rcv_io); + else + seq_buf_printf(&s, + "XMT 0x%x CMPL 0x%x |", + c_stat->xmt_io, c_stat->cmpl_io); + + if (seq_buf_has_overflowed(&s)) + break; } + if (seq_buf_has_overflowed(&s)) + break; + /* Check if nothing to display */ if (!tot_xmt && !tot_cmpl && !tot_rcv) continue; - scnprintf(tmp, sizeof(tmp), "\t->\t[HDWQ Total: "); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; + seq_buf_printf(&s, "\t->\t[HDWQ Total: "); - if (phba->nvmet_support) { - scnprintf(tmp, sizeof(tmp), - "XMT 0x%x CMPL 0x%x RCV 0x%x]\n\n", - tot_xmt, tot_cmpl, tot_rcv); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; - } else { - scnprintf(tmp, sizeof(tmp), - "XMT 0x%x CMPL 0x%x]\n\n", - tot_xmt, tot_cmpl); - if (strlcat(buf, tmp, size) >= size) - goto buffer_done; - } + if (phba->nvmet_support) + seq_buf_printf(&s, + "XMT 0x%x CMPL 0x%x RCV 0x%x]\n\n", + tot_xmt, tot_cmpl, tot_rcv); + else + seq_buf_printf(&s, + "XMT 0x%x CMPL 0x%x]\n\n", + tot_xmt, tot_cmpl); } -buffer_done: len = strnlen(buf, size); return len; } diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index f2cab134af7f..8a795c65e3c3 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -21,6 +21,7 @@ * included with this package. * *******************************************************************/ #include +#include #include #include #include @@ -5103,57 +5104,37 @@ lpfc_info(struct Scsi_Host *host) struct lpfc_hba *phba = vport->phba; int link_speed = 0; static char lpfcinfobuf[384]; - char tmp[384] = {0}; + struct seq_buf s; memset(lpfcinfobuf, 0, sizeof(lpfcinfobuf)); + seq_buf_init(&s, lpfcinfobuf, sizeof(lpfcinfobuf)); if (phba && phba->pcidev){ /* Model Description */ - scnprintf(tmp, sizeof(tmp), phba->ModelDesc); - if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >= - sizeof(lpfcinfobuf)) - goto buffer_done; + seq_buf_printf(&s, "%s", phba->ModelDesc); /* PCI Info */ - scnprintf(tmp, sizeof(tmp), - " on PCI bus %02x device %02x irq %d", - phba->pcidev->bus->number, phba->pcidev->devfn, - phba->pcidev->irq); - if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >= - sizeof(lpfcinfobuf)) - goto buffer_done; + seq_buf_printf(&s, " on PCI bus %02x device %02x irq %d", + phba->pcidev->bus->number, phba->pcidev->devfn, + phba->pcidev->irq); /* Port Number */ - if (phba->Port[0]) { - scnprintf(tmp, sizeof(tmp), " port %s", phba->Port); - if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >= - sizeof(lpfcinfobuf)) - goto buffer_done; - } + if (phba->Port[0]) + seq_buf_printf(&s, " port %s", phba->Port); /* Link Speed */ link_speed = lpfc_sli_port_speed_get(phba); - if (link_speed != 0) { - scnprintf(tmp, sizeof(tmp), - " Logical Link Speed: %d Mbps", link_speed); - if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >= - sizeof(lpfcinfobuf)) - goto buffer_done; - } + if (link_speed != 0) + seq_buf_printf(&s, " Logical Link Speed: %d Mbps", + link_speed); /* Support for BSG ioctls */ - scnprintf(tmp, sizeof(tmp), " BSG"); - if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >= - sizeof(lpfcinfobuf)) - goto buffer_done; + seq_buf_printf(&s, " BSG"); /* PCI resettable */ - if (!lpfc_check_pci_resettable(phba)) { - scnprintf(tmp, sizeof(tmp), " PCI resettable"); - strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)); - } + if (!lpfc_check_pci_resettable(phba)) + seq_buf_printf(&s, " PCI resettable"); } -buffer_done: return lpfcinfobuf; } diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h index a05d203e4777..3e0937cf3ff3 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.h +++ b/drivers/scsi/lpfc/lpfc_scsi.h @@ -158,6 +158,3 @@ struct fcp_cmnd32 { #define TXRDY_PAYLOAD_LEN 12 -/* For sysfs/debugfs tmp string max len */ -#define LPFC_MAX_SCSI_INFO_TMP_LEN 79 - diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 62a30a92b792..cfa4371169f1 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -8109,17 +8110,18 @@ u32 lpfc_rx_monitor_report(struct lpfc_hba *phba, u32 cnt = 0; char tmp[DBG_LOG_STR_SZ] = {0}; bool log_to_kmsg = (!buf || !buf_len) ? true : false; + struct seq_buf s; if (!log_to_kmsg) { /* clear the buffer to be sure */ memset(buf, 0, buf_len); - scnprintf(buf, buf_len, "\t%-16s%-16s%-16s%-16s%-8s%-8s%-8s" - "%-8s%-8s%-8s%-16s\n", - "MaxBPI", "Tot_Data_CMF", - "Tot_Data_Cmd", "Tot_Data_Cmpl", - "Lat(us)", "Avg_IO", "Max_IO", "Bsy", - "IO_cnt", "Info", "BWutil(ms)"); + seq_buf_init(&s, buf, buf_len); + seq_buf_printf(&s, "\t%-16s%-16s%-16s%-16s%-8s%-8s%-8s%-8s%-8s%-8s%-16s\n", + "MaxBPI", "Tot_Data_CMF", + "Tot_Data_Cmd", "Tot_Data_Cmpl", + "Lat(us)", "Avg_IO", "Max_IO", "Bsy", + "IO_cnt", "Info", "BWutil(ms)"); } /* Needs to be _irq because record is called from timer interrupt @@ -8131,24 +8133,27 @@ u32 lpfc_rx_monitor_report(struct lpfc_hba *phba, /* Read out this entry's data. */ if (!log_to_kmsg) { - /* If !log_to_kmsg, then store to buf. */ + /* + * Drop a record whole if it does not fit, without + * consuming its ring entry. + */ scnprintf(tmp, sizeof(tmp), - "%03d:\t%-16llu%-16llu%-16llu%-16llu%-8llu" - "%-8llu%-8llu%-8u%-8u%-8u%u(%u)\n", - *head_idx, entry->max_bytes_per_interval, - entry->cmf_bytes, entry->total_bytes, - entry->rcv_bytes, entry->avg_io_latency, - entry->avg_io_size, entry->max_read_cnt, + "%03d:\t%-16llu%-16llu%-16llu%-16llu%-8llu%-8llu%-8llu%-8u%-8u%-8u%u(%u)\n", + *head_idx, + entry->max_bytes_per_interval, + entry->cmf_bytes, + entry->total_bytes, + entry->rcv_bytes, + entry->avg_io_latency, + entry->avg_io_size, + entry->max_read_cnt, entry->cmf_busy, entry->io_cnt, - entry->cmf_info, entry->timer_utilization, + entry->cmf_info, + entry->timer_utilization, entry->timer_interval); - /* Check for buffer overflow */ - if ((strlen(buf) + strlen(tmp)) >= buf_len) + if (seq_buf_puts(&s, tmp) < 0) break; - - /* Append entry's data to buffer */ - strlcat(buf, tmp, buf_len); } else { lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT, "4410 %02u: MBPI %llu Xmit %llu " diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index ecd365d78ae3..f0152b043e18 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3072,7 +3072,7 @@ static int megasas_reset_bus_host(struct scsi_cmnd *scmd) scmd_printk(KERN_INFO, scmd, "SCSI host state: %d SCSI host busy: %d FW outstanding: %d\n", - scmd->device->host->shost_state, + scsi_get_host_state(scmd->device->host), scsi_host_busy(scmd->device->host), atomic_read(&instance->fw_outstanding)); /* diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 402d1f35d214..f80a21ec161b 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -5172,7 +5172,7 @@ static enum scsi_qc_status mpi3mr_qcmd(struct Scsi_Host *shost, /* Avoid error handling escalation when device is removed or blocked */ - if (scmd->device->host->shost_state == SHOST_RECOVERY && + if (scsi_get_host_state(scmd->device->host) == SHOST_RECOVERY && scmd->cmnd[0] == TEST_UNIT_READY && (stgt_priv_data->dev_removed || (dev_handle == MPI3MR_INVALID_DEV_HANDLE))) { scsi_build_sense(scmd, 0, UNIT_ATTENTION, 0x29, 0x07); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 791a3c5fbf44..fed7aeffec58 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5870,6 +5870,8 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) if (ioc->pcie_sgl_dma_pool) { for (i = 0; i < ioc->scsiio_depth; i++) { + if (!ioc->pcie_sg_lookup[i].pcie_sgl) + continue; dma_pool_free(ioc->pcie_sgl_dma_pool, ioc->pcie_sg_lookup[i].pcie_sgl, ioc->pcie_sg_lookup[i].pcie_sgl_dma); diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index dea78688cc9b..0e12009a87f6 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -5472,7 +5472,7 @@ static enum scsi_qc_status scsih_qcmd(struct Scsi_Host *shost, * Avoid error handling escallation when device is disconnected */ if (handle == MPT3SAS_INVALID_DEVICE_HANDLE || sas_device_priv_data->block) { - if (scmd->device->host->shost_state == SHOST_RECOVERY && + if (scsi_get_host_state(scmd->device->host) == SHOST_RECOVERY && scmd->cmnd[0] == TEST_UNIT_READY) { scsi_build_sense(scmd, 0, UNIT_ATTENTION, 0x29, 0x07); scsi_done(scmd); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 2b9a9c672ec6..bb0cc71de37b 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2302,7 +2302,7 @@ int qla_get_tmf(struct tmf_arg *arg) if (TMF_NOT_READY(fcport)) { ql_log(ql_log_warn, vha, 0x802c, "Unable to acquire TM resource due to disruption.\n"); - rc = EIO; + rc = -EIO; break; } if (ha->active_tmf < MAX_ACTIVE_TMF && @@ -9269,7 +9269,7 @@ static int qla29xx_process_rd_image(struct scsi_qla_host *vha, if (section == TIM) { if (section_size > req->length * qla_req_entry_size(ha)) { ql_log(ql_log_fatal, vha, 0x0098, - "TIM section too large (0x%x bytes, ring 0x%lx bytes).\n", + "TIM section too large (0x%x bytes, ring 0x%zx bytes).\n", section_size, req->length * qla_req_entry_size(ha)); return QLA_FUNCTION_FAILED; diff --git a/drivers/scsi/qla2xxx/qla_nx2.c b/drivers/scsi/qla2xxx/qla_nx2.c index 41ff6fbdb933..04d7ab6ad037 100644 --- a/drivers/scsi/qla2xxx/qla_nx2.c +++ b/drivers/scsi/qla2xxx/qla_nx2.c @@ -3507,7 +3507,7 @@ qla8044_poll_flash_status_reg(struct scsi_qla_host *vha) msleep(QLA8044_FLASH_STATUS_REG_POLL_DELAY); } - if (!retries) + if (retries == -1) ret_val = QLA_FUNCTION_FAILED; return ret_val; diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index d598ab4126f8..c9d9fc7c81fb 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -9411,11 +9411,9 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd) * This routine finds that if reset host is called in EH * scenario or from some application like sg_reset **/ -static int qla4xxx_is_eh_active(struct Scsi_Host *shost) +static bool qla4xxx_is_eh_active(struct Scsi_Host *shost) { - if (shost->shost_state == SHOST_RECOVERY) - return 1; - return 0; + return scsi_get_host_state(shost) == SHOST_RECOVERY; } /** diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 480a0bf2aff3..af27fd3df8d4 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1663,10 +1663,9 @@ static enum scsi_qc_status scsi_dispatch_cmd(struct scsi_cmnd *cmd) goto done; } - if (unlikely(host->shost_state == SHOST_DEL)) { + if (unlikely(scsi_get_host_state(host) == SHOST_DEL)) { cmd->result = (DID_NO_CONNECT << 16); goto done; - } trace_scsi_dispatch_cmd_start(cmd); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index e27da038603a..3b82e80e807a 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1169,6 +1169,7 @@ static unsigned char *scsi_inq_str(unsigned char *buf, unsigned char *inq, /** * scsi_probe_and_add_lun - probe a LUN, if a LUN is found add it + * @shost: SCSI host pointer * @starget: pointer to target device structure * @lun: LUN of target device * @bflagsp: store bflags here if not NULL @@ -1188,17 +1189,18 @@ static unsigned char *scsi_inq_str(unsigned char *buf, unsigned char *inq, * attached at the LUN * - SCSI_SCAN_LUN_PRESENT: a new scsi_device was allocated and initialized **/ -static int scsi_probe_and_add_lun(struct scsi_target *starget, +static int scsi_probe_and_add_lun(struct Scsi_Host *shost, + struct scsi_target *starget, u64 lun, blist_flags_t *bflagsp, struct scsi_device **sdevp, enum scsi_scan_mode rescan, void *hostdata) + __must_hold(&shost->scan_mutex) { struct scsi_device *sdev; unsigned char *result; blist_flags_t bflags; int res = SCSI_SCAN_NO_RESPONSE, result_len = 256; - struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); /* * The rescan flag is used as an optimization, the first scan of a @@ -1334,6 +1336,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, /** * scsi_sequential_lun_scan - sequentially scan a SCSI target + * @shost: SCSI host pointer * @starget: pointer to target structure to scan * @bflags: black/white list flag for LUN 0 * @scsi_level: Which version of the standard does this device adhere to @@ -1346,13 +1349,14 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * * Modifies sdevscan->lun. **/ -static void scsi_sequential_lun_scan(struct scsi_target *starget, +static void scsi_sequential_lun_scan(struct Scsi_Host *shost, + struct scsi_target *starget, blist_flags_t bflags, int scsi_level, enum scsi_scan_mode rescan) + __must_hold(&shost->scan_mutex) { uint max_dev_lun; u64 sparse_lun, lun; - struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); SCSI_LOG_SCAN_BUS(3, starget_printk(KERN_INFO, starget, "scsi scan: Sequential scan\n")); @@ -1412,14 +1416,15 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget, * sparse_lun. */ for (lun = 1; lun < max_dev_lun; ++lun) - if ((scsi_probe_and_add_lun(starget, lun, NULL, NULL, rescan, - NULL) != SCSI_SCAN_LUN_PRESENT) && + if (scsi_probe_and_add_lun(shost, starget, lun, NULL, NULL, + rescan, NULL) != SCSI_SCAN_LUN_PRESENT && !sparse_lun) return; } /** * scsi_report_lun_scan - Scan using SCSI REPORT LUN results + * @shost: SCSI host pointer * @starget: which target * @bflags: Zero or a mix of BLIST_NOLUN, BLIST_REPORTLUN2, or BLIST_NOREPORTLUN * @rescan: nonzero if we can skip code only needed on first scan @@ -1438,8 +1443,10 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget, * 0: scan completed (or no memory, so further scanning is futile) * 1: could not scan with REPORT LUN **/ -static int scsi_report_lun_scan(struct scsi_target *starget, blist_flags_t bflags, - enum scsi_scan_mode rescan) +static int scsi_report_lun_scan(struct Scsi_Host *shost, + struct scsi_target *starget, blist_flags_t bflags, + enum scsi_scan_mode rescan) + __must_hold(&shost->scan_mutex) { unsigned char scsi_cmd[MAX_COMMAND_SIZE]; unsigned int length; @@ -1448,7 +1455,6 @@ static int scsi_report_lun_scan(struct scsi_target *starget, blist_flags_t bflag int result; struct scsi_lun *lunp, *lun_data; struct scsi_device *sdev; - struct Scsi_Host *shost = dev_to_shost(&starget->dev); struct scsi_failure failure_defs[] = { { .sense = UNIT_ATTENTION, @@ -1594,7 +1600,7 @@ static int scsi_report_lun_scan(struct scsi_target *starget, blist_flags_t bflag } else { int res; - res = scsi_probe_and_add_lun(starget, + res = scsi_probe_and_add_lun(shost, starget, lun, NULL, NULL, rescan, NULL); if (res == SCSI_SCAN_NO_RESPONSE) { /* @@ -1641,7 +1647,7 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel, scsi_complete_async_scans(); if (scsi_host_scan_allowed(shost) && scsi_autopm_get_host(shost) == 0) { - scsi_probe_and_add_lun(starget, lun, NULL, &sdev, + scsi_probe_and_add_lun(shost, starget, lun, NULL, &sdev, SCSI_SCAN_RESCAN, hostdata); scsi_autopm_put_host(shost); } @@ -1763,10 +1769,11 @@ int scsi_rescan_device(struct scsi_device *sdev) } EXPORT_SYMBOL(scsi_rescan_device); -static void __scsi_scan_target(struct device *parent, unsigned int channel, - unsigned int id, u64 lun, enum scsi_scan_mode rescan) +static void __scsi_scan_target(struct Scsi_Host *shost, struct device *parent, + unsigned int channel, unsigned int id, u64 lun, + enum scsi_scan_mode rescan) + __must_hold(&shost->scan_mutex) { - struct Scsi_Host *shost = dev_to_shost(parent); blist_flags_t bflags = 0; int res; struct scsi_target *starget; @@ -1786,7 +1793,8 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel, /* * Scan for a specific host/chan/id/lun. */ - scsi_probe_and_add_lun(starget, lun, NULL, NULL, rescan, NULL); + scsi_probe_and_add_lun(shost, starget, lun, NULL, NULL, rescan, + NULL); goto out_reap; } @@ -1794,14 +1802,15 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel, * Scan LUN 0, if there is some response, scan further. Ideally, we * would not configure LUN 0 until all LUNs are scanned. */ - res = scsi_probe_and_add_lun(starget, 0, &bflags, NULL, rescan, NULL); + res = scsi_probe_and_add_lun(shost, starget, 0, &bflags, NULL, rescan, + NULL); if (res == SCSI_SCAN_LUN_PRESENT || res == SCSI_SCAN_TARGET_PRESENT) { - if (scsi_report_lun_scan(starget, bflags, rescan) != 0) + if (scsi_report_lun_scan(shost, starget, bflags, rescan) != 0) /* * The REPORT LUN did not scan the target, * do a sequential scan. */ - scsi_sequential_lun_scan(starget, bflags, + scsi_sequential_lun_scan(shost, starget, bflags, starget->scsi_level, rescan); } @@ -1851,7 +1860,7 @@ void scsi_scan_target(struct device *parent, unsigned int channel, scsi_complete_async_scans(); if (scsi_host_scan_allowed(shost) && scsi_autopm_get_host(shost) == 0) { - __scsi_scan_target(parent, channel, id, lun, rescan); + __scsi_scan_target(shost, parent, channel, id, lun, rescan); scsi_autopm_put_host(shost); } mutex_unlock(&shost->scan_mutex); @@ -1861,6 +1870,7 @@ EXPORT_SYMBOL(scsi_scan_target); static void scsi_scan_channel(struct Scsi_Host *shost, unsigned int channel, unsigned int id, u64 lun, enum scsi_scan_mode rescan) + __must_hold(&shost->scan_mutex) { uint order_id; @@ -1882,11 +1892,11 @@ static void scsi_scan_channel(struct Scsi_Host *shost, unsigned int channel, order_id = shost->max_id - id - 1; else order_id = id; - __scsi_scan_target(&shost->shost_gendev, channel, + __scsi_scan_target(shost, &shost->shost_gendev, channel, order_id, lun, rescan); } else - __scsi_scan_target(&shost->shost_gendev, channel, + __scsi_scan_target(shost, &shost->shost_gendev, channel, id, lun, rescan); } diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index dfc3559e7e04..9480432f650b 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -214,8 +214,9 @@ store_shost_state(struct device *dev, struct device_attribute *attr, if (!state) return -EINVAL; - if (scsi_host_set_state(shost, state)) - return -EINVAL; + scoped_guard(spinlock_irq, shost->host_lock) + if (scsi_host_set_state(shost, state)) + return -EINVAL; return count; } @@ -223,7 +224,7 @@ static ssize_t show_shost_state(struct device *dev, struct device_attribute *attr, char *buf) { struct Scsi_Host *shost = class_to_shost(dev); - const char *name = scsi_host_state_name(shost->shost_state); + const char *name = scsi_host_state_name(scsi_get_host_state(shost)); if (!name) return -EINVAL; diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c index 82953e6a0915..cd638b4a4d7b 100644 --- a/drivers/scsi/snic/snic_main.c +++ b/drivers/scsi/snic/snic_main.c @@ -305,6 +305,7 @@ snic_add_host(struct Scsi_Host *shost, struct pci_dev *pdev) if (!shost->work_q) { SNIC_HOST_ERR(shost, "Failed to Create ScsiHost wq.\n"); + scsi_remove_host(shost); ret = -ENOMEM; } diff --git a/drivers/ufs/core/Makefile b/drivers/ufs/core/Makefile index ce7d16d2cf35..67ab9ffbdf5d 100644 --- a/drivers/ufs/core/Makefile +++ b/drivers/ufs/core/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +CONTEXT_ANALYSIS := y + obj-$(CONFIG_SCSI_UFSHCD) += ufshcd-core.o ufshcd-core-y += ufshcd.o ufs-sysfs.o ufs-mcq.o ufs-txeq.o ufshcd-core-$(CONFIG_RPMB) += ufs-rpmb.o diff --git a/drivers/ufs/core/ufs-debugfs.c b/drivers/ufs/core/ufs-debugfs.c index be527209540d..ed1de70e2ec1 100644 --- a/drivers/ufs/core/ufs-debugfs.c +++ b/drivers/ufs/core/ufs-debugfs.c @@ -65,8 +65,10 @@ static int ee_usr_mask_get(void *data, u64 *val) return 0; } +token_context_lock(ufs_debugfs); + static int ufs_debugfs_get_user_access(struct ufs_hba *hba) -__acquires(&hba->host_sem) + __cond_acquires(0, ufs_debugfs) { down(&hba->host_sem); if (!ufshcd_is_user_access_allowed(hba)) { @@ -74,14 +76,16 @@ __acquires(&hba->host_sem) return -EBUSY; } ufshcd_rpm_get_sync(hba); + __acquire(ufs_debugfs); return 0; } static void ufs_debugfs_put_user_access(struct ufs_hba *hba) -__releases(&hba->host_sem) + __releases(ufs_debugfs) { ufshcd_rpm_put_sync(hba); up(&hba->host_sem); + __release(ufs_debugfs); } static int ee_usr_mask_set(void *data, u64 val) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 69d92387e9d2..2ba244cf40ac 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1317,6 +1317,7 @@ static int ufshcd_wait_for_pending_cmds(struct ufs_hba *hba, break; } + __set_current_state(TASK_UNINTERRUPTIBLE); io_schedule_timeout(msecs_to_jiffies(20)); if (ktime_to_us(ktime_sub(ktime_get(), start)) > wait_timeout_us) { @@ -1353,6 +1354,8 @@ static int ufshcd_wait_for_pending_cmds(struct ufs_hba *hba, * On failure, all acquired locks are released and the tagset is unquiesced. */ int ufshcd_pause_command_processing(struct ufs_hba *hba, u64 timeout_us) + __cond_acquires(0, &hba->host->scan_mutex) + __cond_acquires(0, &hba->clk_scaling_lock) { int ret = 0; @@ -1377,6 +1380,8 @@ int ufshcd_pause_command_processing(struct ufs_hba *hba, u64 timeout_us) * This function resumes command submissions. */ void ufshcd_resume_command_processing(struct ufs_hba *hba) + __releases(&hba->clk_scaling_lock) + __releases(&hba->host->scan_mutex) { up_write(&hba->clk_scaling_lock); blk_mq_unquiesce_tagset(&hba->host->tag_set); @@ -1446,6 +1451,9 @@ static int ufshcd_scale_gear(struct ufs_hba *hba, u32 target_gear, bool scale_up * Return: 0 upon success; -EBUSY upon timeout. */ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) + __cond_acquires(0, &hba->host->scan_mutex) + __cond_acquires(0, &hba->wb_mutex) + __cond_acquires(0, &hba->clk_scaling_lock) { int ret = 0; /* @@ -1475,6 +1483,9 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) } static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err) + __releases(&hba->clk_scaling_lock) + __releases(&hba->wb_mutex) + __releases(&hba->host->scan_mutex) { up_write(&hba->clk_scaling_lock); mutex_unlock(&hba->wb_mutex); @@ -3304,6 +3315,8 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) } static void ufshcd_dev_man_lock(struct ufs_hba *hba) + __acquires(&hba->dev_cmd.lock) + __acquires_shared(&hba->clk_scaling_lock) { ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); @@ -3311,6 +3324,8 @@ static void ufshcd_dev_man_lock(struct ufs_hba *hba) } static void ufshcd_dev_man_unlock(struct ufs_hba *hba) + __releases_shared(&hba->clk_scaling_lock) + __releases(&hba->dev_cmd.lock) { up_read(&hba->clk_scaling_lock); mutex_unlock(&hba->dev_cmd.lock); diff --git a/drivers/ufs/host/Makefile b/drivers/ufs/host/Makefile index 65d8bb23ab7b..7d8db67eb23c 100644 --- a/drivers/ufs/host/Makefile +++ b/drivers/ufs/host/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +CONTEXT_ANALYSIS := y + obj-$(CONFIG_SCSI_UFS_DWC_TC_PCI) += tc-dwc-g210-pci.o ufshcd-dwc.o tc-dwc-g210.o obj-$(CONFIG_SCSI_UFS_DWC_TC_PLATFORM) += tc-dwc-g210-pltfrm.o ufshcd-dwc.o tc-dwc-g210.o obj-$(CONFIG_SCSI_UFS_CDNS_PLATFORM) += cdns-pltfrm.o diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index ecf33b66610c..657c2cb0f881 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -255,9 +255,12 @@ static void finish_netfs_read(struct ceph_osd_request *req) } if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { - ceph_put_page_vector(osd_data->pages, - calc_pages_for(osd_data->alignment, - osd_data->length), false); + int num_pages = calc_pages_for(osd_data->alignment, + osd_data->length); + + for (int i = 0; i < num_pages; i++) + put_page(osd_data->pages[i]); + kvfree(osd_data->pages); } if (err > 0) { ceph_subvolume_metrics_record_io(fsc->mdsc, ceph_inode(inode), @@ -1426,6 +1429,16 @@ void ceph_shift_unused_folios_left(struct folio_batch *fbatch) fbatch->nr = n; } +static void ceph_undo_wrbuffer_claim(struct inode *inode, struct folio *folio) +{ + struct ceph_snap_context *snapc = folio_detach_private(folio); + + if (!snapc) + return; + ceph_put_wrbuffer_cap_refs(ceph_inode(inode), 1, snapc); + ceph_put_snap_context(snapc); +} + static int ceph_submit_write(struct address_space *mapping, struct writeback_control *wbc, @@ -1489,6 +1502,7 @@ int ceph_submit_write(struct address_space *mapping, if (!page) continue; + ceph_undo_wrbuffer_claim(inode, page_folio(page)); redirty_page_for_writepage(wbc, page); unlock_page(page); } @@ -2464,7 +2478,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, } rd_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL, - 1, false, GFP_NOFS); + 1, false, GFP_KERNEL); if (!rd_req) { err = -ENOMEM; goto out_unlock; @@ -2477,12 +2491,12 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, rd_req->r_base_oloc.pool_ns = ceph_get_string(pool_ns); ceph_oid_printf(&rd_req->r_base_oid, "%llx.00000000", ci->i_vino.ino); - err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS); + err = ceph_osdc_alloc_messages(rd_req, GFP_KERNEL); if (err) goto out_unlock; wr_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL, - 1, false, GFP_NOFS); + 1, false, GFP_KERNEL); if (!wr_req) { err = -ENOMEM; goto out_unlock; @@ -2493,7 +2507,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, ceph_oloc_copy(&wr_req->r_base_oloc, &rd_req->r_base_oloc); ceph_oid_copy(&wr_req->r_base_oid, &rd_req->r_base_oid); - err = ceph_osdc_alloc_messages(wr_req, GFP_NOFS); + err = ceph_osdc_alloc_messages(wr_req, GFP_KERNEL); if (err) goto out_unlock; @@ -2532,7 +2546,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, } pool_ns_len = pool_ns ? pool_ns->len : 0; - perm = kmalloc_flex(*perm, pool_ns, pool_ns_len + 1, GFP_NOFS); + perm = kmalloc_flex(*perm, pool_ns, pool_ns_len + 1, GFP_KERNEL); if (!perm) { err = -ENOMEM; goto out_unlock; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d7283fb54cec..bcb04c6cb92c 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -785,9 +785,9 @@ void ceph_add_cap(struct inode *inode, * generation of the MDS session (i.e. has not gone 'stale' due to * us losing touch with the mds). */ -static int __cap_is_valid(struct ceph_cap *cap) +static int __cap_is_valid(struct ceph_inode_info *ci, struct ceph_cap *cap) { - struct inode *inode = &cap->ci->netfs.inode; + struct inode *inode = &ci->netfs.inode; struct ceph_client *cl = cap->session->s_mdsc->fsc->client; unsigned long ttl; u32 gen; @@ -822,7 +822,7 @@ int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented) *implemented = 0; for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) { cap = rb_entry(p, struct ceph_cap, ci_node); - if (!__cap_is_valid(cap)) + if (!__cap_is_valid(ci, cap)) continue; doutc(cl, "%p %llx.%llx cap %p issued %s\n", inode, ceph_vinop(inode), cap, ceph_cap_string(cap->issued)); @@ -855,7 +855,7 @@ int __ceph_caps_issued_other(struct ceph_inode_info *ci, struct ceph_cap *ocap) cap = rb_entry(p, struct ceph_cap, ci_node); if (cap == ocap) continue; - if (!__cap_is_valid(cap)) + if (!__cap_is_valid(ci, cap)) continue; have |= cap->issued; } @@ -866,11 +866,19 @@ int __ceph_caps_issued_other(struct ceph_inode_info *ci, struct ceph_cap *ocap) * Move a cap to the end of the LRU (oldest caps at list head, newest * at list tail). */ -static void __touch_cap(struct ceph_cap *cap) +static void __touch_cap(struct ceph_inode_info *ci, struct ceph_cap *cap) { - struct inode *inode = &cap->ci->netfs.inode; + struct inode *inode = &ci->netfs.inode; struct ceph_mds_session *s = cap->session; struct ceph_client *cl = s->s_mdsc->fsc->client; + static u8 skip_counter; + + if (data_race(++skip_counter)) + /* skip this call most of the time to reduce lock + * contention; the LRU list is still accurate enough + * for ceph_trim_caps() + */ + return; spin_lock(&s->s_cap_lock); if (!s->s_cap_iterator) { @@ -906,7 +914,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) { cap = rb_entry(p, struct ceph_cap, ci_node); - if (!__cap_is_valid(cap)) + if (!__cap_is_valid(ci, cap)) continue; if ((cap->issued & mask) == mask) { doutc(cl, "mask %p %llx.%llx cap %p issued %s (mask %s)\n", @@ -914,7 +922,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) - __touch_cap(cap); + __touch_cap(ci, cap); return 1; } @@ -929,15 +937,15 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) struct rb_node *q; /* touch this + preceding caps */ - __touch_cap(cap); + __touch_cap(ci, cap); for (q = rb_first(&ci->i_caps); q != p; q = rb_next(q)) { cap = rb_entry(q, struct ceph_cap, ci_node); - if (!__cap_is_valid(cap)) + if (!__cap_is_valid(ci, cap)) continue; if (cap->issued & mask) - __touch_cap(cap); + __touch_cap(ci, cap); } } return 1; @@ -979,6 +987,27 @@ int __ceph_caps_revoking_other(struct ceph_inode_info *ci, return 0; } +/* + * Return true if any cap of this inode holds caps which the MDS has + * revoked, but which we have not released yet. + */ +static bool __ceph_is_any_revoking(const struct ceph_inode_info *ci) +{ + const struct rb_node *p; + + lockdep_assert_held(&ci->i_ceph_lock); + + for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) { + const struct ceph_cap *cap = + rb_entry(p, struct ceph_cap, ci_node); + + if (cap->implemented & ~cap->issued) + return true; + } + + return false; +} + int __ceph_caps_used(struct ceph_inode_info *ci) { int used = 0; @@ -1091,7 +1120,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check) for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) { cap = rb_entry(p, struct ceph_cap, ci_node); - if (check && !__cap_is_valid(cap)) + if (check && !__cap_is_valid(ci, cap)) continue; if (cap == ci->i_auth_cap) mds_wanted |= cap->mds_wanted; @@ -1119,20 +1148,20 @@ int ceph_is_any_caps(struct inode *inode) * caller should hold i_ceph_lock. * caller will not hold session s_mutex if called from destroy_inode. */ -void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) +static void __ceph_remove_cap(struct ceph_inode_info *ci, struct ceph_cap *cap, bool queue_release) { - struct ceph_mds_session *session = cap->session; - struct ceph_client *cl = session->s_mdsc->fsc->client; - struct ceph_inode_info *ci = cap->ci; - struct inode *inode = &ci->netfs.inode; + struct ceph_mds_session *session; + struct ceph_client *cl; + struct inode *inode; struct ceph_mds_client *mdsc; int removed = 0; - /* 'ci' being NULL means the remove have already occurred */ - if (!ci) { - doutc(cl, "inode is NULL\n"); + if (ceph_cap_is_removed(cap)) return; - } + + session = cap->session; + cl = session->s_mdsc->fsc->client; + inode = &ci->netfs.inode; lockdep_assert_held(&ci->i_ceph_lock); @@ -1158,8 +1187,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) cap->session = NULL; removed = 1; } - /* protect backpointer with s_cap_lock: see iterate_session_caps */ - cap->ci = NULL; + + /* protect removal marker with both i_ceph_lock and + s_cap_lock, so either one can be used to check for + removal */ + RB_CLEAR_NODE(&cap->ci_node); /* * s_cap_reconnect is protected by s_cap_lock. no one changes @@ -1196,13 +1228,12 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) } void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, + struct ceph_inode_info *ci, bool queue_release) { - struct ceph_inode_info *ci = cap->ci; struct ceph_fs_client *fsc; - /* 'ci' being NULL means the remove have already occurred */ - if (!ci) { + if (ceph_cap_is_removed(cap)) { doutc(mdsc->fsc->client, "inode is NULL\n"); return; } @@ -1215,7 +1246,7 @@ void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, !fsc->blocklisted && !ceph_inode_is_shutdown(&ci->netfs.inode)); - __ceph_remove_cap(cap, queue_release); + __ceph_remove_cap(ci, cap, queue_release); } struct cap_msg_args { @@ -1375,7 +1406,7 @@ void __ceph_remove_caps(struct ceph_inode_info *ci) while (p) { struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); p = rb_next(p); - ceph_remove_cap(mdsc, cap, true); + ceph_remove_cap(mdsc, cap, ci, true); } spin_unlock(&ci->i_ceph_lock); } @@ -1388,11 +1419,11 @@ void __ceph_remove_caps(struct ceph_inode_info *ci) * Make note of max_size reported/requested from mds, revoked caps * that have now been implemented. */ -static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, +static void __prep_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci, + struct ceph_cap *cap, int op, int flags, int used, int want, int retain, int flushing, u64 flush_tid, u64 oldest_flush_tid) { - struct ceph_inode_info *ci = cap->ci; struct inode *inode = &ci->netfs.inode; struct ceph_client *cl = ceph_inode_to_client(inode); int held, revoking; @@ -1421,6 +1452,9 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, cap->implemented &= cap->issued | used; cap->mds_wanted = want; + if ((ci->i_ceph_flags & CEPH_I_FLUSH_FORCE) != 0 && !__ceph_is_any_revoking(ci)) + clear_bit(CEPH_I_FLUSH_FORCE_BIT, &ci->i_ceph_flags); + arg->session = cap->session; arg->ino = ceph_vino(inode).ino; arg->cid = cap->cap_id; @@ -1842,7 +1876,7 @@ struct ceph_cap_flush *ceph_alloc_cap_flush(void) { struct ceph_cap_flush *cf; - cf = kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL); + cf = kmem_cache_alloc(ceph_cap_flush_cachep, GFP_NOFS); if (!cf) return NULL; @@ -2038,6 +2072,14 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) if (ci->i_ceph_flags & CEPH_I_FLUSH) flags |= CHECK_CAPS_FLUSH; + /* + * A revoke whose response was deferred (see handle_cap_grant()) must + * still be acknowledged. Replay the forced flush here so that even a + * check triggered by writeback/invalidation completion sends a cap + * message to the MDS. + */ + if (ci->i_ceph_flags & CEPH_I_FLUSH_FORCE) + flags |= CHECK_CAPS_FLUSH_FORCE; retry: /* Caps wanted by virtue of active open files. */ file_wanted = __ceph_caps_file_wanted(ci); @@ -2210,7 +2252,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) if (want & ~cap->mds_wanted) { if (want & ~(cap->mds_wanted | cap->issued)) goto ack; - if (!__cap_is_valid(cap)) + if (!__cap_is_valid(ci, cap)) goto ack; } @@ -2252,7 +2294,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) mds = cap->mds; /* remember mds, so we don't repeat */ - __prep_cap(&arg, cap, CEPH_CAP_OP_UPDATE, mflags, cap_used, + __prep_cap(&arg, ci, cap, CEPH_CAP_OP_UPDATE, mflags, cap_used, want, retain, flushing, flush_tid, oldest_flush_tid); spin_unlock(&ci->i_ceph_lock); @@ -2314,7 +2356,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid) flush_tid = __mark_caps_flushing(inode, session, true, &oldest_flush_tid); - __prep_cap(&arg, cap, CEPH_CAP_OP_FLUSH, CEPH_CLIENT_CAPS_SYNC, + __prep_cap(&arg, ci, cap, CEPH_CAP_OP_FLUSH, CEPH_CLIENT_CAPS_SYNC, __ceph_caps_used(ci), __ceph_caps_wanted(ci), (cap->issued | cap->implemented), flushing, flush_tid, oldest_flush_tid); @@ -2589,9 +2631,14 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } } - list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) { - if (cf->tid < first_tid) + cf = list_first_entry(&ci->i_cap_flush_list, struct ceph_cap_flush, i_list); + while (&cf->i_list != &ci->i_cap_flush_list) { + struct ceph_cap_flush *next; + + if (cf->tid < first_tid) { + cf = list_next_entry(cf, i_list); continue; + } cap = ci->i_auth_cap; if (!(cap && cap->session == session)) { @@ -2601,6 +2648,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } first_tid = cf->tid + 1; + next = list_next_entry(cf, i_list); if (!cf->is_capsnap) { struct cap_msg_args arg; @@ -2608,7 +2656,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, doutc(cl, "%p %llx.%llx cap %p tid %llu %s\n", inode, ceph_vinop(inode), cap, cf->tid, ceph_cap_string(cf->caps)); - __prep_cap(&arg, cap, CEPH_CAP_OP_FLUSH, + __prep_cap(&arg, ci, cap, CEPH_CAP_OP_FLUSH, (cf->tid < last_snap_flush ? CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0), __ceph_caps_used(ci), @@ -2641,6 +2689,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } spin_lock(&ci->i_ceph_lock); + cf = next; } } @@ -3757,13 +3806,30 @@ static void handle_cap_grant(struct inode *inode, BUG_ON(cap->issued & ~cap->implemented); /* don't let check_caps skip sending a response to MDS for revoke msgs */ - if (!revoke_wait && le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { - cap->mds_wanted = 0; - flags |= CHECK_CAPS_FLUSH_FORCE; - if (cap == ci->i_auth_cap) - check_caps = 1; /* check auth cap only */ - else - check_caps = 2; /* check all caps */ + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + if (revoke_wait) { + /* + * We can't ack the revoke yet: the response is deferred + * until the writeback or cache invalidation queued above + * completes. Set the CEPH_I_FLUSH_FORCE flag to remember + * that a forced cap message is owed so that deferred + * completion (ceph_put_wrbuffer_cap_refs() or the + * invalidate worker, both of which call ceph_check_caps()) + * actually sends one, even if by then the revoked caps look + * unused, the inode is retaining caps, or the MDS has + * re-granted them. Without this, the cap message is never + * sent and the MDS hangs ("isn't responding to + * mclientcaps(revoke)"). + */ + set_bit(CEPH_I_FLUSH_FORCE_BIT, &ci->i_ceph_flags); + } else { + cap->mds_wanted = 0; + flags |= CHECK_CAPS_FLUSH_FORCE; + if (cap == ci->i_auth_cap) + check_caps = 1; /* check auth cap only */ + else + check_caps = 2; /* check all caps */ + } } if (extra_info->inline_version > 0 && @@ -4119,7 +4185,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, goto out_unlock; if (target < 0) { - ceph_remove_cap(mdsc, cap, false); + ceph_remove_cap(mdsc, cap, ci, false); goto out_unlock; } @@ -4156,7 +4222,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, change_auth_cap_ses(ci, tcap->session); } } - ceph_remove_cap(mdsc, cap, false); + ceph_remove_cap(mdsc, cap, ci, false); goto out_unlock; } else if (tsession) { /* add placeholder for the export target */ @@ -4173,7 +4239,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, spin_unlock(&mdsc->cap_dirty_lock); } - ceph_remove_cap(mdsc, cap, false); + ceph_remove_cap(mdsc, cap, ci, false); goto out_unlock; } @@ -4289,7 +4355,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc, inode, ceph_vinop(inode), peer, ocap->seq, ocap->mseq, mds, piseq, pmseq); } - ceph_remove_cap(mdsc, ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE)); + ceph_remove_cap(mdsc, ocap, ci, (ph->flags & CEPH_CAP_FLAG_RELEASE)); } *old_issued = issued; @@ -4887,7 +4953,7 @@ int ceph_encode_inode_release(void **p, struct inode *inode, drop &= ~(used | dirty); cap = __get_cap_for_mds(ci, mds); - if (cap && __cap_is_valid(cap)) { + if (cap && __cap_is_valid(ci, cap)) { unless &= cap->issued; if (unless) { if (unless & CEPH_CAP_AUTH_EXCL) @@ -5046,7 +5112,7 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali cap, ci, inode, ceph_vinop(inode)); is_auth = (cap == ci->i_auth_cap); - __ceph_remove_cap(cap, false); + __ceph_remove_cap(ci, cap, false); if (is_auth) { struct ceph_cap_flush *cf; diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index 64d240759277..bc0a097a4cea 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -298,18 +298,26 @@ int ceph_encode_encrypted_dname(struct inode *parent, char *buf, int elen) * Otherwise, base64 decode the string, and then ask fscrypt to format it * for userland presentation. * + * Though the fscrypt/crypto subsystems broadly expect all buffers to be in the + * linear-mapped region, this function slightly relaxes those requirements: + * fname->ctext, fname->name, and oname->name may be vmalloc(), but not tname. + * * Returns 0 on success or negative error code on error. */ -int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, +int ceph_fname_to_usr(const struct ceph_fname *fname, unsigned char *tname, struct fscrypt_str *oname, bool *is_nokey) { struct inode *dir = fname->dir; struct fscrypt_str _tname = FSTR_INIT(NULL, 0); + struct fscrypt_str _oname; struct fscrypt_str iname; char *name = fname->name; int name_len = fname->name_len; int ret; + if (WARN_ON_ONCE(tname && is_vmalloc_addr(tname))) + return -EIO; + /* Sanity check that the resulting name will fit in the buffer */ if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX) return -EIO; @@ -350,31 +358,47 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, goto out_inode; } + if (!tname && (fname->ctext_len == 0 || + unlikely(is_vmalloc_addr(fname->ctext)) || + unlikely(is_vmalloc_addr(oname->name)))) { + ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname); + if (ret) + goto out_inode; + tname = _tname.name; + } + if (fname->ctext_len == 0) { int declen; - if (!tname) { - ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname); - if (ret) - goto out_inode; - tname = &_tname; - } - - declen = base64_decode(name, name_len, - tname->name, false, BASE64_IMAP); + declen = base64_decode(name, name_len, tname, false, BASE64_IMAP); if (declen <= 0) { ret = -EIO; goto out; } - iname.name = tname->name; + iname.name = tname; iname.len = declen; + } else if (unlikely(is_vmalloc_addr(fname->ctext))) { + memcpy(tname, fname->ctext, fname->ctext_len); + + iname.name = tname; + iname.len = fname->ctext_len; } else { iname.name = fname->ctext; iname.len = fname->ctext_len; } - ret = fscrypt_fname_disk_to_usr(dir, 0, 0, &iname, oname); - if (!ret && (dir != fname->dir)) { + _oname.name = unlikely(is_vmalloc_addr(oname->name)) ? tname : oname->name; + _oname.len = oname->len; + + ret = fscrypt_fname_disk_to_usr(dir, 0, 0, &iname, &_oname); + if (ret) + goto out; + + if (unlikely(is_vmalloc_addr(oname->name))) + memcpy(oname->name, _oname.name, _oname.len); + oname->len = _oname.len; + + if (dir != fname->dir) { char tmp_buf[BASE64_CHARS(NAME_MAX)]; name_len = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%llu", diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h index b748e2060bc9..79cb563fd887 100644 --- a/fs/ceph/crypto.h +++ b/fs/ceph/crypto.h @@ -115,7 +115,7 @@ static inline void ceph_fname_free_buffer(struct inode *parent, fscrypt_fname_free_buffer(fname); } -int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, +int ceph_fname_to_usr(const struct ceph_fname *fname, unsigned char *tname, struct fscrypt_str *oname, bool *is_nokey); int ceph_fscrypt_prepare_readdir(struct inode *dir); @@ -204,7 +204,7 @@ static inline void ceph_fname_free_buffer(struct inode *parent, } static inline int ceph_fname_to_usr(const struct ceph_fname *fname, - struct fscrypt_str *tname, + unsigned char *tname, struct fscrypt_str *oname, bool *is_nokey) { oname->name = fname->name; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4a5e0290f2e3..2e5c0ccb1b34 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -774,8 +774,13 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, d_drop(dentry); err = -ENOENT; } else { - if (d_unhashed(dentry)) - d_add(dentry, NULL); + if (d_unhashed(dentry)) { + struct inode *parent = + d_inode(dentry->d_parent); + if (!parent || + ceph_snap(parent) == CEPH_NOSNAP) + d_add(dentry, NULL); + } } } } @@ -840,6 +845,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, dentry->d_name.len) && !is_root_ceph_dentry(dir, dentry) && ceph_test_mount_opt(fsc, DCACHE) && + ceph_snap(dir) == CEPH_NOSNAP && __ceph_dir_is_complete(ci) && __ceph_caps_issued_mask_metric(ci, CEPH_CAP_FILE_SHARED, 1)) { __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD); @@ -1173,7 +1179,7 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, !req->r_reply_info.head->is_target && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); - ret = ERR_PTR(err); + ret = err ? ERR_PTR(err) : NULL; out_req: if (!IS_ERR(ret) && req->r_dentry != dentry) /* Some other dentry was spliced in */ @@ -1763,11 +1769,11 @@ static int __dir_lease_check(const struct dentry *dentry, if (ret > 0) { if (time_before(jiffies, di->time + lwc->dir_lease_ttl)) return STOP; + if (!lwc->expire_dir_lease) + return KEEP; /* Move dentry to tail of dir lease list if we don't want * to delete it. So dentries in the list are checked in a * round robin manner */ - if (!lwc->expire_dir_lease) - return TOUCH; if (dentry->d_lockref.count > 0 || (di->flags & CEPH_DENTRY_REFERENCED)) return TOUCH; @@ -1794,7 +1800,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.dir_lease = false; lwc.nr_to_scan = CEPH_CAPS_PER_RELEASE * 2; freed = __dentry_leases_walk(mdsc, &lwc); - if (!lwc.nr_to_scan) /* more invalid leases */ + if (freed > 0 && !lwc.nr_to_scan) /* more invalid leases */ return -EAGAIN; if (lwc.nr_to_scan < CEPH_CAPS_PER_RELEASE) @@ -1804,6 +1810,10 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.expire_dir_lease = freed < count; lwc.dir_lease_ttl = mdsc->fsc->mount_options->caps_wanted_delay_max * HZ; freed +=__dentry_leases_walk(mdsc, &lwc); + if (freed == 0 && count == 0) + /* no progress possible currently, retry futile */ + return 0; + if (!lwc.nr_to_scan) /* more to check */ return -EAGAIN; diff --git a/fs/ceph/export.c b/fs/ceph/export.c index b2f2af104679..debb9634b9e3 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -442,6 +442,16 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, return dentry; } +static int ceph_export_copy_name(char *name, const char *src, u32 len) +{ + if (len > NAME_MAX) + return -ENAMETOOLONG; + + memcpy(name, src, len); + name[len] = '\0'; + return 0; +} + static int __get_snap_name(struct dentry *parent, char *name, struct dentry *child) { @@ -513,9 +523,8 @@ static int __get_snap_name(struct dentry *parent, char *name, BUG_ON(!rde->inode.in); if (ceph_snap(inode) == le64_to_cpu(rde->inode.in->snapid)) { - memcpy(name, rde->name, rde->name_len); - name[rde->name_len] = '\0'; - err = 0; + err = ceph_export_copy_name(name, rde->name, + rde->name_len); goto out; } } @@ -580,8 +589,8 @@ static int ceph_get_name(struct dentry *parent, char *name, rinfo = &req->r_reply_info; if (!IS_ENCRYPTED(dir)) { - memcpy(name, rinfo->dname, rinfo->dname_len); - name[rinfo->dname_len] = 0; + err = ceph_export_copy_name(name, rinfo->dname, + rinfo->dname_len); } else { struct fscrypt_str oname = FSTR_INIT(NULL, 0); struct ceph_fname fname = { .dir = dir, @@ -595,10 +604,9 @@ static int ceph_get_name(struct dentry *parent, char *name, goto out; err = ceph_fname_to_usr(&fname, NULL, &oname, NULL); - if (!err) { - memcpy(name, oname.name, oname.len); - name[oname.len] = 0; - } + if (!err) + err = ceph_export_copy_name(name, oname.name, + oname.len); ceph_fname_free_buffer(dir, &oname); } out: diff --git a/fs/ceph/file.c b/fs/ceph/file.c index a4a2a4b6a027..bd3e3f5c269e 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2388,7 +2388,8 @@ static ssize_t ceph_splice_read(struct file *in, loff_t *ppos, * dropping our cap refs and allowing the pending snap to logically * complete _before_ this write occurs. * - * If we are near ENOSPC, write synchronously. + * If requested, nearfull writes are synced to preserve the legacy + * client-side backpressure behavior. */ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) { @@ -2477,6 +2478,54 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err < 0) goto out; + /* + * For O_APPEND writes we may have waited for Fwx exclusive caps + * while the previous Fwx holder (another client) extended the + * file. i_size has been updated via the cap grant message from + * the MDS, but ki_pos is still the old EOF. Re-read i_size here + * (no extra MDS round-trip needed) and adjust ki_pos to the true + * EOF. Since we hold Fwx, no other client can change the file. + */ + if (iocb->ki_flags & IOCB_APPEND) { + loff_t cur_eof = i_size_read(inode); + + if (cur_eof != pos) { + doutc(cl, + "%p %llx.%llx O_APPEND: pos adjusted %lld -> %lld\n", + inode, ceph_vinop(inode), pos, cur_eof); + iocb->ki_pos = cur_eof; + pos = cur_eof; + if (pos >= limit) { + err = -EFBIG; + goto out_caps; + } + iov_iter_truncate(from, limit - pos); + count = iov_iter_count(from); + + /* + * ceph_get_caps() validated the old endoff + * against i_max_size; adjusting ki_pos forward + * may have shifted the write range beyond the + * granted max_size. Re-check and truncate if + * necessary. + */ + spin_lock(&ci->i_ceph_lock); + if (pos + count > (loff_t)ci->i_max_size) { + loff_t max_size = ci->i_max_size; + + spin_unlock(&ci->i_ceph_lock); + if (pos >= max_size) { + err = -EFBIG; + goto out_caps; + } + iov_iter_truncate(from, max_size - pos); + count = iov_iter_count(from); + } else { + spin_unlock(&ci->i_ceph_lock); + } + } + } + err = file_update_time(file); if (err) goto out_caps; @@ -2556,8 +2605,9 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) } if (written >= 0) { - if ((map_flags & CEPH_OSDMAP_NEARFULL) || - (pool_flags & CEPH_POOL_FLAG_NEARFULL)) + if (ceph_test_mount_opt(fsc, NEARFULL_SYNC) && + ((map_flags & CEPH_OSDMAP_NEARFULL) || + (pool_flags & CEPH_POOL_FLAG_NEARFULL))) iocb->ki_flags |= IOCB_DSYNC; written = generic_write_sync(iocb, written); } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 61d7c0b8161f..d52e2b389e0b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1814,7 +1814,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) ceph_dir_clear_ordered(dir); d_delete(dn); } else if (have_lease) { - if (d_unhashed(dn)) + if (d_unhashed(dn) && + ceph_snap(dir) == CEPH_NOSNAP) d_add(dn, NULL); } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3c692ad02c85..a091f77cedaf 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -491,11 +491,11 @@ static int parse_reply_info_readdir(void **p, void *end, struct inode *inode = d_inode(req->r_dentry); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_reply_dir_entry *rde = info->dir_entries + i; - struct fscrypt_str tname = FSTR_INIT(NULL, 0); struct fscrypt_str oname = FSTR_INIT(NULL, 0); struct ceph_fname fname; u32 altname_len, _name_len; u8 *altname, *_name; + u8 *tname = NULL; /* dentry */ ceph_decode_32_safe(p, end, _name_len, bad); @@ -541,9 +541,13 @@ static int parse_reply_info_readdir(void **p, void *end, * to do the base64_decode in-place. It's * safe because the decoded string should * always be shorter, which is 3/4 of origin - * string. + * string. If this message was allocated with + * vmalloc() (happens, but rarely), leave it + * NULL and let ceph_fname_to_usr() allocate + * suitable temporary working space instead. */ - tname.name = _name; + if (likely(!is_vmalloc_addr(_name))) + tname = _name; /* * Set oname to _name too, and this will be @@ -560,7 +564,7 @@ static int parse_reply_info_readdir(void **p, void *end, oname.len = altname_len; } rde->is_nokey = false; - err = ceph_fname_to_usr(&fname, &tname, &oname, &rde->is_nokey); + err = ceph_fname_to_usr(&fname, tname, &oname, &rde->is_nokey); if (err) { pr_err_client(cl, "unable to decode %.*s, got %d\n", _name_len, _name, err); @@ -615,10 +619,36 @@ static int parse_reply_info_filelock(void **p, void *end, #define DELEGATED_INO_AVAILABLE xa_mk_value(1) +static int ceph_insert_deleg_ino(struct ceph_mds_session *s, u64 ino) +{ + struct ceph_client *cl = s->s_mdsc->fsc->client; + int err; + + /* + * Cap how many delegated inodes a single session may hold. This is + * the only place that grows the count, so atomic_add_unless() bounds + * it at exactly CEPH_MAX_DELEG_INOS; s_num_deleg_inos can never exceed + * that. + */ + if (!atomic_add_unless(&s->s_num_deleg_inos, 1, CEPH_MAX_DELEG_INOS)) { + pr_warn_ratelimited_client(cl, + "MDS session already holds %d delegated inodes\n", + CEPH_MAX_DELEG_INOS); + return -EOVERFLOW; + } + + err = xa_insert(&s->s_delegated_inos, ino, DELEGATED_INO_AVAILABLE, + GFP_KERNEL); + if (err) + atomic_dec(&s->s_num_deleg_inos); + return err; +} + static int ceph_parse_deleg_inos(void **p, void *end, struct ceph_mds_session *s) { struct ceph_client *cl = s->s_mdsc->fsc->client; + u64 msg_deleg_inos = 0; u32 sets; ceph_decode_32_safe(p, end, sets, bad); @@ -636,16 +666,34 @@ static int ceph_parse_deleg_inos(void **p, void *end, start, len); continue; } + + /* + * Bound the number of inodes one reply may delegate. + * ceph_insert_deleg_ino() separately caps the per-session + * population, so this only has to stop one reply from spinning + * the insert loop under an attacker-controlled len. + */ + if (len > (u64)CEPH_MAX_DELEG_INOS || + msg_deleg_inos > (u64)CEPH_MAX_DELEG_INOS - len) { + pr_warn_ratelimited_client(cl, + "MDS reply delegates too many inodes (have %llu, +%llu, max %d)\n", + msg_deleg_inos, len, CEPH_MAX_DELEG_INOS); + return -EIO; + } + msg_deleg_inos += len; + while (len--) { - int err = xa_insert(&s->s_delegated_inos, start++, - DELEGATED_INO_AVAILABLE, - GFP_KERNEL); + int err = ceph_insert_deleg_ino(s, start++); + if (!err) { doutc(cl, "added delegated inode 0x%llx\n", start - 1); } else if (err == -EBUSY) { pr_warn_client(cl, "MDS delegated inode 0x%llx more than once.\n", start - 1); + } else if (err == -EOVERFLOW) { + /* ceph_insert_deleg_ino() already warned. */ + return -EIO; } else { return err; } @@ -663,16 +711,17 @@ u64 ceph_get_deleg_ino(struct ceph_mds_session *s) xa_for_each(&s->s_delegated_inos, ino, val) { val = xa_erase(&s->s_delegated_inos, ino); - if (val == DELEGATED_INO_AVAILABLE) + if (val == DELEGATED_INO_AVAILABLE) { + atomic_dec(&s->s_num_deleg_inos); return ino; + } } return 0; } int ceph_restore_deleg_ino(struct ceph_mds_session *s, u64 ino) { - return xa_insert(&s->s_delegated_inos, ino, DELEGATED_INO_AVAILABLE, - GFP_KERNEL); + return ceph_insert_deleg_ino(s, ino); } #else /* BITS_PER_LONG == 64 */ /* @@ -1059,6 +1108,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, INIT_LIST_HEAD(&s->s_waiting); INIT_LIST_HEAD(&s->s_unsafe); xa_init(&s->s_delegated_inos); + atomic_set(&s->s_num_deleg_inos, 0); INIT_LIST_HEAD(&s->s_cap_releases); INIT_WORK(&s->s_cap_release_work, ceph_cap_release_work); @@ -1800,16 +1850,19 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc, * session caps */ -static void detach_cap_releases(struct ceph_mds_session *session, - struct list_head *target) +static int detach_cap_releases(struct ceph_mds_session *session, + struct list_head *target) { struct ceph_client *cl = session->s_mdsc->fsc->client; + const int num_cap_releases = session->s_num_cap_releases; lockdep_assert_held(&session->s_cap_lock); list_splice_init(&session->s_cap_releases, target); session->s_num_cap_releases = 0; doutc(cl, "mds%d\n", session->s_mds); + + return num_cap_releases; } static void dispose_cap_releases(struct ceph_mds_client *mdsc, @@ -1903,7 +1956,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, spin_lock(&session->s_cap_lock); p = p->next; - if (!cap->ci) { + if (ceph_cap_is_removed(cap)) { doutc(cl, "finishing cap %p removal\n", cap); BUG_ON(cap->session != session); cap->session = NULL; @@ -2259,7 +2312,7 @@ static int trim_caps_cb(struct inode *inode, int mds, void *arg) if (oissued) { /* we aren't the only cap.. just remove us */ - ceph_remove_cap(mdsc, cap, true); + ceph_remove_cap(mdsc, cap, ci, true); (*remaining)--; } else { struct dentry *dentry; @@ -2465,9 +2518,7 @@ static void ceph_send_cap_releases(struct ceph_mds_client *mdsc, spin_lock(&session->s_cap_lock); again: - list_splice_init(&session->s_cap_releases, &tmp_list); - num_cap_releases = session->s_num_cap_releases; - session->s_num_cap_releases = 0; + num_cap_releases = detach_cap_releases(session, &tmp_list); spin_unlock(&session->s_cap_lock); while (!list_empty(&tmp_list)) { @@ -4091,13 +4142,19 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe); } + /* + * Now that all mutex-protected state has been updated above + * (the request has been unregistered or added to the + * session's unsafe list), we can unlock it. + */ + mutex_unlock(&mdsc->mutex); + doutc(cl, "tid %lld result %d\n", tid, result); if (test_bit(CEPHFS_FEATURE_REPLY_ENCODING, &session->s_features)) err = parse_reply_info(session, msg, req, (u64)-1); else err = parse_reply_info(session, msg, req, session->s_con.peer_features); - mutex_unlock(&mdsc->mutex); /* Must find target inode outside of mutexes to avoid deadlocks */ rinfo = &req->r_reply_info; @@ -4441,7 +4498,9 @@ static void handle_session(struct ceph_mds_session *session, pr_err_client(cl, "No memory for path\n"); goto fail; } - ceph_decode_copy(&p, cap_auths[i].match.path, _len); + ceph_decode_copy_safe(&p, end, + cap_auths[i].match.path, + _len, bad); /* Remove the tailing '/' */ while (_len && cap_auths[i].match.path[_len - 1] == '/') { @@ -4458,7 +4517,9 @@ static void handle_session(struct ceph_mds_session *session, pr_err_client(cl, "No memory for fs_name\n"); goto fail; } - ceph_decode_copy(&p, cap_auths[i].match.fs_name, _len); + ceph_decode_copy_safe(&p, end, + cap_auths[i].match.fs_name, + _len, bad); } ceph_decode_8_safe(&p, end, cap_auths[i].match.root_squash, bad); @@ -5106,6 +5167,7 @@ static int send_mds_reconnect(struct ceph_mds_client *mdsc, /* Serialized by s_mutex against concurrent ceph_get_deleg_ino(). */ xa_destroy(&session->s_delegated_inos); + atomic_set(&session->s_num_deleg_inos, 0); if (session->s_state == CEPH_MDS_SESSION_CLOSED || session->s_state == CEPH_MDS_SESSION_REJECTED) { pr_info_client(cl, "mds%d skipping reconnect, session %s\n", @@ -5753,7 +5815,7 @@ int ceph_mdsc_schedule_reset(struct ceph_mds_client *mdsc, strscpy(st->last_reason, msg, sizeof(st->last_reason)); spin_unlock(&st->lock); - if (WARN_ON_ONCE(!queue_work(system_unbound_wq, &mdsc->reset_work))) { + if (WARN_ON_ONCE(!queue_work(system_dfl_wq, &mdsc->reset_work))) { spin_lock(&st->lock); st->phase = CEPH_CLIENT_RESET_IDLE; st->last_errno = -EALREADY; @@ -5834,9 +5896,11 @@ static void check_new_map(struct ceph_mds_client *mdsc, ceph_mdsmap_get_addr(newmap, i), sizeof(struct ceph_entity_addr))) { /* just close it */ + ceph_get_mds_session(s); mutex_unlock(&mdsc->mutex); mutex_lock(&s->s_mutex); mutex_lock(&mdsc->mutex); + ceph_put_mds_session(s); ceph_con_close(&s->s_con); mutex_unlock(&s->s_mutex); s->s_state = CEPH_MDS_SESSION_RESTARTING; @@ -5851,6 +5915,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, newstate >= CEPH_MDS_STATE_RECONNECT) { int rc; + ceph_get_mds_session(s); mutex_unlock(&mdsc->mutex); clear_bit(i, targets); rc = send_mds_reconnect(mdsc, s); @@ -5859,6 +5924,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, "mds%d reconnect failed: %d\n", i, rc); mutex_lock(&mdsc->mutex); + ceph_put_mds_session(s); } /* @@ -5871,9 +5937,11 @@ static void check_new_map(struct ceph_mds_client *mdsc, pr_info_client(cl, "mds%d recovery completed\n", s->s_mds); kick_requests(mdsc, i); + ceph_get_mds_session(s); mutex_unlock(&mdsc->mutex); mutex_lock(&s->s_mutex); mutex_lock(&mdsc->mutex); + ceph_put_mds_session(s); ceph_kick_flushing_caps(mdsc, s); mutex_unlock(&s->s_mutex); wake_up_session_caps(s, RECONNECT); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 0ece4c9e3529..3c62e3c3530b 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -300,6 +300,7 @@ struct ceph_mds_session { struct list_head s_waiting; /* waiting requests */ struct list_head s_unsafe; /* unsafe requests */ struct xarray s_delegated_inos; + atomic_t s_num_deleg_inos; }; /* diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 450a4dc9662e..53079ef34c3a 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -3,6 +3,7 @@ #include #include +#include #include #include #include @@ -126,6 +127,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, u8 mdsmap_v; u16 mdsmap_ev; u32 target; + size_t export_targets_len; m = kzalloc_obj(*m, GFP_NOFS); if (!m) @@ -224,8 +226,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, *p += namelen; if (info_v >= 2) { ceph_decode_32_safe(p, end, num_export_targets, bad); + export_targets_len = size_mul(num_export_targets, + sizeof(u32)); + ceph_decode_need(p, end, export_targets_len, bad); pexport_targets = *p; - *p += num_export_targets * sizeof(u32); + *p += export_targets_len; } else { num_export_targets = 0; } @@ -264,6 +269,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, goto nomem; for (j = 0; j < num_export_targets; j++) { target = ceph_decode_32(&pexport_targets); + if (target >= CEPH_MAX_MDS) { + err = -EIO; + goto corrupt; + } info->export_targets[j] = target; } } else { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c05fbd4237f8..15edea30dc8b 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -177,6 +177,7 @@ enum { Opt_wsync, Opt_pagecache, Opt_sparseread, + Opt_nearfull_sync, }; enum ceph_recover_session_mode { @@ -205,6 +206,7 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = { fsparam_flag_no ("ino32", Opt_ino32), fsparam_string ("mds_namespace", Opt_mds_namespace), fsparam_string ("mon_addr", Opt_mon_addr), + fsparam_flag_no ("nearfull_sync", Opt_nearfull_sync), fsparam_flag_no ("poolperm", Opt_poolperm), fsparam_flag_no ("quotadf", Opt_quotadf), fsparam_u32 ("rasize", Opt_rasize), @@ -593,6 +595,12 @@ static int ceph_parse_mount_param(struct fs_context *fc, else fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD; break; + case Opt_nearfull_sync: + if (result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NEARFULL_SYNC; + else + fsopt->flags |= CEPH_MOUNT_OPT_NEARFULL_SYNC; + break; case Opt_test_dummy_encryption: #ifdef CONFIG_FS_ENCRYPTION fscrypt_free_dummy_policy(&fsopt->dummy_enc_policy); @@ -749,6 +757,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",nopagecache"); if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD) seq_puts(m, ",sparseread"); + if (fsopt->flags & CEPH_MOUNT_OPT_NEARFULL_SYNC) + seq_puts(m, ",nearfull_sync"); fscrypt_show_test_dummy_encryption(m, ',', root->d_sb); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 1d6aab060780..72d4e30304dc 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -45,6 +45,7 @@ #define CEPH_MOUNT_OPT_ASYNC_DIROPS (1<<15) /* allow async directory ops */ #define CEPH_MOUNT_OPT_NOPAGECACHE (1<<16) /* bypass pagecache altogether */ #define CEPH_MOUNT_OPT_SPARSEREAD (1<<17) /* always do sparse reads */ +#define CEPH_MOUNT_OPT_NEARFULL_SYNC (1<<18) /* sync writes when nearfull */ #define CEPH_MOUNT_OPT_DEFAULT \ (CEPH_MOUNT_OPT_DCACHE | \ @@ -203,7 +204,19 @@ struct ceph_fs_client { */ struct ceph_cap { struct ceph_inode_info *ci; - struct rb_node ci_node; /* per-ci cap tree */ + + /** + * Per-ci cap tree. Protected with + * `ceph_inode_info.i_ceph_lock`. + * + * Clearing this field with RB_CLEAR_NODE() requires holding + * both `ceph_inode_info.i_ceph_lock` and + * `ceph_mds_session->s_cap_lock`. Calling RB_EMPTY_NODE() + * (via ceph_cap_is_removed()) requires holding at least one + * of these. + */ + struct rb_node ci_node; + struct ceph_mds_session *session; struct list_head session_caps; /* per-session caplist */ u64 cap_id; /* unique cap id (mds provided) */ @@ -641,6 +654,15 @@ static inline int ceph_ino_compare(struct inode *inode, void *data) #define CEPH_MDS_INO_LOG_OFFSET (2 * CEPH_MAX_MDS) #define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY)) +/* + * Upper bound on the number of delegated inodes a single MDS session may + * hold. The MDS normally hands out a small preallocation window (the + * userspace mds_client_prealloc_inos option defaults to 1000) and refills + * it as the client consumes entries. This leaves generous headroom while + * bounding the CPU and memory a malformed delegation interval can consume. + */ +#define CEPH_MAX_DELEG_INOS 8192 + static inline bool ceph_vino_is_reserved(const struct ceph_vino vino) { if (vino.ino >= CEPH_INO_SYSTEM_BASE || @@ -687,6 +709,10 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_SHUTDOWN_BIT (13) /* inode is no longer usable */ #define CEPH_I_ASYNC_CHECK_CAPS_BIT (14) /* check caps after async creating finishes */ +#define CEPH_I_FLUSH_FORCE_BIT (15) /* a revoke's response was deferred; + * force a cap message to the MDS once + * the deferred work completes + */ #define CEPH_I_DIR_ORDERED (1 << CEPH_I_DIR_ORDERED_BIT) #define CEPH_I_FLUSH (1 << CEPH_I_FLUSH_BIT) @@ -699,6 +725,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) #define CEPH_I_ASYNC_CREATE (1 << CEPH_I_ASYNC_CREATE_BIT) #define CEPH_I_SHUTDOWN (1 << CEPH_I_SHUTDOWN_BIT) +#define CEPH_I_FLUSH_FORCE (1 << CEPH_I_FLUSH_FORCE_BIT) /* * Masks of ceph inode work. @@ -1269,8 +1296,22 @@ extern void ceph_add_cap(struct inode *inode, unsigned issued, unsigned wanted, unsigned cap, unsigned seq, u64 realmino, int flags, struct ceph_cap **new_cap); -extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); + +/** + * Determine whether __ceph_remove_cap() has been called on this #cap + * (but the object has not yet been freed because it is protected by + * `ceph_mds_session.s_cap_iterator`). + * + * Caller must lock either `ceph_inode_info.i_ceph_lock` or + * `ceph_mds_session.s_cap_lock`. + */ +static inline bool ceph_cap_is_removed(const struct ceph_cap *cap) +{ + return RB_EMPTY_NODE(&cap->ci_node); +} + extern void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, + struct ceph_inode_info *ci, bool queue_release); extern void __ceph_remove_caps(struct ceph_inode_info *ci); extern void ceph_put_cap(struct ceph_mds_client *mdsc, diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 860fc8e1867d..cc4ffbbcb719 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -848,6 +848,7 @@ static int __build_xattrs(struct inode *inode) name = p; p += len; ceph_decode_32_safe(&p, end, len, bad); + ceph_decode_need(&p, end, len, bad); val = p; p += len; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 064f5b537423..4b59f30ef45d 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -107,6 +107,7 @@ static bool need_uplift_priority(struct f2fs_rwsem *sem, bool is_write) case LOCK_NAME_GC_LOCK: case LOCK_NAME_CP_GLOBAL: case LOCK_NAME_IO_RWSEM: + case LOCK_NAME_NAT_TREE_LOCK: return true; default: f2fs_bug_on(sem->sbi, 1); @@ -766,28 +767,116 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) spin_unlock(&im->ino_lock); } +static void __set_ino_bitmap(struct f2fs_sb_info *sbi, nid_t ino, int type) +{ + struct inode_management *im = &sbi->im[type]; + unsigned long index = INO_SLOT_INDEX(ino); + unsigned int ofs = INO_BIT_OFFSET(ino); + void **slot, *entry; + unsigned long bitmap = 0; + int ret; + + ret = radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); + f2fs_bug_on(sbi, ret); + + spin_lock(&im->ino_lock); + slot = radix_tree_lookup_slot(&im->ino_root, index); + if (slot) { + entry = radix_tree_deref_slot_protected(slot, &im->ino_lock); + bitmap = xa_to_value(entry); + if (!(bitmap & (1UL << ofs))) { + bitmap |= (1UL << ofs); + entry = xa_mk_value(bitmap); + radix_tree_replace_slot(&im->ino_root, slot, entry); + } + } else { + bitmap |= (1UL << ofs); + entry = xa_mk_value(bitmap); + if (unlikely(radix_tree_insert(&im->ino_root, index, entry))) + f2fs_bug_on(sbi, 1); + } + spin_unlock(&im->ino_lock); + radix_tree_preload_end(); +} + +static void __clear_ino_bitmap(struct f2fs_sb_info *sbi, nid_t ino, int type) +{ + struct inode_management *im = &sbi->im[type]; + unsigned long index = INO_SLOT_INDEX(ino); + unsigned int ofs = INO_BIT_OFFSET(ino); + void **slot, *entry; + unsigned long bitmap; + + spin_lock(&im->ino_lock); + slot = radix_tree_lookup_slot(&im->ino_root, index); + if (slot) { + entry = radix_tree_deref_slot_protected(slot, &im->ino_lock); + bitmap = xa_to_value(entry); + if (bitmap & (1UL << ofs)) + bitmap &= ~(1UL << ofs); + + if (bitmap) { + entry = xa_mk_value(bitmap); + radix_tree_replace_slot(&im->ino_root, slot, entry); + } else { + radix_tree_delete(&im->ino_root, index); + } + } + spin_unlock(&im->ino_lock); +} + +static void f2fs_wait_for_inode_record(struct f2fs_sb_info *sbi, int mode) +{ + if (mode != APPEND_INO && mode != UPDATE_INO) + return; + + /* Let's wait for some pending updates for APPEND_INO and UPDATE_INO. */ + flush_workqueue(sbi->evict_wq); +} + +static void __f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + if (type <= FLUSH_INO) + __add_ino_entry(sbi, ino, devidx, type); + else + __set_ino_bitmap(sbi, ino, type); +} + void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { - /* add new dirty ino entry into list */ - __add_ino_entry(sbi, ino, 0, type); + __f2fs_add_ino_entry(sbi, ino, 0, type); } void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { - /* remove dirty ino entry from list */ - __remove_ino_entry(sbi, ino, type); + if (type <= FLUSH_INO) + __remove_ino_entry(sbi, ino, type); + else + __clear_ino_bitmap(sbi, ino, type); } -/* mode should be APPEND_INO, UPDATE_INO or TRANS_DIR_INO */ +/* mode should be APPEND_INO, UPDATE_INO, TRANS_DIR_INO and XATTR_DIR_INO */ bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) { struct inode_management *im = &sbi->im[mode]; - struct ino_entry *e; + unsigned long index = INO_SLOT_INDEX(ino); + unsigned int ofs = INO_BIT_OFFSET(ino); + void *entry; + unsigned long bitmap; + + f2fs_bug_on(sbi, mode <= FLUSH_INO); spin_lock(&im->ino_lock); - e = radix_tree_lookup(&im->ino_root, ino); + entry = radix_tree_lookup(&im->ino_root, index); + if (!entry) { + spin_unlock(&im->ino_lock); + return false; + } + bitmap = xa_to_value(entry); spin_unlock(&im->ino_lock); - return e ? true : false; + + return bitmap & (1UL << ofs); } void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all) @@ -795,9 +884,11 @@ void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all) struct ino_entry *e, *tmp; int i; - for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) { + for (i = all ? ORPHAN_INO : FLUSH_INO; i <= FLUSH_INO; i++) { struct inode_management *im = &sbi->im[i]; + f2fs_wait_for_inode_record(sbi, i); + spin_lock(&im->ino_lock); list_for_each_entry_safe(e, tmp, &im->ino_list, list) { list_del(&e->list); @@ -807,12 +898,20 @@ void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all) } spin_unlock(&im->ino_lock); } + + for (i = APPEND_INO; i < MAX_INO_ENTRY; i++) { + struct inode_management *im = &sbi->im[i]; + + spin_lock(&im->ino_lock); + xa_destroy(&im->ino_root); + spin_unlock(&im->ino_lock); + } } void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type) { - __add_ino_entry(sbi, ino, devidx, type); + __f2fs_add_ino_entry(sbi, ino, devidx, type); } bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, @@ -864,14 +963,14 @@ void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi) void f2fs_add_orphan_inode(struct inode *inode) { /* add new orphan ino entry into list */ - __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO); + f2fs_add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO); f2fs_update_inode_page(inode); } void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { /* remove orphan entry from orphan list */ - __remove_ino_entry(sbi, ino, ORPHAN_INO); + f2fs_remove_ino_entry(sbi, ino, ORPHAN_INO); } static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index dad5c2bd5888..21f396ebe22c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -384,13 +384,32 @@ static void f2fs_write_end_bio(struct bio *bio) bio_put(bio); } -static void f2fs_write_end_io(struct bio *bio) +static void f2fs_write_end_io_work(struct work_struct *work) { - iostat_update_and_unbind_ctx(bio); + struct bio *bio = &container_of(work, struct f2fs_bio, work)->bio; f2fs_write_end_bio(bio); } +static void f2fs_write_end_io(struct bio *bio) +{ + struct f2fs_sb_info *sbi; + + iostat_update_and_unbind_ctx(bio); + + sbi = bio->bi_private; + + if (in_atomic() && bio->bi_iter.bi_size > sbi->max_atc_write_bio_size) { + struct work_struct *w; + + w = &container_of(bio, struct f2fs_bio, bio)->work; + INIT_WORK(w, f2fs_write_end_io_work); + queue_work(sbi->wq, w); + } else { + f2fs_write_end_bio(bio); + } +} + #ifdef CONFIG_BLK_DEV_ZONED static void f2fs_zone_write_end_io(struct bio *bio) { @@ -1216,7 +1235,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - err = inc_valid_block_count(sbi, dn->inode, &count, true); + err = inc_valid_block_count(sbi, dn->inode, &count, true, false); if (unlikely(err)) return err; @@ -1288,10 +1307,11 @@ struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index, if (folio_test_large(folio)) { pgoff_t folio_index = mapping_align_index(mapping, index); + unsigned long nr_pages = folio_nr_pages(folio); f2fs_folio_put(folio, true); invalidate_inode_pages2_range(mapping, folio_index, - folio_index + folio_nr_pages(folio) - 1); + folio_index + nr_pages - 1); f2fs_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT); goto retry; } @@ -1488,7 +1508,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) dn->data_blkaddr = f2fs_data_blkaddr(dn); if (dn->data_blkaddr == NULL_ADDR) { - err = inc_valid_block_count(sbi, dn->inode, &count, true); + err = inc_valid_block_count(sbi, dn->inode, &count, true, false); if (unlikely(err)) return err; } @@ -1497,8 +1517,11 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) old_blkaddr = dn->data_blkaddr; err = f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, &sum, seg_type, NULL); - if (err) + if (err) { + if (old_blkaddr == NULL_ADDR) + dec_valid_block_count(sbi, dn->inode, count); return err; + } if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1); @@ -3900,7 +3923,7 @@ static int f2fs_write_begin(const struct kiocb *iocb, * Will wait that below with our IO control. */ folio = f2fs_filemap_get_folio(mapping, index, - FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_NOFS, + FGP_LOCK | FGP_WRITE | FGP_CREAT, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { err = PTR_ERR(folio); @@ -4460,13 +4483,24 @@ int f2fs_init_wq(struct f2fs_sb_info *sbi) { sbi->wq = alloc_workqueue("f2fs_wq", WQ_UNBOUND | WQ_HIGHPRI, num_online_cpus()); - return sbi->wq ? 0 : -ENOMEM; + if (!sbi->wq) + return -ENOMEM; + + sbi->evict_wq = alloc_workqueue("f2fs_evict_wq", + WQ_UNBOUND | WQ_HIGHPRI, num_online_cpus()); + if (!sbi->evict_wq) { + destroy_workqueue(sbi->wq); + return -ENOMEM; + } + return 0; } void f2fs_destroy_wq(struct f2fs_sb_info *sbi) { if (sbi->wq) destroy_workqueue(sbi->wq); + if (sbi->evict_wq) + destroy_workqueue(sbi->evict_wq); } int __init f2fs_init_bio_entry_cache(void) diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index af88db8fdb71..ff379aff4472 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -352,10 +352,6 @@ static void update_mem_info(struct f2fs_sb_info *sbi) get_cache: si->cache_mem = 0; - /* build gc */ - if (sbi->gc_thread) - si->cache_mem += sizeof(struct f2fs_gc_kthread); - /* build merge flush thread */ if (SM_I(sbi)->fcc_info) si->cache_mem += sizeof(struct flush_cmd_control); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index a9563f7fcd88..fd0e2cd31a81 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -320,6 +320,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, de = find_in_block(dir, dentry_folio, fname, &max_slots, use_hash); if (IS_ERR(de)) { + f2fs_folio_put(dentry_folio, false); *res_folio = ERR_CAST(de); de = NULL; break; @@ -460,7 +461,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, folio_mark_dirty(folio); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); - f2fs_mark_inode_dirty_sync(dir, false); + f2fs_mark_inode_dirty_sync(dir, true); f2fs_folio_put(folio, true); } @@ -615,7 +616,7 @@ void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, clear_inode_flag(inode, FI_NEW_INODE); } inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); - f2fs_mark_inode_dirty_sync(dir, false); + f2fs_mark_inode_dirty_sync(dir, true); if (F2FS_I(dir)->i_current_depth != current_depth) f2fs_i_depth_write(dir, current_depth); @@ -927,7 +928,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct folio *folio, f2fs_folio_put(folio, true); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); - f2fs_mark_inode_dirty_sync(dir, false); + f2fs_mark_inode_dirty_sync(dir, true); if (inode) f2fs_drop_nlink(dir, inode); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 61f6b9714366..37cf9fa8d537 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -17,6 +17,7 @@ #include "f2fs.h" #include "node.h" +#include "segment.h" #include bool sanity_check_extent_cache(struct inode *inode, struct folio *ifolio) @@ -62,6 +63,14 @@ bool sanity_check_extent_cache(struct inode *inode, struct folio *ifolio) __func__, inode->i_ino, ei.blk, ei.fofs, ei.len); return false; } + + if ((GET_SEGOFF_FROM_SEG0(sbi, ei.blk) % BLKS_PER_SEC(sbi)) || + (ei.len % BLKS_PER_SEC(sbi))) { + f2fs_warn(sbi, "%s: device alias inode (ino=%llx)'s extent info [%u, %u, %u] is not aligned to section size %u", + __func__, inode->i_ino, ei.blk, ei.fofs, ei.len, + BLKS_PER_SEC(sbi)); + return false; + } return true; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8376bbe58ee3..9940a6cecf1a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -193,6 +193,7 @@ enum f2fs_lock_name { LOCK_NAME_GC_LOCK, LOCK_NAME_CP_GLOBAL, LOCK_NAME_IO_RWSEM, + LOCK_NAME_NAT_TREE_LOCK, LOCK_NAME_MAX, }; @@ -254,6 +255,7 @@ struct f2fs_mount_info { block_t unusable_cap; /* Amount of space allowed to be * unusable when disabling checkpoint */ + unsigned int resizable_tail_secno; /* number of resizable tail sections */ /* For compression */ unsigned char compress_algorithm; /* algorithm type */ @@ -388,14 +390,18 @@ enum { /* for the list of ino */ enum { ORPHAN_INO, /* for orphan ino list */ + FLUSH_INO, /* for multiple device flushing */ APPEND_INO, /* for append ino list */ UPDATE_INO, /* for update ino list */ TRANS_DIR_INO, /* for transactions dir ino list */ XATTR_DIR_INO, /* for xattr updated dir ino list */ - FLUSH_INO, /* for multiple device flushing */ MAX_INO_ENTRY, /* max. list */ }; +#define INO_BITS_PER_SLOT BITS_PER_XA_VALUE +#define INO_SLOT_INDEX(ino) ((ino) / INO_BITS_PER_SLOT) +#define INO_BIT_OFFSET(ino) ((ino) % INO_BITS_PER_SLOT) + struct ino_entry { struct list_head list; /* list head */ nid_t ino; /* inode number */ @@ -1403,6 +1409,8 @@ struct f2fs_dev_info { unsigned int total_segments; block_t start_blk; block_t end_blk; + bool has_alias; + bool is_reserving; #ifdef CONFIG_BLK_DEV_ZONED unsigned int nr_blkz; /* Total number of zones */ unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ @@ -1747,6 +1755,33 @@ struct decompress_io_ctx { #define MAX_COMPRESS_LOG_SIZE 8 #define MAX_COMPRESS_WINDOW_SIZE(log_size) ((PAGE_SIZE) << (log_size)) +struct f2fs_gc_kthread { + struct task_struct *f2fs_gc_task; + wait_queue_head_t gc_wait_queue_head; + + /* for gc sleep time */ + unsigned int urgent_sleep_time; + unsigned int min_sleep_time; + unsigned int max_sleep_time; + unsigned int no_gc_sleep_time; + + /* for changing gc mode */ + bool gc_wake; + + /* for GC_MERGE mount option */ + wait_queue_head_t fggc_wq; /* + * caller of f2fs_balance_fs() + * will wait on this wait queue. + */ + + /* for gc control for zoned devices */ + unsigned int no_zoned_gc_percent; + unsigned int boost_zoned_gc_percent; + unsigned int valid_thresh_ratio; + unsigned int boost_gc_multiple; + unsigned int boost_gc_greedy; +}; + struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ @@ -1772,6 +1807,8 @@ struct f2fs_sb_info { struct f2fs_sm_info *sm_info; /* segment manager */ /* for bio operations */ + /* Largest write bio size completed in atomic context (atc). */ + u32 max_atc_write_bio_size; struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ /* keep migration IO order for LFS mode */ struct f2fs_rwsem io_order_lock; @@ -1854,6 +1891,7 @@ struct f2fs_sb_info { block_t last_valid_block_count; /* for recovery */ block_t reserved_blocks; /* configurable reserved blocks */ block_t current_reserved_blocks; /* current reserved blocks */ + block_t alias_reserved_blocks; /* reserved blocks for device alias */ /* Additional tracking for no checkpoint mode */ block_t unusable_block_count; /* # of blocks saved by last cp */ @@ -1882,7 +1920,7 @@ struct f2fs_sb_info { * semaphore for GC, avoid * race between GC and GC or CP */ - struct f2fs_gc_kthread *gc_thread; /* GC thread */ + struct f2fs_gc_kthread gc_thread; /* GC thread */ struct atgc_management am; /* atgc management */ unsigned int cur_victim_sec; /* current victim section num */ unsigned int gc_mode; /* current GC state */ @@ -1967,6 +2005,7 @@ struct f2fs_sb_info { spinlock_t dev_lock; /* protect dirty_device */ bool aligned_blksize; /* all devices has the same logical blksize */ unsigned int first_seq_zone_segno; /* first segno in sequential zone */ + unsigned int pinned_area_max_secno; /* upper bound section for pinned files */ unsigned int bggc_io_aware; /* For adjust the BG_GC priority when pending IO */ unsigned int allocate_section_hint; /* the boundary position between devices */ unsigned int allocate_section_policy; /* determine the section writing priority */ @@ -1980,6 +2019,8 @@ struct f2fs_sb_info { struct workqueue_struct *wq; /* bio completion workqueue */ + struct workqueue_struct *evict_wq; /* inode eviction workqueue */ + /* * If we are in irq context, let's update error information into * on-disk superblock in the work. @@ -2556,7 +2597,8 @@ static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi, block_t avail_user_block_count; avail_user_block_count = sbi->user_block_count - - sbi->current_reserved_blocks; + sbi->current_reserved_blocks - + sbi->alias_reserved_blocks; if (test_opt(sbi, RESERVE_ROOT) && !__allow_reserved_root(sbi, inode, cap)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; @@ -2573,7 +2615,8 @@ static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi, static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, - struct inode *inode, blkcnt_t *count, bool partial) + struct inode *inode, blkcnt_t *count, + bool partial, bool alias_reserved) { long long diff = 0, release = 0; block_t avail_user_block_count; @@ -2596,10 +2639,16 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); + if (alias_reserved) + sbi->alias_reserved_blocks -= *count; + avail_user_block_count = get_available_block_count(sbi, inode, true); diff = (long long)sbi->total_valid_block_count + *count - avail_user_block_count; if (unlikely(diff > 0)) { + if (alias_reserved) + sbi->alias_reserved_blocks += *count; + if (!partial) { spin_unlock(&sbi->stat_lock); release = *count; @@ -3830,7 +3879,10 @@ void f2fs_update_inode_page(struct inode *inode); int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc); void f2fs_remove_donate_inode(struct inode *inode); void f2fs_evict_inode(struct inode *inode); -void f2fs_handle_failed_inode(struct inode *inode, struct f2fs_lock_context *lc); +void f2fs_handle_failed_inode(struct inode *inode, + struct f2fs_lock_context *lc, bool add_orphan); +int f2fs_init_evict_inode_work(void); +void f2fs_destroy_evict_inode_work(void); /* * namei.c @@ -4007,6 +4059,8 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr, unsigned int len); +void f2fs_reserve_device_alias(struct f2fs_sb_info *sbi, block_t addr, + unsigned int len); bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); int f2fs_start_discard_thread(struct f2fs_sb_info *sbi); void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); @@ -4095,10 +4149,26 @@ static inline struct inode *fio_inode(struct f2fs_io_info *fio) #define MIN_FRAGMENT_SIZE 1 #define MAX_FRAGMENT_SIZE 512 -static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi) +static inline bool f2fs_need_rand_blk(struct f2fs_sb_info *sbi, + enum log_type type) { - return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG || - F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK; + if (type == CURSEG_COLD_DATA_PINNED) + return false; + return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK; +} + +static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi, + enum log_type type) +{ + if (type == CURSEG_COLD_DATA_PINNED) + return false; + return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG; +} + +static inline bool f2fs_need_rand_seg_blk(struct f2fs_sb_info *sbi, + enum log_type type) +{ + return f2fs_need_rand_blk(sbi, type) || f2fs_need_rand_seg(sbi, type); } /* @@ -4226,7 +4296,9 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); int f2fs_gc_range(struct f2fs_sb_info *sbi, unsigned int start_seg, unsigned int end_seg, - bool dry_run, unsigned int dry_run_sections); + bool dry_run, unsigned int dry_run_sections, bool lock); +void f2fs_reset_gc_victim_resource(struct f2fs_sb_info *sbi, + unsigned int start, unsigned int end); int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 089759366cdc..edc352569e87 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -36,23 +36,69 @@ #include #include -static void f2fs_zero_post_eof_page(struct inode *inode, - loff_t new_size, bool lock) +static int fill_zero(struct inode *inode, pgoff_t index, + loff_t start, loff_t len); + +static int do_zero_post_eof_page(struct inode *inode, loff_t new_size) { loff_t old_size = i_size_read(inode); + unsigned int offset, len; + pgoff_t index; + int err; + + offset = old_size & (PAGE_SIZE - 1); + + if (!offset) + return 0; + + len = min_t(loff_t, PAGE_SIZE - offset, new_size - old_size); + index = old_size >> PAGE_SHIFT; + + if (f2fs_has_inline_data(inode)) { + /* data post eof should be always zero */ + if (new_size <= MAX_INLINE_DATA(inode)) + return 0; + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + + err = fill_zero(inode, index, offset, len); + if (err) + return err; + return filemap_write_and_wait_range(inode->i_mapping, + old_size, old_size + len - 1); +} + +static int f2fs_zero_post_eof_page(struct inode *inode, + loff_t new_size, bool lock, bool writeback) +{ + loff_t old_size = i_size_read(inode); + bool strict = + F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode == FSYNC_MODE_STRICT; if (old_size >= new_size) - return; + return 0; - if (mapping_empty(inode->i_mapping)) - return; + if (!strict && mapping_empty(inode->i_mapping)) + return 0; if (lock) filemap_invalidate_lock(inode->i_mapping); /* zero or drop pages only in range of [old_size, new_size] */ - truncate_inode_pages_range(inode->i_mapping, old_size, new_size); + truncate_inode_pages_range(inode->i_mapping, old_size, new_size - 1); if (lock) filemap_invalidate_unlock(inode->i_mapping); + + if (!writeback || !strict) + return 0; + /* + * In fsync_mode=strict, when we expand an unaligned EOF size, we + * should zero post EOF data and writeback the data immediately, + * so that it can avoid exposing stale data after metadata flush + * and POR. + */ + return do_zero_post_eof_page(inode, new_size); } static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) @@ -132,7 +178,10 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); - f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT, true); + err = f2fs_zero_post_eof_page(inode, + (folio->index + 1) << PAGE_SHIFT, true, false); + if (err) + goto out_pagefault; file_update_time(vmf->vma->vm_file); filemap_invalidate_lock_shared(inode->i_mapping); @@ -189,7 +238,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) out_sem: filemap_invalidate_unlock_shared(inode->i_mapping); - +out_pagefault: sb_end_pagefault(inode->i_sb); out: ret = vmf_fs_error(err); @@ -813,13 +862,19 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) if (IS_DEVICE_ALIASING(inode)) { struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; - struct extent_info ei = et->largest; + struct extent_info ei; + + read_lock(&et->lock); + ei = et->largest; + read_unlock(&et->lock); f2fs_invalidate_blocks(sbi, ei.blk, ei.len); dec_valid_block_count(sbi, inode, ei.len); f2fs_update_time(sbi, REQ_TIME); + f2fs_drop_extent_tree(inode); + f2fs_folio_put(ifolio, true); goto out; } @@ -1096,24 +1151,31 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if ((attr->ia_valid & ATTR_SIZE)) { if (mapping_large_folio_support(inode->i_mapping)) return -EOPNOTSUPP; - if (!f2fs_is_compress_backend_ready(inode) || - IS_DEVICE_ALIASING(inode)) + if (IS_DEVICE_ALIASING(inode)) + return -EPERM; + if (!f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) && !IS_ALIGNED(attr->ia_size, F2FS_BLK_TO_BYTES(fi->i_cluster_size))) return -EINVAL; - /* - * To prevent scattered pin block generation, we don't allow - * smaller/equal size unaligned truncation for pinned file. - * We only support overwrite IO to pinned file, so don't - * care about larger size truncation. - */ - if (f2fs_is_pinned_file(inode) && - attr->ia_size <= i_size_read(inode) && - !IS_ALIGNED(attr->ia_size, - F2FS_BLK_TO_BYTES(CAP_BLKS_PER_SEC(sbi)))) - return -EINVAL; + + if (f2fs_is_pinned_file(inode)) { + /* + * It may break section-aligned fallocate recovery + * mechanism, so do not allow larger size truncation. + */ + if (attr->ia_size > i_size_read(inode)) + return -EINVAL; + /* + * To prevent scattered pin block generation, we don't + * allow smaller/equal size unaligned truncation for + * pinned file. + */ + else if (!IS_ALIGNED(attr->ia_size, + F2FS_BLK_TO_BYTES(CAP_BLKS_PER_SEC(sbi)))) + return -EINVAL; + } } if (is_quota_modification(idmap, inode, attr)) { @@ -1165,8 +1227,12 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, f2fs_down_write(&fi->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); - if (attr->ia_size > old_size) - f2fs_zero_post_eof_page(inode, attr->ia_size, false); + if (attr->ia_size > old_size) { + err = f2fs_zero_post_eof_page(inode, + attr->ia_size, false, true); + if (err) + goto err_out; + } truncate_setsize(inode, attr->ia_size); if (attr->ia_size <= old_size) @@ -1175,6 +1241,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, * do not trim all blocks after i_size if target size is * larger than i_size. */ +err_out: filemap_invalidate_unlock(inode->i_mapping); f2fs_up_write(&fi->i_gc_rwsem[WRITE]); if (err) @@ -1286,7 +1353,9 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; - f2fs_zero_post_eof_page(inode, offset + len, true); + ret = f2fs_zero_post_eof_page(inode, offset + len, true, false); + if (ret) + return ret; pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1573,7 +1642,9 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); - f2fs_zero_post_eof_page(inode, offset + len, false); + ret = f2fs_zero_post_eof_page(inode, offset + len, false, false); + if (ret) + goto out_unlock; f2fs_lock_op(sbi, &lc); f2fs_drop_extent_tree(inode); @@ -1581,6 +1652,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true); f2fs_unlock_op(sbi, &lc); +out_unlock: filemap_invalidate_unlock(inode->i_mapping); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); return ret; @@ -1613,11 +1685,14 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) /* write out all moved pages, if possible */ filemap_invalidate_lock(inode->i_mapping); - filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + if (ret) + goto out_unlock; truncate_pagecache(inode, offset); new_size = i_size_read(inode) - len; ret = f2fs_truncate_blocks(inode, new_size, true); +out_unlock: filemap_invalidate_unlock(inode->i_mapping); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1699,7 +1774,9 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; - f2fs_zero_post_eof_page(inode, offset + len, true); + ret = f2fs_zero_post_eof_page(inode, offset + len, true, false); + if (ret) + return ret; pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1834,7 +1911,9 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(mapping); - f2fs_zero_post_eof_page(inode, offset + len, false); + ret = f2fs_zero_post_eof_page(inode, offset + len, false, false); + if (ret) + goto out_unlock; truncate_pagecache(inode, offset); while (!ret && idx > pg_start) { @@ -1852,6 +1931,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) idx + delta, nr, false); f2fs_unlock_op(sbi, &lc); } +out_unlock: filemap_invalidate_unlock(mapping); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (ret) @@ -1894,7 +1974,9 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, if (err) return err; - f2fs_zero_post_eof_page(inode, offset + len, true); + err = f2fs_zero_post_eof_page(inode, offset + len, true, true); + if (err) + return err; f2fs_balance_fs(sbi, true); @@ -1915,8 +1997,9 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, block_t sec_len; if (map.m_lblk % sec_blks) { - map.m_lblk = rounddown(map.m_lblk, sec_blks); - map.m_len = pg_end - map.m_lblk; + pg_start = rounddown(map.m_lblk, sec_blks); + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; if (off_end) map.m_len++; } @@ -2126,6 +2209,9 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) if (IS_NOQUOTA(inode)) return -EPERM; + if (IS_DEVICE_ALIASING(inode)) + return -EPERM; + if ((iflags ^ masked_flags) & F2FS_CASEFOLD_FL) { if (!f2fs_sb_has_casefold(F2FS_I_SB(inode))) return -EOPNOTSUPP; @@ -2674,6 +2760,17 @@ static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) return fscrypt_ioctl_get_policy(filp, (void __user *)arg); } +static int f2fs_ioc_get_dev_alias_status(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + + if (!IS_DEVICE_ALIASING(inode)) + return -EINVAL; + + return put_user(F2FS_HAS_BLOCKS(inode) ? F2FS_DEV_ALIAS_STATUS_RESERVED : + F2FS_DEV_ALIAS_STATUS_RELEASED, (u32 __user *)arg); +} + static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -3079,6 +3176,9 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (IS_DEVICE_ALIASING(inode)) + return -EOPNOTSUPP; + if (copy_from_user(&range, (struct f2fs_defragment __user *)arg, sizeof(range))) return -EFAULT; @@ -3117,8 +3217,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, struct inode *dst = file_inode(file_out); struct f2fs_sb_info *sbi = F2FS_I_SB(src); struct f2fs_lock_context lc; - size_t olen = len, dst_max_i_size = 0; - size_t dst_osize; + size_t olen = len; + loff_t dst_max_i_size = 0; + loff_t dst_osize, dst_end; int ret; if (file_in->f_path.mnt != file_out->f_path.mnt || @@ -3131,7 +3232,8 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) return -EINVAL; - if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst)) + if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst) || + IS_DEVICE_ALIASING(src) || IS_DEVICE_ALIASING(dst)) return -EOPNOTSUPP; if (pos_out < 0 || pos_in < 0) @@ -3140,8 +3242,6 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (src == dst) { if (pos_in == pos_out) return 0; - if (pos_out > pos_in && pos_out < pos_in + len) - return -EINVAL; } inode_lock(src); @@ -3167,6 +3267,8 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, goto out_unlock; if (len == 0) olen = len = src->i_size - pos_in; + if (src == dst && pos_out > pos_in && pos_out < pos_in + len) + goto out_unlock; if (pos_in + len == src->i_size) len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in; if (len == 0) { @@ -3175,8 +3277,15 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, } dst_osize = dst->i_size; - if (pos_out + olen > dst->i_size) - dst_max_i_size = pos_out + olen; + if (olen > LLONG_MAX - pos_out) + goto out_unlock; + dst_end = pos_out + olen; + if (dst_end > dst->i_size) { + ret = inode_newsize_ok(dst, dst_end); + if (ret) + goto out_unlock; + dst_max_i_size = dst_end; + } /* verify the end result is block aligned */ if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) || @@ -3612,6 +3721,241 @@ static int f2fs_ioc_get_dev_alias_file(struct file *filp, unsigned long arg) (u32 __user *)arg); } +static bool f2fs_get_dev_alias_extent(struct f2fs_sb_info *sbi, + struct dentry *dentry, + struct extent_info *ei) +{ + int i; + + for (i = 1; i < sbi->s_ndevs; i++) { + char *name = strrchr(FDEV(i).path, '/'); + + name = name ? name + 1 : FDEV(i).path; + if (strcmp(name, dentry->d_name.name)) + continue; + + ei->blk = FDEV(i).start_blk; + ei->len = FDEV(i).total_segments << sbi->log_blocks_per_seg; + ei->fofs = 0; + return true; + } + return false; +} + +static int f2fs_ioc_reserve_dev_alias(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; + struct extent_info ei; + struct cp_control cpc = { CP_SYNC, 0, 0, 0 }; + struct f2fs_lock_context lc, glc; + blkcnt_t count; + unsigned int start, end; + int type, err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + + err = mnt_want_write_file(filp); + if (err) + return err; + + inode_lock(inode); + + if (!IS_DEVICE_ALIASING(inode)) { + err = -EINVAL; + goto out_inode_unlock; + } + + if (F2FS_HAS_BLOCKS(inode)) { + err = 0; + goto out_inode_unlock; + } + + if (!f2fs_get_dev_alias_extent(sbi, filp->f_path.dentry, &ei)) { + f2fs_warn(sbi, "device alias file (%s, ino=%llu) has no matching device", + filp->f_path.dentry->d_name.name, + (unsigned long long)inode->i_ino); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE); + err = -EFSCORRUPTED; + goto out_inode_unlock; + } + + spin_lock(&sbi->stat_lock); + if (sbi->total_valid_block_count + ei.len > + get_available_block_count(sbi, inode, true)) { + spin_unlock(&sbi->stat_lock); + err = -ENOSPC; + goto out_inode_unlock; + } + sbi->alias_reserved_blocks += ei.len; + spin_unlock(&sbi->stat_lock); + + spin_lock(&FREE_I(sbi)->segmap_lock); + FDEV(f2fs_target_device_index(sbi, ei.blk)).is_reserving = true; + spin_unlock(&FREE_I(sbi)->segmap_lock); + + start = GET_SEGNO(sbi, ei.blk); + end = GET_SEGNO(sbi, ei.blk + ei.len - 1); + + /* Acquire gc_lock for victim reset, curseg resize, and range GC */ + f2fs_down_write_trace(&sbi->gc_lock, &glc); + + /* Reset the victim information to prevent GC from targeting the range */ + f2fs_reset_gc_victim_resource(sbi, start, end); + + /* Move out cursegs from the target range */ + for (type = CURSEG_HOT_DATA; type < NR_CURSEG_PERSIST_TYPE; type++) { + err = f2fs_allocate_segment_for_resize(sbi, type, start, end); + if (err) + goto out_gc_unlock; + } + + f2fs_lock_op(sbi, &lc); + + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + err = -EINVAL; + f2fs_unlock_op(sbi, &lc); + goto out_gc_unlock; + } + + /* do GC to move out valid blocks in the range all at once! */ + err = f2fs_gc_range(sbi, start, end, false, 0, false); + if (err) { + f2fs_unlock_op(sbi, &lc); + goto out_gc_unlock; + } + + count = ei.len; + err = inc_valid_block_count(sbi, inode, &count, false, true); + if (err) { + f2fs_unlock_op(sbi, &lc); + goto out_gc_unlock; + } + + write_lock(&et->lock); + et->largest = ei; + write_unlock(&et->lock); + clear_inode_flag(inode, FI_NO_EXTENT); + + f2fs_reserve_device_alias(sbi, ei.blk, ei.len); + + i_size_write(inode, (loff_t)ei.len << sbi->log_blocksize); + f2fs_update_inode_page(inode); + + spin_lock(&FREE_I(sbi)->segmap_lock); + FDEV(f2fs_target_device_index(sbi, ei.blk)).is_reserving = false; + spin_unlock(&FREE_I(sbi)->segmap_lock); + + f2fs_unlock_op(sbi, &lc); + f2fs_up_write_trace(&sbi->gc_lock, &glc); + + inode_unlock(inode); + mnt_drop_write_file(filp); + + return f2fs_write_checkpoint(sbi, &cpc); + +out_gc_unlock: + spin_lock(&sbi->stat_lock); + sbi->alias_reserved_blocks -= ei.len; + spin_unlock(&sbi->stat_lock); + + spin_lock(&FREE_I(sbi)->segmap_lock); + FDEV(f2fs_target_device_index(sbi, ei.blk)).is_reserving = false; + spin_unlock(&FREE_I(sbi)->segmap_lock); + f2fs_up_write_trace(&sbi->gc_lock, &glc); + +out_inode_unlock: + inode_unlock(inode); + mnt_drop_write_file(filp); + return err; +} + +static int f2fs_ioc_release_dev_alias(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; + struct extent_info ei = {0, }; + struct cp_control cpc = { CP_SYNC, 0, 0, 0 }; + struct f2fs_lock_context lc, glc; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + + err = mnt_want_write_file(filp); + if (err) + return err; + + inode_lock(inode); + + if (!IS_DEVICE_ALIASING(inode)) { + err = -EINVAL; + goto out_inode_unlock; + } + + if (!F2FS_HAS_BLOCKS(inode)) { + err = 0; + goto out_inode_unlock; + } + + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto out_inode_unlock; + + read_lock(&et->lock); + ei = et->largest; + read_unlock(&et->lock); + + f2fs_down_write_trace(&sbi->gc_lock, &glc); + f2fs_lock_op(sbi, &lc); + + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + err = -EINVAL; + f2fs_unlock_op(sbi, &lc); + f2fs_up_write_trace(&sbi->gc_lock, &glc); + goto out_inode_unlock; + } + + filemap_invalidate_lock(inode->i_mapping); + truncate_setsize(inode, 0); + + err = f2fs_truncate_blocks(inode, 0, false); + if (err) + i_size_write(inode, (loff_t)ei.len << sbi->log_blocksize); + filemap_invalidate_unlock(inode->i_mapping); + + if (err) { + f2fs_unlock_op(sbi, &lc); + f2fs_up_write_trace(&sbi->gc_lock, &glc); + goto out_inode_unlock; + } + + f2fs_update_inode_page(inode); + + f2fs_unlock_op(sbi, &lc); + f2fs_up_write_trace(&sbi->gc_lock, &glc); + + inode_unlock(inode); + mnt_drop_write_file(filp); + + return f2fs_write_checkpoint(sbi, &cpc); + +out_inode_unlock: + inode_unlock(inode); + mnt_drop_write_file(filp); + return err; +} + static int f2fs_ioc_io_prio(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -4037,7 +4381,7 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count, } ret = inc_valid_block_count(sbi, dn->inode, - &to_reserved, false); + &to_reserved, false, false); if (unlikely(ret)) return ret; @@ -4469,7 +4813,7 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) page_idx = folio_next_index(folio); } while (page_len < len); - do { + while (redirty_idx < page_idx) { folio = filemap_lock_folio(mapping, redirty_idx); /* It will never fail, when folio has pinned above */ @@ -4482,7 +4826,7 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) redirty_idx = folio_next_index(folio); folio_unlock(folio); folio_put_refs(folio, 2); - } while (redirty_idx < page_idx); + } return ret; } @@ -4738,8 +5082,14 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_compress_file(filp); case F2FS_IOC_GET_DEV_ALIAS_FILE: return f2fs_ioc_get_dev_alias_file(filp, arg); + case F2FS_IOC_GET_DEV_ALIAS_STATUS: + return f2fs_ioc_get_dev_alias_status(filp, arg); case F2FS_IOC_IO_PRIO: return f2fs_ioc_io_prio(filp, arg); + case F2FS_IOC_RESERVE_DEV_ALIAS: + return f2fs_ioc_reserve_dev_alias(filp); + case F2FS_IOC_RELEASE_DEV_ALIAS: + return f2fs_ioc_release_dev_alias(filp); default: return -ENOTTY; } @@ -4998,8 +5348,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from) if (err) return err; - f2fs_zero_post_eof_page(inode, - iocb->ki_pos + iov_iter_count(from), true); + err = f2fs_zero_post_eof_page(inode, + iocb->ki_pos + iov_iter_count(from), true, true); + if (err) + return err; return count; } @@ -5285,9 +5637,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) bool dio; bool may_need_sync = true; int preallocated; - const loff_t pos = iocb->ki_pos; - const ssize_t count = iov_iter_count(from); ssize_t ret; + loff_t bufio_start_pos; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { ret = -EIO; @@ -5308,15 +5659,17 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) inode_lock(inode); } + ret = f2fs_write_checks(iocb, from); + if (ret <= 0) + goto out_unlock; + if (f2fs_is_pinned_file(inode) && - !f2fs_overwrite_io(inode, pos, count)) { + !f2fs_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) { ret = -EIO; goto out_unlock; } - ret = f2fs_write_checks(iocb, from); - if (ret <= 0) - goto out_unlock; + bufio_start_pos = iocb->ki_pos; /* Determine whether we will do a direct write or a buffered write. */ dio = f2fs_should_use_dio(inode, iocb, from); @@ -5371,8 +5724,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) */ if (ret > 0 && !dio && (iocb->ki_flags & IOCB_DIRECT)) f2fs_flush_buffered_write(iocb->ki_filp->f_mapping, - orig_pos, - orig_pos + ret - 1); + bufio_start_pos, + bufio_start_pos + ret - 1); return ret; } @@ -5526,7 +5879,10 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_DECOMPRESS_FILE: case F2FS_IOC_COMPRESS_FILE: case F2FS_IOC_GET_DEV_ALIAS_FILE: + case F2FS_IOC_GET_DEV_ALIAS_STATUS: case F2FS_IOC_IO_PRIO: + case F2FS_IOC_RESERVE_DEV_ALIAS: + case F2FS_IOC_RELEASE_DEV_ALIAS: break; default: return -ENOIOCTLCMD; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ffaa7ba76a1b..0a00180c21dc 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -31,9 +31,9 @@ static unsigned int count_bits(const unsigned long *addr, static int gc_thread_func(void *data) { struct f2fs_sb_info *sbi = data; - struct f2fs_gc_kthread *gc_th = sbi->gc_thread; - wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; - wait_queue_head_t *fggc_wq = &sbi->gc_thread->fggc_wq; + struct f2fs_gc_kthread *gc_th = &sbi->gc_thread; + wait_queue_head_t *wq = &sbi->gc_thread.gc_wait_queue_head; + wait_queue_head_t *fggc_wq = &sbi->gc_thread.fggc_wq; unsigned int wait_ms; struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, @@ -193,13 +193,9 @@ static int gc_thread_func(void *data) int f2fs_start_gc_thread(struct f2fs_sb_info *sbi) { - struct f2fs_gc_kthread *gc_th; + struct f2fs_gc_kthread *gc_th = &sbi->gc_thread; dev_t dev = sbi->sb->s_bdev->bd_dev; - gc_th = f2fs_kmalloc(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL); - if (!gc_th) - return -ENOMEM; - gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME; gc_th->valid_thresh_ratio = DEF_GC_THREAD_VALID_THRESH_RATIO; gc_th->boost_gc_multiple = BOOST_GC_MULTIPLE; @@ -221,16 +217,14 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi) gc_th->gc_wake = false; - sbi->gc_thread = gc_th; - init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head); - init_waitqueue_head(&sbi->gc_thread->fggc_wq); - sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi, + init_waitqueue_head(&gc_th->gc_wait_queue_head); + init_waitqueue_head(&gc_th->fggc_wq); + gc_th->f2fs_gc_task = kthread_run(gc_thread_func, sbi, "f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(gc_th->f2fs_gc_task)) { int err = PTR_ERR(gc_th->f2fs_gc_task); - kfree(gc_th); - sbi->gc_thread = NULL; + gc_th->f2fs_gc_task = NULL; return err; } @@ -241,14 +235,14 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi) void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi) { - struct f2fs_gc_kthread *gc_th = sbi->gc_thread; + struct f2fs_gc_kthread *gc_th = &sbi->gc_thread; - if (!gc_th) + if (!gc_th->f2fs_gc_task) return; + kthread_stop(gc_th->f2fs_gc_task); + gc_th->f2fs_gc_task = NULL; wake_up_all(&gc_th->fggc_wq); - kfree(gc_th); - sbi->gc_thread = NULL; } static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type) @@ -316,7 +310,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->max_search = sbi->max_victim_search; /* let's select beginning hot/small space first. */ - if (f2fs_need_rand_seg(sbi)) { + if (f2fs_need_rand_seg_blk(sbi, type)) { p->offset = get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); SIT_I(sbi)->last_victim[p->gc_mode] = p->offset; @@ -796,7 +790,7 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, if (one_time) { p.one_time_gc = one_time; if (has_enough_free_secs(sbi, 0, NR_PERSISTENT_LOG)) - valid_thresh_ratio = sbi->gc_thread->valid_thresh_ratio; + valid_thresh_ratio = sbi->gc_thread.valid_thresh_ratio; } retry: @@ -1807,9 +1801,9 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, if (f2fs_sb_has_blkzoned(sbi) && !has_enough_free_blocks(sbi, - sbi->gc_thread->boost_zoned_gc_percent)) + sbi->gc_thread.boost_zoned_gc_percent)) window_granularity *= - sbi->gc_thread->boost_gc_multiple; + sbi->gc_thread.boost_gc_multiple; end_segno = start_segno + window_granularity; } @@ -2156,8 +2150,9 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) int f2fs_gc_range(struct f2fs_sb_info *sbi, unsigned int start_seg, unsigned int end_seg, - bool dry_run, unsigned int dry_run_sections) + bool dry_run, unsigned int dry_run_sections, bool lock) { + struct f2fs_lock_context lc; unsigned int segno; unsigned int gc_secs = dry_run_sections; @@ -2170,66 +2165,102 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi, .ilist = LIST_HEAD_INIT(gc_list.ilist), .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; + int err = 0; + + if (lock) + f2fs_down_write_trace(&sbi->gc_lock, &lc); /* * avoid migrating empty section, as it can be allocated by * log in parallel. */ if (!get_valid_blocks(sbi, segno, true)) - continue; + goto next; if (is_cursec(sbi, GET_SEC_FROM_SEG(sbi, segno))) - continue; + goto next; do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false); put_gc_inode(&gc_list); - if (!dry_run && get_valid_blocks(sbi, segno, true)) - return -EAGAIN; + /* reset all pinned status during fggc */ + f2fs_unpin_all_sections(sbi, true); + + if (!dry_run && get_valid_blocks(sbi, segno, true)) { + err = -EAGAIN; + goto next; + } if (dry_run && dry_run_sections && - !get_valid_blocks(sbi, segno, true) && --gc_secs == 0) - break; + !get_valid_blocks(sbi, segno, true)) { + --gc_secs; + goto next; + } if (fatal_signal_pending(current)) - return -ERESTARTSYS; + err = -ERESTARTSYS; +next: + if (lock) + f2fs_up_write_trace(&sbi->gc_lock, &lc); + if (err) + return err; + if (dry_run && dry_run_sections && !gc_secs) + return 0; } return 0; } +void f2fs_reset_gc_victim_resource(struct f2fs_sb_info *sbi, + unsigned int start, unsigned int end) +{ + int i; + + mutex_lock(&DIRTY_I(sbi)->seglist_lock); + for (i = 0; i < MAX_GC_POLICY; i++) + if (SIT_I(sbi)->last_victim[i] >= start && + SIT_I(sbi)->last_victim[i] <= end) + SIT_I(sbi)->last_victim[i] = 0; + + for (i = BG_GC; i <= FG_GC; i++) + if (sbi->next_victim_seg[i] >= start && + sbi->next_victim_seg[i] <= end) + sbi->next_victim_seg[i] = NULL_SEGNO; + mutex_unlock(&DIRTY_I(sbi)->seglist_lock); +} + static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int secs, bool dry_run) { - unsigned int next_inuse, start, end; + unsigned int secno, next_inuse, start, end, end_secno; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; - int gc_mode, gc_type; + unsigned int freed_secs = 0; int err = 0; int type; - /* Force block allocation for GC */ MAIN_SECS(sbi) -= secs; start = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi); end = MAIN_SEGS(sbi) - 1; + end_secno = GET_SEC_FROM_SEG(sbi, end); - mutex_lock(&DIRTY_I(sbi)->seglist_lock); - for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++) - if (SIT_I(sbi)->last_victim[gc_mode] >= start) - SIT_I(sbi)->last_victim[gc_mode] = 0; + f2fs_reset_gc_victim_resource(sbi, start, end); - for (gc_type = BG_GC; gc_type <= FG_GC; gc_type++) - if (sbi->next_victim_seg[gc_type] >= start) - sbi->next_victim_seg[gc_type] = NULL_SEGNO; - mutex_unlock(&DIRTY_I(sbi)->seglist_lock); + spin_lock(&FREE_I(sbi)->segmap_lock); + for (secno = MAIN_SECS(sbi); secno <= end_secno; secno++) { + if (!test_bit(secno, FREE_I(sbi)->free_secmap)) + freed_secs++; + } + FREE_I(sbi)->free_sections -= freed_secs; + spin_unlock(&FREE_I(sbi)->segmap_lock); /* Move out cursegs from the target range */ - for (type = CURSEG_HOT_DATA; type < NR_CURSEG_PERSIST_TYPE; type++) { + for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++) { err = f2fs_allocate_segment_for_resize(sbi, type, start, end); if (err) goto out; } /* do GC to move out valid blocks in the range */ - err = f2fs_gc_range(sbi, start, end, dry_run, 0); + err = f2fs_gc_range(sbi, start, end, dry_run, 0, false); if (err || dry_run) goto out; @@ -2245,6 +2276,9 @@ static int free_segment_range(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, 1); } out: + spin_lock(&FREE_I(sbi)->segmap_lock); + FREE_I(sbi)->free_sections += freed_secs; + spin_unlock(&FREE_I(sbi)->segmap_lock); MAIN_SECS(sbi) += secs; return err; } @@ -2422,7 +2456,7 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count) set_sbi_flag(sbi, SBI_IS_RESIZEFS); err = free_segment_range(sbi, secs, false); if (err) - goto recover_out; + goto recover_user_blocks; update_sb_metadata(sbi, -secs); @@ -2444,11 +2478,14 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count) f2fs_commit_super(sbi, false); } recover_out: - clear_sbi_flag(sbi, SBI_IS_RESIZEFS); if (err) { + f2fs_bug_on(sbi, err == -EAGAIN); set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_err(sbi, "resize_fs failed, should run fsck to repair!"); - + } +recover_user_blocks: + clear_sbi_flag(sbi, SBI_IS_RESIZEFS); + if (err) { spin_lock(&sbi->stat_lock); sbi->user_block_count += shrunk_blocks; spin_unlock(&sbi->stat_lock); diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index 6c4d4567571e..b015742fb455 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -45,32 +45,7 @@ #define NR_GC_CHECKPOINT_SECS (3) /* data/node/dentry sections */ -struct f2fs_gc_kthread { - struct task_struct *f2fs_gc_task; - wait_queue_head_t gc_wait_queue_head; - /* for gc sleep time */ - unsigned int urgent_sleep_time; - unsigned int min_sleep_time; - unsigned int max_sleep_time; - unsigned int no_gc_sleep_time; - - /* for changing gc mode */ - bool gc_wake; - - /* for GC_MERGE mount option */ - wait_queue_head_t fggc_wq; /* - * caller of f2fs_balance_fs() - * will wait on this wait queue. - */ - - /* for gc control for zoned devices */ - unsigned int no_zoned_gc_percent; - unsigned int boost_zoned_gc_percent; - unsigned int valid_thresh_ratio; - unsigned int boost_gc_multiple; - unsigned int boost_gc_greedy; -}; struct gc_inode_list { struct list_head ilist; @@ -197,6 +172,6 @@ static inline bool need_to_boost_gc(struct f2fs_sb_info *sbi) { if (f2fs_sb_has_blkzoned(sbi)) return !has_enough_free_blocks(sbi, - sbi->gc_thread->boost_zoned_gc_percent); + sbi->gc_thread.boost_zoned_gc_percent); return has_enough_invalid_blocks(sbi); } diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index e2f7bedf1552..aec06fb4fd76 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -732,7 +732,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, f2fs_folio_put(folio, true); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); - f2fs_mark_inode_dirty_sync(dir, false); + f2fs_mark_inode_dirty_sync(dir, true); if (inode) f2fs_drop_nlink(dir, inode); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index c95e0b126da4..96cc0e777567 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -24,6 +25,18 @@ extern const struct address_space_operations f2fs_compress_aops; #endif +#define NUM_PREALLOC_EVICT_INODE_WORK 8 + +static struct kmem_cache *evict_inode_work_cache; +static mempool_t *evict_inode_work_pool; + +struct evict_inode_work { + struct work_struct work; + struct f2fs_sb_info *sbi; + nid_t ino; + unsigned int add_ino_entry_bits; +}; + void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) { if (is_inode_flag_set(inode, FI_NEW_INODE)) @@ -637,6 +650,9 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + + /* Let's prepare APPEND/UPDATE_INO before future access. */ + flush_workqueue(sbi->evict_wq); } else if (S_ISLNK(inode->i_mode)) { if (file_is_encrypt(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; @@ -854,16 +870,32 @@ void f2fs_remove_donate_inode(struct inode *inode) spin_unlock(&sbi->inode_lock[DONATE_INODE]); } +static void f2fs_record_inode_state(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int bits) +{ + if (bits & BIT(APPEND_INO)) + f2fs_add_ino_entry(sbi, ino, APPEND_INO); + if (bits & BIT(UPDATE_INO)) + f2fs_add_ino_entry(sbi, ino, UPDATE_INO); +} + +static void f2fs_evict_inode_work(struct work_struct *work) +{ + struct evict_inode_work *ew = + container_of(work, struct evict_inode_work, work); + + f2fs_record_inode_state(ew->sbi, ew->ino, ew->add_ino_entry_bits); + + mempool_free(ew, evict_inode_work_pool); +} + /* - * Called at the last iput() if i_nlink is zero + * Return true, if we shouldn't go through post_evict_inode. */ -void f2fs_evict_inode(struct inode *inode) +static bool f2fs_pre_evict_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - nid_t xnid = fi->i_xattr_nid; - int err = 0; - bool freeze_protected = false; f2fs_abort_atomic_write(inode, true); @@ -883,13 +915,13 @@ void f2fs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); if ((inode->i_nlink || is_bad_inode(inode)) && - test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode)) + test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode)) f2fs_invalidate_compress_pages(sbi, inode->i_ino); if (inode->i_ino == F2FS_NODE_INO(sbi) || - inode->i_ino == F2FS_META_INO(sbi) || - inode->i_ino == F2FS_COMPRESS_INO(sbi)) - goto out_clear; + inode->i_ino == F2FS_META_INO(sbi) || + inode->i_ino == F2FS_COMPRESS_INO(sbi)) + return true; f2fs_bug_on(sbi, get_dirty_pages(inode)); f2fs_remove_dirty_inode(inode); @@ -898,14 +930,18 @@ void f2fs_evict_inode(struct inode *inode) if (!IS_DEVICE_ALIASING(inode)) f2fs_destroy_extent_tree(inode); - if (inode->i_nlink || is_bad_inode(inode)) - goto no_delete; + return false; +} - err = f2fs_dquot_initialize(inode); - if (err) { - err = 0; +static void f2fs_delete_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + bool freeze_protected = false; + struct f2fs_lock_context lc; + int err = 0; + + if (f2fs_dquot_initialize(inode)) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); - } f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO); f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); @@ -924,30 +960,30 @@ void f2fs_evict_inode(struct inode *inode) if (time_to_inject(sbi, FAULT_EVICT_INODE)) err = -EIO; - if (!err) { - struct f2fs_lock_context lc; + if (err) + goto error_check; - f2fs_lock_op(sbi, &lc); - err = f2fs_remove_inode_page(inode); - f2fs_unlock_op(sbi, &lc); - if (err == -ENOENT) { - err = 0; + f2fs_lock_op(sbi, &lc); + err = f2fs_remove_inode_page(inode); + f2fs_unlock_op(sbi, &lc); - /* - * in fuzzed image, another node may has the same - * block address as inode's, if it was truncated - * previously, truncation of inode node will fail. - */ - if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { - f2fs_warn(F2FS_I_SB(inode), - "f2fs_evict_inode: inconsistent node id, ino:%llu", - inode->i_ino); - f2fs_inode_synced(inode); - set_sbi_flag(sbi, SBI_NEED_FSCK); - } + if (err == -ENOENT) { + err = 0; + + /* + * in fuzzed image, another node may has the same + * block address as inode's, if it was truncated + * previously, truncation of inode node will fail. + */ + if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { + f2fs_warn(F2FS_I_SB(inode), + "f2fs_evict_inode: inconsistent node id, ino:%llu", + inode->i_ino); + f2fs_inode_synced(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); } } - +error_check: /* give more chances, if ENOMEM case */ if (err == -ENOMEM) { err = 0; @@ -957,27 +993,38 @@ void f2fs_evict_inode(struct inode *inode) if (IS_DEVICE_ALIASING(inode)) f2fs_destroy_extent_tree(inode); - if (err) { - f2fs_update_inode_page(inode); - if (dquot_initialize_needed(inode)) - set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + if (!err) + goto unfreeze_out; - /* - * If both f2fs_truncate() and f2fs_update_inode_page() failed - * due to fuzzed corrupted inode, call f2fs_inode_synced() to - * avoid triggering later f2fs_bug_on(). - */ - if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { - f2fs_warn(sbi, - "f2fs_evict_inode: inode is dirty, ino:%llu", - inode->i_ino); - f2fs_inode_synced(inode); - set_sbi_flag(sbi, SBI_NEED_FSCK); - } + f2fs_update_inode_page(inode); + + if (dquot_initialize_needed(inode)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + + /* + * If both f2fs_truncate() and f2fs_update_inode_page() failed + * due to fuzzed corrupted inode, call f2fs_inode_synced() to + * avoid triggering later f2fs_bug_on(). + */ + if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { + f2fs_warn(sbi, + "f2fs_evict_inode: inode is dirty, ino:%llu", + inode->i_ino); + f2fs_inode_synced(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); } +unfreeze_out: if (freeze_protected) sb_end_intwrite(inode->i_sb); -no_delete: +} + +static void f2fs_post_evict_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + nid_t xnid = fi->i_xattr_nid; + unsigned int record_bits = 0; + dquot_drop(inode); stat_dec_inline_xattr(inode); @@ -1003,12 +1050,32 @@ void f2fs_evict_inode(struct inode *inode) inode->i_ino); if (xnid) invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); - if (inode->i_nlink) { - if (is_inode_flag_set(inode, FI_APPEND_WRITE)) - f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO); - if (is_inode_flag_set(inode, FI_UPDATE_WRITE)) - f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO); + + if (!inode->i_nlink) + goto skip_record; + + if (is_inode_flag_set(inode, FI_APPEND_WRITE)) + record_bits = BIT(APPEND_INO); + if (is_inode_flag_set(inode, FI_UPDATE_WRITE)) + record_bits = BIT(UPDATE_INO); + + if (!record_bits) + goto skip_record; + + /* Let's do this in workqueue out of the direct reclaim path. */ + if (current_is_kswapd()) { + f2fs_record_inode_state(sbi, inode->i_ino, record_bits); + } else { + struct evict_inode_work *ew = + mempool_alloc(evict_inode_work_pool, GFP_NOFS); + + ew->sbi = sbi; + ew->ino = inode->i_ino; + ew->add_ino_entry_bits = record_bits; + INIT_WORK(&ew->work, f2fs_evict_inode_work); + queue_work(sbi->evict_wq, &ew->work); } +skip_record: if (is_inode_flag_set(inode, FI_FREE_NID)) { f2fs_alloc_nid_failed(sbi, inode->i_ino); clear_inode_flag(inode, FI_FREE_NID); @@ -1019,13 +1086,29 @@ void f2fs_evict_inode(struct inode *inode) * In that case, f2fs_check_nid_range() is enough to give a clue. */ } -out_clear: +} + +/* + * Called at the last iput() if i_nlink is zero + */ +void f2fs_evict_inode(struct inode *inode) +{ + if (f2fs_pre_evict_inode(inode)) + goto clear_out; + + if (!inode->i_nlink && !is_bad_inode(inode)) + f2fs_delete_inode(inode); + + f2fs_post_evict_inode(inode); + +clear_out: fscrypt_put_encryption_info(inode); clear_inode(inode); } /* caller should call f2fs_lock_op() */ -void f2fs_handle_failed_inode(struct inode *inode, struct f2fs_lock_context *lc) +void f2fs_handle_failed_inode(struct inode *inode, + struct f2fs_lock_context *lc, bool orphan_free) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct node_info ni; @@ -1047,6 +1130,9 @@ void f2fs_handle_failed_inode(struct inode *inode, struct f2fs_lock_context *lc) /* don't make bad inode, since it becomes a regular file. */ unlock_new_inode(inode); + if (!orphan_free) + goto out; + /* * Note: we should add inode to orphan list before f2fs_unlock_op() * so we can prevent losing this orphan when encoutering checkpoint @@ -1079,3 +1165,29 @@ void f2fs_handle_failed_inode(struct inode *inode, struct f2fs_lock_context *lc) /* iput will drop the inode object */ iput(inode); } + +int __init f2fs_init_evict_inode_work(void) +{ + evict_inode_work_cache = + kmem_cache_create("f2fs_evict_inode_work", + sizeof(struct evict_inode_work), 0, 0, NULL); + if (!evict_inode_work_cache) + goto fail; + evict_inode_work_pool = + mempool_create_slab_pool(NUM_PREALLOC_EVICT_INODE_WORK, + evict_inode_work_cache); + if (!evict_inode_work_pool) + goto fail_free_cache; + return 0; + +fail_free_cache: + kmem_cache_destroy(evict_inode_work_cache); +fail: + return -ENOMEM; +} + +void f2fs_destroy_evict_inode_work(void) +{ + mempool_destroy(evict_inode_work_pool); + kmem_cache_destroy(evict_inode_work_cache); +} diff --git a/fs/f2fs/iostat.c b/fs/f2fs/iostat.c index ae265e3e9b2c..12d4e18a6a50 100644 --- a/fs/f2fs/iostat.c +++ b/fs/f2fs/iostat.c @@ -332,6 +332,12 @@ void f2fs_destroy_iostat_processing(void) int f2fs_init_iostat(struct f2fs_sb_info *sbi) { + /* + * The f2fs_iostat tracepoint emits a fixed number of read folio order + * buckets; make sure every order fits so none is silently dropped. + */ + BUILD_BUG_ON(NR_PAGE_ORDERS > F2FS_IOSTAT_RD_FOLIO_ORDERS); + /* init iostat info */ spin_lock_init(&sbi->iostat_lock); spin_lock_init(&sbi->iostat_lat_lock); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 5ae647a352aa..ff86ee07290d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -402,13 +402,16 @@ static int f2fs_create(struct mnt_idmap *idmap, struct inode *dir, d_instantiate_new(dentry, inode); - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(dir)) { + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return err; + } f2fs_balance_fs(sbi, true); return 0; out: - f2fs_handle_failed_inode(inode, &lc); + f2fs_handle_failed_inode(inode, &lc, true); return err; } @@ -425,6 +428,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; + if (IS_DEVICE_ALIASING(inode)) + return -EPERM; + err = fscrypt_prepare_link(old_dentry, dir, dentry); if (err) return err; @@ -452,8 +458,11 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, d_instantiate(dentry, inode); - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(dir)) { + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return err; + } return 0; out: clear_inode_flag(inode, FI_INC_LINK); @@ -557,35 +566,31 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, return ERR_PTR(err); } -static int f2fs_unlink(struct inode *dir, struct dentry *dentry) +static int __do_unlink(struct inode *dir, struct inode *inode, + const struct qstr *name) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); - struct inode *inode = d_inode(dentry); struct f2fs_dir_entry *de; struct f2fs_lock_context lc; struct folio *folio; int err; - trace_f2fs_unlink_enter(dir, dentry); + if (IS_DEVICE_ALIASING(inode)) + return -EPERM; - if (unlikely(f2fs_cp_error(sbi))) { - err = -EIO; - goto out; - } + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; err = f2fs_dquot_initialize(dir); if (err) - goto out; + return err; err = f2fs_dquot_initialize(inode); if (err) - goto out; + return err; - de = f2fs_find_entry(dir, &dentry->d_name, &folio); - if (!de) { - if (IS_ERR(folio)) - err = PTR_ERR(folio); - goto out; - } + de = f2fs_find_entry(dir, name, &folio); + if (!de) + return IS_ERR(folio) ? PTR_ERR(folio) : 0; if (unlikely(inode->i_nlink == 0)) { f2fs_warn(sbi, "%s: inode (ino=%llx) has zero i_nlink", @@ -603,11 +608,28 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) err = f2fs_acquire_orphan_inode(sbi); if (err) { f2fs_unlock_op(sbi, &lc); - f2fs_folio_put(folio, false); - goto out; + goto err_out; } f2fs_delete_entry(de, folio, dir, inode); f2fs_unlock_op(sbi, &lc); + return 0; + +corrupted: + err = -EFSCORRUPTED; + set_sbi_flag(sbi, SBI_NEED_FSCK); +err_out: + f2fs_folio_put(folio, false); + return err; +} + +static int f2fs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err; + + trace_f2fs_unlink_enter(dir, dentry); + err = __do_unlink(dir, d_inode(dentry), &dentry->d_name); + if (err) + goto out; /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid @@ -619,15 +641,9 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) d_invalidate(dentry); if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); - - goto out; -corrupted: - err = -EFSCORRUPTED; - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_folio_put(folio, false); + err = f2fs_sync_fs(F2FS_I_SB(dir)->sb, 1); out: - trace_f2fs_unlink_exit(inode, err); + trace_f2fs_unlink_exit(d_inode(dentry), err); return err; } @@ -654,6 +670,8 @@ static int f2fs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode; size_t len = strlen(symname); struct fscrypt_str disk_link; + bool orphan_free = true; + int ret = -EAGAIN; int err; if (unlikely(f2fs_cp_error(sbi))) @@ -684,17 +702,19 @@ static int f2fs_symlink(struct mnt_idmap *idmap, struct inode *dir, f2fs_lock_op(sbi, &lc); err = f2fs_add_link(dentry, inode); if (err) - goto out_f2fs_handle_failed_inode; + goto free_inode; f2fs_unlock_op(sbi, &lc); f2fs_alloc_nid_done(sbi, inode->i_ino); + /* Write the symlink path to the new inode. */ err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link); if (err) - goto err_out; + goto unlink_free_inode; err = page_symlink(inode, disk_link.name, disk_link.len); + if (err) + goto unlink_free_inode; -err_out: d_instantiate_new(dentry, inode); /* @@ -706,25 +726,29 @@ static int f2fs_symlink(struct mnt_idmap *idmap, struct inode *dir, * If the symlink path is stored into inline_data, there is no * performance regression. */ - if (!err) { - filemap_write_and_wait_range(inode->i_mapping, 0, - disk_link.len - 1); - - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); - } else { - f2fs_unlink(dir, dentry); - } + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + disk_link.len - 1); + if (!ret && IS_DIRSYNC(dir)) + err = f2fs_sync_fs(sbi->sb, 1); f2fs_balance_fs(sbi, true); - goto out_free_encrypted_link; - -out_f2fs_handle_failed_inode: - f2fs_handle_failed_inode(inode, &lc); -out_free_encrypted_link: +out: if (disk_link.name != (unsigned char *)symname) kfree(disk_link.name); return err; + +unlink_free_inode: + ret = __do_unlink(dir, inode, &dentry->d_name); + if (ret) { + /* Give up and leave a broken symlink. */ + d_instantiate_new(dentry, inode); + goto out; + } + orphan_free = false; + f2fs_lock_op(sbi, &lc); +free_inode: + f2fs_handle_failed_inode(inode, &lc, orphan_free); + goto out; } static struct dentry *f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, @@ -762,15 +786,18 @@ static struct dentry *f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, d_instantiate_new(dentry, inode); - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(dir)) { + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return ERR_PTR(err); + } f2fs_balance_fs(sbi, true); return NULL; out_fail: clear_inode_flag(inode, FI_INC_LINK); - f2fs_handle_failed_inode(inode, &lc); + f2fs_handle_failed_inode(inode, &lc, true); return ERR_PTR(err); } @@ -817,13 +844,16 @@ static int f2fs_mknod(struct mnt_idmap *idmap, struct inode *dir, d_instantiate_new(dentry, inode); - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(dir)) { + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return err; + } f2fs_balance_fs(sbi, true); return 0; out: - f2fs_handle_failed_inode(inode, &lc); + f2fs_handle_failed_inode(inode, &lc, true); return err; } @@ -894,7 +924,7 @@ static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, release_out: f2fs_release_orphan_inode(sbi); out: - f2fs_handle_failed_inode(inode, &lc); + f2fs_handle_failed_inode(inode, &lc, true); return err; } @@ -946,6 +976,9 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, bool old_is_dir = S_ISDIR(old_inode->i_mode); int err; + if (IS_DEVICE_ALIASING(old_inode)) + return -EPERM; + if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) @@ -1016,6 +1049,10 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } if (new_inode) { + if (IS_DEVICE_ALIASING(new_inode)) { + err = -EPERM; + goto out_dir; + } err = -ENOTEMPTY; if (old_is_dir && !f2fs_empty_dir(new_inode)) @@ -1076,7 +1113,7 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, f2fs_up_write(&F2FS_I(old_inode)->i_sem); inode_set_ctime_current(old_inode); - f2fs_mark_inode_dirty_sync(old_inode, false); + f2fs_mark_inode_dirty_sync(old_inode, true); f2fs_delete_entry(old_entry, old_folio, old_dir, NULL); old_folio = NULL; @@ -1110,8 +1147,11 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, f2fs_unlock_op(sbi, &lc); - if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) { + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return err; + } f2fs_update_time(sbi, REQ_TIME); return 0; @@ -1143,6 +1183,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, int old_nlink = 0, new_nlink = 0; int err; + if (IS_DEVICE_ALIASING(old_inode) || IS_DEVICE_ALIASING(new_inode)) + return -EPERM; + if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) @@ -1246,7 +1289,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_i_links_write(old_dir, old_nlink > 0); f2fs_up_write(&F2FS_I(old_dir)->i_sem); } - f2fs_mark_inode_dirty_sync(old_dir, false); + f2fs_mark_inode_dirty_sync(old_dir, true); /* update directory entry info of new dir inode */ f2fs_set_link(new_dir, new_entry, new_folio, old_inode); @@ -1265,7 +1308,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_i_links_write(new_dir, new_nlink > 0); f2fs_up_write(&F2FS_I(new_dir)->i_sem); } - f2fs_mark_inode_dirty_sync(new_dir, false); + f2fs_mark_inode_dirty_sync(new_dir, true); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); @@ -1274,8 +1317,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_unlock_op(sbi, &lc); - if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) { + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return err; + } f2fs_update_time(sbi, REQ_TIME); return 0; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 38917e4a7319..86c2e67e43b6 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -401,15 +401,16 @@ bool f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; bool need = false; + struct f2fs_lock_context lc; - f2fs_down_read(&nm_i->nat_tree_lock); + f2fs_down_read_trace(&nm_i->nat_tree_lock, &lc); e = __lookup_nat_cache(nm_i, nid, false); if (e) { if (!get_nat_flag(e, IS_CHECKPOINTED) && !get_nat_flag(e, HAS_FSYNCED_INODE)) need = true; } - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); return need; } @@ -418,12 +419,13 @@ bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; bool is_cp = true; + struct f2fs_lock_context lc; - f2fs_down_read(&nm_i->nat_tree_lock); + f2fs_down_read_trace(&nm_i->nat_tree_lock, &lc); e = __lookup_nat_cache(nm_i, nid, false); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); return is_cp; } @@ -432,16 +434,16 @@ bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; bool need_update = true; - struct f2fs_lock_context lc; + struct f2fs_lock_context lc, nlc; f2fs_down_read_trace(&sbi->node_write, &lc); - f2fs_down_read(&nm_i->nat_tree_lock); + f2fs_down_read_trace(&nm_i->nat_tree_lock, &nlc); e = __lookup_nat_cache(nm_i, ino, false); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &nlc); f2fs_up_read_trace(&sbi->node_write, &lc); return need_update; } @@ -452,6 +454,7 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *new, *e; + struct f2fs_lock_context lc; /* Let's mitigate lock contention of nat_tree_lock during checkpoint */ if (f2fs_rwsem_is_locked(&sbi->cp_global_sem)) @@ -461,7 +464,7 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, if (!new) return; - f2fs_down_write(&nm_i->nat_tree_lock); + f2fs_down_write_trace(&nm_i->nat_tree_lock, &lc); e = __lookup_nat_cache(nm_i, nid, false); if (!e) e = __init_nat_entry(nm_i, new, ne, false, false); @@ -470,7 +473,7 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, nat_get_blkaddr(e) != le32_to_cpu(ne->block_addr) || nat_get_version(e) != ne->version); - f2fs_up_write(&nm_i->nat_tree_lock); + f2fs_up_write_trace(&nm_i->nat_tree_lock, &lc); if (e != new) __free_nat_entry(new); } @@ -482,8 +485,9 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, struct nat_entry *e; struct nat_entry *new = __alloc_nat_entry(sbi, ni->nid, true); bool init_dirty = false; + struct f2fs_lock_context lc; - f2fs_down_write(&nm_i->nat_tree_lock); + f2fs_down_write_trace(&nm_i->nat_tree_lock, &lc); e = __lookup_nat_cache(nm_i, ni->nid, true); if (!e) { init_dirty = true; @@ -533,15 +537,16 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - f2fs_up_write(&nm_i->nat_tree_lock); + f2fs_up_write_trace(&nm_i->nat_tree_lock, &lc); } int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; + struct f2fs_lock_context lc; - if (!f2fs_down_write_trylock(&nm_i->nat_tree_lock)) + if (!f2fs_down_write_trylock_trace(&nm_i->nat_tree_lock, &lc)) return 0; spin_lock(&nm_i->nat_list_lock); @@ -563,7 +568,7 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) } spin_unlock(&nm_i->nat_list_lock); - f2fs_up_write(&nm_i->nat_tree_lock); + f2fs_up_write_trace(&nm_i->nat_tree_lock, &lc); return nr - nr_shrink; } @@ -581,18 +586,19 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, pgoff_t index; int i; bool need_cache = true; + struct f2fs_lock_context lc; ni->flag = 0; ni->nid = nid; retry: /* Check nat cache */ - f2fs_down_read(&nm_i->nat_tree_lock); + f2fs_down_read_trace(&nm_i->nat_tree_lock, &lc); e = __lookup_nat_cache(nm_i, nid, false); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); if (IS_ENABLED(CONFIG_F2FS_CHECK_FS)) { need_cache = false; goto sanity_check; @@ -610,7 +616,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, down_read(&curseg->journal_rwsem); } else if (f2fs_rwsem_is_contended(&nm_i->nat_tree_lock) || !down_read_trylock(&curseg->journal_rwsem)) { - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); goto retry; } @@ -621,13 +627,13 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, } up_read(&curseg->journal_rwsem); if (i >= 0) { - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); goto sanity_check; } /* Fill node_info from nat page */ index = current_nat_addr(sbi, nid); - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); folio = f2fs_get_meta_folio(sbi, index); if (IS_ERR(folio)) @@ -660,6 +666,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, __builtin_return_address(0), ni->ino, ni->nid, ni->blk_addr, ni->version, ni->flag); f2fs_handle_error(sbi, ERROR_INCONSISTENT_NAT); + return -EFSCORRUPTED; } /* cache nat entry */ @@ -1617,7 +1624,7 @@ static struct folio *__get_node_folio(struct f2fs_sb_info *sbi, pgoff_t nid, if (!err) return folio; out_err: - folio_clear_uptodate(folio); + clear_node_folio_dirty(folio); out_put_err: /* ENOENT comes from read_node_folio which is not an error. */ if (err != -ENOENT) @@ -1789,7 +1796,7 @@ static bool __write_node_folio(struct folio *folio, bool atomic, bool do_fsync, /* get old block addr of this node page */ nid = nid_of_node(folio); - if (f2fs_sanity_check_node_footer(sbi, folio, nid, + if (f2fs_sanity_check_node_footer(sbi, folio, folio->index, NODE_TYPE_REGULAR, false)) { fserror_report_metadata(sbi->sb, -EFSCORRUPTED, GFP_NOFS); f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_CORRUPTED_NID); @@ -2009,6 +2016,11 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx", ino, last_folio->index); folio_lock(last_folio); + if (unlikely(!is_node_folio(last_folio))) { + f2fs_folio_put(last_folio, true); + ret = -EAGAIN; + goto out; + } f2fs_folio_wait_writeback(last_folio, NODE, true, true); folio_mark_dirty(last_folio); folio_unlock(last_folio); @@ -2566,8 +2578,9 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi) struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int i, idx; nid_t nid; + struct f2fs_lock_context lc; - f2fs_down_read(&nm_i->nat_tree_lock); + f2fs_down_read_trace(&nm_i->nat_tree_lock, &lc); for (i = 0; i < nm_i->nat_blocks; i++) { if (!test_bit_le(i, nm_i->nat_block_bitmap)) @@ -2590,7 +2603,7 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi) out: scan_curseg_cache(sbi); - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); } static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, @@ -2599,6 +2612,7 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, struct f2fs_nm_info *nm_i = NM_I(sbi); int i = 0, ret; nid_t nid = nm_i->next_scan_nid; + struct f2fs_lock_context lc; if (unlikely(nid >= nm_i->max_nid)) nid = 0; @@ -2625,7 +2639,7 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); - f2fs_down_read(&nm_i->nat_tree_lock); + f2fs_down_read_trace(&nm_i->nat_tree_lock, &lc); while (1) { if (!test_bit_le(NAT_BLOCK_OFFSET(nid), @@ -2641,7 +2655,7 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, } if (ret) { - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); if (ret == -EFSCORRUPTED) { f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); @@ -2668,7 +2682,7 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, /* find free nids from current sum_pages */ scan_curseg_cache(sbi); - f2fs_up_read(&nm_i->nat_tree_lock); + f2fs_up_read_trace(&nm_i->nat_tree_lock, &lc); f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -3205,21 +3219,22 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) nid_t set_idx = 0; LIST_HEAD(sets); int err = 0; + struct f2fs_lock_context lc; /* * during unmount, let's flush nat_bits before checking * nat_cnt[DIRTY_NAT]. */ if (enabled_nat_bits(sbi, cpc)) { - f2fs_down_write(&nm_i->nat_tree_lock); + f2fs_down_write_trace(&nm_i->nat_tree_lock, &lc); remove_nats_in_journal(sbi); - f2fs_up_write(&nm_i->nat_tree_lock); + f2fs_up_write_trace(&nm_i->nat_tree_lock, &lc); } if (!nm_i->nat_cnt[DIRTY_NAT]) return 0; - f2fs_down_write(&nm_i->nat_tree_lock); + f2fs_down_write_trace(&nm_i->nat_tree_lock, &lc); /* * if there are no enough space in journal to store dirty nat @@ -3260,7 +3275,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) break; } - f2fs_up_write(&nm_i->nat_tree_lock); + f2fs_up_write_trace(&nm_i->nat_tree_lock, &lc); /* Allow dirty nats by node block allocation in write_begin */ return err; @@ -3379,7 +3394,8 @@ static int init_node_manager(struct f2fs_sb_info *sbi) mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->nid_list_lock); - init_f2fs_rwsem(&nm_i->nat_tree_lock); + init_f2fs_rwsem_trace(&nm_i->nat_tree_lock, sbi, + LOCK_NAME_NAT_TREE_LOCK); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -3471,6 +3487,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) struct nat_entry_set **setvec = (struct nat_entry_set **)vec; nid_t nid = 0; unsigned int found; + struct f2fs_lock_context lc; if (!nm_i) return; @@ -3489,7 +3506,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) spin_unlock(&nm_i->nid_list_lock); /* destroy nat cache */ - f2fs_down_write(&nm_i->nat_tree_lock); + f2fs_down_write_trace(&nm_i->nat_tree_lock, &lc); while ((found = __gang_lookup_nat_cache(nm_i, nid, NAT_VEC_SIZE, natvec))) { unsigned idx; @@ -3520,7 +3537,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) kmem_cache_free(nat_entry_set_slab, setvec[idx]); } } - f2fs_up_write(&nm_i->nat_tree_lock); + f2fs_up_write_trace(&nm_i->nat_tree_lock, &lc); kvfree(nm_i->nat_block_bitmap); if (nm_i->free_nid_bitmap) { diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 89af8407b667..aaa5227739c8 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -116,18 +116,26 @@ static void del_fsync_inode(struct fsync_inode_entry *entry, int drop) } static int init_recovered_filename(const struct inode *dir, + struct inode *inode, struct f2fs_inode *raw_inode, struct f2fs_filename *fname, struct qstr *usr_fname) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; memset(fname, 0, sizeof(*fname)); fname->disk_name.len = le32_to_cpu(raw_inode->i_namelen); fname->disk_name.name = raw_inode->i_name; - if (WARN_ON(fname->disk_name.len > F2FS_NAME_LEN)) - return -ENAMETOOLONG; + if (unlikely(!fname->disk_name.len || + fname->disk_name.len > F2FS_NAME_LEN)) { + f2fs_err(sbi, "invalid recovered filename length %u for ino %llu", + fname->disk_name.len, inode->i_ino); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE); + return -EFSCORRUPTED; + } if (!IS_ENCRYPTED(dir)) { usr_fname->name = fname->disk_name.name; @@ -158,6 +166,22 @@ static int init_recovered_filename(const struct inode *dir, return 0; } +static const char *recover_printable_name(struct inode *inode, + struct f2fs_inode *raw, + int *name_len) +{ + static const char encrypted_name[] = ""; + + if (file_enc_name(inode)) { + *name_len = sizeof(encrypted_name) - 1; + return encrypted_name; + } + + *name_len = min_t(unsigned int, le32_to_cpu(raw->i_namelen), + F2FS_NAME_LEN); + return raw->i_name; +} + static int recover_dentry(struct inode *inode, struct folio *ifolio, struct list_head *dir_list) { @@ -170,7 +194,8 @@ static int recover_dentry(struct inode *inode, struct folio *ifolio, struct inode *dir, *einode; struct fsync_inode_entry *entry; int err = 0; - char *name; + const char *name; + int name_len; entry = get_fsync_inode(dir_list, pino); if (!entry) { @@ -184,7 +209,7 @@ static int recover_dentry(struct inode *inode, struct folio *ifolio, } dir = entry->inode; - err = init_recovered_filename(dir, raw_inode, &fname, &usr_fname); + err = init_recovered_filename(dir, inode, raw_inode, &fname, &usr_fname); if (err) goto out; retry: @@ -229,12 +254,9 @@ static int recover_dentry(struct inode *inode, struct folio *ifolio, out_put: f2fs_folio_put(folio, false); out: - if (file_enc_name(inode)) - name = ""; - else - name = raw_inode->i_name; - f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %s, dir = %llu, err = %d", - __func__, ino_of_node(ifolio), name, + name = recover_printable_name(inode, raw_inode, &name_len); + f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %.*s, dir = %llu, err = %d", + __func__, ino_of_node(ifolio), name_len, name, IS_ERR(dir) ? 0 : dir->i_ino, err); return err; } @@ -282,7 +304,8 @@ static int recover_inode(struct inode *inode, struct folio *folio) { struct f2fs_inode *raw = F2FS_INODE(folio); struct f2fs_inode_info *fi = F2FS_I(inode); - char *name; + const char *name; + int name_len; int err; inode->i_mode = le16_to_cpu(raw->i_mode); @@ -331,13 +354,11 @@ static int recover_inode(struct inode *inode, struct folio *folio) f2fs_mark_inode_dirty_sync(inode, true); - if (file_enc_name(inode)) - name = ""; - else - name = F2FS_INODE(folio)->i_name; + name = recover_printable_name(inode, raw, &name_len); - f2fs_notice(F2FS_I_SB(inode), "recover_inode: ino = %x, name = %s, inline = %x", - ino_of_node(folio), name, raw->i_inline); + f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %.*s, inline = %x", + __func__, ino_of_node(folio), name_len, name, + raw->i_inline); return 0; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 642668a1847c..63b712d3d599 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -261,7 +261,7 @@ static int __replace_atomic_write_block(struct inode *inode, pgoff_t index, } else { blkcnt_t count = 1; - err = inc_valid_block_count(sbi, inode, &count, true); + err = inc_valid_block_count(sbi, inode, &count, true, false); if (err) { f2fs_put_dnode(&dn); return err; @@ -452,15 +452,14 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) f2fs_submit_merged_write(sbi, DATA); f2fs_submit_all_merged_ipu_writes(sbi); - if (test_opt(sbi, GC_MERGE) && sbi->gc_thread && - sbi->gc_thread->f2fs_gc_task) { + if (test_opt(sbi, GC_MERGE) && sbi->gc_thread.f2fs_gc_task) { DEFINE_WAIT(wait); - prepare_to_wait(&sbi->gc_thread->fggc_wq, &wait, + prepare_to_wait(&sbi->gc_thread.fggc_wq, &wait, TASK_UNINTERRUPTIBLE); - wake_up(&sbi->gc_thread->gc_wait_queue_head); + wake_up(&sbi->gc_thread.gc_wait_queue_head); io_schedule(); - finish_wait(&sbi->gc_thread->fggc_wq, &wait); + finish_wait(&sbi->gc_thread.fggc_wq, &wait); } else { struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, @@ -566,21 +565,59 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi, return ret; } +static void f2fs_flush_end_io(struct bio *bio) +{ + complete(bio->bi_private); +} + +struct f2fs_flush_bio { + struct bio bio; + struct completion wait; +}; + static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) { + struct f2fs_flush_bio *flush_bio; + unsigned long devices = 0; int ret = 0; int i; if (!f2fs_is_multi_device(sbi)) return __submit_flush_wait(sbi, sbi->sb->s_bdev); + flush_bio = kmalloc(array_size(sbi->s_ndevs, sizeof(*flush_bio)), + GFP_NOFS | __GFP_NOFAIL); + for (i = 0; i < sbi->s_ndevs; i++) { if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO)) continue; - ret = __submit_flush_wait(sbi, FDEV(i).bdev); - if (ret) - break; + + bio_init(&flush_bio[i].bio, FDEV(i).bdev, NULL, 0, + REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); + init_completion(&flush_bio[i].wait); + flush_bio[i].bio.bi_private = &flush_bio[i].wait; + flush_bio[i].bio.bi_end_io = f2fs_flush_end_io; + devices |= BIT(i); + submit_bio(&flush_bio[i].bio); } + + for (i = 0; i < sbi->s_ndevs; i++) { + int err; + + if (!(devices & BIT(i))) + continue; + + wait_for_completion(&flush_bio[i].wait); + err = blk_status_to_errno(flush_bio[i].bio.bi_status); + trace_f2fs_issue_flush(FDEV(i).bdev, test_opt(sbi, NOBARRIER), + test_opt(sbi, FLUSH_MERGE), err); + if (!err) + f2fs_update_iostat(sbi, NULL, FS_FLUSH_IO, 0); + else if (!ret) + ret = err; + bio_uninit(&flush_bio[i].bio); + } + kfree(flush_bio); return ret; } @@ -2502,35 +2539,42 @@ static int update_sit_entry_for_alloc(struct f2fs_sb_info *sbi, struct seg_entry unsigned int segno, block_t blkaddr, unsigned int offset, int del) { bool exist; + int del_count = del; + int i; - exist = f2fs_test_and_set_bit(offset, se->cur_valid_map); - if (unlikely(exist)) { - f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr); - f2fs_bug_on(sbi, 1); - se->valid_blocks--; - del = 0; - } + f2fs_bug_on(sbi, GET_SEGNO(sbi, blkaddr) != GET_SEGNO(sbi, blkaddr + del_count - 1)); - if (f2fs_block_unit_discard(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) - sbi->discard_blks--; - - /* - * SSR should never reuse block which is checkpointed - * or newly invalidated. - */ - if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { - if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) { - se->ckpt_valid_blocks++; - if (__is_large_section(sbi)) - get_sec_entry(sbi, segno)->ckpt_valid_blocks++; + for (i = 0; i < del_count; i++) { + exist = f2fs_test_and_set_bit(offset + i, se->cur_valid_map); + if (unlikely(exist)) { + f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr + i); + f2fs_bug_on(sbi, 1); + se->valid_blocks--; + del -= 1; + continue; } - } - if (!f2fs_test_bit(offset, se->ckpt_valid_map)) { - se->ckpt_valid_blocks += del; - if (__is_large_section(sbi)) - get_sec_entry(sbi, segno)->ckpt_valid_blocks += del; + if (f2fs_block_unit_discard(sbi) && + !f2fs_test_and_set_bit(offset + i, se->discard_map)) + sbi->discard_blks--; + + /* + * SSR should never reuse block which is checkpointed + * or newly invalidated. + */ + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { + if (!f2fs_test_and_set_bit(offset + i, se->ckpt_valid_map)) { + se->ckpt_valid_blocks++; + if (__is_large_section(sbi)) + get_sec_entry(sbi, segno)->ckpt_valid_blocks++; + } + } + + if (!f2fs_test_bit(offset + i, se->ckpt_valid_map)) { + se->ckpt_valid_blocks += 1; + if (__is_large_section(sbi)) + get_sec_entry(sbi, segno)->ckpt_valid_blocks += 1; + } } if (__is_large_section(sbi)) @@ -2585,9 +2629,14 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr, unsigned int segno = GET_SEGNO(sbi, addr); struct sit_info *sit_i = SIT_I(sbi); block_t addr_start = addr, addr_end = addr + len - 1; - unsigned int seg_num = GET_SEGNO(sbi, addr_end) - segno + 1; + unsigned int seg_num; unsigned int i = 1, max_blocks = sbi->blocks_per_seg, cnt; + if (len == 0) + return; + + seg_num = GET_SEGNO(sbi, addr_end) - segno + 1; + f2fs_bug_on(sbi, addr == NULL_ADDR); if (addr == NEW_ADDR || addr == COMPRESS_ADDR) return; @@ -2620,6 +2669,52 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr, up_write(&sit_i->sentry_lock); } +void f2fs_reserve_device_alias(struct f2fs_sb_info *sbi, block_t addr, + unsigned int len) +{ + unsigned int segno = GET_SEGNO(sbi, addr); + struct sit_info *sit_i = SIT_I(sbi); + block_t addr_start = addr, addr_end = addr + len - 1; + unsigned int seg_num; + unsigned int i = 1, max_blocks = sbi->blocks_per_seg, cnt; + + if (len == 0) + return; + + seg_num = GET_SEGNO(sbi, addr_end) - segno + 1; + + down_write(&sit_i->sentry_lock); + + if (seg_num == 1) + cnt = len; + else + cnt = max_blocks - GET_BLKOFF_FROM_SEG0(sbi, addr); + + do { + update_segment_mtime(sbi, addr_start, 0); + update_sit_entry(sbi, addr_start, cnt); + __set_test_and_inuse(sbi, segno); + + /* Remove the segment from PRE (prefree) to prevent checkpoint from freeing it! */ + mutex_lock(&DIRTY_I(sbi)->seglist_lock); + if (test_and_clear_bit(segno, DIRTY_I(sbi)->dirty_segmap[PRE])) + DIRTY_I(sbi)->nr_dirty[PRE]--; + mutex_unlock(&DIRTY_I(sbi)->seglist_lock); + + /* add it into dirty seglist */ + locate_dirty_segment(sbi, segno); + + /* update @addr_start and @cnt and @segno */ + addr_start = START_BLOCK(sbi, ++segno); + if (++i == seg_num) + cnt = GET_BLKOFF_FROM_SEG0(sbi, addr_end) + 1; + else + cnt = max_blocks; + } while (i <= seg_num); + + up_write(&sit_i->sentry_lock); +} + bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) { struct sit_info *sit_i = SIT_I(sbi); @@ -2758,8 +2853,13 @@ static int is_next_segment_free(struct f2fs_sb_info *sbi, unsigned int segno = curseg->segno + 1; struct free_segmap_info *free_i = FREE_I(sbi); - if (segno < MAIN_SEGS(sbi) && segno % SEGS_PER_SEC(sbi)) + if (segno < MAIN_SEGS(sbi) && segno % SEGS_PER_SEC(sbi)) { + int devi = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno)); + + if (f2fs_dev_is_reserving(sbi, devi)) + return 0; return !test_bit(segno, free_i->free_segmap); + } return 0; } @@ -2777,8 +2877,10 @@ static int get_new_segment(struct f2fs_sb_info *sbi, unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg); unsigned int alloc_policy = sbi->allocate_section_policy; unsigned int alloc_hint = sbi->allocate_section_hint; + unsigned int max_secno = MAIN_SECS(sbi); bool init = true; - int i; + bool looped = false; + int i, devi; int ret = 0; spin_lock(&free_i->segmap_lock); @@ -2791,8 +2893,13 @@ static int get_new_segment(struct f2fs_sb_info *sbi, if (!new_sec && ((*newseg + 1) % SEGS_PER_SEC(sbi))) { segno = find_next_zero_bit(free_i->free_segmap, GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1); - if (segno < GET_SEG_FROM_SEC(sbi, hint + 1)) + if (segno < GET_SEG_FROM_SEC(sbi, hint + 1)) { + devi = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno)); + + if (f2fs_dev_is_alloc_blocked(sbi, devi, pinning)) + goto find_other_zone; goto got_it; + } } #ifdef CONFIG_BLK_DEV_ZONED @@ -2802,7 +2909,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi, */ if (f2fs_sb_has_blkzoned(sbi)) { /* Prioritize writing to conventional zones */ - if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning) + if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV) segno = 0; else segno = max(sbi->first_seq_zone_segno, *newseg); @@ -2818,43 +2925,57 @@ static int get_new_segment(struct f2fs_sb_info *sbi, alloc_hint > MAIN_SECS(sbi)) alloc_hint = MAIN_SECS(sbi); - if (alloc_policy == ALLOCATE_FORWARD_FROM_HINT && - hint < alloc_hint) - hint = alloc_hint; - else if (alloc_policy == ALLOCATE_FORWARD_WITHIN_HINT && - hint >= alloc_hint) + if (pinning) { + max_secno = sbi->pinned_area_max_secno; hint = 0; + } else if (alloc_policy == ALLOCATE_FORWARD_FROM_HINT && + hint < alloc_hint) { + hint = alloc_hint; + } else if (alloc_policy == ALLOCATE_FORWARD_WITHIN_HINT && + hint >= alloc_hint) { + hint = 0; + } find_other_zone: - secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint); + secno = find_next_zero_bit(free_i->free_secmap, max_secno, hint); -#ifdef CONFIG_BLK_DEV_ZONED - if (secno >= MAIN_SECS(sbi) && f2fs_sb_has_blkzoned(sbi)) { - /* Write only to sequential zones */ - if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) { - hint = GET_SEC_FROM_SEG(sbi, sbi->first_seq_zone_segno); - secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint); - } else - secno = find_first_zero_bit(free_i->free_secmap, - MAIN_SECS(sbi)); - if (secno >= MAIN_SECS(sbi)) { - ret = -ENOSPC; - f2fs_bug_on(sbi, 1); - goto out_unlock; - } - } -#endif - - if (secno >= MAIN_SECS(sbi)) { - secno = find_first_zero_bit(free_i->free_secmap, - MAIN_SECS(sbi)); - if (secno >= MAIN_SECS(sbi)) { - ret = -ENOSPC; + if (secno >= max_secno) { + if (looped) { + ret = (pinning && has_unpinned_area(sbi)) ? + -EAGAIN : -ENOSPC; f2fs_bug_on(sbi, !pinning); goto out_unlock; } + hint = 0; +#ifdef CONFIG_BLK_DEV_ZONED + /* Write only to sequential zones */ + if (f2fs_sb_has_blkzoned(sbi) && + sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) + hint = GET_SEC_FROM_SEG(sbi, sbi->first_seq_zone_segno); +#endif + looped = true; + goto find_other_zone; } + segno = GET_SEG_FROM_SEC(sbi, secno); + + devi = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno)); + + if (f2fs_dev_is_alloc_blocked(sbi, devi, pinning)) { + while (devi < sbi->s_ndevs && + f2fs_dev_is_alloc_blocked(sbi, devi, pinning)) { + unsigned int end_segno = GET_SEGNO(sbi, FDEV(devi).end_blk); + + hint = GET_SEC_FROM_SEG(sbi, end_segno) + 1; + devi++; + } + goto find_other_zone; + } + + if (sec_usage_check(sbi, secno)) { + hint = secno + 1; + goto find_other_zone; + } zoneno = GET_ZONE_FROM_SEC(sbi, secno); /* give up on finding another zone */ @@ -2886,12 +3007,6 @@ static int get_new_segment(struct f2fs_sb_info *sbi, goto out_unlock; } - /* no free section in conventional device or conventional zone */ - if (new_sec && pinning && - f2fs_is_sequential_zone_area(sbi, START_BLOCK(sbi, segno))) { - ret = -EAGAIN; - goto out_unlock; - } __set_inuse(sbi, segno); *newseg = segno; out_unlock: @@ -2937,7 +3052,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) sanity_check_seg_type(sbi, seg_type); if (__is_large_section(sbi)) { - if (f2fs_need_rand_seg(sbi)) { + if (f2fs_need_rand_seg_blk(sbi, type)) { unsigned int hint = GET_SEC_FROM_SEG(sbi, curseg->segno); if (GET_SEC_FROM_SEG(sbi, curseg->segno + 1) != hint) @@ -2946,7 +3061,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) GET_SEG_FROM_SEC(sbi, hint + 1) - 1); } return curseg->segno; - } else if (f2fs_need_rand_seg(sbi)) { + } else if (f2fs_need_rand_seg_blk(sbi, type)) { return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); } @@ -3002,7 +3117,7 @@ static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) curseg->next_segno = segno; reset_curseg(sbi, type, 1); curseg->alloc_type = LFS; - if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) + if (f2fs_need_rand_blk(sbi, type)) curseg->fragment_remained_chunk = get_random_u32_inclusive(1, sbi->max_fragment_chunk); return 0; @@ -3357,15 +3472,17 @@ int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi) err = f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); f2fs_unlock_op(sbi, &lc); - if (f2fs_sb_has_blkzoned(sbi) && err == -EAGAIN && gc_required) { - f2fs_down_write_trace(&sbi->gc_lock, &lc); - err = f2fs_gc_range(sbi, 0, sbi->first_seq_zone_segno - 1, - true, ZONED_PIN_SEC_REQUIRED_COUNT); - f2fs_up_write_trace(&sbi->gc_lock, &lc); - - gc_required = false; - if (!err) + if (has_unpinned_area(sbi) && err == -EAGAIN && gc_required) { + err = f2fs_gc_range(sbi, 0, + sbi->pinned_area_max_secno * SEGS_PER_SEC(sbi) - 1, + true, ZONED_PIN_SEC_REQUIRED_COUNT, true); + if (err) + return err; + err = f2fs_sync_fs(sbi->sb, 1); + if (!err) { + gc_required = false; goto retry; + } } return err; @@ -3820,7 +3937,7 @@ int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct folio *folio, curseg->next_blkoff = f2fs_find_next_ssr_block(sbi, curseg); } else { curseg->next_blkoff++; - if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) + if (f2fs_need_rand_blk(sbi, type)) f2fs_randomize_chunk(sbi, curseg); } if (curseg->next_blkoff >= f2fs_usable_blks_in_seg(sbi, curseg->segno)) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index b0c06b3580b4..5949aa5200ac 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -43,6 +43,7 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments) #define MAIN_SECS(sbi) ((sbi)->total_sections) +#define has_unpinned_area(sbi) ((sbi)->pinned_area_max_secno < MAIN_SECS(sbi)) #define TOTAL_SEGS(sbi) \ (SM_I(sbi) ? SM_I(sbi)->segment_count : \ @@ -796,20 +797,6 @@ F2FS_IPU_POLICY(F2FS_IPU_ASYNC); F2FS_IPU_POLICY(F2FS_IPU_NOCACHE); F2FS_IPU_POLICY(F2FS_IPU_HONOR_OPU_WRITE); -static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi, - int type) -{ - struct curseg_info *curseg = CURSEG_I(sbi, type); - return curseg->segno; -} - -static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi, - int type) -{ - struct curseg_info *curseg = CURSEG_I(sbi, type); - return curseg->alloc_type; -} - static inline bool valid_main_segno(struct f2fs_sb_info *sbi, unsigned int segno) { @@ -954,10 +941,32 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type) - (base + 1) + type; } +static inline bool f2fs_dev_is_reserving(struct f2fs_sb_info *sbi, int devi) +{ + if (!f2fs_sb_has_device_alias(sbi)) + return false; + return FDEV(devi).is_reserving; +} + +static inline bool f2fs_dev_is_alloc_blocked(struct f2fs_sb_info *sbi, + int devi, bool pinning) +{ + if (!f2fs_sb_has_device_alias(sbi)) + return false; + return (pinning && FDEV(devi).has_alias) || FDEV(devi).is_reserving; +} + static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno) { if (is_cursec(sbi, secno) || (sbi->cur_victim_sec == secno)) return true; + if (f2fs_sb_has_device_alias(sbi)) { + block_t start_blk = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno)); + int devi = f2fs_target_device_index(sbi, start_blk); + + if (f2fs_dev_is_reserving(sbi, devi)) + return true; + } return false; } diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index b88babcf6ab4..4f6bf5926de4 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -109,7 +109,8 @@ unsigned long f2fs_shrink_scan(struct shrinker *shrink, freed += f2fs_shrink_age_extent_tree(sbi, nr >> 2); /* shrink read extent cache entries */ - freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2); + if (freed < nr) + freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2); /* shrink clean nat cache entries */ if (freed < nr) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index be22c31015ef..1314b6ccced9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -235,6 +235,7 @@ enum { Opt_jqfmt, Opt_checkpoint, Opt_lookup_mode, + Opt_resizable_tail_secno, Opt_err, }; @@ -366,6 +367,7 @@ static const struct fs_parameter_spec f2fs_param_specs[] = { fsparam_flag("age_extent_cache", Opt_age_extent_cache), fsparam_enum("errors", Opt_errors, f2fs_param_errors), fsparam_enum("lookup_mode", Opt_lookup_mode, f2fs_param_lookup_mode), + fsparam_u32("resizable_tail_secno", Opt_resizable_tail_secno), {} }; @@ -404,6 +406,7 @@ static match_table_t f2fs_checkpoint_tokens = { #define F2FS_SPEC_errors (1 << 23) #define F2FS_SPEC_lookup_mode (1 << 24) #define F2FS_SPEC_reserve_node (1 << 25) +#define F2FS_SPEC_resizable_tail_secno (1 << 26) struct f2fs_fs_context { struct f2fs_mount_info info; @@ -551,6 +554,17 @@ static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).unusable_cap_perc); } +static inline void adjust_pinned_area_boundary(struct f2fs_sb_info *sbi) +{ + sbi->pinned_area_max_secno = MAIN_SECS(sbi); + if (f2fs_sb_has_blkzoned(sbi) && sbi->first_seq_zone_segno != NULL_SEGNO) + sbi->pinned_area_max_secno = min(sbi->pinned_area_max_secno, + GET_SEC_FROM_SEG(sbi, sbi->first_seq_zone_segno)); + if (F2FS_OPTION(sbi).resizable_tail_secno) + sbi->pinned_area_max_secno = min(sbi->pinned_area_max_secno, + MAIN_SECS(sbi) - F2FS_OPTION(sbi).resizable_tail_secno); +} + static void init_once(void *foo) { struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; @@ -1235,6 +1249,10 @@ static int f2fs_parse_param(struct fs_context *fc, struct fs_parameter *param) F2FS_CTX_INFO(ctx).lookup_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_lookup_mode; break; + case Opt_resizable_tail_secno: + F2FS_CTX_INFO(ctx).resizable_tail_secno = result.uint_32; + ctx->spec_mask |= F2FS_SPEC_resizable_tail_secno; + break; } return 0; } @@ -1763,6 +1781,9 @@ static void f2fs_apply_options(struct fs_context *fc, struct super_block *sb) F2FS_OPTION(sbi).errors = F2FS_CTX_INFO(ctx).errors; if (ctx->spec_mask & F2FS_SPEC_lookup_mode) F2FS_OPTION(sbi).lookup_mode = F2FS_CTX_INFO(ctx).lookup_mode; + if (ctx->spec_mask & F2FS_SPEC_resizable_tail_secno) + F2FS_OPTION(sbi).resizable_tail_secno = + F2FS_CTX_INFO(ctx).resizable_tail_secno; f2fs_apply_compression(fc, sb); f2fs_apply_test_dummy_encryption(fc, sb); @@ -1771,6 +1792,13 @@ static void f2fs_apply_options(struct fs_context *fc, struct super_block *sb) static int f2fs_sanity_check_options(struct f2fs_sb_info *sbi, bool remount) { + unsigned int total_sections = le32_to_cpu(sbi->raw_super->section_count); + + if (F2FS_OPTION(sbi).resizable_tail_secno >= total_sections) { + f2fs_err(sbi, "Option resizable_tail_secno is larger than or equal to total sections (%u >= %u)", + F2FS_OPTION(sbi).resizable_tail_secno, total_sections); + return -EINVAL; + } if (f2fs_sb_has_device_alias(sbi) && !test_opt(sbi, READ_EXTENT_CACHE)) { f2fs_err(sbi, "device aliasing requires extent cache"); @@ -2058,7 +2086,8 @@ static void f2fs_put_super(struct super_block *sb) if (!get_pages(sbi, i)) continue; f2fs_err(sbi, "detect filesystem reference count leak during " - "umount, type: %d, count: %lld", i, get_pages(sbi, i)); + "umount, type: %d, count: %lld, err: %d, cp_err: %d", + i, get_pages(sbi, i), err, f2fs_cp_error(sbi)); f2fs_bug_on(sbi, 1); } @@ -2456,9 +2485,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, "adaptive"); else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS) seq_puts(seq, "lfs"); - else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG) + else if (f2fs_need_rand_seg(sbi, NO_CHECK_TYPE)) seq_puts(seq, "fragment:segment"); - else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) + else if (f2fs_need_rand_blk(sbi, NO_CHECK_TYPE)) seq_puts(seq, "fragment:block"); seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); if (test_opt(sbi, RESERVE_ROOT) || test_opt(sbi, RESERVE_NODE)) @@ -2543,6 +2572,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).lookup_mode == LOOKUP_AUTO) seq_show_option(seq, "lookup_mode", "auto"); + if (F2FS_OPTION(sbi).resizable_tail_secno) + seq_printf(seq, ",resizable_tail_secno=%u", + F2FS_OPTION(sbi).resizable_tail_secno); + return 0; } @@ -2585,6 +2618,7 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount) F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL; F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE; + F2FS_OPTION(sbi).resizable_tail_secno = 0; set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); @@ -2943,11 +2977,11 @@ static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) if ((flags & SB_RDONLY) || (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF && !test_opt(sbi, GC_MERGE))) { - if (sbi->gc_thread) { + if (sbi->gc_thread.f2fs_gc_task) { f2fs_stop_gc_thread(sbi); need_restart_gc = true; } - } else if (!sbi->gc_thread) { + } else if (!sbi->gc_thread.f2fs_gc_task) { err = f2fs_start_gc_thread(sbi); if (err) goto restore_opts; @@ -2959,7 +2993,9 @@ static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) set_sbi_flag(sbi, SBI_IS_DIRTY); set_sbi_flag(sbi, SBI_IS_CLOSE); - f2fs_sync_fs(sb, 1); + err = f2fs_sync_fs(sb, 1); + if (err) + goto restore_gc; clear_sbi_flag(sbi, SBI_IS_CLOSE); } @@ -3042,6 +3078,7 @@ static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); + adjust_pinned_area_boundary(sbi); limit_reserve_root(sbi); fc->sb_flags = (flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); @@ -3168,7 +3205,7 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data, repeat: folio = mapping_read_folio_gfp(mapping, off >> PAGE_SHIFT, - GFP_NOFS); + GFP_KERNEL); if (IS_ERR(folio)) { if (PTR_ERR(folio) == -ENOMEM) { memalloc_retry_wait(GFP_NOFS); @@ -5004,6 +5041,39 @@ static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi) sbi->readdir_ra = true; } +static void f2fs_restore_device_alias(struct f2fs_sb_info *sbi) +{ + struct inode *root = d_inode(sbi->sb->s_root); + struct f2fs_dir_entry *de; + struct folio *folio; + int i; + + if (!f2fs_sb_has_device_alias(sbi)) + return; + + for (i = 1; i < sbi->s_ndevs; i++) { + char *name = strrchr(FDEV(i).path, '/'); + struct inode *inode; + struct qstr qstr; + + name = name ? name + 1 : FDEV(i).path; + qstr.name = name; + qstr.len = strlen(name); + + de = f2fs_find_entry(root, &qstr, &folio); + if (!de) + continue; + + inode = f2fs_iget(sbi->sb, le32_to_cpu(de->ino)); + if (!IS_ERR(inode)) { + if (IS_DEVICE_ALIASING(inode)) + FDEV(i).has_alias = true; + iput(inode); + } + f2fs_folio_put(folio, 0); + } +} + static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) { struct f2fs_fs_context *ctx = fc->fs_private; @@ -5068,6 +5138,7 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_fs_info = sbi; sbi->raw_super = raw_super; + sbi->max_atc_write_bio_size = UINT_MAX; INIT_WORK(&sbi->s_error_work, f2fs_record_error_work); memcpy(sbi->errors, raw_super->s_errors, MAX_F2FS_ERRORS); @@ -5207,6 +5278,7 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) sbi->last_valid_block_count = sbi->total_valid_block_count; sbi->reserved_blocks = 0; sbi->current_reserved_blocks = 0; + sbi->alias_reserved_blocks = 0; limit_reserve_root(sbi); adjust_unusable_cap_perc(sbi); @@ -5249,6 +5321,8 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) /* get segno of first zoned block device */ sbi->first_seq_zone_segno = get_first_seq_zone_segno(sbi); + adjust_pinned_area_boundary(sbi); + sbi->reserved_pin_section = f2fs_sb_has_blkzoned(sbi) ? ZONED_PIN_SEC_REQUIRED_COUNT : GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)); @@ -5434,6 +5508,8 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) f2fs_update_time(sbi, REQ_TIME); clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + f2fs_restore_device_alias(sbi); + sbi->umount_lock_holder = NULL; return 0; @@ -5701,10 +5777,16 @@ static int __init init_f2fs_fs(void) err = f2fs_init_xattr_cache(); if (err) goto free_casefold_cache; - err = register_filesystem(&f2fs_fs_type); + err = f2fs_init_evict_inode_work(); if (err) goto free_xattr_cache; + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_evict_inode_cache; return 0; + +free_evict_inode_cache: + f2fs_destroy_evict_inode_work(); free_xattr_cache: f2fs_destroy_xattr_cache(); free_casefold_cache: @@ -5747,6 +5829,7 @@ static int __init init_f2fs_fs(void) static void __exit exit_f2fs_fs(void) { unregister_filesystem(&f2fs_fs_type); + f2fs_destroy_evict_inode_work(); f2fs_destroy_xattr_cache(); f2fs_destroy_casefold_cache(); f2fs_destroy_compress_cache(); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 665687244c93..811e350a1430 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -75,7 +75,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) { if (struct_type == GC_THREAD) - return (unsigned char *)sbi->gc_thread; + return (unsigned char *)&sbi->gc_thread; else if (struct_type == SM_INFO) return (unsigned char *)SM_I(sbi); else if (struct_type == DCC_INFO) @@ -557,7 +557,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a, return -EINVAL; cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, level); - if (test_opt(sbi, MERGE_CHECKPOINT)) { + if (cprc->f2fs_issue_ckpt) { ret = set_task_ioprio(cprc->f2fs_issue_ckpt, cprc->ckpt_thread_ioprio); if (ret) @@ -664,20 +664,20 @@ static ssize_t __sbi_store(struct f2fs_attr *a, sbi->gc_mode = GC_NORMAL; } else if (t == 1) { sbi->gc_mode = GC_URGENT_HIGH; - if (sbi->gc_thread) { - sbi->gc_thread->gc_wake = true; + if (sbi->gc_thread.f2fs_gc_task) { + sbi->gc_thread.gc_wake = true; wake_up_interruptible_all( - &sbi->gc_thread->gc_wait_queue_head); + &sbi->gc_thread.gc_wait_queue_head); wake_up_discard_thread(sbi, true); } } else if (t == 2) { sbi->gc_mode = GC_URGENT_LOW; } else if (t == 3) { sbi->gc_mode = GC_URGENT_MID; - if (sbi->gc_thread) { - sbi->gc_thread->gc_wake = true; + if (sbi->gc_thread.f2fs_gc_task) { + sbi->gc_thread.gc_wake = true; wake_up_interruptible_all( - &sbi->gc_thread->gc_wait_queue_head); + &sbi->gc_thread.gc_wait_queue_head); } } else { return -EINVAL; @@ -934,14 +934,14 @@ static ssize_t __sbi_store(struct f2fs_attr *a, if (!strcmp(a->attr.name, "gc_boost_gc_multiple")) { if (t < 1 || t > SEGS_PER_SEC(sbi)) return -EINVAL; - sbi->gc_thread->boost_gc_multiple = (unsigned int)t; + sbi->gc_thread.boost_gc_multiple = (unsigned int)t; return count; } if (!strcmp(a->attr.name, "gc_boost_gc_greedy")) { if (t > GC_GREEDY) return -EINVAL; - sbi->gc_thread->boost_gc_greedy = (unsigned int)t; + sbi->gc_thread.boost_gc_greedy = (unsigned int)t; return count; } @@ -989,8 +989,8 @@ static ssize_t __sbi_store(struct f2fs_attr *a, if (sbi->cprc_info.f2fs_issue_ckpt) set_user_nice(sbi->cprc_info.f2fs_issue_ckpt, PRIO_TO_NICE(sbi->critical_task_priority)); - if (sbi->gc_thread && sbi->gc_thread->f2fs_gc_task) - set_user_nice(sbi->gc_thread->f2fs_gc_task, + if (sbi->gc_thread.f2fs_gc_task) + set_user_nice(sbi->gc_thread.f2fs_gc_task, PRIO_TO_NICE(sbi->critical_task_priority)); return count; } @@ -1007,13 +1007,15 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, ssize_t ret; bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") || a->struct_type == GC_THREAD); + bool thread_entry = !strcmp(a->attr.name, "ckpt_thread_ioprio") || + !strcmp(a->attr.name, "critical_task_priority"); - if (gc_entry) { + if (gc_entry || thread_entry) { if (!down_read_trylock(&sbi->sb->s_umount)) return -EAGAIN; } ret = __sbi_store(a, sbi, buf, count); - if (gc_entry) + if (gc_entry || thread_entry) up_read(&sbi->sb->s_umount); return ret; @@ -1266,6 +1268,7 @@ F2FS_SBI_RW_ATTR(gc_idle_interval, interval_time[GC_TIME]); F2FS_SBI_RW_ATTR(umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); F2FS_SBI_RW_ATTR(gc_pin_file_thresh, gc_pin_file_threshold); F2FS_SBI_RW_ATTR(gc_reclaimed_segments, gc_reclaimed_segs); +F2FS_SBI_RW_ATTR(max_atc_write_bio_size, max_atc_write_bio_size); F2FS_SBI_GENERAL_RW_ATTR(max_victim_search); F2FS_SBI_GENERAL_RW_ATTR(migration_granularity); F2FS_SBI_GENERAL_RW_ATTR(migration_window_granularity); @@ -1310,6 +1313,7 @@ F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy); #endif F2FS_SBI_GENERAL_RW_ATTR(carve_out); F2FS_SBI_GENERAL_RW_ATTR(reserved_pin_section); +F2FS_SBI_GENERAL_RO_ATTR(pinned_area_max_secno); F2FS_SBI_GENERAL_RW_ATTR(bggc_io_aware); F2FS_SBI_GENERAL_RW_ATTR(max_lock_elapsed_time); F2FS_SBI_GENERAL_RW_ATTR(lock_duration_priority); @@ -1509,6 +1513,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(seq_file_ra_mul), ATTR_LIST(gc_segment_mode), ATTR_LIST(gc_reclaimed_segments), + ATTR_LIST(max_atc_write_bio_size), ATTR_LIST(max_fragment_chunk), ATTR_LIST(max_fragment_hole), ATTR_LIST(current_atomic_write), @@ -1521,6 +1526,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(max_read_extent_count), ATTR_LIST(carve_out), ATTR_LIST(reserved_pin_section), + ATTR_LIST(pinned_area_max_secno), ATTR_LIST(allocate_section_hint), ATTR_LIST(allocate_section_policy), ATTR_LIST(max_lock_elapsed_time), diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index ed33e5110f2a..6728d1488cad 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -119,7 +119,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, unsigned char old_advise = F2FS_I(inode)->i_advise; unsigned char new_advise; - if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (value == NULL) return -EINVAL; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 60264833bb63..848a0d338b89 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1737,8 +1737,8 @@ static struct attr_def *ntfs_attr_find_in_attrdef(const struct ntfs_volume *vol, struct attr_def *ad; WARN_ON(!type); - for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef < - vol->attrdef_size && ad->type; ++ad) { + for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef <= + vol->attrdef_size - (s32)sizeof(*ad) && ad->type; ++ad) { /* We have not found it yet, carry on searching. */ if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type))) continue; @@ -2500,7 +2500,7 @@ int ntfs_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -EIO; + return err; } /* @@ -2639,7 +2639,7 @@ static int ntfs_non_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -1; + return err; } /* @@ -5704,12 +5704,12 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo lcn << vol->cluster_size_bits, alloc_cnt << vol->cluster_size_bits); - if (err > 0) + if (err) goto out; } if (signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5730,7 +5730,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo up_write(&ni->runlist.lock); mutex_unlock(&ni->mrec_lock); if (err || signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5756,4 +5756,8 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo mutex_unlock(&ni->mrec_lock); out: return err >= 0 ? 0 : err; +signal_out: + if (!err) + err = -EINTR; + goto out; } diff --git a/fs/ntfs/bdev-io.c b/fs/ntfs/bdev-io.c index 86db4d9298ed..4f27eed3b072 100644 --- a/fs/ntfs/bdev-io.c +++ b/fs/ntfs/bdev-io.c @@ -34,7 +34,7 @@ int ntfs_bdev_read(struct block_device *bdev, char *data, loff_t start, size_t s int error; struct bio *bio; blk_opf_t op; - sector_t sector = start >> SECTOR_SHIFT; + sector_t sector = ntfs_bytes_to_bio_sector(start); if (start & (SECTOR_SIZE - 1)) return -EINVAL; diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index b1436b3151b9..1840b7d84c62 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -64,7 +64,7 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) end = start_buf; while (end < end_buf) { - u64 aligned_start, aligned_count; + u64 aligned_start, aligned_end, aligned_count; u64 start = find_next_zero_bit(bitmap, end_buf - start_buf, end - start_buf) + start_buf; if (start >= end_buf) @@ -74,8 +74,10 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) start - start_buf) + start_buf; aligned_start = ALIGN(ntfs_cluster_to_bytes(vol, start), dq); - aligned_count = - ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end - start), dq); + aligned_end = ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end), dq); + if (aligned_start >= aligned_end) + continue; + aligned_count = aligned_end - aligned_start; if (aligned_count >= range->minlen) { ret = blkdev_issue_discard(vol->sb->s_bdev, aligned_start >> 9, aligned_count >> 9, GFP_NOFS); diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 2225630b19d7..197d8607fc63 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -1414,7 +1414,7 @@ static int ntfs_write_cb(struct ntfs_inode *ni, loff_t pos, struct page **pages, bio_pos = ntfs_cluster_to_bytes(vol, bio_lcn); bio = bio_alloc(vol->sb->s_bdev, DIV_ROUND_UP(bio_size, PAGE_SIZE), REQ_OP_WRITE, GFP_NOIO); - bio->bi_iter.bi_sector = ntfs_bytes_to_sector(vol, bio_pos); + bio->bi_iter.bi_sector = ntfs_bytes_to_bio_sector(bio_pos); for (i = 0; bio_size; i++) { unsigned int len = min_t(unsigned int, bio_size, PAGE_SIZE); diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index cdd306933d73..3f4ba7667522 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -404,10 +404,12 @@ static int ntfs_set_ea(struct inode *inode, const char *name, size_t name_len, *packed_ea_size = p_ea_info->ea_length; mark_mft_record_dirty(ni); out: - if (ea_info_qsize > 0) - NInoSetHasEA(ni); - else - NInoClearHasEA(ni); + if (!err) { + if (ea_info_qsize > 0) + NInoSetHasEA(ni); + else + NInoClearHasEA(ni); + } kvfree(ea_buf); kvfree(old_ea_buf); @@ -615,7 +617,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u8); } else if (size < sizeof(u8)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u8); *(u8 *)buffer = (u8)(le32_to_cpu(ni->flags) & 0x3F); @@ -628,7 +630,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u32); } else if (size < sizeof(u32)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u32); *(u32 *)buffer = le32_to_cpu(ni->flags); @@ -753,18 +755,39 @@ static int ntfs_new_attr_flags(struct ntfs_inode *ni, __le32 fattr) old_arec_size = le32_to_cpu(a->length); /* - * Move payloads before shrinking the record. Otherwise resizing moves + * Move payloads before shrinking the record. Otherwise resizing moves * the following attribute over the old payload before it can be copied. + * + * When offsets increase, move mapping_pairs first to avoid name + * overwriting the start of mapping_pairs. */ if (arec_size < old_arec_size) { - if (a->name_length && name_ofs != old_name_ofs) - memmove((u8 *)a + name_ofs, (u8 *)a + old_name_ofs, - a->name_length * sizeof(__le16)); - if (mp_ofs != old_mp_ofs) - memmove((u8 *)a + mp_ofs, (u8 *)a + old_mp_ofs, mp_size); + if (name_ofs > old_name_ofs) { + /* Payload offsets increased: move mapping pairs first. */ + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + } else { + /* Payload offsets decreased or unchanged: move name first. */ + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + } } - err = ntfs_attr_record_resize(m, a, arec_size); + err = ntfs_attr_record_resize(ctx->mrec, a, arec_size); if (unlikely(err)) goto err_out; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 88747217ba61..8164326b7812 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -270,18 +270,25 @@ static int ntfs_setattr_size(struct inode *vi, struct iattr *attr) return err; inode_dio_wait(vi); + + /* + * Serialize with page faults and pagecache instantiation so that + * readers cannot observe the size change until the attribute + * updates below have completed. + */ + filemap_invalidate_lock(vi->i_mapping); if (attr->ia_size > old_size) { truncate_pagecache(vi, old_size); i_size_write(vi, attr->ia_size); pagecache_isize_extended(vi, old_size, attr->ia_size); - } else + } else { truncate_setsize(vi, attr->ia_size); + } err = ntfs_truncate_vfs(vi, attr->ia_size, old_size); - if (err) { + if (err) i_size_write(vi, old_size); - return err; - } + filemap_invalidate_unlock(vi->i_mapping); return err; } @@ -669,6 +676,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); + struct address_space *mapping = inode->i_mapping; vm_fault_t ret; if (NInoWofCompressed(NTFS_I(inode))) @@ -677,7 +685,14 @@ static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); + /* + * Serialize against truncate/fallocate which hold the lock + * exclusively while invalidating pagecache and changing extents. + */ + filemap_invalidate_lock_shared(mapping); ret = iomap_page_mkwrite(vmf, &ntfs_page_mkwrite_iomap_ops, NULL); + filemap_invalidate_unlock_shared(mapping); + sb_end_pagefault(inode->i_sb); return ret; } @@ -1116,7 +1131,6 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le struct ntfs_volume *vol = ni->vol; int err = 0; loff_t old_size; - bool map_locked = false; if (mode & ~(NTFS_FALLOC_FL_SUPPORTED)) return -EOPNOTSUPP; @@ -1148,16 +1162,13 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le inode_lock(vi); if (NInoCompressed(ni) || NInoEncrypted(ni) || NInoWofCompressed(ni)) { - err = -EOPNOTSUPP; - goto out; + inode_unlock(vi); + return -EOPNOTSUPP; } inode_dio_wait(vi); - if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | - FALLOC_FL_INSERT_RANGE)) { - filemap_invalidate_lock(vi->i_mapping); - map_locked = true; - } + /* Take invalidate_lock for all fallocate operations to prevent races */ + filemap_invalidate_lock(vi->i_mapping); switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: @@ -1182,14 +1193,15 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le err = file_modified(file); out: - if (map_locked) - filemap_invalidate_unlock(vi->i_mapping); + if (!err && mode == 0 && NInoNonResident(ni) && + offset > old_size) { + truncate_pagecache(vi, old_size); + pagecache_isize_extended(vi, old_size, offset); + } + + filemap_invalidate_unlock(vi->i_mapping); + if (!err) { - if (mode == 0 && NInoNonResident(ni) && - offset > old_size) { - truncate_pagecache(vi, old_size); - pagecache_isize_extended(vi, old_size, offset); - } NInoSetFileNameDirty(ni); inode_set_mtime_to_ts(vi, inode_set_ctime_current(vi)); mark_inode_dirty(vi); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 32edb4045178..5aedc045f65a 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1852,7 +1852,7 @@ int ntfs_read_inode_mount(struct inode *vi) struct mft_record *m = NULL; struct attr_record *a; struct ntfs_attr_search_ctx *ctx; - unsigned int i, nr_blocks; + unsigned int i; int err; size_t new_rl_count; @@ -1896,11 +1896,6 @@ int ntfs_read_inode_mount(struct inode *vi) goto err_out; } - /* Determine the first block of the $MFT/$DATA attribute. */ - nr_blocks = ntfs_bytes_to_sector(vol, vol->mft_record_size); - if (!nr_blocks) - nr_blocks = 1; - /* Load $MFT/$DATA's first mft record. */ err = ntfs_bdev_read(sb->s_bdev, (char *)m, ntfs_cluster_to_bytes(vol, vol->mft_lcn), i); @@ -3780,8 +3775,7 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + + ntfs_bytes_to_bio_sector(ntfs_cluster_to_bytes(vol, lcn) + lcn_folio_off); length = min_t(unsigned long, diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index aa2e017a4384..0d6cd08ee2e7 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -53,10 +53,10 @@ int ntfs_cluster_free_from_rl_nolock(struct ntfs_volume *vol, if (rl->lcn < 0) continue; err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length); - if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err)) - ret = err; - else + if (likely(!err)) nr_freed += rl->length; + else if (!ret || ret == -ENOMEM) + ret = err; } ntfs_inc_free_clusters(vol, nr_freed); ntfs_debug("Done."); @@ -1045,8 +1045,9 @@ s64 __ntfs_cluster_free(struct ntfs_inode *ni, const s64 start_vcn, s64 count, "Failed to rollback (error %i). Leaving inconsistent metadata! Unmount and run chkdsk.", (int)delta); NVolSetErrors(vol); + } else { + ntfs_dec_free_clusters(vol, delta); } - ntfs_dec_free_clusters(vol, delta); up_write(&vol->lcnbmp_lock); memalloc_nofs_restore(memalloc_flags); ntfs_error(vol->sb, "Aborting (error %i).", err); diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 984a0827f9ac..7e58c99f1728 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -499,8 +499,8 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + - lcn_folio_off + folio_ofs); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + + lcn_folio_off + folio_ofs); if (bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) err = submit_bio_wait(bio); @@ -580,7 +580,7 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn err = pre_write_mst_fixup((struct ntfs_record *)fixup_m, vol->mft_record_size); if (err) { ntfs_error(vol->sb, "Failed to apply mst fixups!"); - goto err_out; + goto unmap_err_out; } folio_size = vol->mft_record_size / ni->mft_lcn_count; @@ -592,8 +592,8 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + - clu_off); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + + clu_off); if (!bio_add_folio(bio, folio, folio_size, ni->folio_ofs + offset)) { @@ -645,6 +645,8 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn return 0; put_bio_out: bio_put(bio); +unmap_err_out: + kunmap_local(kaddr); err_out: /* * The caller should mark the base inode as bad so no more I/O @@ -2740,8 +2742,8 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + off); + ntfs_bytes_to_bio_sector( + ntfs_cluster_to_bytes(vol, lcn) + off); } if (vol->cluster_size == NTFS_BLOCK_SIZE && diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index df5a75d506f6..45f77848a9cf 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "volume.h" @@ -71,8 +72,6 @@ #define NTFS_CLU_TO_POFS(vol, clu) (((u64)(clu) << (vol)->cluster_size_bits) & \ ~PAGE_MASK) -#define NTFS_B_TO_SECTOR(vol, b) ((b) >> ((vol)->sb)->s_blocksize_bits) - enum { NTFS_BLOCK_SIZE = 512, NTFS_BLOCK_SIZE_BITS = 9, @@ -154,11 +153,10 @@ static inline u64 ntfs_cluster_to_poff(const struct ntfs_volume *vol, return (clu << vol->cluster_size_bits) & ~PAGE_MASK; } -/* Convert byte offset to sector (block) number. */ -static inline sector_t ntfs_bytes_to_sector(const struct ntfs_volume *vol, - u64 bytes) +/* Convert a byte offset on the volume to a bio sector number. */ +static inline sector_t ntfs_bytes_to_bio_sector(u64 bytes) { - return bytes >> vol->sb->s_blocksize_bits; + return bytes >> SECTOR_SHIFT; } /* Global variables. */ diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index 5e483a2f9060..1a6073e22677 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -405,7 +405,7 @@ unsigned int ntfs_reparse_tag_dt_types(struct ntfs_volume *vol, unsigned long mr vi = ntfs_iget(vol->sb, mref); if (IS_ERR(vi)) - return PTR_ERR(vi); + return DT_UNKNOWN; reparse_attr = (struct reparse_point *)ntfs_attr_readall(NTFS_I(vi), AT_REPARSE_POINT, NULL, 0, &attr_size); @@ -694,8 +694,9 @@ static int update_reparse_data(struct ntfs_inode *ni, struct ntfs_index_context goto put_rp_inode; } - if (set_reparse_index(ni, xr, ((const struct reparse_point *)value)->reparse_tag) && - oldsize > 0) { + err = set_reparse_index(ni, xr, + ((const struct reparse_point *)value)->reparse_tag); + if (err && oldsize > 0) { /* * If cannot index, try to remove the reparse * data and log the error. There will be an diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 30481e5d5dd4..60d43339c590 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -557,8 +557,8 @@ static bool is_boot_sector_ntfs(const struct super_block *sb, * Check sectors per cluster value is valid and the cluster size * is not above the maximum (2MB). */ - if (b->bpb.sectors_per_cluster > 0x80 && - b->bpb.sectors_per_cluster < 0xf4) + if (b->bpb.sectors_per_cluster < 0xf4 && + !is_power_of_2(b->bpb.sectors_per_cluster)) goto not_ntfs; /* Check reserved/unused fields are really zero. */ @@ -695,7 +695,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * = -log2(mft_record_size) bytes. mft_record_size normaly is * 1024 bytes, which is encoded as 0xF6 (-10 in decimal). */ - vol->mft_record_size = 1 << -clusters_per_mft_record; + vol->mft_record_size = 1U << -clusters_per_mft_record; vol->mft_record_size_mask = vol->mft_record_size - 1; vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1; ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size, @@ -732,7 +732,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * index_record_size normaly equals 4096 bytes, which is * encoded as 0xF4 (-12 in decimal). */ - vol->index_record_size = 1 << -clusters_per_index_record; + vol->index_record_size = 1U << -clusters_per_index_record; vol->index_record_size_mask = vol->index_record_size - 1; vol->index_record_size_bits = ffs(vol->index_record_size) - 1; ntfs_debug("vol->index_record_size = %i (0x%x)", @@ -1241,9 +1241,9 @@ static bool load_and_init_attrdef(struct ntfs_volume *vol) goto failed; } NInoSetSparseDisabled(NTFS_I(ino)); - /* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */ + /* FILE_AttrDef must hold at least one entry and fit inside 31 bits. */ i_size = i_size_read(ino); - if (i_size <= 0 || i_size > 0x7fffffff) + if (i_size < (s64)sizeof(struct attr_def) || i_size > 0x7fffffff) goto iput_failed; vol->attrdef = kvzalloc(i_size, GFP_NOFS); if (!vol->attrdef) @@ -1862,7 +1862,8 @@ static int ntfs_sync_fs(struct super_block *sb, int wait) return 0; /* If there are some dirty buffers in the bdev inode */ - if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { + if (!NVolErrors(vol) && + ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { ntfs_warning(sb, "Failed to clear dirty bit in volume information flags. Run chkdsk."); err = -EIO; } diff --git a/fs/ntfs/wof.c b/fs/ntfs/wof.c index 8f84c2212eee..9847259e5b1a 100644 --- a/fs/ntfs/wof.c +++ b/fs/ntfs/wof.c @@ -39,8 +39,6 @@ struct ntfs_wof_workspace { struct mutex *lock; const struct ntfs_codec_ops *codec; u32 comp_unit; - void *input; - size_t input_size; void *output; void *scratch; }; @@ -97,30 +95,36 @@ static struct ntfs_wof_workspace *ntfs_wof_workspace(u8 block_size_bits) } } +/* + * Size of the buffer a chunk is read into. A chunk is read straight off the + * device, so the buffer has to hold @comp_unit bytes plus the leading partial + * sector. + */ +static size_t ntfs_wof_input_size(const struct ntfs_wof_workspace *ws) +{ + return round_up((size_t)ws->comp_unit + 511, 512); +} + static int ntfs_wof_workspace_prepare(struct ntfs_wof_workspace *ws) { - void *input, *output, *scratch; + void *output, *scratch; size_t scratch_size; - if (ws->input) + if (ws->output) return 0; - ws->input_size = round_up((size_t)ws->comp_unit + 511, 512); scratch_size = ws->codec->scratch_size(ws->comp_unit); if (!scratch_size) return -EINVAL; - input = kvmalloc(ws->input_size, GFP_NOFS); output = kvmalloc(ws->comp_unit, GFP_NOFS); scratch = kvzalloc(scratch_size, GFP_NOFS); - if (!input || !output || !scratch) { - kvfree(input); + if (!output || !scratch) { kvfree(output); kvfree(scratch); return -ENOMEM; } - ws->input = input; ws->output = output; ws->scratch = scratch; return 0; @@ -134,10 +138,8 @@ void ntfs_wof_free_workspaces(void) struct ntfs_wof_workspace *ws = ntfs_wof_workspaces[i]; mutex_lock(ws->lock); - kvfree(ws->input); kvfree(ws->output); kvfree(ws->scratch); - ws->input = NULL; ws->output = NULL; ws->scratch = NULL; mutex_unlock(ws->lock); @@ -602,6 +604,51 @@ static int ntfs_wof_try_direct(struct ntfs_wof_workspace *ws, chunk_end, src, src_len, dst_len); } +/* + * Decompress one chunk into @folio. Only this step needs the workspace, so it + * is the only step that takes the workspace lock. + */ +static int ntfs_wof_decompress_chunk(struct ntfs_wof_workspace *ws, + struct ntfs_volume *vol, + struct address_space *mapping, + struct folio *folio, loff_t folio_start, + loff_t folio_end, u64 chunk_file_offset, + char *chunk_mem, u32 chunk_size, + u32 decomp_size) +{ + loff_t chunk_end = chunk_file_offset + decomp_size; + loff_t copy_start, copy_end; + int err; + + mutex_lock(ws->lock); + err = ntfs_wof_workspace_prepare(ws); + if (err) + goto out_unlock; + + err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, + chunk_end, chunk_mem, chunk_size, + decomp_size); + if (err != -EAGAIN) + goto out_unlock; + + err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, + decomp_size); + if (err) { + ntfs_error(vol->sb, "Decompression failed: %d", err); + err = -EINVAL; + goto out_unlock; + } + + copy_start = max_t(loff_t, folio_start, chunk_file_offset); + copy_end = min_t(loff_t, folio_end, chunk_file_offset + decomp_size); + memcpy_to_folio(folio, copy_start - folio_start, + ws->output + copy_start - chunk_file_offset, + copy_end - copy_start); +out_unlock: + mutex_unlock(ws->lock); + return err; +} + int ntfs_read_wof_compressed_block(struct folio *folio) { struct address_space *mapping = folio->mapping; @@ -613,6 +660,8 @@ int ntfs_read_wof_compressed_block(struct folio *folio) loff_t folio_start = folio_pos(folio); loff_t folio_end = folio_next_pos(folio); char *chunk_mem; + void *input; + size_t input_size; u32 decomp_size; u64 chunk_count, chunk_idx, last_chunk, chunk_offset; int err = 0; @@ -652,10 +701,12 @@ int ntfs_read_wof_compressed_block(struct folio *folio) goto out_iput; } - mutex_lock(ws->lock); - err = ntfs_wof_workspace_prepare(ws); - if (err) - goto out_unlock_ws; + input_size = ntfs_wof_input_size(ws); + input = kvmalloc(input_size, GFP_NOFS); + if (!input) { + err = -ENOMEM; + goto out_iput; + } chunk_idx = div_u64(folio_start, ws->comp_unit); last_chunk = @@ -663,55 +714,35 @@ int ntfs_read_wof_compressed_block(struct folio *folio) chunk_count = DIV_ROUND_UP_ULL(i_size, ws->comp_unit); for (; chunk_idx <= last_chunk; chunk_idx++) { u32 chunk_size; - u64 chunk_file_offset; - loff_t chunk_end, copy_start, copy_end; decomp_size = chunk_idx + 1 == chunk_count ? i_size - chunk_idx * ws->comp_unit : ws->comp_unit; err = parse_wof_chunk_table(ni, wof_ni, chunk_idx, chunk_count, decomp_size, &chunk_offset, - &chunk_size, ws->input, - ws->input_size); + &chunk_size, input, input_size); if (err) - goto out_unlock_ws; + goto out_free_input; err = ntfs_read_wof_chunk(vol, wof_ni, chunk_offset, chunk_size, - ws->input, ws->input_size, - &chunk_mem); + input, input_size, &chunk_mem); if (err) - goto out_unlock_ws; + goto out_free_input; - chunk_file_offset = chunk_idx * ws->comp_unit; - chunk_end = chunk_file_offset + decomp_size; - err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, - chunk_end, chunk_mem, chunk_size, - decomp_size); - if (!err) - continue; - if (err != -EAGAIN) - goto out_unlock_ws; - - err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, - decomp_size); - if (err) { - ntfs_error(vol->sb, "Decompression failed: %d", err); - err = -EINVAL; - goto out_unlock_ws; - } - copy_start = max_t(loff_t, folio_start, chunk_file_offset); - copy_end = min_t(loff_t, folio_end, - chunk_file_offset + decomp_size); - memcpy_to_folio(folio, copy_start - folio_start, - ws->output + copy_start - chunk_file_offset, - copy_end - copy_start); + err = ntfs_wof_decompress_chunk(ws, vol, mapping, folio, + folio_start, folio_end, + chunk_idx * ws->comp_unit, + chunk_mem, chunk_size, + decomp_size); + if (err) + goto out_free_input; } if (folio_end > i_size) folio_zero_segment(folio, i_size - folio_start, folio_size(folio)); -out_unlock_ws: - mutex_unlock(ws->lock); +out_free_input: + kvfree(input); out_iput: iput(wof_inode); out: diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 204afc5e984b..1c78c695d0dd 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1240,7 +1240,7 @@ static int ignore_hardlimit(struct dquot *dquot) { struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - return capable(CAP_SYS_RESOURCE) && + return capable_noaudit(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || !(info->dqi_flags & DQF_ROOT_SQUASH)); } diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f5aad5f61dce..f8aa9e7b4bc6 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -3555,6 +3555,7 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int bytes_returned = 0; __u16 params, byte_count, data_count, param_offset, offset; + size_t cifs_acl_size, bytes_available; cifs_dbg(FYI, "In SetPosixACL (Unix) for path %s\n", fileName); setAclRetry: @@ -3574,8 +3575,7 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, } params = 6 + name_len; pSMB->MaxParameterCount = cpu_to_le16(2); - /* BB find max SMB size from sess */ - pSMB->MaxDataCount = cpu_to_le16(1000); + pSMB->MaxDataCount = cpu_to_le16(min_t(unsigned int, CIFSMaxBufSize, USHRT_MAX)); pSMB->MaxSetupCount = 0; pSMB->Reserved = 0; pSMB->Flags = 0; @@ -3587,6 +3587,15 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, parm_data = ((char *)pSMB) + offset; pSMB->ParameterOffset = cpu_to_le16(param_offset); + /* make sure we can fit the larger cifs_posix_aces in the buffer */ + cifs_acl_size = sizeof(struct cifs_posix_acl) + + (acl->a_count * sizeof(struct cifs_posix_ace)); + bytes_available = (CIFSMaxBufSize + MAX_HEADER_SIZE(tcon->ses->server)) - offset; + if (cifs_acl_size > bytes_available || cifs_acl_size > USHRT_MAX) { + rc = -E2BIG; + goto setACLerrorExit; + } + /* convert to on the wire format for POSIX ACL */ data_count = posix_acl_to_cifs(parm_data, acl, acl_type); @@ -6325,8 +6334,10 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, int name_len; int rc = 0; int bytes_returned = 0; - __u16 params, param_offset, byte_count, offset, count; + __u16 params, param_offset; + unsigned int byte_count, offset, count; int remap = cifs_remap(cifs_sb); + unsigned int total_len; cifs_dbg(FYI, "In SetEA\n"); SetEARetry: @@ -6378,6 +6389,13 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, pSMB->Reserved3 = 0; pSMB->SubCommand = cpu_to_le16(TRANS2_SET_PATH_INFORMATION); byte_count = 3 /* pad */ + params + count; + if (check_add_overflow(in_len, byte_count, &total_len) || + byte_count > U16_MAX || + total_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { + cifs_dbg(VFS, "EA request too large: %u bytes\n", total_len); + cifs_buf_release(pSMB); + return -E2BIG; + } pSMB->DataCount = cpu_to_le16(count); parm_data->list_len = cpu_to_le32(count); parm_data->list.EA_flags = 0; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index bcd7f1ae99ba..b6e98eb31673 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4189,14 +4189,25 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, return rc; } -static int -cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) +static int set_fs_context_auth(struct smb3_fs_context *ctx, + struct cifs_ses *ses) { ctx->sectype = ses->sectype; - /* krb5 is special, since we don't need username or pw */ - if (ctx->sectype == Kerberos) + /* + * krb5 is special as we might need to pass username (passwordless) down + * to cifs.upcall(8) for keytab. + */ + if (ctx->sectype == Kerberos) { + if (ses->user_name && ses->user_name[0]) { + ctx->username = kstrndup(ses->user_name, + CIFS_MAX_USERNAME_LEN, + GFP_KERNEL); + if (!ctx->username) + return -ENOMEM; + } return 0; + } return cifs_set_cifscreds(ctx, ses); } @@ -4236,7 +4247,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; ctx->unicode = master_tcon->ses->unicode; - rc = cifs_set_vol_auth(ctx, master_tcon->ses); + rc = set_fs_context_auth(ctx, master_tcon->ses); if (rc) { tcon = ERR_PTR(rc); goto out; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index bdcd54157e6c..d7b0a9512dfa 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -999,26 +999,50 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) struct cifs_tcon *tcon; int rc; - rc = filemap_write_and_wait(inode->i_mapping); - if (is_interrupt_error(rc)) + rc = inode_lock_killable(inode); + if (rc) return -ERESTARTSYS; + + filemap_invalidate_lock(inode->i_mapping); + + rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto out; + } mapping_set_error(inode->i_mapping, rc); cfile = find_writable_file(cinode, FIND_FSUID_ONLY); rc = cifs_file_flush(xid, inode, cfile); if (!rc) { if (cfile) { + struct netfs_inode *ictx = netfs_inode(inode); + tcon = tlink_tcon(cfile->tlink); server = tcon->ses->server; + netfs_wb_begin(ictx, false); rc = server->ops->set_file_size(xid, tcon, cfile, 0, false); - } - if (!rc) { - netfs_resize_file(&cinode->netfs, 0, true); - cifs_setsize(inode, 0); + if (!rc) { + netfs_resize_file(&cinode->netfs, 0, true); + cifs_setsize(inode, 0); + cifs_invalidate_cache(inode, 0); + } + netfs_wb_end(ictx); + } else { + /* + * No cached handle; evict stale pages so they can't + * be served after the file is later extended; let + * the server's O_TRUNC open response set the i_size + */ + truncate_inode_pages(inode->i_mapping, 0); cifs_invalidate_cache(inode, 0); } } + +out: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); if (cfile) cifsFileInfo_put(cfile); return rc; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7d6738ffcb80..cb4fd09f996e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1839,31 +1839,31 @@ smb2_ioctl_query_info(const unsigned int xid, * * @tcon: destination file tcon * @bytes_left: how many bytes are left to copy + * @chunk_size: maximum size of a single chunk * * Return: maximum number of chunks with which Chunks[] can be filled. */ static inline u32 -calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left, u32 chunk_size) { 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) + if (!chunk_size || !max_bytes_copy || !max_chunks) return 0; /* chunks needed for the remaining bytes */ - need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + need = DIV_ROUND_UP_ULL(bytes_left, chunk_size); /* chunks allowed per cc request */ - allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + allowed = DIV_ROUND_UP(max_bytes_copy, chunk_size); return (u32)umin(need, umin(max_chunks, allowed)); } /** - * smb2_copychunk_range - server-side copy of data range + * __smb2_copychunk_range - server-side copy of data range * * @xid: transaction id * @src_file: source file @@ -1875,15 +1875,15 @@ calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) * 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. + * Return: 0 on success; negative errno on failure. */ -static ssize_t -smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *src_file, - struct cifsFileInfo *dst_file, - u64 src_off, - u64 len, - u64 dst_off) +static int +__smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { int rc = 0; unsigned int ret_data_len = 0; @@ -1891,12 +1891,14 @@ smb2_copychunk_range(const unsigned int xid, struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; struct srv_copychunk *chunk; - u32 chunks, chunk_count, chunk_bytes; + u32 chunks, chunk_count, chunk_bytes, chunk_size; u32 copy_bytes, copy_bytes_left; u32 chunks_written, bytes_written; u64 total_bytes_left = len; u64 src_off_prev, dst_off_prev; + u64 max_chunk = 0; u32 retries = 0; + bool reverse = false; tcon = tlink_tcon(dst_file->tlink); @@ -1904,8 +1906,50 @@ smb2_copychunk_range(const unsigned int xid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); + /* + * Same-file left shifts are safe in forward order. For a right shift, + * let L be the copy length, delta the distance between the source and + * destination, and C the normal chunk size: + * + * delta >= L: copy forwards using C + * delta < L: + * delta >= C: copy backwards using C + * delta < C: copy backwards with chunks limited to delta + * + * Copying backwards prevents one chunk from overwriting data needed by + * a later chunk. Limiting the chunk size to delta prevents an individual + * chunk from overlapping itself. + * This limit can be removed once all supported servers handle overlapping + * descriptors safely. + * + * A small right shift over a large range may therefore require many + * chunks. + */ + if (src_file == dst_file && dst_off > src_off) { + u64 delta = dst_off - src_off; + + if (delta < len) { + reverse = true; + max_chunk = delta; + } + } + + /* + * A backward copy walks the offsets down from the end of the range. + * Do this once, outside the retry loop, so a retry does not move the + * offsets again. + */ + if (reverse) { + src_off += len; + dst_off += len; + } + retry: - chunk_count = calc_chunk_count(tcon, total_bytes_left); + chunk_size = READ_ONCE(tcon->max_bytes_chunk); + if (max_chunk && max_chunk < chunk_size) + chunk_size = (u32)max_chunk; + + chunk_count = calc_chunk_count(tcon, total_bytes_left, chunk_size); if (!chunk_count) { rc = -EOPNOTSUPP; goto out; @@ -1946,16 +1990,21 @@ smb2_copychunk_range(const unsigned int xid, while (copy_bytes_left > 0 && chunks < chunk_count) { chunk = &cc_req->Chunks[chunks++]; + chunk_bytes = umin(copy_bytes_left, chunk_size); + if (reverse) { + src_off -= chunk_bytes; + dst_off -= chunk_bytes; + } + chunk->SourceOffset = cpu_to_le64(src_off); chunk->TargetOffset = cpu_to_le64(dst_off); - - chunk_bytes = umin(copy_bytes_left, 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; + if (!reverse) { + src_off += chunk_bytes; + dst_off += chunk_bytes; + } copy_bytes_left -= chunk_bytes; copy_bytes += chunk_bytes; @@ -2003,6 +2052,18 @@ smb2_copychunk_range(const unsigned int xid, goto out; } + /* + * A successful COPYCHUNK should copy every descriptor (MS-SMB2 + * 3.3.5.15.6). Reject a short backward copy because the rewind + * below only supports forward copying. + */ + if (unlikely(reverse && bytes_written < copy_bytes)) { + cifs_tcon_dbg(VFS, "Copychunk short write %u/%u (reverse)\n", + bytes_written, copy_bytes); + rc = -EIO; + goto out; + } + /* Partial write: rewind */ if (bytes_written < copy_bytes) { u32 delta = copy_bytes - bytes_written; @@ -2064,10 +2125,27 @@ smb2_copychunk_range(const unsigned int xid, 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; + return 0; } } +static ssize_t +smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) +{ + int rc; + + rc = __smb2_copychunk_range(xid, src_file, dst_file, src_off, len, + dst_off); + if (rc) + return rc; + return len; +} + static int smb2_flush_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) @@ -2218,7 +2296,7 @@ smb2_duplicate_extents(const unsigned int xid, trgtfile->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dest_off, len); inode = d_inode(trgtfile->dentry); - if (inode->i_size < dest_off + len) { + if (i_size_read(inode) < dest_off + len) { rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); if (rc) goto duplicate_extents_out; @@ -2235,7 +2313,10 @@ smb2_duplicate_extents(const unsigned int xid, if (ret_data_len > 0) cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); - if (rc == 0) { + if (rc) { + CIFS_I(inode)->time = 0; /* force reval */ + cifs_invalidate_cache(inode, 0); + } else { qrc = SMB2_query_info(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, &file_inf); spin_lock(&inode->i_lock); @@ -3441,6 +3522,13 @@ 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); + new_size = offset + len; + if (!keep_size && i_size_read(inode) < new_size) { + rc = inode_newsize_ok(inode, new_size); + if (rc) + goto out; + } + filemap_invalidate_lock(inode->i_mapping); netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); @@ -3464,6 +3552,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, if (keep_size == false && !CIFS_CACHE_READ(cifsi)) goto zero_range_exit; + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); + rc = smb3_zero_data(file, tcon, offset, len, xid); if (rc < 0) goto zero_range_exit; @@ -3471,7 +3562,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, /* * do we also need to change the size of the file? */ - new_size = offset + len; if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) { rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_size); @@ -3488,6 +3578,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); + out: free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3533,6 +3624,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, */ truncate_pagecache_range(inode, offset, offset + len - 1); netfs_wait_for_outstanding_io(inode); + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -3938,18 +4031,26 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, } filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); + spin_lock(&inode->i_lock); netfs_write_zero_point(inode, old_eof); spin_unlock(&inode->i_lock); - netfs_wait_for_outstanding_io(inode); - rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - old_eof - off - len, off); + rc = __smb2_copychunk_range(xid, cfile, cfile, off + len, + old_eof - off - len, off); if (rc < 0) goto out_2; @@ -3982,7 +4083,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); - __u64 count, old_eof, new_eof; + loff_t old_eof, new_eof; xid = get_xid(); @@ -3992,15 +4093,32 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out; } - count = old_eof - off; - new_eof = old_eof + len; + if (check_add_overflow(old_eof, len, &new_eof)) { + rc = -EFBIG; + goto out; + } + rc = inode_newsize_ok(inode, new_eof); + if (rc) + goto out; + + /* SET_ZERO_DATA creates a hole only in a sparse file. */ + rc = smb2_set_sparse(xid, tcon, cfile, inode, true); + if (rc) + goto out; filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); @@ -4013,7 +4131,12 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); - rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); + /* + * Move [off, old_eof) right by len. The helper copies backwards if the + * source and destination ranges overlap. + */ + rc = __smb2_copychunk_range(xid, cfile, cfile, off, old_eof - off, + off + len); if (rc < 0) goto out_2; spin_lock(&inode->i_lock); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index fdf4e50c27ce..e266859818a4 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -101,12 +101,11 @@ void __release_mid(struct TCP_Server_Info *server, struct mid_q_entry *midEntry) trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { - pr_debug("slow rsp: cmd %d mid %llu", - midEntry->command, midEntry->mid); - cifs_info("A: 0x%lx S: 0x%lx R: 0x%lx\n", - now - midEntry->when_alloc, - now - midEntry->when_sent, - now - midEntry->when_received); + pr_debug("slow rsp: cmd %d mid %llu A: 0x%lx S: 0x%lx R: 0x%lx\n", + midEntry->command, midEntry->mid, + now - midEntry->when_alloc, + now - midEntry->when_sent, + now - midEntry->when_received); } } #endif diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 91fdd1ddc61f..4cb92d6599ee 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -13,6 +13,7 @@ #include "mgmt/ksmbd_ida.h" #include "mgmt/user_session.h" #include "connection.h" +#include "vfs_cache.h" #include "compress.h" #include "transport_tcp.h" #include "transport_rdma.h" @@ -384,12 +385,12 @@ static void ksmbd_conn_cancel_async_requests(struct ksmbd_conn *conn) spin_lock(&conn->request_lock); list_for_each_entry_safe(work, tmp, &conn->async_requests, async_request_entry) { - if (work->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&work->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) continue; ksmbd_debug(CONN, "Cancel async request id %d\n", work->async_id); - work->state = KSMBD_WORK_CANCELLED; if (work->cancel_fn) work->cancel_fn(work->cancel_argv); } @@ -473,6 +474,9 @@ int ksmbd_conn_wait_idle_sess(struct ksmbd_conn *curr_conn, if (retry_count >= max_timeout) return -EIO; + /* A blocked byte-range lock cannot drain until teardown wakes it. */ + ksmbd_wake_session_blocked_works(sess); + down_read(&conn_list_lock); hash_for_each(conn_list, bkt, conn, hlist) { if (ksmbd_session_is_bound_to_conn(sess, conn)) { diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index b2d9580bddc6..cc9f18ede80d 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -146,9 +146,9 @@ static struct ksmbd_share_config *__share_lookup(const char *name) static int parse_veto_list(struct ksmbd_share_config *share, char *veto_list, - int veto_list_sz) + size_t veto_list_sz) { - int sz = 0; + size_t sz; if (!veto_list_sz) return 0; @@ -156,7 +156,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, while (veto_list_sz > 0) { struct ksmbd_veto_pattern *p; - sz = strlen(veto_list); + sz = strnlen(veto_list, veto_list_sz); if (!sz) break; @@ -164,7 +164,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, if (!p) return -ENOMEM; - p->pattern = kstrdup(veto_list, KSMBD_DEFAULT_GFP); + p->pattern = kstrndup(veto_list, sz, KSMBD_DEFAULT_GFP); if (!p->pattern) { kfree(p); return -ENOMEM; @@ -172,6 +172,9 @@ static int parse_veto_list(struct ksmbd_share_config *share, list_add(&p->list, &share->veto_list); + if (sz == veto_list_sz) + break; + veto_list += sz + 1; veto_list_sz -= (sz + 1); } @@ -224,17 +227,28 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, } if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - int path_len = PATH_MAX; + size_t path_len; - if (resp->payload_sz) - path_len = resp->payload_sz - resp->veto_list_sz; - - share->path = kstrndup(ksmbd_share_config_path(resp), path_len, - KSMBD_DEFAULT_GFP); - if (!share->path) { - ret = -ENOMEM; + if (resp->payload_sz <= resp->veto_list_sz) { + ret = -EINVAL; } else { - ret = 0; + path_len = resp->payload_sz - resp->veto_list_sz; + if (resp->veto_list_sz) + path_len--; + + if (!path_len) { + ret = -EINVAL; + } else { + share->path = kstrndup( + ksmbd_share_config_path(resp), + path_len, KSMBD_DEFAULT_GFP); + if (!share->path) + ret = -ENOMEM; + else + ret = 0; + } + } + if (share->path) { share->path_sz = strlen(share->path); while (share->path_sz > 1 && share->path[share->path_sz - 1] == '/') diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 7022d5d656b4..2eb8f730e99e 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -666,10 +666,21 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out; + down_write(&prev_sess->chann_lock); + if (prev_sess->tearing_down) { + up_write(&prev_sess->chann_lock); + goto out; + } + prev_sess->tearing_down = true; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_RECONNECT); err = ksmbd_conn_wait_idle_sess(conn, prev_sess); if (err) { - ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_SETUP); + down_write(&prev_sess->chann_lock); + prev_sess->tearing_down = false; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_GOOD); goto out; } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f8a24c33f7fe..3e52d4cc1324 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -42,6 +42,7 @@ struct ksmbd_session { bool sign; bool enc; + bool tearing_down; int state; __u8 *Preauth_HashValue; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a8046f477d54..d656832d82ef 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -97,6 +97,11 @@ static int register_session_channel(struct ksmbd_session *sess, int rc = 0; down_write(&sess->chann_lock); + if (sess->tearing_down) { + rc = -ESHUTDOWN; + goto out; + } + if (xa_load(&sess->ksmbd_chann_list, (long)conn)) goto out; @@ -873,7 +878,8 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) req = smb_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || - req->FileInfoClass == FILE_ALL_INFORMATION)) || + req->FileInfoClass == FILE_ALL_INFORMATION || + req->FileInfoClass == FILE_NORMALIZED_NAME_INFORMATION)) || req->InfoType == SMB2_O_INFO_SECURITY) sz = large_sz; } @@ -3086,17 +3092,41 @@ int smb2_session_logoff(struct ksmbd_work *work) smb2_set_err_rsp(work); return -ENOENT; } + + down_write(&sess->chann_lock); + if (sess->tearing_down) { + up_write(&sess->chann_lock); + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_USER_SESSION_DELETED; + smb2_set_err_rsp(work); + return -ENOENT; + } + sess->tearing_down = true; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_RECONNECT); ksmbd_conn_unlock(conn); + err = ksmbd_conn_wait_idle_sess(conn, sess); + if (err) { + down_write(&sess->chann_lock); + sess->tearing_down = false; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_GOOD); + rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; + smb2_set_err_rsp(work); + return err; + } + ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return -ENOENT; + err = -ENOENT; + } else { + err = 0; } down_write(&conn->session_lock); @@ -3106,6 +3136,9 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_SETUP); + if (err) + return err; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); if (err) { @@ -6757,7 +6790,7 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, { struct smb2_file_alt_name_info *file_info; char *filename, *normalized, *stream_name; - int conv_len, filename_len; + int buf_free_len, conv_len, filename_len; if (work->conn->dialect < SMB311_PROT_ID) { rsp->hdr.Status = STATUS_NOT_SUPPORTED; @@ -6781,6 +6814,14 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, return -ENOMEM; filename_len = strlen(normalized); + buf_free_len = smb2_resp_buf_len(work, sizeof(*rsp) + + sizeof(*file_info)); + if (buf_free_len < 0 || + (size_t)buf_free_len < (filename_len + 1) * sizeof(__le16)) { + kfree(normalized); + return -EINVAL; + } + file_info = (struct smb2_file_alt_name_info *)rsp->Buffer; conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, normalized, filename_len, @@ -7444,6 +7485,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct object_id_info *info; info = (struct object_id_info *)(rsp->Buffer); + memset(info, 0, sizeof(*info)); if (path.mnt->mnt_sb->s_uuid_len == 16) memcpy(info->objid, path.mnt->mnt_sb->s_uuid.b, @@ -7499,6 +7541,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FreeSpaceStopFiltering = 0; info->DefaultQuotaThreshold = cpu_to_le64(SMB2_NO_FID); info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); + info->FileSystemControlFlags = 0; info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); fixed_len = 48; @@ -7521,6 +7564,9 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->UserBlocksAvail = cpu_to_le64(stfs.f_bavail); info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); + info->FileSysIdentifier = + cpu_to_le64((u64)(u32)stfs.f_fsid.val[1] << 32 | + (u32)stfs.f_fsid.val[0]); rsp->OutputBufferLength = cpu_to_le32(56); fixed_len = 56; } @@ -8620,13 +8666,18 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) } aux_payload_buf = - kvmalloc(rpc_resp->payload_sz, KSMBD_DEFAULT_GFP); + kvmalloc(ALIGN(rpc_resp->payload_sz, 8), + KSMBD_DEFAULT_GFP); if (!aux_payload_buf) { err = -ENOMEM; goto out; } memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); + if (rpc_resp->payload_sz & 7) + memset(aux_payload_buf + rpc_resp->payload_sz, 0, + ALIGN(rpc_resp->payload_sz, 8) - + rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, @@ -9680,14 +9731,14 @@ int smb2_cancel(struct ksmbd_work *work) * still on conn->async_requests with a live cancel_fn * pointing at the freed file_lock. */ - if (iter->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) break; ksmbd_debug(SMB, "smb2 with AsyncId %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->Id.AsyncId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; if (iter->cancel_fn == smb2_notify_cancel_fn) cancelled_notify = smb2_notify_cancel_claim(iter->cancel_argv); @@ -9716,11 +9767,16 @@ int smb2_cancel(struct ksmbd_work *work) iter == work) continue; + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) + break; + ksmbd_debug(SMB, "smb2 with mid %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->MessageId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; + if (iter->cancel_fn) + iter->cancel_fn(iter->cancel_argv); break; } spin_unlock(&conn->request_lock); diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 8ad2e5a5cca8..1fad6ccf3a72 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -383,10 +383,10 @@ void free_acl_state(struct posix_acl_state *state) kfree(state->groups); } -static void parse_dacl(struct mnt_idmap *idmap, - struct smb_acl *pdacl, char *end_of_acl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_fattr *fattr) +static int parse_dacl(struct mnt_idmap *idmap, + struct smb_acl *pdacl, char *end_of_acl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_fattr *fattr) { int i, ret; u16 num_aces = 0; @@ -400,13 +400,13 @@ static void parse_dacl(struct mnt_idmap *idmap, bool owner_found = false, group_found = false, others_found = false; if (!pdacl) - return; + return 0; /* validate that we do not go past end of acl */ if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); - return; + return -EINVAL; } ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n", @@ -418,31 +418,31 @@ static void parse_dacl(struct mnt_idmap *idmap, num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces <= 0) - return; + return 0; dacl_size = le16_to_cpu(pdacl->size); if (dacl_size < sizeof(struct smb_acl)) - return; + return -EINVAL; if (num_aces > (dacl_size - sizeof(struct smb_acl)) / (offsetof(struct smb_ace, sid) + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) - return; + return -EINVAL; ret = init_acl_state(&acl_state, num_aces); if (ret) - return; + return ret; ret = init_acl_state(&default_acl_state, num_aces); if (ret) { free_acl_state(&acl_state); - return; + return ret; } ppace = kmalloc_objs(struct smb_ace *, num_aces, KSMBD_DEFAULT_GFP); if (!ppace) { free_acl_state(&default_acl_state); free_acl_state(&acl_state); - return; + return -ENOMEM; } /* @@ -451,8 +451,10 @@ static void parse_dacl(struct mnt_idmap *idmap, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { - if (end_of_acl - acl_base < acl_size) - break; + if (end_of_acl - acl_base < acl_size) { + ret = -EINVAL; + goto out; + } ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; @@ -465,8 +467,10 @@ static void parse_dacl(struct mnt_idmap *idmap, (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || (le16_to_cpu(ppace[i]->size) < - acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) - break; + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) { + ret = -EINVAL; + goto out; + } acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = @@ -524,8 +528,8 @@ static void parse_dacl(struct mnt_idmap *idmap, temp_fattr.cf_uid = INVALID_UID; ret = sid_to_id(idmap, &ppace[i]->sid, SIDOWNER, &temp_fattr); if (ret || uid_eq(temp_fattr.cf_uid, INVALID_UID)) { - pr_err("%s: Error %d mapping Owner SID to uid\n", - __func__, ret); + pr_err_ratelimited("%s: Error %d mapping Owner SID to uid\n", + __func__, ret); continue; } @@ -541,7 +545,6 @@ static void parse_dacl(struct mnt_idmap *idmap, ((acl_mode & 0700) >> 6) | 0004; } } - kfree(ppace); if (owner_found) { /* The owner must be set to at least read-only. */ @@ -584,10 +587,12 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_acls = posix_acl_alloc(acl_state.users->n + acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_acls) { - cf_pace = fattr->cf_acls->a_entries; - posix_state_to_acl(&acl_state, cf_pace); + if (!fattr->cf_acls) { + ret = -ENOMEM; + goto out; } + cf_pace = fattr->cf_acls->a_entries; + posix_state_to_acl(&acl_state, cf_pace); } } @@ -598,14 +603,20 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_dacls = posix_acl_alloc(default_acl_state.users->n + default_acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_dacls) { - cf_pdace = fattr->cf_dacls->a_entries; - posix_state_to_acl(&default_acl_state, cf_pdace); + if (!fattr->cf_dacls) { + ret = -ENOMEM; + goto out; } + cf_pdace = fattr->cf_dacls->a_entries; + posix_state_to_acl(&default_acl_state, cf_pdace); } } + ret = 0; +out: + kfree(ppace); free_acl_state(&acl_state); free_acl_state(&default_acl_state); + return ret; } static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, @@ -966,8 +977,10 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, if (dacloffset < sizeof(struct smb_ntsd)) return -EINVAL; - parse_dacl(idmap, dacl_ptr, end_of_acl, - owner_sid_ptr, group_sid_ptr, fattr); + rc = parse_dacl(idmap, dacl_ptr, end_of_acl, + owner_sid_ptr, group_sid_ptr, fattr); + if (rc) + return rc; } return 0; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 4b0b572a3e1b..e550aa41ad2c 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -532,14 +532,21 @@ static int ipc_validate_msg(struct ipc_msg_table_entry *entry) if (entry->msg_sz < sizeof(struct ksmbd_share_config_response)) return -EINVAL; - if (resp->payload_sz) { - if (resp->payload_sz < resp->veto_list_sz) - return -EINVAL; + if (strnlen(resp->share_name, sizeof(resp->share_name)) == + sizeof(resp->share_name)) + return -EINVAL; - if (check_add_overflow(sizeof(struct ksmbd_share_config_response), - resp->payload_sz, &msg_sz)) - return -EINVAL; - } + if (resp->veto_list_sz > resp->payload_sz) + return -EINVAL; + + if (resp->flags != KSMBD_SHARE_FLAG_INVALID && + !(resp->flags & KSMBD_SHARE_FLAG_PIPE) && + resp->payload_sz <= resp->veto_list_sz) + return -EINVAL; + + if (check_add_overflow(sizeof(struct ksmbd_share_config_response), + resp->payload_sz, &msg_sz)) + return -EINVAL; break; } case KSMBD_EVENT_LOGIN_REQUEST_EXT: diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 832e93084605..4968cfc1a572 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -39,6 +39,7 @@ struct tcp_transport { static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); +static void ksmbd_tcp_stop_listener(struct interface *iface); static struct interface *alloc_iface(char *ifname); static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); @@ -321,13 +322,20 @@ static int ksmbd_tcp_run_kthread(struct interface *iface) int rc; struct task_struct *kthread; - kthread = kthread_run(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", - iface->name); + kthread = kthread_create(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", + iface->name); if (IS_ERR(kthread)) { rc = PTR_ERR(kthread); return rc; } + + /* + * The listener can exit after its socket is shutdown, so keep the + * task_struct alive until the caller has stopped it. + */ + get_task_struct(kthread); iface->ksmbd_kthread = kthread; + wake_up_process(kthread); return 0; } @@ -598,12 +606,7 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, if (iface && iface->state == IFACE_STATE_CONFIGURED) { ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", iface->name); - kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - sock_release(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - + ksmbd_tcp_stop_listener(iface); iface->state = IFACE_STATE_DOWN; break; } @@ -631,11 +634,25 @@ static void tcp_stop_kthread(struct task_struct *kthread) if (!kthread) return; - ret = kthread_stop(kthread); + ret = kthread_stop_put(kthread); if (ret) pr_err("failed to stop forker thread\n"); } +static void ksmbd_tcp_stop_listener(struct interface *iface) +{ + if (iface->ksmbd_socket) + kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); + + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + + if (iface->ksmbd_socket) { + sock_release(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + } +} + void ksmbd_tcp_destroy(void) { struct interface *iface, *tmp; @@ -643,6 +660,7 @@ void ksmbd_tcp_destroy(void) unregister_netdevice_notifier(&ksmbd_netdev_notifier); list_for_each_entry_safe(iface, tmp, &iface_list, entry) { + ksmbd_tcp_stop_listener(iface); list_del(&iface->entry); kfree(iface->name); kfree(iface); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 81626d204249..fd2c595f0486 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -846,12 +846,25 @@ static void set_close_state_blocked_works(struct ksmbd_file *fp) spin_lock(&fp->f_lock); list_for_each_entry(cancel_work, &fp->blocked_works, fp_entry) { - cancel_work->state = KSMBD_WORK_CLOSED; - cancel_work->cancel_fn(cancel_work->cancel_argv); + if (xchg(&cancel_work->state, KSMBD_WORK_CLOSED) == + KSMBD_WORK_ACTIVE) + cancel_work->cancel_fn(cancel_work->cancel_argv); } spin_unlock(&fp->f_lock); } +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess) +{ + struct ksmbd_file_table *ft = &sess->file_table; + struct ksmbd_file *fp; + unsigned int id; + + read_lock(&ft->lock); + idr_for_each_entry(ft->idr, fp, id) + set_close_state_blocked_works(fp); + read_unlock(&ft->lock); +} + int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 502efb16f05f..1884f6deb9d0 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -226,6 +226,7 @@ void ksmbd_stop_durable_scavenger(void); bool ksmbd_durable_scavenger_active(void); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); void ksmbd_close_session_fds(struct ksmbd_work *work); +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess); int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 604ba3e841d2..6e3513b13cfa 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -438,6 +438,8 @@ static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char if (!ei->name) return NULL; kref_init(&ei->kref); + INIT_LIST_HEAD(&ei->children); + INIT_LIST_HEAD(&ei->list); return ei; } @@ -729,8 +731,6 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode ei->entries = entries; ei->nr_entries = size; ei->data = data; - INIT_LIST_HEAD(&ei->children); - INIT_LIST_HEAD(&ei->list); scoped_guard(mutex, &eventfs_mutex) { if (!parent->is_freed) @@ -802,9 +802,6 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ei->attr.uid = uid; ei->attr.gid = gid; - INIT_LIST_HEAD(&ei->children); - INIT_LIST_HEAD(&ei->list); - ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; ti->private = ei; diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c index a4a0158f712d..1f770795ee70 100644 --- a/fs/ubifs/auth.c +++ b/fs/ubifs/auth.c @@ -217,7 +217,7 @@ int ubifs_sb_verify_signature(struct ubifs_info *c, signode = snod->node; - if (le32_to_cpu(signode->len) > snod->len + sizeof(struct ubifs_sig_node)) { + if (le32_to_cpu(signode->len) > snod->len - sizeof(struct ubifs_sig_node)) { ubifs_err(c, "invalid signature len %d", le32_to_cpu(signode->len)); err = -EINVAL; goto out_destroy; diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index d425861e6b82..48cd64eb2d01 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -26,7 +26,7 @@ typedef int (*dbg_znode_callback)(struct ubifs_info *c, #define UBIFS_DFS_DIR_LEN (3 + 1 + 2 + 3 + 1) /** - * ubifs_debug_info - per-FS debugging information. + * struct ubifs_debug_info - per-FS debugging information. * @old_zroot: old index root - used by 'dbg_check_old_index()' * @old_zroot_level: old index root level - used by 'dbg_check_old_index()' * @old_zroot_sqnum: old index root sqnum - used by 'dbg_check_old_index()' @@ -119,7 +119,7 @@ struct ubifs_debug_info { }; /** - * ubifs_global_debug_info - global (not per-FS) UBIFS debugging information. + * struct ubifs_global_debug_info - global (not per-FS) UBIFS debugging information. * * @chk_gen: if general extra checks are enabled * @chk_index: if index xtra checks are enabled diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 8142d9d6fe5d..71497c1b4753 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -33,7 +33,7 @@ /** * key_mask_hash - mask a valid hash value. - * @val: value to be masked + * @hash: value to be masked * * We use hash values as offset in directories, so values %0 and %1 are * reserved for "." and "..". %2 is reserved for "end of readdir" marker. This diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index b62a154c7bd4..00db0d19a85e 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -738,6 +738,7 @@ struct ubifs_jhead { * struct ubifs_zbranch - key/coordinate/length branch stored in znodes. * @key: key * @znode: znode address in memory + * @leaf: leaf node * @lnum: LEB number of the target node (indexing node or data node) * @offs: target node offset within @lnum * @len: target node length @@ -801,7 +802,7 @@ struct ubifs_znode { * @gc_seq: GC sequence number to detect races with GC * @cnt: number of data nodes for bulk read * @blk_cnt: number of data blocks including holes - * @oef: end of file reached + * @eof: end of file reached */ struct bu_info { union ubifs_key key; @@ -985,7 +986,7 @@ struct ubifs_budg_info { }; /** - * ubifs_stats_info - per-FS statistics information. + * struct ubifs_stats_info - per-FS statistics information. * @magic_errors: number of bad magic numbers (will be reset with a new mount). * @node_errors: number of bad nodes (will be reset with a new mount). * @crc_errors: number of bad crcs (will be reset with a new mount). @@ -1051,6 +1052,7 @@ struct ubifs_debug_info; * @rw_incompat: the media is not R/W compatible * @assert_action: action to take when a ubifs_assert() fails * @authenticated: flag indigating the FS is mounted in authenticated mode + * @superblock_need_write: superblock node needs to be written * * @tnc_mutex: protects the Tree Node Cache (TNC), @zroot, @cnext, @enext, and * @calc_idx_sz @@ -1588,8 +1590,9 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node, * @expected: first hash * @got: second hash * - * Compare two hashes @expected and @got. Returns 0 when they are equal, a - * negative error code otherwise. + * Compare two hashes @expected and @got. + * + * Returns: 0 when they are equal, a negative error code otherwise. */ static inline int ubifs_check_hash(const struct ubifs_info *c, const u8 *expected, const u8 *got) @@ -1603,8 +1606,9 @@ static inline int ubifs_check_hash(const struct ubifs_info *c, * @expected: first HMAC * @got: second HMAC * - * Compare two hashes @expected and @got. Returns 0 when they are equal, a - * negative error code otherwise. + * Compare two hashes @expected and @got. + * + * Returns: 0 when they are equal, a negative error code otherwise. */ static inline int ubifs_check_hmac(const struct ubifs_info *c, const u8 *expected, const u8 *got) @@ -1644,7 +1648,7 @@ static inline void ubifs_exit_authentication(struct ubifs_info *c) * @c: UBIFS file-system description object * @br: branch to get the hash from * - * This returns a pointer to the hash of a branch. Since the key already is a + * Returns: a pointer to the hash of a branch. Since the key already is a * dynamically sized object we cannot use a struct member here. */ static inline u8 *ubifs_branch_hash(struct ubifs_info *c, @@ -1694,7 +1698,7 @@ static inline int ubifs_node_verify_hmac(const struct ubifs_info *c, * ubifs_auth_node_sz - returns the size of an authentication node * @c: UBIFS file-system description object * - * This function returns the size of an authentication node which can + * Returns: the size of an authentication node which can * be 0 for unauthenticated filesystems or the real size of an auth node * authentication is enabled. */ diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 9f7133e02576..399a207f2d0e 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -91,6 +91,7 @@ xfs-y += xfs_aops.o \ xfs_healthmon.o \ xfs_icache.o \ xfs_ioctl.o \ + xfs_ioend.o \ xfs_iomap.o \ xfs_iops.o \ xfs_inode.o \ diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index c0b9f9f2c413..fca2eb74908c 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -359,7 +359,11 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) # define xfs_update_rtsb(bp, sb_bp) ((void)0) -# define xfs_log_rtsb(tp, sb_bp) (NULL) +static inline struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp, + const struct xfs_buf *sb_bp) +{ + return NULL; +} # define xfs_rtgroup_get_geometry(rtg, rgeo) (-EOPNOTSUPP) #endif /* CONFIG_XFS_RT */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 75f2a021ee6d..f0341adbb879 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1470,36 +1470,33 @@ xfs_sync_sb_buf( bool update_rtsb) { struct xfs_trans *tp; - struct xfs_buf *bp; - struct xfs_buf *rtsb_bp = NULL; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); if (error) return error; - bp = xfs_trans_getsb(tp); xfs_log_sb(tp); - xfs_trans_bhold(tp, bp); - if (update_rtsb) { - rtsb_bp = xfs_log_rtsb(tp, bp); - if (rtsb_bp) - xfs_trans_bhold(tp, rtsb_bp); - } + if (update_rtsb) + xfs_log_rtsb(tp, xfs_trans_getsb(tp)); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) - goto out; - /* - * write out the sb buffer to get the changes to disk - */ - error = xfs_bwrite(bp); - if (!error && rtsb_bp) - error = xfs_bwrite(rtsb_bp); -out: - if (rtsb_bp) - xfs_buf_relse(rtsb_bp); - xfs_buf_relse(bp); + return error; + + /* Re-acquire and write the sb and rtsb to disk. */ + xfs_buf_lock(mp->m_sb_bp); + error = xfs_bwrite(mp->m_sb_bp); + xfs_buf_unlock(mp->m_sb_bp); + if (error) + return error; + + if (update_rtsb && mp->m_rtsb_bp) { + xfs_buf_lock(mp->m_rtsb_bp); + error = xfs_bwrite(mp->m_rtsb_bp); + xfs_buf_unlock(mp->m_rtsb_bp); + } + return error; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 74a6089abadf..8b6119776fb3 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -20,6 +20,7 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_icache.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_rtgroup.h" #include @@ -36,15 +37,6 @@ XFS_WPC(struct iomap_writepage_ctx *ctx) return container_of(ctx, struct xfs_writepage_ctx, ctx); } -/* - * Fast and loose check if this write could update the on-disk inode size. - */ -static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) -{ - return ioend->io_offset + ioend->io_size > - XFS_I(ioend->io_inode)->i_disk_size; -} - /* * Update on-disk file size now that data has been written to disk. */ @@ -80,175 +72,6 @@ xfs_setfilesize( return xfs_trans_commit(tp); } -static void -xfs_ioend_put_open_zones( - struct iomap_ioend *ioend) -{ - struct iomap_ioend *tmp; - - /* - * Put the open zone for all ioends merged into this one (if any). - */ - list_for_each_entry(tmp, &ioend->io_list, io_list) - xfs_open_zone_put(tmp->io_private); - - /* - * The main ioend might not have an open zone if the submission failed - * before xfs_zone_alloc_and_submit got called. - */ - if (ioend->io_private) - xfs_open_zone_put(ioend->io_private); -} - -/* - * IO write completion. - */ -STATIC void -xfs_end_ioend_write( - struct iomap_ioend *ioend) -{ - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - bool is_zoned = xfs_is_zoned_inode(ip); - xfs_off_t offset = ioend->io_offset; - size_t size = ioend->io_size; - unsigned int nofs_flag; - int error; - - /* - * We can allocate memory here while doing writeback on behalf of - * memory reclaim. To avoid memory allocation deadlocks set the - * task-wide nofs context for the following operations. - */ - nofs_flag = memalloc_nofs_save(); - - /* - * Just clean up the in-memory structures if the fs has been shut down. - */ - if (xfs_is_shutdown(mp)) { - error = -EIO; - goto done; - } - - /* - * Clean up all COW blocks and underlying data fork delalloc blocks on - * I/O error. The delalloc punch is required because this ioend was - * mapped to blocks in the COW fork and the associated pages are no - * longer dirty. If we don't remove delalloc blocks here, they become - * stale and can corrupt free space accounting on unmount. - */ - error = blk_status_to_errno(ioend->io_bio.bi_status); - if (unlikely(error)) { - /* - * Zoned writes update the in-core open zone accounting before - * I/O submission. A failed write leaves that state - * inconsistent, so shut down the filesystem instead of letting - * later writers wait forever for open zone space to become - * available. - */ - if (is_zoned) { - xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); - goto done; - } - if (ioend->io_flags & IOMAP_IOEND_SHARED) { - ASSERT(!is_zoned); - xfs_reflink_cancel_cow_range(ip, offset, size, true); - xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, - offset + size, NULL); - } - goto done; - } - - /* - * Success: commit the COW or unwritten blocks if needed. - */ - if (is_zoned) - error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, - ioend->io_private, NULLFSBLOCK); - else if (ioend->io_flags & IOMAP_IOEND_SHARED) - error = xfs_reflink_end_cow(ip, offset, size); - else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size, false); - - if (!error && - !(ioend->io_flags & IOMAP_IOEND_DIRECT) && - xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, offset, size); -done: - if (is_zoned) - xfs_ioend_put_open_zones(ioend); - iomap_finish_ioends(ioend, error); - memalloc_nofs_restore(nofs_flag); -} - -/* - * Finish all pending IO completions that require transactional modifications. - * - * We try to merge physical and logically contiguous ioends before completion to - * minimise the number of transactions we need to perform during IO completion. - * Both unwritten extent conversion and COW remapping need to iterate and modify - * one physical extent at a time, so we gain nothing by merging physically - * discontiguous extents here. - * - * The ioend chain length that we can be processing here is largely unbound in - * length and we may have to perform significant amounts of work on each ioend - * to complete it. Hence we have to be careful about holding the CPU for too - * long in this loop. - */ -void -xfs_end_io( - struct work_struct *work) -{ - struct xfs_inode *ip = - container_of(work, struct xfs_inode, i_ioend_work); - struct iomap_ioend *ioend; - struct list_head tmp; - unsigned long flags; - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - list_replace_init(&ip->i_ioend_list, &tmp); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - - iomap_sort_ioends(&tmp); - while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, - io_list))) { - list_del_init(&ioend->io_list); - iomap_ioend_try_merge(ioend, &tmp); - if (bio_op(&ioend->io_bio) == REQ_OP_READ) - iomap_finish_ioends(ioend, - blk_status_to_errno(ioend->io_bio.bi_status)); - else - xfs_end_ioend_write(ioend); - cond_resched(); - } -} - -void -xfs_end_bio( - struct bio *bio) -{ - struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - unsigned long flags; - - /* - * For Appends record the actually written block number and set the - * boundary flag if needed. - */ - if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { - ioend->io_sector = bio->bi_iter.bi_sector; - xfs_mark_rtg_boundary(ioend); - } - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, - &ip->i_ioend_work)); - list_add_tail(&ioend->io_list, &ip->i_ioend_list); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); -} - /* * We cannot cancel the ioend directly on error. We may have already set other * pages under writeback and hence we have to run I/O completion to mark the @@ -631,13 +454,8 @@ xfs_zoned_map_blocks( XFS_BMAPI_REMAP); xfs_iunlock(ip, XFS_ILOCK_EXCL); - wpc->iomap.type = IOMAP_MAPPED; - wpc->iomap.flags = IOMAP_F_DIRTY; - wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; - wpc->iomap.offset = offset; - wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); - wpc->iomap.flags = IOMAP_F_ANON_WRITE; - + xfs_iomap_set_anon_write(ip, &wpc->iomap, offset, + XFS_FSB_TO_B(mp, count_fsb)); trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); return 0; } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 5a7a0f1a0b49..d5ae5c9d4c26 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -10,6 +10,5 @@ extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); -void xfs_end_bio(struct bio *bio); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 7bff07e31cbd..426a67b813a7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,7 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_file.h" -#include "xfs_aops.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_error.h" #include "xfs_errortag.h" diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index b6a3bc9f143c..041bb2105ec6 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -1174,8 +1174,7 @@ xfs_getfsmap( if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1])) return -EINVAL; - use_rmap = xfs_has_rmapbt(mp) && - has_capability_noaudit(current, CAP_SYS_ADMIN); + use_rmap = xfs_has_rmapbt(mp) && capable_noaudit(CAP_SYS_ADMIN); head->fmh_entries = 0; /* Set up our device handlers. */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9d8dd30bd927..a857b8aa255c 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -82,24 +82,20 @@ static inline xa_mark_t ici_tag_to_mark(unsigned int tag) /* * Allocate and initialise an xfs_inode. + * + * This can happen in context of already dirtied transactions, so the memory + * allocations must not fail. */ struct xfs_inode * xfs_inode_alloc( struct xfs_mount *mp, xfs_ino_t ino) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; struct xfs_inode *ip; - /* - * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL - * and return NULL here on ENOMEM. - */ - ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL); - - if (inode_init_always(mp->m_super, VFS_I(ip))) { - kmem_cache_free(xfs_inode_cache, ip); - return NULL; - } + ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, gfp); + inode_init_always_gfp(mp->m_super, VFS_I(ip), gfp); VFS_I(ip)->i_ino = ino; /* VFS doesn't initialise i_mode! */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1b53701bebea..96ca3e480cb9 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -647,7 +647,7 @@ xfs_ioctl_setattr_get_trans( goto out_error; error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, - has_capability_noaudit(current, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_error; diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c new file mode 100644 index 000000000000..40695d18dac0 --- /dev/null +++ b/fs/xfs/xfs_ioend.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2025 Christoph Hellwig. + * All Rights Reserved. + */ +#include "xfs_platform.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_iomap.h" +#include "xfs_trace.h" +#include "xfs_bmap_util.h" +#include "xfs_reflink.h" +#include "xfs_zone_alloc.h" +#include "xfs_ioend.h" + +static void +xfs_ioend_put_open_zones( + struct iomap_ioend *ioend) +{ + struct iomap_ioend *tmp; + + /* + * Put the open zone for all ioends merged into this one (if any). + */ + list_for_each_entry(tmp, &ioend->io_list, io_list) + xfs_open_zone_put(tmp->io_private); + + /* + * The main ioend might not have an open zone if the submission failed + * before xfs_zone_alloc_and_submit got called. + */ + if (ioend->io_private) + xfs_open_zone_put(ioend->io_private); +} + +static void +xfs_end_ioend_write( + struct iomap_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + bool is_zoned = xfs_is_zoned_inode(ip); + xfs_off_t offset = ioend->io_offset; + size_t size = ioend->io_size; + unsigned int nofs_flag; + int error; + + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + + /* + * Just clean up the in-memory structures if the fs has been shut down. + */ + if (xfs_is_shutdown(mp)) { + error = -EIO; + goto done; + } + + /* + * Clean up all COW blocks and underlying data fork delalloc blocks on + * I/O error. The delalloc punch is required because this ioend was + * mapped to blocks in the COW fork and the associated pages are no + * longer dirty. If we don't remove delalloc blocks here, they become + * stale and can corrupt free space accounting on unmount. + */ + error = blk_status_to_errno(ioend->io_bio.bi_status); + if (unlikely(error)) { + /* + * Zoned writes update the in-core open zone accounting before + * I/O submission. A failed write leaves that state + * inconsistent, so shut down the filesystem instead of letting + * later writers wait forever for open zone space to become + * available. + */ + if (is_zoned) { + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + goto done; + } + if (ioend->io_flags & IOMAP_IOEND_SHARED) { + ASSERT(!is_zoned); + xfs_reflink_cancel_cow_range(ip, offset, size, true); + xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, + offset + size, NULL); + } + goto done; + } + + /* + * Success: commit the COW or unwritten blocks if needed. + */ + if (is_zoned) + error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, + ioend->io_private, NULLFSBLOCK); + else if (ioend->io_flags & IOMAP_IOEND_SHARED) + error = xfs_reflink_end_cow(ip, offset, size); + else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) + error = xfs_iomap_write_unwritten(ip, offset, size, false); + + if (!error && + !(ioend->io_flags & IOMAP_IOEND_DIRECT) && + xfs_ioend_is_append(ioend)) + error = xfs_setfilesize(ip, offset, size); +done: + if (is_zoned) + xfs_ioend_put_open_zones(ioend); + iomap_finish_ioends(ioend, error); + memalloc_nofs_restore(nofs_flag); +} + +/* + * Finish all pending IO completions that require transactional modifications. + * + * We try to merge physical and logically contiguous ioends before completion to + * minimise the number of transactions we need to perform during IO completion. + * Both unwritten extent conversion and COW remapping need to iterate and modify + * one physical extent at a time, so we gain nothing by merging physically + * discontiguous extents here. + * + * The ioend chain length that we can be processing here is largely unbound in + * length and we may have to perform significant amounts of work on each ioend + * to complete it. Hence we have to be careful about holding the CPU for too + * long in this loop. + */ +void +xfs_end_io( + struct work_struct *work) +{ + struct xfs_inode *ip = + container_of(work, struct xfs_inode, i_ioend_work); + struct iomap_ioend *ioend; + struct list_head tmp; + unsigned long flags; + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + list_replace_init(&ip->i_ioend_list, &tmp); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); + + iomap_sort_ioends(&tmp); + while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, + io_list))) { + list_del_init(&ioend->io_list); + iomap_ioend_try_merge(ioend, &tmp); + if (bio_op(&ioend->io_bio) == REQ_OP_READ) + iomap_finish_ioends(ioend, + blk_status_to_errno(ioend->io_bio.bi_status)); + else + xfs_end_ioend_write(ioend); + cond_resched(); + } +} + +void +xfs_end_bio( + struct bio *bio) +{ + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + unsigned long flags; + + /* + * For Appends record the actually written block number and set the + * boundary flag if needed. + */ + if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { + ioend->io_sector = bio->bi_iter.bi_sector; + xfs_mark_rtg_boundary(ioend); + } + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); +} diff --git a/fs/xfs/xfs_ioend.h b/fs/xfs/xfs_ioend.h new file mode 100644 index 000000000000..525865767fca --- /dev/null +++ b/fs/xfs/xfs_ioend.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __XFS_IOEND_H +#define __XFS_IOEND_H + +/* + * Fast and loose check if this write could update the on-disk inode size. + */ +static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) +{ + return ioend->io_offset + ioend->io_size > + XFS_I(ioend->io_inode)->i_disk_size; +} + +void xfs_end_bio(struct bio *bio); + +#endif /* __XFS_IOEND_H */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 71c45be8c652..7c6238fed61e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1083,12 +1083,7 @@ xfs_zoned_direct_write_iomap_begin( return error; } - iomap->type = IOMAP_MAPPED; - iomap->flags = IOMAP_F_DIRTY; - iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; - iomap->offset = offset; - iomap->length = length; - iomap->flags = IOMAP_F_ANON_WRITE; + xfs_iomap_set_anon_write(ip, iomap, offset, length); return 0; } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index cffcec532ea6..c906c62d46f3 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -29,6 +29,20 @@ int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, struct xfs_zone_alloc_ctx *ac, bool *did_zero); +static inline void +xfs_iomap_set_anon_write( + struct xfs_inode *ip, + struct iomap *iomap, + loff_t offset, + loff_t length) +{ + iomap->type = IOMAP_MAPPED; + iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; + iomap->offset = offset; + iomap->length = length; + iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; +} + static inline xfs_filblks_t xfs_aligned_fsb_count( xfs_fileoff_t offset_fsb, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 4a3299abf774..d1306e723899 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -834,7 +834,7 @@ xfs_setattr_nonsize( } error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, - has_capability_noaudit(current, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_dqrele; diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h index 59a33c60e0ca..5d542e95fe44 100644 --- a/fs/xfs/xfs_platform.h +++ b/fs/xfs/xfs_platform.h @@ -289,15 +289,4 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, # define PTR_FMT "%p" #endif -/* - * Helper for IO routines to grab backing pages from allocated kernel memory. - */ -static inline struct page * -kmem_to_page(void *addr) -{ - if (is_vmalloc_addr(addr)) - return vmalloc_to_page(addr); - return virt_to_page(addr); -} - #endif /* _XFS_PLATFORM_H */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4b2eeb7783f7..b24db75eaedc 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -445,7 +445,7 @@ xfs_shutdown_devices( blkdev_issue_flush(mp->m_logdev_targp->bt_bdev); invalidate_bdev(mp->m_logdev_targp->bt_bdev); } - if (mp->m_rtdev_targp) { + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) { blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); invalidate_bdev(mp->m_rtdev_targp->bt_bdev); } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 1e025848811a..a5d25b703dfc 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -521,7 +521,8 @@ xfs_trans_log_buf( { struct xfs_buf_log_item *bip = bp->b_log_item; - ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(first <= last); + ASSERT(last < BBTOB(bp->b_length)); ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); xfs_trans_dirty_buf(tp, bp); diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 7d13fa7ab30a..bdbb60cc5d5b 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -793,17 +793,35 @@ xfs_get_cached_zone( rcu_read_lock(); oz = VFS_I(ip)->i_private; - if (oz) { - /* - * GC only steals open zones at mount time, so no GC zones - * should end up in the cache. - */ - ASSERT(!oz->oz_is_gc); - if (!atomic_inc_not_zero(&oz->oz_ref)) - oz = NULL; - } - rcu_read_unlock(); + if (!oz) + goto out_unlock; + /* + * GC only steals open zones at mount time, so no GC zones should end up + * in the cache. + */ + ASSERT(!oz->oz_is_gc); + + /* + * Drop the old cached open zone if it is full. + */ + if (oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + spin_lock(&ip->i_flags_lock); + oz = VFS_I(ip)->i_private; + if (oz && oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + VFS_I(ip)->i_private = NULL; + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); + oz = NULL; + goto out_unlock; + } + spin_unlock(&ip->i_flags_lock); + } + + if (!atomic_inc_not_zero(&oz->oz_ref)) + oz = NULL; +out_unlock: + rcu_read_unlock(); return oz; } @@ -818,18 +836,41 @@ xfs_get_cached_zone( * that were every written to, but significantly simplifies the cached zone * lookup. Because the open_zone is clearly marked as full when all data * in the underlying RTG was written, the caching is always safe. + * + * Called with a reference on @oz held. And returns two references on the + * returned zone: one for the caller and one for pinning the zone in + * inode->i_private. */ -static void +static struct xfs_open_zone * xfs_set_cached_zone( struct xfs_inode *ip, struct xfs_open_zone *oz) { struct xfs_open_zone *old_oz; + /* + * If the open zone cached in the inode still has free space, use that + * instead of the new open zone just selected. This can happen when + * multiple threads race to perform zone selection for an inode. + * io_uring worker threads seem to be good way to trigger this. + * + * We need to grab an extra reference to this open zone as the caller + * owns a reference in addition to the i_private pointer. + */ + spin_lock(&ip->i_flags_lock); + old_oz = VFS_I(ip)->i_private; + if (old_oz && old_oz->oz_allocated < rtg_blocks(old_oz->oz_rtg) && + atomic_inc_not_zero(&old_oz->oz_ref)) { + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); + return old_oz; + } + VFS_I(ip)->i_private = oz; atomic_inc(&oz->oz_ref); - old_oz = xchg(&VFS_I(ip)->i_private, oz); + spin_unlock(&ip->i_flags_lock); if (old_oz) xfs_open_zone_put(old_oz); + return oz; } static void @@ -873,14 +914,13 @@ xfs_zone_alloc_and_submit( * the inode is still associated with a zone and use that if so. */ if (!*oz) - *oz = xfs_get_cached_zone(ip); - - if (!*oz) { select_zone: + *oz = xfs_get_cached_zone(ip); + if (!*oz) { *oz = xfs_select_zone(mp, write_hint, pack_tight); if (!*oz) goto out_error; - xfs_set_cached_zone(ip, *oz); + *oz = xfs_set_cached_zone(ip, *oz); } alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index d0b85179a3d2..5fdcf98a2133 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -869,6 +869,11 @@ xfs_zone_gc_write_chunk( WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); list_move_tail(&chunk->entry, &data->writing); + /* + * If we run on top of stacked block device, the read I/O might have + * reset bi_bdev, restore it to the one we want. + */ + bio_set_dev(&chunk->bio, mp->m_rtdev_targp->bt_bdev); bio_reuse(&chunk->bio, REQ_OP_WRITE); while ((split_chunk = xfs_zone_gc_split_write(data, chunk))) xfs_zone_gc_submit_write(data, split_chunk); diff --git a/include/dt-bindings/sound/qcom,q6dsp-lpass-ports.h b/include/dt-bindings/sound/qcom,q6dsp-lpass-ports.h index 2e879a3c09ae..3a99703dbc4a 100644 --- a/include/dt-bindings/sound/qcom,q6dsp-lpass-ports.h +++ b/include/dt-bindings/sound/qcom,q6dsp-lpass-ports.h @@ -237,34 +237,34 @@ /* Clock ID for RX CORE MCLK2 2X MCLK */ #define LPASS_CLK_ID_RX_CORE_MCLK2_2X_MCLK 70 -#define LAPSS_CLK_ID_QAIF_IF0_IBIT 71 -#define LAPSS_CLK_ID_QAIF_IF0_EBIT 72 -#define LAPSS_CLK_ID_QAIF_IF1_IBIT 73 -#define LAPSS_CLK_ID_QAIF_IF1_EBIT 74 -#define LAPSS_CLK_ID_QAIF_IF2_IBIT 75 -#define LAPSS_CLK_ID_QAIF_IF2_EBIT 76 -#define LAPSS_CLK_ID_QAIF_IF3_IBIT 77 -#define LAPSS_CLK_ID_QAIF_IF3_EBIT 78 -#define LAPSS_CLK_ID_QAIF_IF4_IBIT 79 -#define LAPSS_CLK_ID_QAIF_IF4_EBIT 80 -#define LAPSS_CLK_ID_QAIF_IF5_IBIT 81 -#define LAPSS_CLK_ID_QAIF_IF5_EBIT 82 -#define LAPSS_CLK_ID_QAIF_IF6_IBIT 83 -#define LAPSS_CLK_ID_QAIF_IF6_EBIT 84 -#define LAPSS_CLK_ID_QAIF_IF7_IBIT 85 -#define LAPSS_CLK_ID_QAIF_IF7_EBIT 86 -#define LAPSS_CLK_ID_QAIF_IF8_IBIT 87 -#define LAPSS_CLK_ID_QAIF_IF8_EBIT 88 -#define LAPSS_CLK_ID_QAIF_IF9_IBIT 89 -#define LAPSS_CLK_ID_QAIF_IF9_EBIT 90 -#define LAPSS_CLK_ID_QAIF_IF10_IBIT 91 -#define LAPSS_CLK_ID_QAIF_IF10_EBIT 92 -#define LAPSS_CLK_ID_QAIF_IF11_IBIT 93 -#define LAPSS_CLK_ID_QAIF_IF11_EBIT 94 -#define LAPSS_CLK_ID_QAIF_IF12_IBIT 95 -#define LAPSS_CLK_ID_QAIF_IF12_EBIT 96 -#define LAPSS_CLK_ID_VA_QAIF_IF0_IBIT 97 -#define LAPSS_CLK_ID_VA_QAIF_IF0_EBIT 98 +#define LPASS_CLK_ID_QAIF_IF0_IBIT 71 +#define LPASS_CLK_ID_QAIF_IF0_EBIT 72 +#define LPASS_CLK_ID_QAIF_IF1_IBIT 73 +#define LPASS_CLK_ID_QAIF_IF1_EBIT 74 +#define LPASS_CLK_ID_QAIF_IF2_IBIT 75 +#define LPASS_CLK_ID_QAIF_IF2_EBIT 76 +#define LPASS_CLK_ID_QAIF_IF3_IBIT 77 +#define LPASS_CLK_ID_QAIF_IF3_EBIT 78 +#define LPASS_CLK_ID_QAIF_IF4_IBIT 79 +#define LPASS_CLK_ID_QAIF_IF4_EBIT 80 +#define LPASS_CLK_ID_QAIF_IF5_IBIT 81 +#define LPASS_CLK_ID_QAIF_IF5_EBIT 82 +#define LPASS_CLK_ID_QAIF_IF6_IBIT 83 +#define LPASS_CLK_ID_QAIF_IF6_EBIT 84 +#define LPASS_CLK_ID_QAIF_IF7_IBIT 85 +#define LPASS_CLK_ID_QAIF_IF7_EBIT 86 +#define LPASS_CLK_ID_QAIF_IF8_IBIT 87 +#define LPASS_CLK_ID_QAIF_IF8_EBIT 88 +#define LPASS_CLK_ID_QAIF_IF9_IBIT 89 +#define LPASS_CLK_ID_QAIF_IF9_EBIT 90 +#define LPASS_CLK_ID_QAIF_IF10_IBIT 91 +#define LPASS_CLK_ID_QAIF_IF10_EBIT 92 +#define LPASS_CLK_ID_QAIF_IF11_IBIT 93 +#define LPASS_CLK_ID_QAIF_IF11_EBIT 94 +#define LPASS_CLK_ID_QAIF_IF12_IBIT 95 +#define LPASS_CLK_ID_QAIF_IF12_EBIT 96 +#define LPASS_CLK_ID_VA_QAIF_IF0_IBIT 97 +#define LPASS_CLK_ID_VA_QAIF_IF0_EBIT 98 #define LPASS_HW_AVTIMER_VOTE 101 #define LPASS_HW_MACRO_VOTE 102 diff --git a/include/keys/trusted_tpm.h b/include/keys/trusted_tpm.h index 0fadc6a4f166..3a0fa3bc8454 100644 --- a/include/keys/trusted_tpm.h +++ b/include/keys/trusted_tpm.h @@ -3,7 +3,6 @@ #define __TRUSTED_TPM_H #include -#include extern struct trusted_key_ops trusted_key_tpm_ops; diff --git a/include/linux/capability.h b/include/linux/capability.h index 37db92b3d6f8..f8532d92fcad 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -145,6 +145,7 @@ extern bool has_capability_noaudit(struct task_struct *t, int cap); extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); +bool capable_noaudit(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); extern bool ns_capable_setid(struct user_namespace *ns, int cap); @@ -167,6 +168,10 @@ static inline bool capable(int cap) { return true; } +static inline bool capable_noaudit(int cap) +{ + return true; +} static inline bool ns_capable(struct user_namespace *ns, int cap) { return true; diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 63e0e2aa1ce9..691e1bdece49 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -313,8 +313,6 @@ int ceph_wait_for_latest_osdmap(struct ceph_client *client, /* pagevec.c */ extern void ceph_release_page_vector(struct page **pages, int num_pages); -extern void ceph_put_page_vector(struct page **pages, int num_pages, - bool dirty); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern void ceph_copy_from_page_vector(struct page **pages, void *data, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7a631a257613..3754d697854b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -527,7 +527,10 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ - /* sequence number for cgroup.kill, serialized by css_set_lock. */ + /* + * Sequence number for cgroup.kill. Incremented with both cgroup_mutex + * and css_set_lock held. Readers hold either one. + */ unsigned int kill_seq; struct kernfs_node *kn; /* cgroup kernfs entry */ diff --git a/include/linux/designware_i2c.h b/include/linux/designware_i2c.h new file mode 100644 index 000000000000..53f37f18a722 --- /dev/null +++ b/include/linux/designware_i2c.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Synopsys DesignWare I2C register definitions + * + * Copyright (C) 2026, Intel Corporation + */ + +#ifndef __LINUX_DESIGNWARE_I2C_H +#define __LINUX_DESIGNWARE_I2C_H + +#include + +/* + * Registers offset + */ +#define DW_IC_CON 0x00 +#define DW_IC_TAR 0x04 +#define DW_IC_SAR 0x08 +#define DW_IC_DATA_CMD 0x10 +#define DW_IC_SS_SCL_HCNT 0x14 +#define DW_IC_SS_SCL_LCNT 0x18 +#define DW_IC_FS_SCL_HCNT 0x1c +#define DW_IC_FS_SCL_LCNT 0x20 +#define DW_IC_HS_SCL_HCNT 0x24 +#define DW_IC_HS_SCL_LCNT 0x28 +#define DW_IC_INTR_STAT 0x2c +#define DW_IC_INTR_MASK 0x30 +#define DW_IC_RAW_INTR_STAT 0x34 +#define DW_IC_RX_TL 0x38 +#define DW_IC_TX_TL 0x3c +#define DW_IC_CLR_INTR 0x40 +#define DW_IC_CLR_RX_UNDER 0x44 +#define DW_IC_CLR_RX_OVER 0x48 +#define DW_IC_CLR_TX_OVER 0x4c +#define DW_IC_CLR_RD_REQ 0x50 +#define DW_IC_CLR_TX_ABRT 0x54 +#define DW_IC_CLR_RX_DONE 0x58 +#define DW_IC_CLR_ACTIVITY 0x5c +#define DW_IC_CLR_STOP_DET 0x60 +#define DW_IC_CLR_START_DET 0x64 +#define DW_IC_CLR_GEN_CALL 0x68 +#define DW_IC_ENABLE 0x6c +#define DW_IC_STATUS 0x70 +#define DW_IC_TXFLR 0x74 +#define DW_IC_RXFLR 0x78 +#define DW_IC_SDA_HOLD 0x7c +#define DW_IC_TX_ABRT_SOURCE 0x80 +#define DW_IC_ENABLE_STATUS 0x9c +#define DW_IC_CLR_RESTART_DET 0xa8 +#define DW_IC_SMBUS_INTR_STAT 0xc8 +#define DW_IC_SMBUS_INTR_MASK 0xcc +#define DW_IC_CLR_SMBUS_INTR 0xd4 +#define DW_IC_COMP_PARAM_1 0xf4 +#define DW_IC_COMP_VERSION 0xf8 +#define DW_IC_COMP_TYPE 0xfc + +/* DW_IC_CON bits */ +#define DW_IC_CON_MASTER BIT(0) +#define DW_IC_CON_SPEED_STD (1 << 1) +#define DW_IC_CON_SPEED_FAST (2 << 1) +#define DW_IC_CON_SPEED_HIGH (3 << 1) +#define DW_IC_CON_SPEED_MASK GENMASK(2, 1) +#define DW_IC_CON_10BITADDR_SLAVE BIT(3) +#define DW_IC_CON_10BITADDR_MASTER BIT(4) +#define DW_IC_CON_RESTART_EN BIT(5) +#define DW_IC_CON_SLAVE_DISABLE BIT(6) +#define DW_IC_CON_STOP_DET_IFADDRESSED BIT(7) +#define DW_IC_CON_TX_EMPTY_CTRL BIT(8) +#define DW_IC_CON_RX_FIFO_FULL_HLD_CTRL BIT(9) +#define DW_IC_CON_BUS_CLEAR_CTRL BIT(11) + +/* DW_IC_DATA_CMD bits */ +#define DW_IC_DATA_CMD_DAT GENMASK(7, 0) +#define DW_IC_DATA_CMD_FIRST_DATA_BYTE BIT(11) + +/* DW_IC_INTR_* bits */ +#define DW_IC_INTR_RX_UNDER BIT(0) +#define DW_IC_INTR_RX_OVER BIT(1) +#define DW_IC_INTR_RX_FULL BIT(2) +#define DW_IC_INTR_TX_OVER BIT(3) +#define DW_IC_INTR_TX_EMPTY BIT(4) +#define DW_IC_INTR_RD_REQ BIT(5) +#define DW_IC_INTR_TX_ABRT BIT(6) +#define DW_IC_INTR_RX_DONE BIT(7) +#define DW_IC_INTR_ACTIVITY BIT(8) +#define DW_IC_INTR_STOP_DET BIT(9) +#define DW_IC_INTR_START_DET BIT(10) +#define DW_IC_INTR_GEN_CALL BIT(11) +#define DW_IC_INTR_RESTART_DET BIT(12) +#define DW_IC_INTR_MST_ON_HOLD BIT(13) + +/* DW_IC_ENABLE bits */ +#define DW_IC_ENABLE_ENABLE BIT(0) +#define DW_IC_ENABLE_ABORT BIT(1) + +/* DW_IC_STATUS bits */ +#define DW_IC_STATUS_ACTIVITY BIT(0) +#define DW_IC_STATUS_TFE BIT(2) +#define DW_IC_STATUS_RFNE BIT(3) +#define DW_IC_STATUS_MASTER_ACTIVITY BIT(5) +#define DW_IC_STATUS_SLAVE_ACTIVITY BIT(6) +#define DW_IC_STATUS_MASTER_HOLD_TX_FIFO_EMPTY BIT(7) + +/* DW_IC_SMBUS_INTR_* bits */ +#define DW_IC_SMBUS_INTR_ALERT BIT(10) + +#endif /* __LINUX_DESIGNWARE_I2C_H */ diff --git a/include/linux/edac.h b/include/linux/edac.h index e6b4e51130e5..f7a8218f9cc0 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -598,9 +598,6 @@ struct mem_ctl_info { int op_state; struct dentry *debugfs; - u8 fake_inject_layer[EDAC_MAX_LAYERS]; - bool fake_inject_ue; - u16 fake_inject_count; /* * Memory Controller hierarchy diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 3a2d35a9f307..a0cf0398519f 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -57,20 +57,21 @@ struct ip_mc_socklist { }; struct ip_sf_list { - struct ip_sf_list *sf_next; + struct ip_sf_list __rcu *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ + struct rcu_head rcu; }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; - struct ip_sf_list *sources; - struct ip_sf_list *tomb; + struct ip_sf_list __rcu *sources; + struct ip_sf_list __rcu *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 671c13494566..421f6fc45451 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3082,6 +3082,11 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) return skb->transport_header != (typeof(skb->transport_header))~0U; } +static inline void skb_unset_transport_header(struct sk_buff *skb) +{ + skb->transport_header = (typeof(skb->transport_header))~0U; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 799a8f7d2741..3d405cc4c121 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -572,12 +572,12 @@ DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_nested, __acquires(_T), __releases(*(raw #define class_raw_spinlock_nested_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_nested, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, - raw_spin_lock_irq_disable(_T->lock), - raw_spin_unlock_irq_enable(_T->lock)) + raw_spin_lock_irq(_T->lock), + raw_spin_unlock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irq, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irq, _T) -DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq_disable(_T->lock)) +DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irq_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irq_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irq_try, _T) @@ -592,13 +592,14 @@ DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_bh_try, __acquires(_T), __releases(*(raw #define class_raw_spinlock_bh_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_bh_try, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, - raw_spin_lock_irq_disable(_T->lock), - raw_spin_unlock_irq_enable(_T->lock)) + raw_spin_lock_irqsave(_T->lock, _T->flags), + raw_spin_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave, _T) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try, - raw_spin_trylock_irq_disable(_T->lock)) + raw_spin_trylock_irqsave(_T->lock, _T->flags)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irqsave_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave_try, _T) @@ -617,13 +618,13 @@ DECLARE_LOCK_GUARD_1_ATTRS(spinlock_try, __acquires(_T), __releases(*(spinlock_t #define class_spinlock_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_try, _T) DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, - spin_lock_irq_disable(_T->lock), - spin_unlock_irq_enable(_T->lock)) + spin_lock_irq(_T->lock), + spin_unlock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irq, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irq, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try, - spin_trylock_irq_disable(_T->lock)) + spin_trylock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irq_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irq_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irq_try, _T) @@ -639,13 +640,14 @@ DECLARE_LOCK_GUARD_1_ATTRS(spinlock_bh_try, __acquires(_T), __releases(*(spinloc #define class_spinlock_bh_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_bh_try, _T) DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, - spin_lock_irq_disable(_T->lock), - spin_unlock_irq_enable(_T->lock)) + spin_lock_irqsave(_T->lock, _T->flags), + spin_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irqsave, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irqsave, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try, - spin_trylock_irq_disable(_T->lock)) + spin_trylock_irqsave(_T->lock, _T->flags)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irqsave_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irqsave_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irqsave_try, _T) diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 202da079d500..0db277af45c3 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -25,10 +25,8 @@ #include #include -#define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ - -#define TPM2_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE -#define TPM2_MAX_PCR_BANKS 8 +#include +#include struct tpm_chip; struct trusted_key_payload; @@ -36,49 +34,6 @@ struct trusted_key_options; /* opaque structure, holds auth session parameters like the session key */ struct tpm2_auth; -enum tpm2_session_types { - TPM2_SE_HMAC = 0x00, - TPM2_SE_POLICY = 0x01, - TPM2_SE_TRIAL = 0x02, -}; - -/* if you add a new hash to this, increment TPM_MAX_HASHES below */ -enum tpm_algorithms { - TPM_ALG_ERROR = 0x0000, - TPM_ALG_SHA1 = 0x0004, - TPM_ALG_AES = 0x0006, - TPM_ALG_KEYEDHASH = 0x0008, - TPM_ALG_SHA256 = 0x000B, - TPM_ALG_SHA384 = 0x000C, - TPM_ALG_SHA512 = 0x000D, - TPM_ALG_NULL = 0x0010, - TPM_ALG_SM3_256 = 0x0012, - TPM_ALG_ECC = 0x0023, - TPM_ALG_CFB = 0x0043, -}; - -/* - * maximum number of hashing algorithms a TPM can have. This is - * basically a count of every hash in tpm_algorithms above - */ -#define TPM_MAX_HASHES 5 - -enum tpm2_curves { - TPM2_ECC_NONE = 0x0000, - TPM2_ECC_NIST_P256 = 0x0003, -}; - -struct tpm_digest { - u16 alg_id; - u8 digest[TPM2_MAX_DIGEST_SIZE]; -} __packed; - -struct tpm_bank_info { - u16 alg_id; - u16 digest_size; - u16 crypto_id; -}; - enum TPM_OPS_FLAGS { TPM_OPS_AUTO_STARTUP = BIT(0), }; @@ -136,7 +91,7 @@ struct tpm_chip_seqops { const struct seq_operations *seqops; }; -/* fixed define for the curve we use which is NIST_P256 */ +/* Fixed define for the curve we use which is NIST_P256 */ #define EC_PT_SZ 32 /* @@ -218,124 +173,11 @@ struct tpm_chip { #endif }; -#define TPM_HEADER_SIZE 10 - -enum tpm2_const { - TPM2_PLATFORM_PCR = 24, - TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), -}; - -enum tpm2_timeouts { - TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 4000, - TPM2_TIMEOUT_C = 200, - TPM2_TIMEOUT_D = 30, -}; - -enum tpm2_durations { - TPM2_DURATION_SHORT = 20, - TPM2_DURATION_LONG = 2000, - TPM2_DURATION_DEFAULT = 120000, -}; - -enum tpm2_structures { - TPM2_ST_NO_SESSIONS = 0x8001, - TPM2_ST_SESSIONS = 0x8002, - TPM2_ST_CREATION = 0x8021, -}; - -/* Indicates from what layer of the software stack the error comes from */ -#define TSS2_RC_LAYER_SHIFT 16 -#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) - -enum tpm2_return_codes { - TPM2_RC_SUCCESS = 0x0000, - TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ - TPM2_RC_HANDLE = 0x008B, - TPM2_RC_INTEGRITY = 0x009F, - TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ - TPM2_RC_FAILURE = 0x0101, - TPM2_RC_DISABLED = 0x0120, - TPM2_RC_UPGRADE = 0x012D, - TPM2_RC_COMMAND_CODE = 0x0143, - TPM2_RC_TESTING = 0x090A, /* RC_WARN */ - TPM2_RC_REFERENCE_H0 = 0x0910, - TPM2_RC_RETRY = 0x0922, - TPM2_RC_SESSION_MEMORY = 0x0903, -}; - -enum tpm2_command_codes { - TPM2_CC_FIRST = 0x011F, - TPM2_CC_HIERARCHY_CONTROL = 0x0121, - TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, - TPM2_CC_CREATE_PRIMARY = 0x0131, - TPM2_CC_SEQUENCE_COMPLETE = 0x013E, - TPM2_CC_SELF_TEST = 0x0143, - TPM2_CC_STARTUP = 0x0144, - TPM2_CC_SHUTDOWN = 0x0145, - TPM2_CC_NV_READ = 0x014E, - TPM2_CC_CREATE = 0x0153, - TPM2_CC_LOAD = 0x0157, - TPM2_CC_SEQUENCE_UPDATE = 0x015C, - TPM2_CC_UNSEAL = 0x015E, - TPM2_CC_CONTEXT_LOAD = 0x0161, - TPM2_CC_CONTEXT_SAVE = 0x0162, - TPM2_CC_FLUSH_CONTEXT = 0x0165, - TPM2_CC_READ_PUBLIC = 0x0173, - TPM2_CC_START_AUTH_SESS = 0x0176, - TPM2_CC_VERIFY_SIGNATURE = 0x0177, - TPM2_CC_GET_CAPABILITY = 0x017A, - TPM2_CC_GET_RANDOM = 0x017B, - TPM2_CC_PCR_READ = 0x017E, - TPM2_CC_PCR_EXTEND = 0x0182, - TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, - TPM2_CC_HASH_SEQUENCE_START = 0x0186, - TPM2_CC_CREATE_LOADED = 0x0191, - TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ -}; - -enum tpm2_permanent_handles { - TPM2_RH_NULL = 0x40000007, - TPM2_RS_PW = 0x40000009, -}; - -/* Most Significant Octet for key types */ -enum tpm2_mso_type { - TPM2_MSO_NVRAM = 0x01, - TPM2_MSO_SESSION = 0x02, - TPM2_MSO_POLICY = 0x03, - TPM2_MSO_PERMANENT = 0x40, - TPM2_MSO_VOLATILE = 0x80, - TPM2_MSO_PERSISTENT = 0x81, -}; - static inline enum tpm2_mso_type tpm2_handle_mso(u32 handle) { return handle >> 24; } -enum tpm2_capabilities { - TPM2_CAP_HANDLES = 1, - TPM2_CAP_COMMANDS = 2, - TPM2_CAP_PCRS = 5, - TPM2_CAP_TPM_PROPERTIES = 6, -}; - -enum tpm2_properties { - TPM_PT_TOTAL_COMMANDS = 0x0129, -}; - -enum tpm2_startup_types { - TPM2_SU_CLEAR = 0x0000, - TPM2_SU_STATE = 0x0001, -}; - -enum tpm2_cc_attrs { - TPM2_CC_ATTR_CHANDLES = 25, - TPM2_CC_ATTR_RHANDLE = 28, - TPM2_CC_ATTR_VENDOR = 29, -}; - #define TPM_VID_INTEL 0x8086 #define TPM_VID_WINBOND 0x1050 #define TPM_VID_STM 0x104A @@ -359,77 +201,11 @@ enum tpm_chip_flags { #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -struct tpm_header { - __be16 tag; - __be32 length; - union { - __be32 ordinal; - __be32 return_code; - }; -} __packed; - -enum tpm_buf_flags { - /* the capacity exceeded: */ - TPM_BUF_OVERFLOW = BIT(0), - /* TPM2B format: */ - TPM_BUF_TPM2B = BIT(1), - /* read out of boundary: */ - TPM_BUF_BOUNDARY_ERROR = BIT(2), -}; - -/* - * A string buffer type for constructing TPM commands. - */ -struct tpm_buf { - u32 flags; - u32 length; - u8 *data; - u8 handles; -}; - -enum tpm2_object_attributes { - TPM2_OA_FIXED_TPM = BIT(1), - TPM2_OA_ST_CLEAR = BIT(2), - TPM2_OA_FIXED_PARENT = BIT(4), - TPM2_OA_SENSITIVE_DATA_ORIGIN = BIT(5), - TPM2_OA_USER_WITH_AUTH = BIT(6), - TPM2_OA_ADMIN_WITH_POLICY = BIT(7), - TPM2_OA_NO_DA = BIT(10), - TPM2_OA_ENCRYPTED_DUPLICATION = BIT(11), - TPM2_OA_RESTRICTED = BIT(16), - TPM2_OA_DECRYPT = BIT(17), - TPM2_OA_SIGN = BIT(18), -}; - -enum tpm2_session_attributes { - TPM2_SA_CONTINUE_SESSION = BIT(0), - TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), - TPM2_SA_AUDIT_RESET = BIT(3), - TPM2_SA_DECRYPT = BIT(5), - TPM2_SA_ENCRYPT = BIT(6), - TPM2_SA_AUDIT = BIT(7), -}; - struct tpm2_hash { unsigned int crypto_id; unsigned int tpm_id; }; -int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal); -void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal); -int tpm_buf_init_sized(struct tpm_buf *buf); -void tpm_buf_reset_sized(struct tpm_buf *buf); -void tpm_buf_destroy(struct tpm_buf *buf); -u32 tpm_buf_length(struct tpm_buf *buf); -void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length); -void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value); -void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value); -void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); -u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); -u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); -u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); -void tpm_buf_append_handle(struct tpm_chip *chip, struct tpm_buf *buf, u32 handle); - /* * Check if TPM device is in the firmware upgrade mode. */ diff --git a/include/linux/tpm_buf.h b/include/linux/tpm_buf.h new file mode 100644 index 000000000000..f8c105d8b8bf --- /dev/null +++ b/include/linux/tpm_buf.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Following copyright information was take from the original file + * where the definitions were moved from: + * + * Copyright (C) 2004,2007,2008 IBM Corporation + * + * Authors: + * Leendert van Doorn + * Dave Safford + * Reiner Sailer + * Kylene Hall + * Debora Velarde + * + * Maintained by: + * + * Device driver for TCG/TCPA TPM (trusted platform module). + * Specifications at www.trustedcomputinggroup.org + */ + +#ifndef __LINUX_TPM_BUF_H__ +#define __LINUX_TPM_BUF_H__ + +#include +#include + +enum tpm_buf_flags { + /* TPM2B format: */ + TPM_BUF_TPM2B = BIT(0), + /* The buffer is in invalid and unusable state: */ + TPM_BUF_INVALID = BIT(1), +}; + +/* + * A buffer for constructing and parsing TPM commands, responses and sized + * (TPM2B) buffers. + */ +struct tpm_buf { + u8 flags; + u8 handles; + u16 length; + u16 capacity; + u8 data[]; +}; + +void tpm_buf_init(struct tpm_buf *buf, u16 buf_size); +void tpm_buf_init_sized(struct tpm_buf *buf, u16 buf_size); +void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal); +void tpm_buf_reset_sized(struct tpm_buf *buf); +u16 tpm_buf_length(struct tpm_buf *buf); +void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length); +void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value); +void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value); +void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); +u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); +u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); +u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); +void tpm_buf_append_handle(struct tpm_buf *buf, u32 handle); + +#endif diff --git a/include/linux/tpm_command.h b/include/linux/tpm_command.h index f5c03e9c3913..fc446a1282e2 100644 --- a/include/linux/tpm_command.h +++ b/include/linux/tpm_command.h @@ -2,28 +2,520 @@ #ifndef __LINUX_TPM_COMMAND_H__ #define __LINUX_TPM_COMMAND_H__ +#include + /* - * TPM Command constants from specifications at - * http://www.trustedcomputinggroup.org + * == TPM 1 Family Chips == + * + * TPM 1.2 Main Specification: + * https://trustedcomputinggroup.org/resource/tpm-main-specification/ */ +#define TPM_MAX_ORDINAL 243 + /* Command TAGS */ -#define TPM_TAG_RQU_COMMAND 193 -#define TPM_TAG_RQU_AUTH1_COMMAND 194 -#define TPM_TAG_RQU_AUTH2_COMMAND 195 -#define TPM_TAG_RSP_COMMAND 196 -#define TPM_TAG_RSP_AUTH1_COMMAND 197 -#define TPM_TAG_RSP_AUTH2_COMMAND 198 +enum tpm_command_tags { + TPM_TAG_RQU_COMMAND = 193, + TPM_TAG_RQU_AUTH1_COMMAND = 194, + TPM_TAG_RQU_AUTH2_COMMAND = 195, + TPM_TAG_RSP_COMMAND = 196, + TPM_TAG_RSP_AUTH1_COMMAND = 197, + TPM_TAG_RSP_AUTH2_COMMAND = 198, +}; /* Command Ordinals */ -#define TPM_ORD_GETRANDOM 70 -#define TPM_ORD_OSAP 11 -#define TPM_ORD_OIAP 10 -#define TPM_ORD_SEAL 23 -#define TPM_ORD_UNSEAL 24 +enum tpm_command_ordinals { + TPM_ORD_CONTINUE_SELFTEST = 83, + TPM_ORD_GET_CAP = 101, + TPM_ORD_GET_RANDOM = 70, + TPM_ORD_PCR_EXTEND = 20, + TPM_ORD_PCR_READ = 21, + TPM_ORD_OSAP = 11, + TPM_ORD_OIAP = 10, + TPM_ORD_SAVESTATE = 152, + TPM_ORD_SEAL = 23, + TPM_ORD_STARTUP = 153, + TPM_ORD_UNSEAL = 24, +}; + +enum tpm_capabilities { + TPM_CAP_FLAG = 4, + TPM_CAP_PROP = 5, + TPM_CAP_VERSION_1_1 = 0x06, + TPM_CAP_VERSION_1_2 = 0x1A, +}; + +enum tpm_sub_capabilities { + TPM_CAP_PROP_PCR = 0x101, + TPM_CAP_PROP_MANUFACTURER = 0x103, + TPM_CAP_FLAG_PERM = 0x108, + TPM_CAP_FLAG_VOL = 0x109, + TPM_CAP_PROP_OWNER = 0x111, + TPM_CAP_PROP_TIS_TIMEOUT = 0x115, + TPM_CAP_PROP_TIS_DURATION = 0x120, +}; + +/* Return Codes */ +enum tpm_return_codes { + TPM_BASE_MASK = 0, + TPM_NON_FATAL_MASK = 0x00000800, + TPM_SUCCESS = TPM_BASE_MASK + 0, + TPM_ERR_DEACTIVATED = TPM_BASE_MASK + 6, + TPM_ERR_DISABLED = TPM_BASE_MASK + 7, + TPM_ERR_FAIL = TPM_BASE_MASK + 9, + TPM_ERR_FAILEDSELFTEST = TPM_BASE_MASK + 28, + TPM_ERR_INVALID_POSTINIT = TPM_BASE_MASK + 38, + TPM_ERR_INVALID_FAMILY = TPM_BASE_MASK + 55, + TPM_WARN_RETRY = TPM_BASE_MASK + TPM_NON_FATAL_MASK + 0, + TPM_WARN_DOING_SELFTEST = TPM_BASE_MASK + TPM_NON_FATAL_MASK + 2, +}; + +struct stclear_flags_t { + __be16 tag; + u8 deactivated; + u8 disableForceClear; + u8 physicalPresence; + u8 physicalPresenceLock; + u8 bGlobalLock; +} __packed; + +struct tpm1_version { + u8 major; + u8 minor; + u8 rev_major; + u8 rev_minor; +} __packed; + +struct tpm1_version2 { + __be16 tag; + struct tpm1_version version; +} __packed; + +struct timeout_t { + __be32 a; + __be32 b; + __be32 c; + __be32 d; +} __packed; + +struct duration_t { + __be32 tpm_short; + __be32 tpm_medium; + __be32 tpm_long; +} __packed; + +struct permanent_flags_t { + __be16 tag; + u8 disable; + u8 ownership; + u8 deactivated; + u8 readPubek; + u8 disableOwnerClear; + u8 allowMaintenance; + u8 physicalPresenceLifetimeLock; + u8 physicalPresenceHWEnable; + u8 physicalPresenceCMDEnable; + u8 CEKPUsed; + u8 TPMpost; + u8 TPMpostLock; + u8 FIPS; + u8 operator; + u8 enableRevokeEK; + u8 nvLocked; + u8 readSRKPub; + u8 tpmEstablished; + u8 maintenanceDone; + u8 disableFullDALogicInfo; +} __packed; + +typedef union { + struct permanent_flags_t perm_flags; + struct stclear_flags_t stclear_flags; + __u8 owned; + __be32 num_pcrs; + struct tpm1_version version1; + struct tpm1_version2 version2; + __be32 manufacturer_id; + struct timeout_t timeout; + struct duration_t duration; +} cap_t; + +/* + * 128 bytes is an arbitrary cap. This could be as large as TPM_BUFSIZE - 18 + * bytes, but 128 is still a relatively large number of random bytes and + * anything much bigger causes users of struct tpm_cmd_t to start getting + * compiler warnings about stack frame size. + */ +#define TPM_MAX_RNG_DATA 128 + +struct tpm1_get_random_out { + __be32 rng_data_len; + u8 rng_data[TPM_MAX_RNG_DATA]; +} __packed; /* Other constants */ #define SRKHANDLE 0x40000000 #define TPM_NONCE_SIZE 20 +#define TPM_ST_CLEAR 1 + +/* + * == TPM 2 Family Chips == + * + * TPM 2.0 Library + * https://trustedcomputinggroup.org/resource/tpm-library-specification/ + */ + +/* TPM2 specific constants. */ +#define TPM2_SPACE_BUFFER_SIZE 16384 /* 16 kB */ + +enum tpm2_session_types { + TPM2_SE_HMAC = 0x00, + TPM2_SE_POLICY = 0x01, + TPM2_SE_TRIAL = 0x02, +}; + +enum tpm2_timeouts { + TPM2_TIMEOUT_A = 750, + TPM2_TIMEOUT_B = 4000, + TPM2_TIMEOUT_C = 200, + TPM2_TIMEOUT_D = 30, + TPM2_DURATION_SHORT = 20, + TPM2_DURATION_MEDIUM = 750, + TPM2_DURATION_LONG = 2000, + TPM2_DURATION_LONG_LONG = 300000, + TPM2_DURATION_DEFAULT = 120000, +}; + +enum tpm2_structures { + TPM2_ST_NO_SESSIONS = 0x8001, + TPM2_ST_SESSIONS = 0x8002, + TPM2_ST_CREATION = 0x8021, +}; + +/* Indicates from what layer of the software stack the error comes from */ +#define TSS2_RC_LAYER_SHIFT 16 +#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) + +enum tpm2_return_codes { + TPM2_RC_SUCCESS = 0x0000, + TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ + TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INTEGRITY = 0x009F, + TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ + TPM2_RC_FAILURE = 0x0101, + TPM2_RC_DISABLED = 0x0120, + TPM2_RC_UPGRADE = 0x012D, + TPM2_RC_COMMAND_CODE = 0x0143, + TPM2_RC_TESTING = 0x090A, /* RC_WARN */ + TPM2_RC_REFERENCE_H0 = 0x0910, + TPM2_RC_RETRY = 0x0922, + TPM2_RC_SESSION_MEMORY = 0x0903, +}; + +enum tpm2_command_codes { + TPM2_CC_FIRST = 0x011F, + TPM2_CC_HIERARCHY_CONTROL = 0x0121, + TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, + TPM2_CC_CREATE_PRIMARY = 0x0131, + TPM2_CC_SEQUENCE_COMPLETE = 0x013E, + TPM2_CC_SELF_TEST = 0x0143, + TPM2_CC_STARTUP = 0x0144, + TPM2_CC_SHUTDOWN = 0x0145, + TPM2_CC_NV_READ = 0x014E, + TPM2_CC_CREATE = 0x0153, + TPM2_CC_LOAD = 0x0157, + TPM2_CC_SEQUENCE_UPDATE = 0x015C, + TPM2_CC_UNSEAL = 0x015E, + TPM2_CC_CONTEXT_LOAD = 0x0161, + TPM2_CC_CONTEXT_SAVE = 0x0162, + TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_READ_PUBLIC = 0x0173, + TPM2_CC_START_AUTH_SESS = 0x0176, + TPM2_CC_VERIFY_SIGNATURE = 0x0177, + TPM2_CC_GET_CAPABILITY = 0x017A, + TPM2_CC_GET_RANDOM = 0x017B, + TPM2_CC_PCR_READ = 0x017E, + TPM2_CC_PCR_EXTEND = 0x0182, + TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, + TPM2_CC_HASH_SEQUENCE_START = 0x0186, + TPM2_CC_CREATE_LOADED = 0x0191, + TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ +}; + +enum tpm2_capabilities { + TPM2_CAP_HANDLES = 1, + TPM2_CAP_COMMANDS = 2, + TPM2_CAP_PCRS = 5, + TPM2_CAP_TPM_PROPERTIES = 6, +}; + +enum tpm2_properties { + TPM_PT_TOTAL_COMMANDS = 0x0129, +}; + +enum tpm2_startup_types { + TPM2_SU_CLEAR = 0x0000, + TPM2_SU_STATE = 0x0001, +}; + +enum tpm2_cc_attrs { + TPM2_CC_ATTR_CHANDLES = 25, + TPM2_CC_ATTR_RHANDLE = 28, + TPM2_CC_ATTR_VENDOR = 29, +}; + +enum tpm2_permanent_handles { + TPM2_RH_NULL = 0x40000007, + TPM2_RS_PW = 0x40000009, +}; + +/* Most Significant Octet for key types */ +enum tpm2_mso_type { + TPM2_MSO_NVRAM = 0x01, + TPM2_MSO_SESSION = 0x02, + TPM2_MSO_POLICY = 0x03, + TPM2_MSO_PERMANENT = 0x40, + TPM2_MSO_VOLATILE = 0x80, + TPM2_MSO_PERSISTENT = 0x81, +}; + +enum tpm2_curves { + TPM2_ECC_NONE = 0x0000, + TPM2_ECC_NIST_P256 = 0x0003, +}; + +enum tpm2_object_attributes { + TPM2_OA_FIXED_TPM = BIT(1), + TPM2_OA_ST_CLEAR = BIT(2), + TPM2_OA_FIXED_PARENT = BIT(4), + TPM2_OA_SENSITIVE_DATA_ORIGIN = BIT(5), + TPM2_OA_USER_WITH_AUTH = BIT(6), + TPM2_OA_ADMIN_WITH_POLICY = BIT(7), + TPM2_OA_NO_DA = BIT(10), + TPM2_OA_ENCRYPTED_DUPLICATION = BIT(11), + TPM2_OA_RESTRICTED = BIT(16), + TPM2_OA_DECRYPT = BIT(17), + TPM2_OA_SIGN = BIT(18), +}; + +enum tpm2_session_attributes { + TPM2_SA_CONTINUE_SESSION = BIT(0), + TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), + TPM2_SA_AUDIT_RESET = BIT(3), + TPM2_SA_DECRYPT = BIT(5), + TPM2_SA_ENCRYPT = BIT(6), + TPM2_SA_AUDIT = BIT(7), +}; + +enum tpm2_pcr_select { + TPM2_PLATFORM_PCR = 24, + TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), +}; + +enum tpm2_handle_types { + TPM2_HT_HMAC_SESSION = 0x02000000, + TPM2_HT_POLICY_SESSION = 0x03000000, + TPM2_HT_TRANSIENT = 0x80000000, +}; + +enum tpm2_pt_props { + TPM2_PT_NONE = 0x00000000, + TPM2_PT_GROUP = 0x00000100, + TPM2_PT_FIXED = TPM2_PT_GROUP * 1, + TPM2_PT_FAMILY_INDICATOR = TPM2_PT_FIXED + 0, + TPM2_PT_LEVEL = TPM2_PT_FIXED + 1, + TPM2_PT_REVISION = TPM2_PT_FIXED + 2, + TPM2_PT_DAY_OF_YEAR = TPM2_PT_FIXED + 3, + TPM2_PT_YEAR = TPM2_PT_FIXED + 4, + TPM2_PT_MANUFACTURER = TPM2_PT_FIXED + 5, + TPM2_PT_VENDOR_STRING_1 = TPM2_PT_FIXED + 6, + TPM2_PT_VENDOR_STRING_2 = TPM2_PT_FIXED + 7, + TPM2_PT_VENDOR_STRING_3 = TPM2_PT_FIXED + 8, + TPM2_PT_VENDOR_STRING_4 = TPM2_PT_FIXED + 9, + TPM2_PT_VENDOR_TPM_TYPE = TPM2_PT_FIXED + 10, + TPM2_PT_FIRMWARE_VERSION_1 = TPM2_PT_FIXED + 11, + TPM2_PT_FIRMWARE_VERSION_2 = TPM2_PT_FIXED + 12, + TPM2_PT_INPUT_BUFFER = TPM2_PT_FIXED + 13, + TPM2_PT_HR_TRANSIENT_MIN = TPM2_PT_FIXED + 14, + TPM2_PT_HR_PERSISTENT_MIN = TPM2_PT_FIXED + 15, + TPM2_PT_HR_LOADED_MIN = TPM2_PT_FIXED + 16, + TPM2_PT_ACTIVE_SESSIONS_MAX = TPM2_PT_FIXED + 17, + TPM2_PT_PCR_COUNT = TPM2_PT_FIXED + 18, + TPM2_PT_PCR_SELECT_MIN = TPM2_PT_FIXED + 19, + TPM2_PT_CONTEXT_GAP_MAX = TPM2_PT_FIXED + 20, + TPM2_PT_NV_COUNTERS_MAX = TPM2_PT_FIXED + 22, + TPM2_PT_NV_INDEX_MAX = TPM2_PT_FIXED + 23, + TPM2_PT_MEMORY = TPM2_PT_FIXED + 24, + TPM2_PT_CLOCK_UPDATE = TPM2_PT_FIXED + 25, + TPM2_PT_CONTEXT_HASH = TPM2_PT_FIXED + 26, + TPM2_PT_CONTEXT_SYM = TPM2_PT_FIXED + 27, + TPM2_PT_CONTEXT_SYM_SIZE = TPM2_PT_FIXED + 28, + TPM2_PT_ORDERLY_COUNT = TPM2_PT_FIXED + 29, + TPM2_PT_MAX_COMMAND_SIZE = TPM2_PT_FIXED + 30, + TPM2_PT_MAX_RESPONSE_SIZE = TPM2_PT_FIXED + 31, + TPM2_PT_MAX_DIGEST = TPM2_PT_FIXED + 32, + TPM2_PT_MAX_OBJECT_CONTEXT = TPM2_PT_FIXED + 33, + TPM2_PT_MAX_SESSION_CONTEXT = TPM2_PT_FIXED + 34, + TPM2_PT_PS_FAMILY_INDICATOR = TPM2_PT_FIXED + 35, + TPM2_PT_PS_LEVEL = TPM2_PT_FIXED + 36, + TPM2_PT_PS_REVISION = TPM2_PT_FIXED + 37, + TPM2_PT_PS_DAY_OF_YEAR = TPM2_PT_FIXED + 38, + TPM2_PT_PS_YEAR = TPM2_PT_FIXED + 39, + TPM2_PT_SPLIT_MAX = TPM2_PT_FIXED + 40, + TPM2_PT_TOTAL_COMMANDS = TPM2_PT_FIXED + 41, + TPM2_PT_LIBRARY_COMMANDS = TPM2_PT_FIXED + 42, + TPM2_PT_VENDOR_COMMANDS = TPM2_PT_FIXED + 43, + TPM2_PT_NV_BUFFER_MAX = TPM2_PT_FIXED + 44, + TPM2_PT_MODES = TPM2_PT_FIXED + 45, + TPM2_PT_MAX_CAP_BUFFER = TPM2_PT_FIXED + 46, + TPM2_PT_VAR = TPM2_PT_GROUP * 2, + TPM2_PT_PERMANENT = TPM2_PT_VAR + 0, + TPM2_PT_STARTUP_CLEAR = TPM2_PT_VAR + 1, + TPM2_PT_HR_NV_INDEX = TPM2_PT_VAR + 2, + TPM2_PT_HR_LOADED = TPM2_PT_VAR + 3, + TPM2_PT_HR_LOADED_AVAIL = TPM2_PT_VAR + 4, + TPM2_PT_HR_ACTIVE = TPM2_PT_VAR + 5, + TPM2_PT_HR_ACTIVE_AVAIL = TPM2_PT_VAR + 6, + TPM2_PT_HR_TRANSIENT_AVAIL = TPM2_PT_VAR + 7, + TPM2_PT_HR_PERSISTENT = TPM2_PT_VAR + 8, + TPM2_PT_HR_PERSISTENT_AVAIL = TPM2_PT_VAR + 9, + TPM2_PT_NV_COUNTERS = TPM2_PT_VAR + 10, + TPM2_PT_NV_COUNTERS_AVAIL = TPM2_PT_VAR + 11, + TPM2_PT_ALGORITHM_SET = TPM2_PT_VAR + 12, + TPM2_PT_LOADED_CURVES = TPM2_PT_VAR + 13, + TPM2_PT_LOCKOUT_COUNTER = TPM2_PT_VAR + 14, + TPM2_PT_MAX_AUTH_FAIL = TPM2_PT_VAR + 15, + TPM2_PT_LOCKOUT_INTERVAL = TPM2_PT_VAR + 16, + TPM2_PT_LOCKOUT_RECOVERY = TPM2_PT_VAR + 17, + TPM2_PT_NV_WRITE_RECOVERY = TPM2_PT_VAR + 18, + TPM2_PT_AUDIT_COUNTER_0 = TPM2_PT_VAR + 19, + TPM2_PT_AUDIT_COUNTER_1 = TPM2_PT_VAR + 20, +}; + +struct tpm2_pcr_read_out { + __be32 update_cnt; + __be32 pcr_selects_cnt; + __be16 hash_alg; + u8 pcr_select_size; + u8 pcr_select[TPM2_PCR_SELECT_MIN]; + __be32 digests_cnt; + __be16 digest_size; + u8 digest[]; +} __packed; + +struct tpm2_get_random_out { + __be16 size; + u8 buffer[TPM_MAX_RNG_DATA]; +} __packed; + +struct tpm2_get_cap_out { + u8 more_data; + __be32 subcap_id; + __be32 property_cnt; + __be32 property_id; + __be32 value; +} __packed; + +struct tpm2_pcr_selection { + __be16 hash_alg; + u8 size_of_select; + u8 pcr_select[3]; +} __packed; + +struct tpm2_context { + __be64 sequence; + __be32 saved_handle; + __be32 hierarchy; + __be16 blob_size; +} __packed; + +/* + * == TPM Common Defs == + */ + +#define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ +#define TPM_BUFSIZE 4096 + +/* + * SHA-512 is, as of today, the largest digest in the TCG algorithm repository. + */ +#define TPM2_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE + +/* + * A TPM name digest i.e., TPMT_HA, is a concatenation of TPM_ALG_ID of the + * name algorithm and hash of TPMT_PUBLIC. + */ +#define TPM2_MAX_NAME_SIZE (TPM2_MAX_DIGEST_SIZE + 2) + +/* + * Fixed define for the size of a name. This is actually HASHALG size + * plus 2, so 32 for SHA256 + */ +#define TPM2_NULL_NAME_SIZE 34 + +/* + * The maximum number of PCR banks. + */ +#define TPM2_MAX_PCR_BANKS 8 + +/* If you add a new hash to this, increment TPM_MAX_HASHES below */ +enum tpm_algorithms { + TPM_ALG_ERROR = 0x0000, + TPM_ALG_SHA1 = 0x0004, + TPM_ALG_AES = 0x0006, + TPM_ALG_KEYEDHASH = 0x0008, + TPM_ALG_SHA256 = 0x000B, + TPM_ALG_SHA384 = 0x000C, + TPM_ALG_SHA512 = 0x000D, + TPM_ALG_NULL = 0x0010, + TPM_ALG_SM3_256 = 0x0012, + TPM_ALG_ECC = 0x0023, + TPM_ALG_CFB = 0x0043, +}; + +/* + * The locality (0 - 4) for a TPM, as defined in section 3.2 of the + * Client Platform Profile Specification. + */ +enum tpm_localities { + TPM_LOCALITY_0 = 0, /* Static RTM */ + TPM_LOCALITY_1 = 1, /* Dynamic OS */ + TPM_LOCALITY_2 = 2, /* DRTM Environment */ + TPM_LOCALITY_3 = 3, /* Aux Components */ + TPM_LOCALITY_4 = 4, /* CPU DRTM Establishment */ + TPM_MAX_LOCALITY = TPM_LOCALITY_4 +}; + +/* + * Structure to represent active PCR algorithm banks usable by the + * TPM chip. + */ +struct tpm_bank_info { + u16 alg_id; + u16 digest_size; + u16 crypto_id; +}; + +/* + * Maximum number of hashing algorithms a TPM can have. This is + * basically a count of every hash in tpm_algorithms above + */ +#define TPM_MAX_HASHES 5 + +struct tpm_digest { + u16 alg_id; + u8 digest[TPM2_MAX_DIGEST_SIZE]; +} __packed; + +#define TPM_HEADER_SIZE 10 + +struct tpm_header { + __be16 tag; + __be32 length; + union { + __be32 ordinal; + __be32 return_code; + }; +} __packed; #endif diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index aff8ea2fa98e..40fe92eb7deb 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -3,7 +3,7 @@ #ifndef __LINUX_TPM_EVENTLOG_H__ #define __LINUX_TPM_EVENTLOG_H__ -#include +#include #define TCG_EVENT_NAME_LEN_MAX 255 #define MAX_TEXT_EVENT 1000 /* Max event string length */ diff --git a/include/linux/tpm_ptp.h b/include/linux/tpm_ptp.h new file mode 100644 index 000000000000..e80ed810a269 --- /dev/null +++ b/include/linux/tpm_ptp.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Following copyright information was take from the original file + * where the definitions were moved + * from: + * + * Copyright (C) 2005, 2006 IBM Corporation + * Copyright (C) 2014, 2015 Intel Corporation + * + * Authors: + * Leendert van Doorn + * Kylene Hall + * + * Maintained by: + * + * Device driver for TCG/TCPA TPM (trusted platform module). + * Specifications at www.trustedcomputinggroup.org + * + * This device driver implements the TPM interface as defined in + * the TCG TPM Interface Spec version 1.2, revision 1.0. + */ + +#ifndef __LINUX_TPM_PTP_H__ +#define __LINUX_TPM_PTP_H__ + +/* + * TCG PC Client Platform TPM Profile (PTP) Specification + * https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ + */ + +/* TIS/FIFO macros and definitions */ + +enum tis_access { + TPM_ACCESS_VALID = 0x80, + TPM_ACCESS_ACTIVE_LOCALITY = 0x20, /* (R) */ + TPM_ACCESS_RELINQUISH_LOCALITY = 0x20, /* (W) */ + TPM_ACCESS_REQUEST_PENDING = 0x04, /* (W) */ + TPM_ACCESS_REQUEST_USE = 0x02, /* (W) */ +}; + +enum tis_status { + TPM_STS_VALID = 0x80, /* (R) */ + TPM_STS_COMMAND_READY = 0x40, /* (R) */ + TPM_STS_DATA_AVAIL = 0x10, /* (R) */ + TPM_STS_DATA_EXPECT = 0x08, /* (R) */ + TPM_STS_GO = 0x20, /* (W) */ + TPM_STS_RESPONSE_RETRY = 0x02, /* (R) */ + TPM_STS_READ_ZERO = 0x23, /* bits that must be zero on read */ +}; + +enum tis_int_flags { + TPM_GLOBAL_INT_ENABLE = 0x80000000, + TPM_INTF_BURST_COUNT_STATIC = 0x100, + TPM_INTF_CMD_READY_INT = 0x080, + TPM_INTF_INT_EDGE_FALLING = 0x040, + TPM_INTF_INT_EDGE_RISING = 0x020, + TPM_INTF_INT_LEVEL_LOW = 0x010, + TPM_INTF_INT_LEVEL_HIGH = 0x008, + TPM_INTF_LOCALITY_CHANGE_INT = 0x004, + TPM_INTF_STS_VALID_INT = 0x002, + TPM_INTF_DATA_AVAIL_INT = 0x001, +}; + +enum tis_defaults { + TIS_MEM_LEN = 0x5000, + TIS_SHORT_TIMEOUT = 750, /* ms */ + TIS_LONG_TIMEOUT = 4000, /* 4 secs */ + TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */ + TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */ +}; + +#define TIS_MEM_X86_LPC_BASE 0xFED40000 +#define INTEL_LEGACY_BLK_BASE_ADDR 0xFED08000 + +enum tis_x86_defaults { + TIS_MEM_X86_LEN = 0x5000, + ILB_REMAP_SIZE = 0x100, + LPC_CNTRL_OFFSET = 0x84, + LPC_CLKRUN_EN = (1 << 2), +}; + +/* + * Some timeout values are needed before it is known whether the chip is + * TPM 1.0 or TPM 2.0. + */ +#define TIS_TIMEOUT_A_MAX max_t(int, TIS_SHORT_TIMEOUT, TPM2_TIMEOUT_A) +#define TIS_TIMEOUT_B_MAX max_t(int, TIS_LONG_TIMEOUT, TPM2_TIMEOUT_B) +#define TIS_TIMEOUT_C_MAX max_t(int, TIS_SHORT_TIMEOUT, TPM2_TIMEOUT_C) +#define TIS_TIMEOUT_D_MAX max_t(int, TIS_SHORT_TIMEOUT, TPM2_TIMEOUT_D) + +#define TPM_ACCESS(l) (0x0000 | ((l) << 12)) +#define TPM_INT_ENABLE(l) (0x0008 | ((l) << 12)) +#define TPM_INT_VECTOR(l) (0x000C | ((l) << 12)) +#define TPM_INT_STATUS(l) (0x0010 | ((l) << 12)) +#define TPM_INTF_CAPS(l) (0x0014 | ((l) << 12)) +#define TPM_STS(l) (0x0018 | ((l) << 12)) +#define TPM_STS3(l) (0x001b | ((l) << 12)) +#define TPM_DATA_FIFO(l) (0x0024 | ((l) << 12)) +#define TPM_INTF_ID(l) (0x0030 | ((l) << 12)) + +#define TPM_DID_VID(l) (0x0F00 | ((l) << 12)) +#define TPM_RID(l) (0x0F04 | ((l) << 12)) + +/* TPM HW Interface and Capabilities */ +#define TPM_TIS_INTF_ACTIVE 0x00 +#define TPM_CRB_INTF_ACTIVE 0x01 + +#define TPM_INTID_INTERFACE_TYPE GENMASK(3, 0) +#define TPM_INTID_INTERFACE_VERSION GENMASK(7, 4) +#define TPM_INTID_CAP_LOCALITY BIT(8) +#define TPM_INTID_CAP_TIS BIT(13) +#define TPM_INTID_CAP_CRB BIT(14) +#define TPM_INTID_CAP_IF_RES GENMASK(16, 15) +#define TPM_INTID_INTERFACE_SELECTOR GENMASK(18, 17) +#define TPM_INTID_INTF_SEL_LOCK BIT(19) + +#define TPM_TIS_INTF_12 0x00 +#define TPM_TIS_INTF_13 0x02 +#define TPM2_TIS_INTF_13 0x03 + +#define TPM_INTF_DATA_AVAIL_INT_SUPPORT BIT(0) +#define TPM_INTF_STS_VALID_INT_SUPPORT BIT(1) +#define TPM_INTF_LOCALITY_CHANGE_INT_SUPPORT BIT(2) +#define TPM_INTF_INTERRUPT_LEVEL_HIGH BIT(3) +#define TPM_INTF_INTERRUPT_LEVEL_LOW BIT(4) +#define TPM_INTF_INTERRUPT_EDGE_RISING BIT(5) +#define TPM_INTF_INTERRUPT_EDGE_FALLING BIT(6) +#define TPM_INTF_COMMAND_READY_INT_SUPPORT BIT(7) +#define TPM_INTF_BURST_COUNT_STATIC BIT(8) +#define TPM_INTF_DATA_TRANSFER_SIZE_SUPPORT GENMASK(10, 9) +#define TPM_INTF_INTERFACE_VERSION GENMASK(30, 28) + +#endif diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 3357ee62d10b..5549298c1ec6 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -229,6 +229,9 @@ struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, struct sockaddr_vm *dst, struct net *net); +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 238ad3349456..795fb41b45f5 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -88,8 +88,6 @@ struct ip6_sf_socklist { struct in6_addr sl_addr[] __counted_by(sl_max); }; -#define IP6_SFBLOCK 10 /* allocate this many at once */ - struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; diff --git a/include/net/ip.h b/include/net/ip.h index a8f57b4f4aa2..6f602df72ee6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -704,7 +704,8 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, static __inline__ void inet_reset_saddr(struct sock *sk) { - inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; + inet_sk(sk)->inet_saddr = 0; + WRITE_ONCE(inet_sk(sk)->inet_rcv_saddr, 0); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 670c20876f26..436495ff2271 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -765,8 +765,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason); +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 98b0ccf0813e..16243ec376cd 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -2,6 +2,7 @@ #ifndef _SCSI_SCSI_HOST_H #define _SCSI_SCSI_HOST_H +#include #include #include #include @@ -727,7 +728,7 @@ struct Scsi_Host { unsigned int irq; - enum scsi_host_state shost_state; + enum scsi_host_state shost_state __guarded_by(host_lock); /* ldm bits */ struct device shost_gendev, shost_dev; @@ -788,11 +789,18 @@ static inline struct Scsi_Host *dev_to_shost(struct device *dev) return container_of(dev, struct Scsi_Host, shost_gendev); } +static inline enum scsi_host_state scsi_get_host_state(struct Scsi_Host *shost) +{ + return context_unsafe(READ_ONCE(shost->shost_state)); +} + static inline int scsi_host_in_recovery(struct Scsi_Host *shost) { - return shost->shost_state == SHOST_RECOVERY || - shost->shost_state == SHOST_CANCEL_RECOVERY || - shost->shost_state == SHOST_DEL_RECOVERY || + enum scsi_host_state state = scsi_get_host_state(shost); + + return state == SHOST_RECOVERY || + state == SHOST_CANCEL_RECOVERY || + state == SHOST_DEL_RECOVERY || shost->tmf_in_progress; } @@ -838,8 +846,9 @@ static inline struct device *scsi_get_device(struct Scsi_Host *shost) **/ static inline int scsi_host_scan_allowed(struct Scsi_Host *shost) { - return shost->shost_state == SHOST_RUNNING || - shost->shost_state == SHOST_RECOVERY; + enum scsi_host_state state = scsi_get_host_state(shost); + + return state == SHOST_RUNNING || state == SHOST_RECOVERY; } extern void scsi_unblock_requests(struct Scsi_Host *); @@ -943,6 +952,7 @@ static inline unsigned char scsi_host_get_guard(struct Scsi_Host *shost) return shost->prot_guard_type; } -extern int scsi_host_set_state(struct Scsi_Host *, enum scsi_host_state); +int scsi_host_set_state(struct Scsi_Host *shost, enum scsi_host_state state) + __must_hold(shost->host_lock); #endif /* _SCSI_SCSI_HOST_H */ diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 88a6159364d0..4154035af414 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -179,7 +179,8 @@ int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info int snd_rawmidi_kernel_open_nested(struct snd_rawmidi *rmidi, int subdevice, int mode, struct snd_rawmidi_file *rfile, int depth); -int snd_rawmidi_kernel_release(struct snd_rawmidi_file *rfile); +int snd_rawmidi_kernel_release_nested(struct snd_rawmidi_file *rfile, + int depth); int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream, struct snd_rawmidi_params *params); int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream, @@ -201,6 +202,11 @@ static inline int snd_rawmidi_kernel_open(struct snd_rawmidi *rmidi, return snd_rawmidi_kernel_open_nested(rmidi, subdevice, mode, rfile, 0); } +static inline int snd_rawmidi_kernel_release(struct snd_rawmidi_file *rfile) +{ + return snd_rawmidi_kernel_release_nested(rfile, 0); +} + /* set up the tied devices */ static inline void snd_rawmidi_tie_devices(struct snd_rawmidi *r1, struct snd_rawmidi *r2) diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 270c1a2c24c4..d53be932df01 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -191,7 +191,8 @@ TRACE_DEFINE_ENUM(CP_PHASE_FINISH_CHECKPOINT); { LOCK_NAME_NODE_WRITE, "node_write" }, \ { LOCK_NAME_GC_LOCK, "gc_lock" }, \ { LOCK_NAME_CP_GLOBAL, "cp_global" }, \ - { LOCK_NAME_IO_RWSEM, "io_rwsem" }) + { LOCK_NAME_IO_RWSEM, "io_rwsem" }, \ + { LOCK_NAME_NAT_TREE_LOCK, "nat_tree_lock" }) struct f2fs_sb_info; struct f2fs_io_info; @@ -2114,6 +2115,14 @@ DEFINE_EVENT(f2fs_zip_end, f2fs_decompress_pages_end, ); #ifdef CONFIG_F2FS_IOSTAT +/* + * Number of read folio order buckets emitted by the f2fs_iostat tracepoint. + * TP_printk() cannot loop, so the field count is fixed here and must be >= + * the largest possible NR_PAGE_ORDERS (14 on arm64 with 64K pages). The + * BUILD_BUG_ON() in f2fs_update_read_folio_count() enforces this. + */ +#define F2FS_IOSTAT_RD_FOLIO_ORDERS 16 + TRACE_EVENT(f2fs_iostat, TP_PROTO(struct f2fs_sb_info *sbi, unsigned long long *iostat, @@ -2151,7 +2160,7 @@ TRACE_EVENT(f2fs_iostat, __field(unsigned long long, fs_mrio) __field(unsigned long long, fs_discard) __field(unsigned long long, fs_reset_zone) - __array(unsigned long long, read_folio_count, 11) + __array(unsigned long long, read_folio_count, F2FS_IOSTAT_RD_FOLIO_ORDERS) ), TP_fast_assign( @@ -2186,7 +2195,8 @@ TRACE_EVENT(f2fs_iostat, __entry->fs_reset_zone = iostat[FS_ZONE_RESET_IO]; memset(__entry->read_folio_count, 0, sizeof(__entry->read_folio_count)); memcpy(__entry->read_folio_count, read_folio_count, - sizeof(unsigned long long) * min_t(int, NR_PAGE_ORDERS, 11)); + sizeof(unsigned long long) * + min_t(int, NR_PAGE_ORDERS, F2FS_IOSTAT_RD_FOLIO_ORDERS)); ), TP_printk("dev = (%d,%d), " @@ -2201,7 +2211,8 @@ TRACE_EVENT(f2fs_iostat, "fs [data=%llu, (gc_data=%llu, cdata=%llu), " "node=%llu, meta=%llu], " "read_folio_count [0=%llu, 1=%llu, 2=%llu, 3=%llu, 4=%llu, " - "5=%llu, 6=%llu, 7=%llu, 8=%llu, 9=%llu, 10=%llu]", + "5=%llu, 6=%llu, 7=%llu, 8=%llu, 9=%llu, 10=%llu, 11=%llu, " + "12=%llu, 13=%llu, 14=%llu, 15=%llu]", show_dev(__entry->dev), __entry->app_wio, __entry->app_dio, __entry->app_bio, __entry->app_mio, __entry->app_bcdio, __entry->app_mcdio, __entry->fs_dio, __entry->fs_cdio, @@ -2218,7 +2229,9 @@ TRACE_EVENT(f2fs_iostat, __entry->read_folio_count[4], __entry->read_folio_count[5], __entry->read_folio_count[6], __entry->read_folio_count[7], __entry->read_folio_count[8], __entry->read_folio_count[9], - __entry->read_folio_count[10]) + __entry->read_folio_count[10], __entry->read_folio_count[11], + __entry->read_folio_count[12], __entry->read_folio_count[13], + __entry->read_folio_count[14], __entry->read_folio_count[15]) ); #ifndef __F2FS_IOSTAT_LATENCY_TYPE diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h index 09ae115099df..6937b778ae54 100644 --- a/include/trace/events/icmp.h +++ b/include/trace/events/icmp.h @@ -27,17 +27,20 @@ TRACE_EVENT(icmp_send, TP_fast_assign( struct iphdr *iph = ip_hdr(skb); - struct udphdr *uh = udp_hdr(skb); - int proto_4 = iph->protocol; + struct udphdr _uh, *uh = NULL; __be32 *p32; __entry->skbaddr = skb; __entry->type = type; __entry->code = code; - if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head || - (u8 *)uh + sizeof(struct udphdr) - > skb_tail_pointer(skb)) { + if (iph->protocol == IPPROTO_UDP) + uh = skb_header_pointer(skb, + skb_network_offset(skb) + + (iph->ihl << 2), + sizeof(_uh), &_uh); + + if (!uh) { __entry->sport = 0; __entry->dport = 0; __entry->ulen = 0; diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 7f2e594be4eb..3d363f12f66a 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -228,7 +228,7 @@ struct drm_msm_gem_cpu_fini { struct drm_msm_syncobj { __u32 handle; /* in, syncobj handle. */ - __u32 flags; /* in, from MSM_SUBMIT_SYNCOBJ_FLAGS */ + __u32 flags; /* in, from MSM_SYNCOBJ_FLAGS */ __u64 point; /* in, timepoint for timeline syncobjs. */ }; @@ -393,9 +393,9 @@ struct drm_msm_vm_bind { __s32 fence_fd; /** @queue_id: in, submitqueue id */ __u32 queue_id; - /** @in_syncobjs: in, ptr to array of drm_msm_gem_syncobj */ + /** @in_syncobjs: in, ptr to array of drm_msm_syncobj */ __u64 in_syncobjs; - /** @out_syncobjs: in, ptr to array of drm_msm_gem_syncobj */ + /** @out_syncobjs: in, ptr to array of drm_msm_syncobj */ __u64 out_syncobjs; /** @nr_in_syncobjs: in, number of entries in in_syncobj */ __u32 nr_in_syncobjs; diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h index 795e26258355..4409ada2fecb 100644 --- a/include/uapi/linux/f2fs.h +++ b/include/uapi/linux/f2fs.h @@ -45,6 +45,9 @@ #define F2FS_IOC_START_ATOMIC_REPLACE _IO(F2FS_IOCTL_MAGIC, 25) #define F2FS_IOC_GET_DEV_ALIAS_FILE _IOR(F2FS_IOCTL_MAGIC, 26, __u32) #define F2FS_IOC_IO_PRIO _IOW(F2FS_IOCTL_MAGIC, 27, __u32) +#define F2FS_IOC_RESERVE_DEV_ALIAS _IO(F2FS_IOCTL_MAGIC, 28) +#define F2FS_IOC_RELEASE_DEV_ALIAS _IO(F2FS_IOCTL_MAGIC, 29) +#define F2FS_IOC_GET_DEV_ALIAS_STATUS _IOR(F2FS_IOCTL_MAGIC, 30, __u32) /* * should be same as XFS_IOC_GOINGDOWN. @@ -70,6 +73,10 @@ enum { F2FS_IOPRIO_MAX, }; +/* for F2FS_IOC_GET_DEV_ALIAS_STATUS */ +#define F2FS_DEV_ALIAS_STATUS_RELEASED 0 +#define F2FS_DEV_ALIAS_STATUS_RESERVED 1 + struct f2fs_gc_range { __u32 sync; __u64 start; diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index aa872a41ffb9..3538e11b5175 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -289,6 +289,13 @@ enum { * If @disable_fm is not zero, ubi doesn't create new fastmap even the module * param 'fm_autoconvert' is set, and existed old fastmap will be destroyed * after doing full scanning. + * + * The @wl_threshold defines the maximum difference between the highest and the + * lowest erase counter value of eraseblocks of this UBI device. When this + * threshold is exceeded, UBI starts performing wear leveling by means of + * moving data from eraseblock with low erase counter to eraseblocks with high + * erase counter. If @wl_threshold is zero, the default kernel value of + * %CONFIG_MTD_UBI_WL_THRESHOLD is used. The accepted range is 2-65536. */ struct ubi_attach_req { __s32 ubi_num; @@ -297,7 +304,8 @@ struct ubi_attach_req { __s16 max_beb_per1024; __s8 disable_fm; __s8 need_resv_pool; - __s8 padding[8]; + __s32 wl_threshold; + __s8 padding[4]; }; /* diff --git a/io_uring/query.c b/io_uring/query.c index 4321f0b94b4b..7bce2ec162c1 100644 --- a/io_uring/query.c +++ b/io_uring/query.c @@ -76,6 +76,9 @@ static int io_handle_query_entry(union io_query_data *data, void __user *uhdr, if (copy_from_user(&hdr, uhdr, sizeof(hdr))) return -EFAULT; + /* copy_struct_to_user() zeros up to usize bytes */ + if (hdr.size > PAGE_SIZE) + return -E2BIG; usize = hdr.size; hdr.size = min(hdr.size, IO_MAX_QUERY_SIZE); udata = u64_to_user_ptr(hdr.query_data); diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 76af129ba8ca..2b756017423f 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -125,7 +125,7 @@ static void io_waitid_remove_wq(struct io_kiocb *req) } } -static void io_waitid_complete(struct io_kiocb *req, int ret) +static void io_waitid_complete(struct io_kiocb *req, int ret, bool copy_si) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); @@ -137,13 +137,16 @@ static void io_waitid_complete(struct io_kiocb *req, int ret) hlist_del_init(&req->hash_node); io_waitid_remove_wq(req); - ret = io_waitid_finish(req, ret); + if (copy_si) + ret = io_waitid_finish(req, ret); + else + io_waitid_free(req); if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); } -static bool __io_waitid_cancel(struct io_kiocb *req) +static bool __io_waitid_cancel(struct io_kiocb *req, bool copy_si) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); @@ -159,21 +162,32 @@ static bool __io_waitid_cancel(struct io_kiocb *req) if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) return false; - io_waitid_complete(req, -ECANCELED); + io_waitid_complete(req, -ECANCELED, copy_si); io_req_queue_tw_complete(req, -ECANCELED); return true; } +static bool io_waitid_cancel_cb(struct io_kiocb *req) +{ + return __io_waitid_cancel(req, true); +} + +static bool io_waitid_cancel_nocopy_cb(struct io_kiocb *req) +{ + return __io_waitid_cancel(req, false); +} + int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, unsigned int issue_flags) { - return io_cancel_remove(ctx, cd, issue_flags, &ctx->waitid_list, __io_waitid_cancel); + return io_cancel_remove(ctx, cd, issue_flags, &ctx->waitid_list, io_waitid_cancel_cb); } bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all) { - return io_cancel_remove_all(ctx, tctx, &ctx->waitid_list, cancel_all, __io_waitid_cancel); + return io_cancel_remove_all(ctx, tctx, &ctx->waitid_list, cancel_all, + tctx ? io_waitid_cancel_cb : io_waitid_cancel_nocopy_cb); } static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req) @@ -202,6 +216,11 @@ static void io_waitid_cb(struct io_tw_req tw_req, io_tw_token_t tw) int ret; io_tw_lock(ctx, tw); + if (unlikely(tw.cancel)) { + io_waitid_complete(req, -ECANCELED, false); + io_req_task_complete(tw_req, tw); + return; + } ret = __do_wait(&iwa->wo); @@ -229,7 +248,7 @@ static void io_waitid_cb(struct io_tw_req tw_req, io_tw_token_t tw) } } - io_waitid_complete(req, ret); + io_waitid_complete(req, ret, true); io_req_task_complete(tw_req, tw); } diff --git a/kernel/capability.c b/kernel/capability.c index 829f49ae07b9..90e6ab62f6db 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -326,7 +326,6 @@ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } -EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, @@ -416,6 +415,24 @@ bool capable(int cap) return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); + +/** + * capable_noaudit - Determine if the current task has a superior + * capability in effect by checking the process's effective + * capabilities (unaudited). + * @cap: The capability to be tested for + * + * This is the same as capable(), except it uses CAP_OPT_NOAUDIT as to prevent + * issuing spurious audit messages. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool capable_noaudit(int cap) +{ + return ns_capable_noaudit(&init_user_ns, cap); +} +EXPORT_SYMBOL(capable_noaudit); #endif /* CONFIG_MULTIUSER */ /** diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c3a12fee7528..2d532bf2c0c7 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6873,10 +6873,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); - if (kargs->cgrp) - kargs->kill_seq = kargs->cgrp->kill_seq; - else - kargs->kill_seq = cset->dfl_cgrp->kill_seq; + kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { @@ -6940,6 +6937,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) put_css_set(cset); kargs->cgrp = dst_cgrp; + kargs->kill_seq = dst_cgrp->kill_seq; return ret; err: diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d100634fa12b..2538faac9aba 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1259,6 +1259,28 @@ static void reset_partition_data(struct cpuset *cs) cpumask_copy(cs->effective_cpus, parent->effective_cpus); } +/* Return true if isolated_cpus changes. */ +static bool isolated_cpu_update(int new_prs, int cpu) +{ + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + + if (new_prs == PRS_ISOLATED) { + if (cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_set_cpu(cpu, isolated_cpus); + return true; + } + + /* CPUs isolated at boot must remain isolated. */ + if (!cpumask_test_cpu(cpu, + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) || + !cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_clear_cpu(cpu, isolated_cpus); + return true; +} + /* * isolated_cpus_update - Update the isolated_cpus mask * @old_prs: old partition_root_state @@ -1267,19 +1289,16 @@ static void reset_partition_data(struct cpuset *cs) */ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { + bool updated = false; + int cpu; + WARN_ON_ONCE(old_prs == new_prs); lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); - if (new_prs == PRS_ISOLATED) { - if (cpumask_subset(xcpus, isolated_cpus)) - return; - cpumask_or(isolated_cpus, isolated_cpus, xcpus); - } else { - if (!cpumask_intersects(xcpus, isolated_cpus)) - return; - cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - } - update_housekeeping = true; + for_each_cpu(cpu, xcpus) + updated |= isolated_cpu_update(new_prs, cpu); + if (updated) + update_housekeeping = true; } /* diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 10af28a9f2c0..713aa26b2828 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -876,9 +876,9 @@ struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) * unloading. The init_tasks ("swappers") should be excluded * from the iteration because: * - * - It's unsafe to use __setschduler_prio() on an init_task to - * determine the sched_class to use as it won't preserve its - * idle_sched_class. + * - It's unsafe to use __setscheduler_class() on an init_task + * to determine the sched_class to use as it won't preserve + * its idle_sched_class. * * - ops.init/exit_task() can easily be confused if called with * init_tasks as they, e.g., share PID 0. @@ -2806,6 +2806,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, * @p: task to finish dispatching * @qseq_at_dispatch: qseq when @p started getting dispatched * @dsq_id: destination DSQ ID + * @slice: slice carried by the insert verdict, 0 keeps the current value + * @vtime: vtime carried by the insert verdict, committed on PRIQ inserts * @enq_flags: %SCX_ENQ_* * * Dispatching to local DSQs may need to wait for queueing to complete or @@ -5514,7 +5516,7 @@ static const struct kset_uevent_ops scx_uevent_ops = { }; /* - * Used by sched_fork() and __setscheduler_prio() to pick the matching + * Used by sched_fork() and __setscheduler_class() to pick the matching * sched_class. dl/rt are already handled. */ bool task_should_scx(int policy) @@ -7694,7 +7696,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * Enable ops for every task. Fork is excluded by scx_fork_rwsem * preventing new tasks from being added. No need to exclude tasks - * leaving as sched_ext_free() can handle both prepped and enabled + * leaving as sched_ext_dead() can handle both prepped and enabled * tasks. Prep all tasks first and then enable them with preemption * disabled. * @@ -7786,7 +7788,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * We're fully committed and can't fail. The task READY -> ENABLED - * transitions here are synchronized against sched_ext_free() through + * transitions here are synchronized against sched_ext_dead() through * scx_tasks_lock. */ percpu_down_write(&scx_fork_rwsem); @@ -8079,6 +8081,7 @@ static int bpf_scx_check_member(const struct btf_type *t, case offsetof(struct sched_ext_ops, cgroup_init): case offsetof(struct sched_ext_ops, cgroup_exit): case offsetof(struct sched_ext_ops, cgroup_prep_move): + case offsetof(struct sched_ext_ops, cgroup_set_bandwidth): #endif case offsetof(struct sched_ext_ops, cpu_online): case offsetof(struct sched_ext_ops, cpu_offline): @@ -9003,12 +9006,6 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, if (unlikely(READ_ONCE(sch->aborting))) return false; - if (unlikely(!scx_task_on_sched(sch, p))) { - scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", - p->comm, p->pid); - return false; - } - /* * Can be called from either ops.dispatch() holding the dispatched rq's * lock or any context where no rq lock is held. If latter, lock @p's @@ -9040,6 +9037,17 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, goto out; } + /* + * @p has been on $src_dsq and can't move anymore. If @p is not on @sch, + * the caller didn't have authority over @p at the time of the call. + */ + if (unlikely(!scx_task_on_sched(sch, p))) { + scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", + p->comm, p->pid); + raw_spin_unlock(&src_dsq->lock); + goto out; + } + /* @p is still on $src_dsq and stable, determine the destination */ dst_dsq = find_dsq_for_dispatch(sch, locked_rq ?: this_rq(), dsq_id, task_cpu(p)); @@ -9765,7 +9773,7 @@ __bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *i * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator * @it: iterator to destroy * - * Undo scx_iter_scx_dsq_new(). + * Undo bpf_iter_scx_dsq_new(). */ __bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) { @@ -11041,3 +11049,16 @@ static int __init scx_init(void) return 0; } __initcall(scx_init); + +/* + * Compatibility markers for userspace. Existence of a marker function + * represents that the kernel supports that sched-ext feature. + */ + +/* + * scx_compat_marker_cgroup_set_bandwidth_may_sleep: advertises that + * ops.cgroup_set_bandwidth() may be implemented as a sleepable callback. + */ +#ifdef CONFIG_EXT_GROUP_SCHED +DEFINE_SCX_COMPAT_MARKER(cgroup_set_bandwidth_may_sleep); +#endif /* CONFIG_EXT_GROUP_SCHED */ diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 27bbf5e04d90..0967b99a4948 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -442,7 +442,7 @@ struct sched_ext_ops { * * Note that this callback may be called from a CPU other than the * one the task is going to run on. This can happen when a task - * property is changed (i.e., affinity), since scx_next_task_scx(), + * property is changed (i.e., affinity), since set_next_task_scx(), * which triggers this callback, may run on a CPU different from * the task's assigned CPU. * @@ -753,7 +753,7 @@ struct sched_ext_ops { * @burst_us: bandwidth control burst * * Update @cgrp's bandwidth control parameters. This is from the cpu.max - * cgroup interface. + * cgroup interface. This operation may block. * * @quota_us / @period_us determines the CPU bandwidth @cgrp is entitled * to. For example, if @period_us is 1_000_000 and @quota_us is @@ -2001,6 +2001,27 @@ struct scx_bstr_buf { char line[SCX_EXIT_MSG_LEN]; }; +/* Internal helper for DEFINE_SCX_COMPAT_MARKER(). */ +#define DECLARE_SCX_COMPAT_MARKER(func) \ + extern void scx_compat_marker_##func(void) + +/** + * DEFINE_SCX_COMPAT_MARKER() - define a userspace capability marker + * @func: marker suffix; the defined symbol is scx_compat_marker_@func + * + * Emit an empty, callerless function that is retained in the kernel's BTF. + * Its presence is part of the kernel<->userspace contract: userspace probes + * scx_compat_marker_@func (e.g. via BTF) to detect that this kernel supports + * the corresponding feature. + * + * The leading declaration suppresses the missing-prototype warning; the + * trailing declaration consumes the semicolon at the use site. + */ +#define DEFINE_SCX_COMPAT_MARKER(func) \ + DECLARE_SCX_COMPAT_MARKER(func); \ + __used __retain void scx_compat_marker_##func(void) {} \ + DECLARE_SCX_COMPAT_MARKER(func) + extern struct scx_sched __rcu *scx_root; DECLARE_PER_CPU(struct rq *, scx_locked_rq_state); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6d881e530f89..8dff37059faf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7253,7 +7253,7 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) * period the timer is deactivated until scheduling resumes; cfs_b->idle is * used to track this state. */ -static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) __must_hold(&cfs_b->lock) { int throttled; @@ -7288,10 +7288,10 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) * This check is repeated as we release cfs_b->lock while we unthrottle. */ while (throttled && cfs_b->runtime > 0) { - raw_spin_unlock_irq_enable(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ throttled = distribute_cfs_runtime(cfs_b); - raw_spin_lock_irq_disable(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); } /* @@ -7399,7 +7399,7 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { /* confirm we're still not at a refresh boundary */ - scoped_guard(raw_spinlock_irq, &cfs_b->lock) { + scoped_guard(raw_spinlock_irqsave, &cfs_b->lock) { u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); cfs_b->slack_started = false; @@ -7484,14 +7484,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) int idle = 0; int count = 0; - guard(raw_spinlock_irq)(&cfs_b->lock); + CLASS(raw_spinlock_irqsave, cfsb_guard)(&cfs_b->lock); for (;;) { overrun = hrtimer_forward_now(timer, cfs_b->period); if (!overrun) break; - idle = do_sched_cfs_period_timer(cfs_b, overrun); + idle = do_sched_cfs_period_timer(cfs_b, overrun, cfsb_guard.flags); if (++count > 3) { u64 new, old = ktime_to_ns(cfs_b->period); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3c3ed639923d..b0963ac6fd16 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5805,8 +5805,11 @@ __rb_get_reader_page_from_remote(struct ring_buffer_per_cpu *cpu_buffer) prev_reader = cpu_buffer->subbuf_ids[cpu_buffer->meta_page->reader.id]; - WARN_ON_ONCE(cpu_buffer->remote->swap_reader_page(cpu_buffer->cpu, - cpu_buffer->remote->priv)); + if (cpu_buffer->remote->swap_reader_page(cpu_buffer->cpu, + cpu_buffer->remote->priv)) { + pr_warn_ratelimited("Remote reader page swap failed\n"); + return NULL; + } /* nr_pages doesn't include the reader page */ if (WARN_ON_ONCE(cpu_buffer->meta_page->reader.id > cpu_buffer->nr_pages)) return NULL; diff --git a/kernel/trace/simple_ring_buffer.c b/kernel/trace/simple_ring_buffer.c index f4642f5adda3..49913bb0057a 100644 --- a/kernel/trace/simple_ring_buffer.c +++ b/kernel/trace/simple_ring_buffer.c @@ -160,8 +160,8 @@ int simple_ring_buffer_swap_reader_page(struct simple_rb_per_cpu *cpu_buffer) overrun = cpu_buffer->meta->overrun; } while (!simple_bpage_unset_head_link(last, reader, SIMPLE_RB_LINK_NORMAL) && retry--); - if (!retry) - return -EINVAL; + if (retry < 0) + return -EBUSY; cpu_buffer->head_page = simple_bpage_from_link(reader->link.next); cpu_buffer->head_page->link.prev = &reader->link; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3e0907aef172..a946e0183fd1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8216,6 +8216,8 @@ buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, /* Do not allow tracing while changing the order of the ring buffer */ tracing_stop_tr(tr); + trace_access_lock(RING_BUFFER_ALL_CPUS); + old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); if (old_order == order) goto out; @@ -8255,6 +8257,7 @@ buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, #endif (*ppos)++; out: + trace_access_unlock(RING_BUFFER_ALL_CPUS); if (ret) cnt = ret; tracing_start_tr(tr); @@ -9728,7 +9731,8 @@ __init static void enable_instances(void) tr = trace_array_create_systems(name, NULL, addr, size); if (IS_ERR(tr)) { - pr_warn("Tracing: Failed to create instance buffer %s\n", curr_str); + pr_warn("Tracing: Failed to create instance buffer '%s' (%ld)\n", name, + PTR_ERR(tr)); continue; } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9f8f2d02276c..1d39eaf6a0f7 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -5019,6 +5019,8 @@ static __init void event_test_stuff(void) struct task_struct *test_thread; test_thread = kthread_run(event_test_thread, NULL, "test-events"); + if (WARN_ON(IS_ERR(test_thread))) + return; msleep(1); kthread_stop(test_thread); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 893bd8b0e48a..963e0d6b61fd 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6661,8 +6661,10 @@ static int hist_register_trigger(char *glob, tracing_set_filter_buffering(file->tr, true); } - if (named_data) + if (named_data) { + remove_hist_vars(hist_data); destroy_hist_data(hist_data); + } out: return ret; } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 2bbc89d4a266..93cda2f6f269 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -868,6 +868,9 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) struct user_event_mm *mm = user_event_mm_alloc(t); struct user_event_enabler *enabler; + /* On failure, do not free parent's copy */ + t->user_event_mm = NULL; + if (!mm) return; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3c034cbc5bb3..1ae3732a2c51 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3197,7 +3197,16 @@ __acquires(&pool->lock) #ifdef CONFIG_PREEMPT_RT static void worker_lock_callback(struct worker_pool *pool) { - spin_lock(&pool->cb_lock); + /* + * SINGLE_DEPTH_NESTING is for a dead pool's bh_worker() running from + * drain_dead_softirq_workfn() inside a live pool's bh_worker(). The + * unlocked read is stable: the flag is only set while @pool's CPU is + * dead, inside a serialized hotplug operation. data_race() as the value + * only affects the lockdep annotation and the read can be elided when + * lockdep is disabled. + */ + spin_lock_nested(&pool->cb_lock, + data_race(pool->flags) & POOL_BH_DRAINING ? SINGLE_DEPTH_NESTING : 0); } static void worker_unlock_callback(struct worker_pool *pool) @@ -5285,12 +5294,6 @@ static void pwq_release_workfn(struct kthread_work *work) mutex_unlock(&wq->mutex); } - if (!is_percpu_pool(pool)) { - mutex_lock(&wq_pool_mutex); - put_unbound_pool(pool); - mutex_unlock(&wq_pool_mutex); - } - if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); @@ -5300,6 +5303,12 @@ static void pwq_release_workfn(struct kthread_work *work) raw_spin_unlock_irq(&nna->lock); } + if (!is_percpu_pool(pool)) { + mutex_lock(&wq_pool_mutex); + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + } + kfree_rcu(pwq, rcu); /* @@ -8050,6 +8059,9 @@ static int wq_watchdog_param_set_thresh(const char *val, if (ret) return ret; + if (thresh > MAX_JIFFY_OFFSET / HZ) + return -ERANGE; + if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else @@ -8080,12 +8092,12 @@ static inline void wq_watchdog_init(void) { } static void bh_pool_kick_normal(struct irq_work *irq_work) { - raise_softirq_irqoff(TASKLET_SOFTIRQ); + raise_softirq(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { - raise_softirq_irqoff(HI_SOFTIRQ); + raise_softirq(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 35a1be57e386..d7355c73f93e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2632,11 +2632,11 @@ int hci_register_dev(struct hci_dev *hdev) if (error) BT_WARN("register suspend notifier failed error:%d\n", error); - queue_work(hdev->req_workqueue, &hdev->power_on); - idr_init(&hdev->adv_monitors_idr); msft_register(hdev); + queue_work(hdev->req_workqueue, &hdev->power_on); + return id; err_wqueue: diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ee459dd411f5..644e31160d55 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1337,7 +1337,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan) struct l2cap_ecred_conn_data { struct { struct l2cap_ecred_conn_req_hdr req; - __le16 scid[5]; + __le16 scid[L2CAP_ECRED_CONN_SCID_MAX]; } __packed pdu; struct l2cap_chan *chan; struct pid *pid; @@ -1352,7 +1352,7 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) if (chan == conn->chan) return; - if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + if (!test_bit(FLAG_DEFER_SETUP, &chan->flags)) return; pid = chan->ops->get_peer_pid(chan); @@ -1362,9 +1362,16 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) chan->mode != L2CAP_MODE_EXT_FLOWCTL || chan->state != BT_CONNECT) return; + if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + return; + if (test_and_set_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; + /* Unreachable, checked in l2cap_connect (+timer drops it if reached) */ + if (WARN_ON_ONCE(conn->count >= ARRAY_SIZE(conn->pdu.scid))) + return; + l2cap_ecred_init(chan, 0); /* Set the same ident so we can match on the rsp */ @@ -3894,6 +3901,9 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); + if (chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + /* Check if channel for outgoing connection or if it wasn't deferred * since in those cases it must be skipped. */ @@ -3904,6 +3914,10 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) /* Reset ident so only one response is sent */ chan->ident = 0; + /* Unreachable, check in l2cap_ecred_conn_req. If reached, drop rest */ + if (WARN_ON_ONCE(rsp->count >= ARRAY_SIZE(rsp->pdu.scid))) + rsp->pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_NO_MEM); + /* Include all channels pending with the same ident */ if (!rsp->pdu.rsp.result) rsp_flex->dcid[rsp->count++] = cpu_to_le16(chan->scid); @@ -5063,6 +5077,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_LE_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); @@ -7369,6 +7384,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, goto done; } + mutex_lock(&conn->lock); + l2cap_chan_lock(chan); + if (chan->mode == L2CAP_MODE_EXT_FLOWCTL) { struct l2cap_chan_data data; @@ -7376,19 +7394,20 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, data.pid = chan->ops->get_peer_pid(chan); data.count = 1; - l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + __l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + + /* Leave room for non-deferred channel that ends the group. */ + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + data.count += 1; /* Check if there isn't too many channels being connected */ if (data.count > L2CAP_ECRED_CONN_SCID_MAX) { hci_conn_drop(hcon); err = -EPROTO; - goto done; + goto chan_unlock; } } - mutex_lock(&conn->lock); - l2cap_chan_lock(chan); - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { hci_conn_drop(hcon); err = -EBUSY; diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index ded68568e6c9..d9dd722db3eb 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -769,8 +769,8 @@ void msft_register(struct hci_dev *hdev) INIT_LIST_HEAD(&msft->handle_map); INIT_LIST_HEAD(&msft->address_filters); - hdev->msft_data = msft; mutex_init(&msft->filter_lock); + hdev->msft_data = msft; } void msft_release(struct hci_dev *hdev) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3ef5d8bbf552..3e9b10f8abf1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -808,7 +808,11 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct hlist_node *tmp; rcu_assign_pointer(*pp, pg->next); - hlist_del_init(&pg->mglist); + /* Keep ->next (held under multicast_lock, freed later by the GC work): + * a port->mglist teardown walk may have latched this node as its next, + * and deleting other groups of the same port must not truncate it. + */ + hlist_del_init_rcu(&pg->mglist); br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) br_multicast_del_group_src(ent, false); @@ -835,6 +839,13 @@ static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; + /* A teardown walk over port->mglist can reach a group that an earlier + * iteration already deleted as a side effect. It is off mp->ports by + * now, so skip it instead of falling through to the WARN_ON() below. + */ + if (hlist_unhashed(&pg->mglist)) + return; + mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 05f6eea299fc..b323b61e7023 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -2142,6 +2142,11 @@ static int process_banner_prefix(struct ceph_connection *con) payload_len = ceph_decode_16(&p); dout("%s con %p payload_len %d\n", __func__, con, payload_len); + if (payload_len < sizeof(u64) + sizeof(u64)) { + con->error_msg = "protocol error, bad banner payload len"; + return -EINVAL; + } + return prepare_read_banner_payload(con, payload_len); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 28d76c2f6b3e..f36ce5ae7568 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -5802,6 +5803,31 @@ static inline void convert_extent_map(struct ceph_sparse_read *sr) } #endif +static bool sparse_extent_map_valid(struct ceph_sparse_read *sr) +{ + u64 req_end, pos; + int i; + + if (check_add_overflow(sr->sr_req_off, sr->sr_req_len, &req_end)) + return false; + + pos = sr->sr_req_off; + for (i = 0; i < sr->sr_count; i++) { + struct ceph_sparse_extent *ext = &sr->sr_extent[i]; + u64 end; + + if (ext->off < pos) + return false; + if (check_add_overflow(ext->off, ext->len, &end)) + return false; + if (end > req_end) + return false; + pos = end; + } + + return true; +} + static int osd_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor, char **pbuf) @@ -5852,6 +5878,10 @@ static int osd_sparse_read(struct ceph_connection *con, fallthrough; case CEPH_SPARSE_READ_DATA_LEN: convert_extent_map(sr); + if (!sparse_extent_map_valid(sr)) { + pr_warn_ratelimited("invalid sparse extent map\n"); + return -EREMOTEIO; + } ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index d6282f0bcff8..cf34b35c9a90 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -517,6 +517,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) ceph_decode_need(p, end, 4*sizeof(u32), bad); b->id = ceph_decode_32(p); + if (b->id != -1 - i) + goto bad; b->type = ceph_decode_16(p); if (b->type == 0) goto bad; diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 858359873c4d..a6aa5b3b7a1e 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -10,19 +10,6 @@ #include -void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty) -{ - int i; - - for (i = 0; i < num_pages; i++) { - if (dirty) - set_page_dirty_lock(pages[i]); - put_page(pages[i]); - } - kvfree(pages); -} -EXPORT_SYMBOL(ceph_put_page_vector); - void ceph_release_page_vector(struct page **pages, int num_pages) { int i; diff --git a/net/core/dev.c b/net/core/dev.c index 38336858c168..290e0f099e6b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -12703,7 +12703,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { - struct netdev_name_node *name_node; + struct netdev_name_node *name_node, *tmp; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; @@ -12749,13 +12749,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, } /* Check that none of the altnames conflicts. */ err = -EEXIST; - netdev_for_each_altname(dev, name_node) { - if (netdev_name_in_use(net, name_node->name)) { - NL_SET_ERR_MSG_FMT(extack, - "An interface with the altname %s exists in the target netns", - name_node->name); - goto out; + netdev_for_each_altname_safe(dev, name_node, tmp) { + if (!netdev_name_in_use(net, name_node->name)) + continue; + + if (!check_net(net_old)) { + __netdev_name_node_alt_destroy(name_node); + continue; } + + NL_SET_ERR_MSG_FMT(extack, + "An interface with the altname %s exists in the target netns", + name_node->name); + goto out; } /* Check that new_ifindex isn't used yet. */ @@ -13210,7 +13216,6 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { - struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -13234,10 +13239,6 @@ static void __net_exit default_device_exit_net(struct net *net) if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); - netdev_for_each_altname_safe(dev, name_node, tmp) - if (netdev_name_in_use(&init_net, name_node->name)) - __netdev_name_node_alt_destroy(name_node); - err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 1b84385c04bd..d8c0a2867120 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -22,6 +22,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) if (unlikely(!(dev->flags & IFF_UP))) goto drop; + skb_unset_transport_header(skb); + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { res = netif_rx(skb); goto unlock; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8f8956fb061b..08d7f35cf608 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1073,7 +1073,8 @@ netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, if (WARN_ON(size > max_size)) return 0; - size = ALIGN(size, dma_get_cache_alignment()); + size = ALIGN(size, max_t(unsigned int, dma_get_cache_alignment(), + __alignof__(struct skb_shared_info))); *offset = pool->frag_offset; if (netmem && *offset + size > max_size) { diff --git a/net/core/sock.c b/net/core/sock.c index 1ad41904db25..fa60b7494c58 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2494,6 +2494,9 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); #endif +#if IS_ENABLED(CONFIG_INET_PSP) + RCU_INIT_POINTER(newsk->psp_assoc, NULL); +#endif /* SANITY */ if (likely(newsk->sk_net_refcnt)) { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0483519b7fb0..7a362f2e2c2b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -874,7 +874,7 @@ static void fib_rebalance(struct fib_info *fi) change_nexthops(fi) { int upper_bound; - if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { + if (!total || nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { upper_bound = -1; } else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) && nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b80b8a92f46e..d56355aca797 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -188,6 +188,10 @@ static void ip_ma_put(struct ip_mc_list *im) } } +#define pmc_dereference(e, pmc) \ + rcu_dereference_protected(e, lockdep_is_held(&(pmc)->lock) || \ + lockdep_is_held(&(pmc)->interface->mc_tomb_lock)) + #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ @@ -198,13 +202,28 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +#define for_each_psf_mclock(pmc, psf) \ + for (psf = pmc_dereference((pmc)->sources, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + +#define for_each_psf_rcu(im, psf) \ + for (psf = rcu_dereference((im)->sources); \ + psf; \ + psf = rcu_dereference(psf->sf_next)) + +#define for_each_psf_tomb(pmc, psf) \ + for (psf = pmc_dereference((pmc)->tomb, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { - next = psf->sf_next; - kfree(psf); + next = rcu_dereference_protected(psf->sf_next, 1); + kfree_rcu(psf, rcu); psf = next; } } @@ -349,7 +368,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) struct ip_sf_list *psf; int scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -494,7 +513,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; - struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; + struct ip_sf_list *psf, *psf_next, *psf_prev; + struct ip_sf_list __rcu **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; @@ -517,7 +537,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf_list = sdeleted ? &pmc->tomb : &pmc->sources; - if (!*psf_list) + if (!rcu_access_pointer(*psf_list)) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; @@ -533,10 +553,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } first = 1; psf_prev = NULL; - for (psf = *psf_list; psf; psf = psf_next) { + for (psf = pmc_dereference(*psf_list, pmc); + psf; + psf = psf_next) { __be32 *psrc; - psf_next = psf->sf_next; + psf_next = pmc_dereference(psf->sf_next, pmc); if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; @@ -583,10 +605,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + psf_next); else - *psf_list = psf->sf_next; - kfree(psf); + rcu_assign_pointer(*psf_list, + psf_next); + kfree_rcu(psf, rcu); continue; } } @@ -655,28 +679,29 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) /* * remove zero-count source records from a source filter list */ -static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) +static void igmpv3_clear_zeros(struct ip_sf_list __rcu **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf = *ppsf; psf; psf = psf_next) { - psf_next = psf->sf_next; + for (psf = rcu_dereference_protected(*ppsf, 1); psf; psf = psf_next) { + psf_next = rcu_dereference_protected(psf->sf_next, 1); if (psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, psf_next); else - *ppsf = psf->sf_next; - kfree(psf); - } else + rcu_assign_pointer(*ppsf, psf_next); + kfree_rcu(psf, rcu); + } else { psf_prev = psf; + } } } static void kfree_pmc(struct ip_mc_list *pmc) { - ip_sf_list_clear_all(pmc->sources); - ip_sf_list_clear_all(pmc->tomb); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->sources, 1)); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->tomb, 1)); kfree(pmc); } @@ -710,7 +735,8 @@ static void igmpv3_send_cr(struct in_device *in_dev) igmpv3_clear_zeros(&pmc->sources); } } - if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { + if (pmc->crcount == 0 && !rcu_access_pointer(pmc->tomb) && + !rcu_access_pointer(pmc->sources)) { if (pmc_prev) pmc_prev->next = pmc_next; else @@ -896,7 +922,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) int i, scount; scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { @@ -927,7 +953,7 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) /* mark INCLUDE-mode sources */ scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) @@ -1228,11 +1254,12 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; + for_each_psf_mclock(im, psf) + psf->sf_crcount = pmc->crcount; pmc->tomb = im->tomb; pmc->sources = im->sources; - im->tomb = im->sources = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) - psf->sf_crcount = pmc->crcount; + RCU_INIT_POINTER(im->tomb, NULL); + RCU_INIT_POINTER(im->sources, NULL); } spin_unlock_bh(&im->lock); @@ -1271,9 +1298,18 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { - swap(im->tomb, pmc->tomb); - swap(im->sources, pmc->sources); - for (psf = im->sources; psf; psf = psf->sf_next) + struct ip_sf_list *sources, *tomb; + + tomb = rcu_replace_pointer(im->tomb, + rcu_dereference_protected(pmc->tomb, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->tomb, tomb); + + sources = rcu_replace_pointer(im->sources, + rcu_dereference_protected(pmc->sources, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->sources, sources); + for_each_psf_mclock(im, psf) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { @@ -1310,8 +1346,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); - psf = pmc->tomb; - pmc->tomb = NULL; + psf = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } @@ -1990,7 +2026,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, int rv = 0; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1999,7 +2035,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* source filter not found, or count wrong => bug */ return -ESRCH; } - psf->sf_count[sfmode]--; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } @@ -2011,19 +2047,28 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* no more filters for this source */ if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + pmc_dereference(psf->sf_next, pmc)); else - pmc->sources = psf->sf_next; + rcu_assign_pointer(pmc->sources, + pmc_dereference(psf->sf_next, pmc)); #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); - psf->sf_next = pmc->tomb; - pmc->tomb = psf; - rv = 1; - } else + struct ip_sf_list *dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); + rv = 1; + } + } #endif - kfree(psf); + kfree_rcu(psf, rcu); } return rv; } @@ -2060,7 +2105,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); } err = 0; for (i = 0; i < sfcount; i++) { @@ -2083,7 +2128,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -2104,7 +2149,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -2114,12 +2159,12 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; - if (psf_prev) { - psf_prev->sf_next = psf; - } else - pmc->sources = psf; + if (psf_prev) + rcu_assign_pointer(psf_prev->sf_next, psf); + else + rcu_assign_pointer(pmc->sources, psf); } - psf->sf_count[sfmode]++; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } @@ -2132,13 +2177,15 @@ static void sf_markstate(struct ip_mc_list *pmc) struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; + } + } } static int sf_setstate(struct ip_mc_list *pmc) @@ -2149,27 +2196,31 @@ static int sf_setstate(struct ip_mc_list *pmc) int new_in, rv; rv = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { new_in = psf->sf_count[MCAST_INCLUDE] != 0; + } if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { + struct ip_sf_list *dpsf_next; + + dpsf_next = pmc_dereference(dpsf->sf_next, pmc); if (prev) - prev->sf_next = dpsf->sf_next; + rcu_assign_pointer(prev->sf_next, dpsf_next); else - pmc->tomb = dpsf->sf_next; - kfree(dpsf); + rcu_assign_pointer(pmc->tomb, dpsf_next); + kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; @@ -2181,17 +2232,19 @@ static int sf_setstate(struct ip_mc_list *pmc) * add or update "delete" records if an active filter * is now inactive */ - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; + } if (!dpsf) { dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ - dpsf->sf_next = pmc->tomb; - pmc->tomb = dpsf; + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; @@ -2231,7 +2284,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) - pmc->sfcount[sfmode]++; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); @@ -2242,7 +2295,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int j; if (!delta) - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { @@ -2262,7 +2315,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -2278,13 +2331,13 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); - tomb = pmc->tomb; - pmc->tomb = NULL; - sources = pmc->sources; - pmc->sources = NULL; + tomb = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); + sources = pmc_dereference(pmc->sources, pmc); + RCU_INIT_POINTER(pmc->sources, NULL); pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; + WRITE_ONCE(pmc->sfcount[MCAST_INCLUDE], 0); + WRITE_ONCE(pmc->sfcount[MCAST_EXCLUDE], 1); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); @@ -2866,20 +2919,19 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { - spin_lock_bh(&im->lock); - for (psf = im->sources; psf; psf = psf->sf_next) { + for_each_psf_rcu(im, psf) { if (psf->sf_inaddr == src_addr) break; } if (psf) - rv = psf->sf_count[MCAST_INCLUDE] || - psf->sf_count[MCAST_EXCLUDE] != - im->sfcount[MCAST_EXCLUDE]; + rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || + READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != + READ_ONCE(im->sfcount[MCAST_EXCLUDE]); else - rv = im->sfcount[MCAST_EXCLUDE] != 0; - spin_unlock_bh(&im->lock); - } else + rv = READ_ONCE(im->sfcount[MCAST_EXCLUDE]) != 0; + } else { rv = 1; /* unspecified source; tentatively allow */ + } } return rv; } @@ -3043,7 +3095,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); - psf = im->sources; + psf = pmc_dereference(im->sources, im); if (likely(psf)) { state->im = im; state->idev = idev; @@ -3059,7 +3111,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - psf = psf->sf_next; + psf = pmc_dereference(psf->sf_next, state->im); while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; @@ -3075,7 +3127,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); - psf = state->im->sources; + psf = pmc_dereference(state->im->sources, state->im); } out: return psf; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b4237d0e994d..1c867a302444 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3182,8 +3182,7 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -3257,7 +3256,7 @@ void __tcp_close(struct sock *sk, long timeout) struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); @@ -3276,7 +3275,7 @@ void __tcp_close(struct sock *sk, long timeout) if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -3377,14 +3376,14 @@ int tcp_disconnect(struct sock *sk, int flags) } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), + tcp_send_active_reset(sk, SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) @@ -4562,9 +4561,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - ca_ops = icsk->icsk_ca_ops; + rcu_read_lock(); + ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); + rcu_read_unlock(); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) @@ -4577,16 +4578,24 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = !inet_csk_in_pingpong_mode(sk); break; - case TCP_CONGESTION: + case TCP_CONGESTION: { + char ca_name[TCP_CA_NAME_MAX] = {}; + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) + + rcu_read_lock(); + memcpy(ca_name, READ_ONCE(icsk->icsk_ca_ops)->name, + sizeof(ca_name)); + rcu_read_unlock(); + + if (copy_to_sockptr(optval, ca_name, len)) return -EFAULT; return 0; - + } case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; @@ -5147,8 +5156,7 @@ int tcp_abort(struct sock *sk, int err) bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index e9f6c77e0631..8e83ef81fc18 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -223,7 +223,7 @@ void tcp_assign_congestion_control(struct sock *sk) ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -253,7 +253,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 274e628e7cf8..5b457f68a581 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -111,7 +111,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk) /* No ECN support? Fall back to Reno. Also need to clear * ECT from sk since it is set during 3WHS for DCTCP. */ - inet_csk(sk)->icsk_ca_ops = &dctcp_reno; + WRITE_ONCE(inet_csk(sk)->icsk_ca_ops, &dctcp_reno); INET_ECN_dontxmit(sk); } @@ -228,7 +228,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { memset(&info->dctcp, 0, sizeof(info->dctcp)); - if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) { + if (READ_ONCE(inet_csk(sk)->icsk_ca_ops) != &dctcp_reno) { info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f3fa0b18eda0..0ddfd5af6e58 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -507,7 +507,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); ca_got_dst = true; } rcu_read_unlock(); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3b1fdcd3cb29..e74d99ca9fac 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -332,6 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + flush |= NAPI_GRO_CB(p)->is_flist != NAPI_GRO_CB(skb)->is_flist; skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) @@ -395,12 +396,20 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, struct net *net; int iif, sdif; - if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) - return; - p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -410,7 +419,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); } @@ -430,7 +439,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) if (!th) goto flush; - tcp4_check_fraglist_gro(head, skb, th); + if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + tcp4_check_fraglist_gro(head, skb, th); return tcp_gro_receive(head, skb, th); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6f4dca4a4de9..d960e3de7d50 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3849,9 +3849,9 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason) +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason) { + gfp_t priority = sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN); struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); @@ -4092,7 +4092,7 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); } rcu_read_unlock(); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 1038e7ba9c2e..e56eae4bc341 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -126,7 +126,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -809,7 +809,7 @@ static void tcp_keepalive_timer(struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); goto death; } @@ -836,7 +836,7 @@ static void tcp_keepalive_timer(struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a01db598c00b..b3887c42adfd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -900,6 +900,15 @@ static struct sock *__udp4_lib_err_encap(struct net *net, return sk; } +static void udp_err_update_exception(struct net *net, struct sk_buff *skb, + int type, int code, u32 info) +{ + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, IPPROTO_UDP); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, IPPROTO_UDP); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -923,6 +932,8 @@ int udp_err(struct sk_buff *skb, u32 info) int harderr; int err; + udp_err_update_exception(net, skb, type, code, info); + uh = (struct udphdr *)(skb->data + (iph->ihl << 2)); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, @@ -2166,10 +2177,10 @@ int __udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->inet_daddr = 0; + WRITE_ONCE(inet->inet_daddr, 0); inet->inet_dport = 0; sock_rps_reset_rxhash(sk); - sk->sk_bound_dev_if = 0; + WRITE_ONCE(sk->sk_bound_dev_if, 0); if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 51941ad656a3..09a4552f7f08 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -445,7 +445,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb, struct inet6_dev *idev) hdr->segments_left--; addr = hdr->segments + hdr->segments_left; - skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, -skb_network_offset(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); @@ -469,7 +469,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb, struct inet6_dev *idev) } ipv6_hdr(skb)->hop_limit--; - skb_pull(skb, sizeof(struct ipv6hdr)); + skb_pull(skb, skb_transport_offset(skb)); goto looped_back; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69c51f1a5bf0..8ebda0b6a78b 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -878,6 +878,7 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); __be16 payload_protocol; int ret; @@ -888,6 +889,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; + if (t->parms.collect_md) + tun_info = skb_tunnel_info_txcheck(skb); + payload_protocol = skb_protocol(skb, true); switch (payload_protocol) { case htons(ETH_P_IP): @@ -907,7 +911,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) + if (!IS_ERR(tun_info)) DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index aaba4c2aae23..ecef55f26189 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -240,7 +240,8 @@ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, return err; } - mc_lst->next = np->ipv6_mc_list; + rcu_assign_pointer(mc_lst->next, + sock_dereference(np->ipv6_mc_list, sk)); rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; @@ -300,7 +301,8 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - *lnk = mc_lst->next; + rcu_assign_pointer(*lnk, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); return 0; } @@ -333,7 +335,8 @@ void __ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { - np->ipv6_mc_list = mc_lst->next; + rcu_assign_pointer(np->ipv6_mc_list, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); } } @@ -355,12 +358,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; + struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; - struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; - int i, j, rv; + int i, j; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; @@ -409,13 +412,11 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ - rv = !0; for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) + if (ipv6_addr_equal(&psl->sl_addr[i], source)) break; } - if (rv) /* source not found */ + if (i == psl->sl_count) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ @@ -424,58 +425,74 @@ int ip6_mc_source(int add, int omode, struct sock *sk, goto done; } + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + + if (psl->sl_count == 1) { + newpsl = NULL; + } else { + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + psl->sl_count - 1), + GFP_KERNEL); + if (!newpsl) { + atomic_add(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + err = -ENOBUFS; + goto done; + } + newpsl->sl_max = psl->sl_count - 1; + newpsl->sl_count = psl->sl_count - 1; + for (j = 0; j < i; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + for (j = i + 1; j < psl->sl_count; j++) + newpsl->sl_addr[j - 1] = psl->sl_addr[j]; + } + /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); - for (j = i+1; j < psl->sl_count; j++) - psl->sl_addr[j-1] = psl->sl_addr[j]; - psl->sl_count--; + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); err = 0; goto done; } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_mld_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(sysctl_mld_max_msf)) { err = -ENOBUFS; goto done; } - if (!psl || psl->sl_count == psl->sl_max) { - struct ip6_sf_socklist *newpsl; - int count = IP6_SFBLOCK; + if (psl) { + for (i = 0; i < psl->sl_count; i++) { + if (ipv6_addr_equal(&psl->sl_addr[i], source)) + goto done; /* err = -EADDRNOTAVAIL */ + } + } - if (psl) - count += psl->sl_max; - newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), - GFP_KERNEL); - if (!newpsl) { - err = -ENOBUFS; - goto done; - } - newpsl->sl_max = count; - newpsl->sl_count = count - IP6_SFBLOCK; - if (psl) { - for (i = 0; i < psl->sl_count; i++) - newpsl->sl_addr[i] = psl->sl_addr[i]; - atomic_sub(struct_size(psl, sl_addr, psl->sl_max), - &sk->sk_omem_alloc); - } - rcu_assign_pointer(pmc->sflist, newpsl); - kfree_rcu(psl, rcu); - psl = newpsl; + i = psl ? psl->sl_count + 1 : 1; + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, i), + GFP_KERNEL); + if (!newpsl) { + err = -ENOBUFS; + goto done; } - rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) /* There is an error in the address. */ - goto done; + newpsl->sl_max = i; + newpsl->sl_count = i; + if (psl) { + for (j = 0; j < psl->sl_count; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; } - for (j = psl->sl_count-1; j >= i; j--) - psl->sl_addr[j+1] = psl->sl_addr[j]; - psl->sl_addr[i] = *source; - psl->sl_count++; - err = 0; + newpsl->sl_addr[i - 1] = *source; + /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); + + if (psl) + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); + err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); @@ -784,9 +801,11 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (!pmc) return; if (pmc_prev) - rcu_assign_pointer(pmc_prev->next, pmc->next); + rcu_assign_pointer(pmc_prev->next, + mc_dereference(pmc->next, idev)); else - rcu_assign_pointer(idev->mc_tomb, pmc->next); + rcu_assign_pointer(idev->mc_tomb, + mc_dereference(pmc->next, idev)); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { @@ -966,7 +985,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev, return -ENOMEM; } - rcu_assign_pointer(mc->next, idev->mc_list); + rcu_assign_pointer(mc->next, mc_dereference(idev->mc_list, idev)); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); @@ -1000,7 +1019,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) WRITE_ONCE(ma->mca_users, new_users); if (new_users == 0) { - *map = ma->next; + rcu_assign_pointer(*map, + mc_dereference(ma->next, idev)); igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, @@ -2351,14 +2371,18 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { - psf->sf_crcount = idev->mc_qrv; - rcu_assign_pointer(psf->sf_next, - mc_dereference(pmc->mca_tomb, idev)); - rcu_assign_pointer(pmc->mca_tomb, psf); - rv = 1; - } else { - kfree_rcu(psf, rcu); + struct ip6_sf_list *dpsf = kmalloc_obj(*dpsf); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = idev->mc_qrv; + rcu_assign_pointer(dpsf->sf_next, + mc_dereference(pmc->mca_tomb, idev)); + rcu_assign_pointer(pmc->mca_tomb, dpsf); + rv = 1; + } } + kfree_rcu(psf, rcu); } return rv; } @@ -2621,7 +2645,7 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) static void igmp6_join_group(struct ifmcaddr6 *ma) { - unsigned long delay; + unsigned long delay, interval; mc_assert_locked(ma->idev); @@ -2630,13 +2654,17 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); + interval = unsolicited_report_interval(ma->idev); + delay = interval; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } + if (delay >= interval) + delay = get_random_u32_below(interval); + if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); WRITE_ONCE(ma->mca_flags, ma->mca_flags | @@ -3001,7 +3029,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); unsigned int mca_flags = READ_ONCE(im->mca_flags); - unsigned long expires = READ_ONCE(im->mca_work.timer.expires); + long delta = READ_ONCE(im->mca_work.timer.expires) - jiffies; seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", @@ -3009,7 +3037,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) &im->mca_addr, READ_ONCE(im->mca_users), mca_flags, (mca_flags & MAF_TIMER_RUNNING) ? - jiffies_to_clock_t(expires - jiffies) : 0); + jiffies_delta_to_clock_t(delta) : 0); return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6a40c5074543..9658939511e0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3255,7 +3255,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + ip6_redirect(skb, sock_net(sk), skb->dev->ifindex, READ_ONCE(sk->sk_mark), sk_uid(sk)); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index f2a659cd6183..eec3778855eb 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -26,7 +26,18 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -36,7 +47,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fd875908ac0c..93478d1ad576 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -690,6 +690,17 @@ static struct sock *__udp6_lib_err_encap(struct net *net, return sk; } +static void udpv6_err_update_exception(struct net *net, struct sk_buff *skb, + u8 type, __be32 info) +{ + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); +} + static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -703,6 +714,8 @@ static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int harderr; int err; + udpv6_err_update_exception(net, skb, type, info); + daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; saddr = &hdr->saddr; sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 4e5cc9da6e06..db261ecd19af 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -210,12 +210,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, phs_hdr->flags = flags; if (flags == AF_IUCV_FLAG_SYN) phs_hdr->window = iucv->msglimit; - else if ((flags == AF_IUCV_FLAG_WIN) || !flags) { - confirm_recv = atomic_read(&iucv->msg_recv); - phs_hdr->window = confirm_recv; - if (confirm_recv) - phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; - } memcpy(phs_hdr->destUserID, iucv->dst_user_id, 8); memcpy(phs_hdr->destAppName, iucv->dst_name, 8); memcpy(phs_hdr->srcUserID, iucv->src_user_id, 8); @@ -250,13 +244,22 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); + /* Claim the receive credit here, not while building the header: every + * way this frame can be dropped has now been ruled out, so the window + * is zeroed only for as long as the transmit itself takes. + */ + if (flags == AF_IUCV_FLAG_WIN || !flags) { + confirm_recv = atomic_xchg(&iucv->msg_recv, 0); + phs_hdr->window = confirm_recv; + if (confirm_recv) + phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; + } + atomic_inc(&iucv->skbs_in_xmit); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { atomic_dec(&iucv->skbs_in_xmit); - } else { - atomic_sub(confirm_recv, &iucv->msg_recv); - WARN_ON(atomic_read(&iucv->msg_recv) < 0); + atomic_add(confirm_recv, &iucv->msg_recv); } return net_xmit_eval(err); @@ -1241,6 +1244,7 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, struct iucv_sock *iucv = iucv_sk(sk); unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; + bool send_win = false; int err = 0; u32 offset; @@ -1331,16 +1335,20 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, if (skb_queue_empty(&iucv->backlog_skb_q)) { if (!list_empty(&iucv->message_q.list)) iucv_process_message_q(sk); - if (atomic_read(&iucv->msg_recv) >= - iucv->msglimit / 2) { - err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); - if (err) { - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); - } - } + if (iucv->transport == AF_IUCV_TRANS_HIPER && + atomic_read(&iucv->msg_recv) >= + iucv->msglimit / 2) + send_win = true; } spin_unlock_bh(&iucv->message_q.lock); + + if (send_win) { + err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); + if (err) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } + } } done: diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 8f2bff268392..c53aa293a222 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -76,7 +76,12 @@ struct ieee802154_local { struct work_struct rx_mac_cmd_work; /* Association */ - struct ieee802154_pan_device *assoc_dev; + /* assoc_lock protects assoc_dev_extended_addr, assoc_addr, + * assoc_status, the assoc_done reinit/complete pairing and the + * IEEE802154_IS_ASSOCIATING bit in @ongoing. + */ + spinlock_t assoc_lock; + __le64 assoc_dev_extended_addr; struct completion assoc_done; __le16 assoc_addr; u8 assoc_status; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index ea1efef3572a..63e89bd586e3 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -104,6 +104,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker); init_completion(&local->assoc_done); + spin_lock_init(&local->assoc_lock); /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 005338f89b75..dd156c01ac49 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -536,7 +536,9 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, struct ieee802154_association_req_frame frame = {}; struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; + __le16 resp_short_addr; struct sk_buff *skb; + u8 resp_status; int ret; frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD; @@ -578,9 +580,11 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, return ret; } - local->assoc_dev = coord; + spin_lock(&local->assoc_lock); reinit_completion(&local->assoc_done); + local->assoc_dev_extended_addr = coord->extended_addr; set_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + spin_unlock(&local->assoc_lock); ret = ieee802154_mlme_tx_one_locked(local, sdata, skb); if (ret) { @@ -599,25 +603,37 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, goto clear_assoc; } - if (local->assoc_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { - if (local->assoc_status == IEEE802154_PAN_AT_CAPACITY) + /* The association is complete: mac802154_process_association_resp() + * cleared the associating bit before waking us, so a second (e.g. + * malicious) ASSOC RESP can no longer pass the recheck and overwrite + * the result. Snapshot assoc_status/assoc_addr under the lock. + */ + spin_lock(&local->assoc_lock); + resp_status = local->assoc_status; + resp_short_addr = local->assoc_addr; + spin_unlock(&local->assoc_lock); + + if (resp_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { + if (resp_status == IEEE802154_PAN_AT_CAPACITY) ret = -ERANGE; else ret = -EPERM; dev_warn(&sdata->dev->dev, "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr, - local->assoc_status == IEEE802154_PAN_AT_CAPACITY ? + resp_status == IEEE802154_PAN_AT_CAPACITY ? "PAN at capacity" : "access denied"); - goto clear_assoc; + return ret; } - ret = 0; - *short_addr = local->assoc_addr; + *short_addr = resp_short_addr; + + return 0; clear_assoc: + spin_lock(&local->assoc_lock); clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); - local->assoc_dev = NULL; + spin_unlock(&local->assoc_lock); return ret; } @@ -639,19 +655,28 @@ int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata, dest->mode != IEEE802154_EXTENDED_ADDRESSING)) return -EINVAL; - if (unlikely(dest->extended_addr != wpan_dev->extended_addr || - src->extended_addr != local->assoc_dev->extended_addr)) + spin_lock(&local->assoc_lock); + if (unlikely(!test_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing) || + dest->extended_addr != wpan_dev->extended_addr || + src->extended_addr != local->assoc_dev_extended_addr)) { + spin_unlock(&local->assoc_lock); return -ENODEV; + } memcpy(&resp_pl, skb->data, sizeof(resp_pl)); local->assoc_addr = resp_pl.short_addr; local->assoc_status = resp_pl.status; + /* Clear the associating bit before waking the waiter: once the result + * is saved, any subsequent (e.g. malicious) ASSOC RESP must fail the + * test_bit() recheck above and can no longer overwrite the result. + */ + clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + complete(&local->assoc_done); + spin_unlock(&local->assoc_lock); dev_dbg(&skb->dev->dev, "ASSOC RESP 0x%x received from %8phC, getting short address %04x\n", - local->assoc_status, &deaddr, local->assoc_addr); - - complete(&local->assoc_done); + resp_pl.status, &deaddr, resp_pl.short_addr); return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b474d03620a7..e1f08f71cdb1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3109,8 +3109,7 @@ static void mptcp_do_fastclose(struct sock *sk) */ inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_send_active_reset(ssk, ssk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(ssk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); unlock: release_sock(ssk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 06a107d4e839..87ccb84e9927 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -690,7 +690,7 @@ mptcp_send_active_reset_reason(struct sock *sk) enum sk_rst_reason reason; reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); - tcp_send_active_reset(sk, GFP_ATOMIC, reason); + tcp_send_active_reset(sk, reason); } /* Made the fwd mem carried by the given skb available to the msk, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 331f78689075..6974b57056e7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2675,7 +2675,8 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; - int tp_len, off; + u32 tp_len; + int off; ph.raw = frame; @@ -2695,7 +2696,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, break; } if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + pr_err("packet size is too long (%u > %d)\n", tp_len, size_max); return -EMSGSIZE; } diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index a30fa56e6aa3..78347c937af7 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -9,6 +9,7 @@ #include /* For TIOCINQ/OUTQ */ #include #include +#include #include @@ -120,8 +121,10 @@ static DEFINE_XARRAY_ALLOC(qrtr_ports); * @nid: node id * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port * @qrtr_tx_lock: lock for qrtr_tx_flow inserts + * @hello_sent: hello packet send successful * @rx_queue: receive queue * @item: list item for broadcast list + * @say_hello: delayed work for sending hello packet */ struct qrtr_node { struct mutex ep_lock; @@ -132,8 +135,11 @@ struct qrtr_node { struct xarray qrtr_tx_flow; struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ + bool hello_sent; + struct sk_buff_head rx_queue; struct list_head item; + struct delayed_work say_hello; }; /** @@ -187,6 +193,8 @@ static void __qrtr_node_release(struct kref *kref) list_del(&node->item); mutex_unlock(&qrtr_node_lock); + cancel_delayed_work_sync(&node->say_hello); + skb_queue_purge(&node->rx_queue); /* Free tx flow counters */ @@ -341,6 +349,14 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, size_t len = skb->len; int rc, confirm_rx; + mutex_lock(&node->ep_lock); + if (!node->hello_sent && type != QRTR_TYPE_HELLO) { + mutex_unlock(&node->ep_lock); + kfree_skb(skb); + return -EAGAIN; + } + mutex_unlock(&node->ep_lock); + confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { kfree_skb(skb); @@ -353,7 +369,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); if (to->sq_port == QRTR_PORT_CTRL) { - hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_node_id = cpu_to_le32(READ_ONCE(node->nid)); hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); } else { hdr->dst_node_id = cpu_to_le32(to->sq_node); @@ -372,6 +388,8 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, rc = node->ep->xmit(node->ep, skb); else kfree_skb(skb); + if (!rc && type == QRTR_TYPE_HELLO) + node->hello_sent = true; mutex_unlock(&node->ep_lock); } /* Need to ensure that a subsequent message carries the otherwise lost @@ -379,6 +397,9 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, if (rc && confirm_rx) qrtr_tx_flow_failed(node, to->sq_node, to->sq_port); + if (rc == -EAGAIN && type == QRTR_TYPE_HELLO) + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return rc; } @@ -416,7 +437,7 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) spin_lock_irqsave(&qrtr_nodes_lock, flags); radix_tree_insert(&qrtr_nodes, nid, node); if (node->nid == QRTR_EP_NID_AUTO) - node->nid = nid; + WRITE_ONCE(node->nid, nid); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); } @@ -570,6 +591,38 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt, return skb; } +static void qrtr_hello_work(struct work_struct *work) +{ + struct sockaddr_qrtr from = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct sockaddr_qrtr to = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; + struct qrtr_node *node; + struct qrtr_sock *ctrl; + struct sk_buff *skb; + + node = container_of(to_delayed_work(work), struct qrtr_node, say_hello); + + /* NS must be bound before we can send; retry with backoff if not ready */ + ctrl = qrtr_port_lookup(QRTR_PORT_CTRL); + if (!ctrl) { + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL); + if (!skb) { + qrtr_port_put(ctrl); + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + pkt->cmd = cpu_to_le32(QRTR_TYPE_HELLO); + from.sq_node = qrtr_local_nid; + to.sq_node = node->nid; + qrtr_node_enqueue(node, skb, QRTR_TYPE_HELLO, &from, &to); + qrtr_port_put(ctrl); +} + /** * qrtr_endpoint_register() - register a new endpoint * @ep: endpoint to register @@ -595,6 +648,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) node->nid = QRTR_EP_NID_AUTO; node->ep = ep; + node->hello_sent = false; + INIT_DELAYED_WORK(&node->say_hello, qrtr_hello_work); + xa_init(&node->qrtr_tx_flow); mutex_init(&node->qrtr_tx_lock); @@ -605,6 +661,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) mutex_unlock(&qrtr_node_lock); ep->node = node; + /* Initiate HELLO handshake from the core layer */ + schedule_delayed_work(&node->say_hello, 0); + return 0; } EXPORT_SYMBOL_GPL(qrtr_endpoint_register); @@ -879,6 +938,9 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, mutex_lock(&qrtr_node_lock); list_for_each_entry(node, &qrtr_all_nodes, item) { + /* Skip nodes with no assigned node ID yet. */ + if (READ_ONCE(node->nid) == QRTR_EP_NID_AUTO) + continue; skbn = pskb_copy(skb, GFP_KERNEL); if (!skbn) break; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index c5e7e01db249..bcb090ee79d4 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -212,6 +212,7 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, pr_err("failed to send lookup notification\n"); } +/* Announce the list of servers registered on the local node */ static int announce_servers(struct sockaddr_qrtr *sq) { struct qrtr_server *srv; @@ -326,38 +327,8 @@ static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) return 0; } -static int say_hello(struct sockaddr_qrtr *dest) -{ - struct qrtr_ctrl_pkt pkt; - struct msghdr msg = { }; - struct kvec iv; - int ret; - - iv.iov_base = &pkt; - iv.iov_len = sizeof(pkt); - - memset(&pkt, 0, sizeof(pkt)); - pkt.cmd = cpu_to_le32(QRTR_TYPE_HELLO); - - msg.msg_name = (struct sockaddr *)dest; - msg.msg_namelen = sizeof(*dest); - - ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) - pr_err("failed to send hello msg\n"); - - return ret; -} - -/* Announce the list of servers registered on the local node */ static int ctrl_cmd_hello(struct sockaddr_qrtr *sq) { - int ret; - - ret = say_hello(sq); - if (ret < 0) - return ret; - return announce_servers(sq); } @@ -774,10 +745,6 @@ int qrtr_ns_init(void) qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; - ret = say_hello(&qrtr_ns.bcast_sq); - if (ret < 0) - goto err_wq; - /* As the qrtr ns socket owner and creator is the same module, we have * to decrease the qrtr module reference count to guarantee that it * remains zero after the ns socket is created, otherwise, executing diff --git a/net/rds/connection.c b/net/rds/connection.c index 7c8ab8e973e1..b6c4beb50eaf 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -106,10 +106,12 @@ static struct rds_connection *rds_conn_lookup(struct net *net, } /* - * This is called by transports as they're bringing down a connection. - * It clears partial message state so that the transport can start sending - * and receiving over this connection again in the future. It is up to - * the transport to have serialized this call with its send and recv. + * This is called by rds_conn_shutdown() once the transport has brought + * a path down. It clears partial message state so that the transport + * can start sending and receiving over this path again in the future. + * The caller owns RDS_IN_XMIT and RDS_RECV_REFILL across this call, + * which is what serializes it against the send and receive-refill + * paths. */ static void rds_conn_path_reset(struct rds_conn_path *cp) { @@ -120,7 +122,16 @@ static void rds_conn_path_reset(struct rds_conn_path *cp) rds_stats_inc(s_conn_reset); rds_send_path_reset(cp); - cp->cp_flags = 0; + + /* Clear the bits the reset is responsible for individually: a + * blanket cp_flags = 0 is a plain store that can clobber a + * concurrent atomic read-modify-write on the same word. + * RDS_IN_XMIT and RDS_RECV_REFILL are held as locks by the + * caller, rds_conn_shutdown(), which releases them once the + * teardown is complete. + */ + clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); /* Do not clear next_rx_seq here, else we cannot distinguish * retransmitted packets from new packets, and will hand all @@ -406,28 +417,70 @@ void rds_conn_shutdown(struct rds_conn_path *cp) } mutex_unlock(&cp->cp_cm_lock); + /* Quiesce the transmit and receive-refill paths by + * acquiring their bit locks, not merely waiting for + * them to be released: with a plain wait, either path + * can re-take its lock the instant after we sample it + * clear and then run concurrently with the transport + * shutdown and the path reset below. Holding both + * locks across the teardown makes that structurally + * impossible. + */ wait_event(cp->cp_waitq, - !test_bit(RDS_IN_XMIT, &cp->cp_flags)); + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); wait_event(cp->cp_waitq, - !test_bit(RDS_RECV_REFILL, &cp->cp_flags)); + !test_and_set_bit(RDS_RECV_REFILL, &cp->cp_flags)); conn->c_trans->conn_path_shutdown(cp); rds_conn_path_reset(cp); + /* Release the two locks and wake any waiter (e.g. + * rds_tcp_reset_callbacks()) that blocked on them while + * we held them. The unlock orders the transport's ring + * re-initialization and the path reset above before + * either bit is seen clear. rds_conn_path_reset() leaves + * both bits alone: ownership ends here, not inside the + * reset. + */ + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + clear_bit_unlock(RDS_RECV_REFILL, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); + if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, - RDS_CONN_DOWN) && - !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { - /* This can happen - eg when we're in the middle of tearing - * down the connection, and someone unloads the rds module. - * Quite reproducible with loopback connections. - * Mostly harmless. + /* The path was dropped again while we tore it + * down: by a socket state-change callback in + * irq context on receipt of a FIN, or by an + * accept that claimed the path just before a + * drop put it back to RDS_CONN_ERROR and then + * installed a fresh socket on it. Unless a + * pending destroy suppressed it, the drop also + * queued another shutdown pass, and that pass + * must run, because it is what tears down + * whatever attached to the path after the + * transport shutdown above sampled its state. + * Consuming the RDS_CONN_ERROR here would turn + * that pass into a no-op: leave the state + * alone, and let the pass finish the job. * - * Note that this also happens with rds-tcp because - * we could have triggered rds_conn_path_drop in irq - * mode from rds_tcp_state change on the receipt of - * a FIN, thus we need to recheck for RDS_CONN_ERROR - * here. + * Quiesce the reconnect timer before bailing + * out, though. When a pending destroy did + * suppress the queue, no later pass runs, and + * rds_conn_path_destroy() is about to flush + * cp_down_w and free the path: it must not + * find cp_conn_w still armed. A successor + * pass, when there is one, re-arms the + * reconnect from its own tail. + */ + cancel_delayed_work_sync(&cp->cp_conn_w); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); + + if (rds_conn_path_state(cp) == RDS_CONN_ERROR) + return; + /* No current cp_state writer leaves a + * DISCONNECTING path in any state but + * RDS_CONN_ERROR; report loudly if one ever + * does. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 357128d34a54..bd6cb3ffaa57 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -363,15 +363,14 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { - clear_bit(RDS_RECV_REFILL, &conn->c_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_RECV_REFILL, &conn->c_flags); /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ - if (waitqueue_active(&conn->c_waitq)) + if (wq_has_sleeper(&conn->c_waitq)) wake_up_all(&conn->c_waitq); } @@ -392,7 +391,9 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) /* the goal here is to just make sure that someone, somewhere * is posting buffers. If we can't get the refill lock, - * let them do their thing + * let them do their thing. The holder may also be + * rds_conn_shutdown() tearing the path down, in which case + * there is nothing to post. */ if (!acquire_refill(conn)) return; diff --git a/net/rds/send.c b/net/rds/send.c index 15a1b97f13e7..1afa981e5c06 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -114,8 +114,13 @@ static void release_in_xmit(struct rds_conn_path *cp) * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. + * + * wq_has_sleeper() supplies the full barrier that orders the wait + * queue read after the bit clear; clear_bit_unlock() alone is only + * a release and would let this check read a stale empty queue, + * losing the wake-up. */ - if (waitqueue_active(&cp->cp_waitq)) + if (wq_has_sleeper(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } @@ -239,8 +244,11 @@ int rds_send_xmit(struct rds_conn_path *cp) WRITE_ONCE(cp->cp_send_gen, send_gen); /* - * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, - * we do the opposite to avoid races. + * rds_conn_shutdown() sets the conn state and then acquires + * RDS_IN_XMIT; we take the lock first and then check the state. + * Ownership is decided by the atomic RMW on the cp_flags word: + * if the teardown won the bit we back off here, and if we won + * it the teardown waits until we release it. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b263634ac750..774a71f88d37 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -115,46 +115,90 @@ void rds_tcp_restore_callbacks(struct socket *sock, } /* - * rds_tcp_reset_callbacks() switches the to the new sock and - * returns the existing tc->t_sock. + * rds_tcp_reset_callbacks() switches a path to a new socket and + * releases the old one it finds in tc->t_sock, resolving a duelling + * SYN. * - * The only functions that set tc->t_sock are rds_tcp_set_callbacks - * and rds_tcp_reset_callbacks. Send and receive trust that - * it is set. The absence of RDS_CONN_UP bit protects those paths - * from being called while it isn't set. + * tc->t_sock is set by rds_tcp_set_callbacks() and cleared by + * rds_tcp_restore_callbacks(). Four paths write it: the active + * connect in rds_tcp_conn_path_connect(), which sets it and clears it + * again on failure; the accept path in rds_tcp_accept_one(), which + * sets it for a path with no socket yet; the teardown in + * rds_tcp_conn_path_shutdown(), which clears it; and the swap done + * here, which does both. The connect and accept paths are serialized + * against each other by t_conn_path_lock. Send and receive trust + * that it is set: the absence of RDS_CONN_UP protects those paths + * from being called while it isn't, and the swap done here runs under + * RDS_IN_XMIT so that it cannot interleave with a sender already + * inside rds_send_xmit(). */ void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp) { struct rds_tcp_connection *tc = cp->cp_transport_data; - struct socket *osock = tc->t_sock; - - if (!osock) - goto newsock; + struct socket *osock; /* Need to resolve a duelling SYN between peers. * We have an outstanding SYN to this peer, which may * potentially have transitioned to the RDS_CONN_UP state, * so we must quiesce any send threads before resetting - * cp_transport_data. We quiesce these threads by setting - * cp_state to something other than RDS_CONN_UP, and then - * waiting for any existing threads in rds_send_xmit to - * complete release_in_xmit(). (Subsequent threads entering - * rds_send_xmit() will bail on !rds_conn_up(). + * cp_transport_data. Setting cp_state to something other + * than RDS_CONN_UP stops new senders, and owning RDS_IN_XMIT + * excludes any thread already inside rds_send_xmit() - or a + * teardown in rds_conn_shutdown(), which holds the same lock + * for the duration of the transport shutdown - for the whole + * socket swap and the rds_send_path_reset() below. * - * However an incoming syn-ack at this point would end up - * marking the conn as RDS_CONN_UP, and would again permit - * rds_send_xmi() threads through, so ideally we would - * synchronize on RDS_CONN_UP after lock_sock(), but cannot - * do that: waiting on !RDS_IN_XMIT after lock_sock() may - * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT - * would not get set. As a result, we set c_state to - * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change - * cannot mark rds_conn_path_up() in the window before lock_sock() + * An incoming syn-ack at this point would end up marking the + * conn as RDS_CONN_UP, and would again permit rds_send_xmit() + * threads through, so ideally we would synchronize on + * RDS_CONN_UP after lock_sock(), but cannot do that: acquiring + * RDS_IN_XMIT after lock_sock() may end up deadlocking with + * tcp_sendmsg(), which takes the socket lock while holding + * RDS_IN_XMIT. As a result, we set c_state to + * RDS_CONN_RESETTING, to ensure that rds_tcp_state_change + * cannot mark rds_conn_path_up() in the window before + * lock_sock(). + * + * Only make that transition if the path is still connecting + * (or already resetting from an earlier duel). A path in any + * other state - typically RDS_CONN_DISCONNECTING or + * RDS_CONN_ERROR with a shutdown in flight - is dropped + * instead. That still replaces its state, with RDS_CONN_ERROR, + * and, unless a pending destroy is about to reap the whole + * connection anyway, queues one more shutdown pass. A shutdown + * already in flight leaves that RDS_CONN_ERROR alone when it + * finishes; the queued pass then completes the transition to + * RDS_CONN_DOWN and tears down anything that attached to the + * path in the meantime. + */ + if (!rds_conn_path_transition(cp, RDS_CONN_CONNECTING, + RDS_CONN_RESETTING) && + !rds_conn_path_transition(cp, RDS_CONN_RESETTING, + RDS_CONN_RESETTING)) + rds_conn_path_drop(cp, 0); + wait_event(cp->cp_waitq, + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); + + /* Read t_sock only while owning RDS_IN_XMIT, never before the + * wait: the teardown in rds_conn_shutdown() releases the old + * socket and clears t_sock, so a pointer sampled earlier can + * be stale by the time we wake up. The teardown holds the + * same lock while it does so, so what we read here cannot + * change under us until we release it. + */ + osock = tc->t_sock; + if (!osock) + goto newsock; + + /* reset receive side state for rds_tcp_data_recv() for osock. + * + * The sync cancels while owning RDS_IN_XMIT rely on cp_wq + * being ordered: a teardown blocked on the bit occupies + * cp_wq's only execution slot, so cp_send_w and cp_recv_w are + * pending at most and the cancels never flush. Nothing here + * may flush or wait on cp_wq itself. */ - atomic_set(&cp->cp_state, RDS_CONN_RESETTING); - wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); - /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); lock_sock(osock->sk); @@ -172,6 +216,9 @@ void rds_tcp_reset_callbacks(struct socket *sock, lock_sock(sock->sk); rds_tcp_set_callbacks(sock, cp); release_sock(sock->sk); + + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); } /* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index a3db9b057084..13fa60c1985b 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -295,7 +295,11 @@ int rds_tcp_accept_one(struct rds_tcp_net *rtn) if (rs_tcp->t_sock) { /* Duelling SYN has been handled in rds_tcp_accept_one() */ rds_tcp_reset_callbacks(new_sock, cp); - /* rds_connect_path_complete() marks RDS_CONN_UP */ + /* rds_connect_path_complete() marks RDS_CONN_UP, or, + * if a concurrent shutdown won the duel, drops the + * path again and the pass that drop queues reaps the + * socket installed above. + */ rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b4415d358c91..37eced84dfa5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -443,12 +443,21 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + /* TCA_ACT_USED_HW_STATS */ + + nla_total_size(sizeof(struct nla_bitfield32)) + + nla_total_size(sizeof(u32)) /* TCA_ACT_IN_HW_COUNT */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) - /* TCA_STATS_PKT64 */ - + nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_BASIC_HW */ + + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64, emitted by both of the basic copies above */ + + 2 * nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_RATE_EST */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est)) + /* TCA_STATS_RATE_EST64 */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ @@ -1688,12 +1697,12 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct tc_action *actions[], int event, + struct tc_action *actions[], size_t attr_size, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, @@ -1858,11 +1867,13 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, struct tc_action *action) { - size_t attr_size = tcf_action_fill_size(action); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; struct sk_buff *skb; + size_t attr_size; + + attr_size = tcf_action_full_attrs_size(tcf_action_fill_size(action)); skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) @@ -1879,15 +1890,18 @@ static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) { const struct tc_action_ops *ops = action->ops; - struct sk_buff *skb; + struct sk_buff *skb = NULL; int ret; - if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { - skb = NULL; - } else { + if (rtnl_notify_needed(net, 0, RTNLGRP_TC)) { skb = tcf_reoffload_del_notify_msg(net, action); + /* The action has already lost its hardware instance and is + * skip_sw, so it must be released whether or not the + * notification can be built. Drop the notification rather + * than leave an action behind that processes no packets. + */ if (IS_ERR(skb)) - return PTR_ERR(skb); + skb = NULL; } ret = tcf_idr_release_unsafe(action); @@ -2044,7 +2058,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, attr_size = tcf_action_full_attrs_size(attr_size); if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, actions, event, extack); + ret = tcf_get_notify(net, portid, n, actions, attr_size, event, + extack); else { /* delete */ ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0e275b58151c..1cefea571efd 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1703,6 +1703,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + + if (msk_depth && !nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "A mask attribute is invalid"); + return -EINVAL; + } } return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac6d0fa5a40e..a3e65c8cf29e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -370,6 +370,10 @@ static int u32_init(struct tcf_proto *tp) refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); + if (root_ht->handle == 0) { + kfree(root_ht); + return -ENOMEM; + } root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); @@ -695,21 +699,33 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, return ret; } -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid, int *err) { u32 index = htid | 0x800; u32 max = htid | 0xFFF; + *err = 0; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { index = htid + 1; - if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, - GFP_KERNEL)) - index = max; + *err = idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL); + if (*err) + return 0; } return index; } +static int u32_kid_extack(int err, struct netlink_ext_ack *extack) +{ + if (err == -ENOSPC) + NL_SET_ERR_MSG_MOD(extack, "Hash table node ID pool exhausted"); + else + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate node ID"); + return err; +} + static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_CLASSID] = { .type = NLA_U32 }, [TCA_U32_HASH] = { .type = NLA_U32 }, @@ -1079,7 +1095,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, * handle which is used to uniquely identify the match entry. */ if (!TC_U32_NODE(handle)) { - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } else { handle = htid | TC_U32_NODE(handle); err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, @@ -1091,7 +1109,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, /* The user did not give us a handle; lets just generate one * from the table's pool of nodeids. */ - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } if (tb[TCA_U32_SEL] == NULL) { diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5f988b3a8814..d666cec6b194 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -212,8 +212,10 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - - if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { + if (unlikely(ntohs(ch->length) < sizeof(*ch))) { + chunk->pdiscard = 1; + } else if (chunk->chunk_end + sizeof(*ch) <= + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 236e25abc7a4..84a4c97d0f75 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3215,6 +3215,9 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, *errp = param.p; switch (param.p->type) { case SCTP_PARAM_ERR_CAUSE: + if (length < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_errhdr)) + return false; break; case SCTP_PARAM_IPV4_ADDRESS: if (length != sizeof(struct sctp_ipv4addr_param)) @@ -3448,20 +3451,15 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, case SCTP_PARAM_ERR_CAUSE: length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; - if (asconf_ack_len > 0) - return err_param->cause; - else - return SCTP_ERROR_INV_PARAM; - break; + return err_param->cause; default: return SCTP_ERROR_INV_PARAM; } } length = ntohs(asconf_ack_param->param_hdr.length); - asconf_ack_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; + asconf_ack_param = (void *)asconf_ack_param + SCTP_PAD4(length); + asconf_ack_len -= SCTP_PAD4(length); } return err_code; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 94716406d602..0d99b7e8c082 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1545,17 +1545,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); - /* - * SCTP has a hard time with timer starts. Because we process - * timer starts as side effects, it can be hard to tell if we - * have already started a timer or not, which leads to BUG - * halts when we call add_timer. So here, instead of just starting - * a timer, if the timer is already started, and just mod - * the timer with the shorter of the two expiration times - */ - if (!timer_pending(timer)) + if (!timer_reduce(timer, jiffies + timeout)) sctp_association_hold(asoc); - timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: diff --git a/net/tipc/link.c b/net/tipc/link.c index 49dfc098d89b..6427c69f8929 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -504,7 +504,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); - strcpy(l->if_name, if_name); + strscpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; @@ -574,7 +574,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { - strcpy(l->name, tipc_bclink_name); + strscpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); @@ -1898,7 +1898,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); - strcpy(data, l->if_name); + memcpy(data, l->if_name, TIPC_MAX_IF_NAME); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 253c72d1366e..6fda36ab1766 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -763,21 +763,40 @@ struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); + u32 max_user_pub = TIPC_MAX_PUBL - 1; struct tipc_net *tn = tipc_net(net); struct publication *p = NULL; struct sk_buff *skb = NULL; + bool protocol_type = false; u32 rc_dests; - spin_lock_bh(&tn->nametbl_lock); + if (ua->sr.type == TIPC_NODE_STATE || ua->sr.type == TIPC_LINK_STATE || + ua->sr.type == TIPC_TOP_SRV) + protocol_type = true; - if (nt->local_publ_count >= TIPC_MAX_PUBL) { - pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); + spin_lock_bh(&tn->nametbl_lock); + if (protocol_type) + goto insert; + + /* Reserve one entry for node state service type because it has cluster + * scope and it is distributed in bulk. So, the maximum number of user's + * publications is (TIPC_MAX_PUBL - 1). + */ + if (nt->local_publ_count >= max_user_pub) { + pr_warn("Bind failed, max limit %u reached\n", max_user_pub); goto exit; } +insert: p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { - nt->local_publ_count++; + /* Not count node state, link state and topology server types + * so that maximum nt->local_publ_count does not prevent + * protocol service types from being inserted into the name + * table. + */ + if (!protocol_type) + nt->local_publ_count++; skb = tipc_named_publish(net, p); } rc_dests = nt->rc_dests; @@ -810,7 +829,10 @@ void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { - nt->local_publ_count--; + if (p->sr.type != TIPC_NODE_STATE && + p->sr.type != TIPC_LINK_STATE && + p->sr.type != TIPC_TOP_SRV) + nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); diff --git a/net/tipc/node.c b/net/tipc/node.c index 683a136e53ef..bd91378b7540 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1333,7 +1333,9 @@ static void tipc_node_reset_links(struct tipc_node *n) pr_warn("Resetting all links to %x\n", n->addr); + tipc_node_write_lock(n); trace_tipc_node_reset_links(n, true, " "); + tipc_node_write_unlock_fast(n); for (i = 0; i < MAX_BEARERS; i++) { tipc_node_link_down(n, i, false); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a33b2a2d381d..f840498b58af 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,6 +438,38 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); +/** + * vsock_check_source - validate a packet source against a socket peer + * @vsk: socket receiving the packet + * @transport: transport receiving the packet + * @src: source address from the packet + * + * Return: true if the packet arrived on the socket's assigned transport and + * its source matches the stored peer. Loopback packets are generated + * internally and always use the local CID as their source, including + * connections using a valid CID alias. + * + * The caller must hold the socket lock and must not call this for listening + * sockets, which accept packets from any source and have no assigned + * transport. + */ +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src) +{ + if (vsk->transport != transport) + return false; + + if (src->svm_port != vsk->remote_addr.svm_port) + return false; + + if (src->svm_cid == vsk->remote_addr.svm_cid) + return true; + + return transport->get_local_cid() == VMADDR_CID_LOCAL; +} +EXPORT_SYMBOL_GPL(vsock_check_source); + void vsock_remove_sock(struct vsock_sock *vsk) { /* Transport reassignment must not remove the binding. */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 88df82364f77..f225f53ed4ba 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1836,7 +1836,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, * lock_sock (note: listener sockets are not assigned to any transport) */ if (sock_flag(sk, SOCK_DONE) || - (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { + (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &t->transport, &src))) { (void)virtio_transport_reset_no_sock(t, skb, net); release_sock(sk); sock_put(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1c4ee039c166..1f186e8f8364 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -680,11 +680,13 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) struct vmci_transport_packet *pkt; struct vsock_sock *vsk; bool bh_process_pkt; + bool drop_pkt; int err; sk = NULL; err = VMCI_SUCCESS; bh_process_pkt = false; + drop_pkt = false; /* Ignore incoming packets from resources that aren't vsock * implementations. @@ -765,17 +767,29 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - /* The local context ID may be out of date, update it. */ - vsk->local_addr.svm_cid = dst.svm_cid; + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &vmci_transport, &src)) { + drop_pkt = true; + err = VMCI_ERROR_NO_ACCESS; + } else { + /* The local context ID may be out of date, update it. */ + vsk->local_addr.svm_cid = dst.svm_cid; - if (sk->sk_state == TCP_ESTABLISHED) - vmci_trans(vsk)->notify_ops->handle_notify_pkt( - sk, pkt, true, &dst, &src, - &bh_process_pkt); + if (sk->sk_state == TCP_ESTABLISHED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt(sk, pkt, true, + &dst, &src, + &bh_process_pkt); + } } bh_unlock_sock(sk); + if (drop_pkt) { + if (vmci_transport_send_reset_bh(&dst, &src, pkt) < 0) + pr_err("unable to send reset\n"); + goto out; + } + if (!bh_process_pkt) { struct vmci_transport_recv_pkt_info *recv_pkt_info; @@ -900,6 +914,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) { struct vmci_transport_recv_pkt_info *recv_pkt_info; struct vmci_transport_packet *pkt; + struct sockaddr_vm src; struct sock *sk; recv_pkt_info = @@ -908,6 +923,12 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) pkt = &recv_pkt_info->pkt; lock_sock(sk); + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsock_sk(sk), &vmci_transport, &src)) { + vmci_transport_reply_reset(pkt); + goto out; + } /* The local context ID may be out of date. */ vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; @@ -937,6 +958,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) break; } +out: release_sock(sk); kfree(recv_pkt_info); /* Release reference obtained in the stream callback when we fetched diff --git a/rust/Makefile b/rust/Makefile index 48adcd9b7851..da1a7409d984 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -354,7 +354,8 @@ rusttestlib-pin_init: $(src)/pin-init/src/lib.rs rusttestlib-macros \ rusttestlib-kernel: private rustc_target_flags = --extern ffi \ --extern build_error --extern macros --extern pin_init \ --extern bindings --extern uapi \ - --extern zerocopy=$(objtree)/$(obj)/test/libzerocopy.rlib --extern zerocopy_derive + --extern zerocopy=$(objtree)/$(obj)/test/libzerocopy.rlib \ + --extern zerocopy_derive=$(objtree)/$(obj)/test/$(libzerocopy_derive_name) rusttestlib-kernel: $(src)/kernel/lib.rs rusttestlib-bindings rusttestlib-uapi \ rusttestlib-build_error rusttestlib-pin_init $(obj)/$(libmacros_name) \ $(obj)/bindings.o rusttestlib-zerocopy rusttestlib-zerocopy_derive FORCE @@ -656,7 +657,8 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L -Zunstable-options \ $(if $(link_helper),;$(LLVM_LINK) --internalize --suppress-warnings $(patsubst %.o,%.bc,$@) \ $(obj)/helpers/helpers$(if $(part-of-module),_module).bc -o $(patsubst %.o,%.m.bc,$@); \ - $(CC) $(CLANG_FLAGS) $(KBUILD_CFLAGS) -Wno-override-module -c $(patsubst %.o,%.m.bc,$@) -o $@ \ + $(CC) $(CLANG_FLAGS) $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS)) \ + $(CC_FLAGS_RUST_INLINE_HELPERS) -Wno-override-module -c $(patsubst %.o,%.m.bc,$@) -o $@ \ $(cmd_ld_single)) \ $(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@) \ $(cmd_objtool) diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs index 4e974c768dbd..f54cedcb6fd5 100644 --- a/rust/kernel/jump_label.rs +++ b/rust/kernel/jump_label.rs @@ -44,6 +44,7 @@ macro_rules! static_branch_unlikely { #[macro_export] #[doc(hidden)] +#[cfg(not(testlib))] #[cfg(CONFIG_JUMP_LABEL)] macro_rules! arch_static_branch { ($key:path, $keytyp:ty, $field:ident, $branch:expr) => {'my_label: { @@ -61,6 +62,17 @@ macro_rules! arch_static_branch { }}; } +#[macro_export] +#[doc(hidden)] +#[cfg(testlib)] +#[cfg(CONFIG_JUMP_LABEL)] +macro_rules! arch_static_branch { + ($key:path, $keytyp:ty, $field:ident, $branch:expr) => { + // The asm falls through until patched, which never happens on the host. + false + }; +} + #[cfg(CONFIG_JUMP_LABEL)] pub use arch_static_branch; diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs index 406e3a028c55..0f367264ee2e 100644 --- a/rust/kernel/list.rs +++ b/rust/kernel/list.rs @@ -249,7 +249,7 @@ /// assert_eq!(list.iter().count(), 3); /// } /// -/// // Pop the items from the list using `pop_front()` and verify the content. +/// // Pop the items from the list using `pop_back()` and verify the content. /// { /// assert_eq!(list.pop_back().ok_or(EINVAL)?.value.foo(), ("a", 15)); /// assert_eq!(list.pop_back().ok_or(EINVAL)?.value.foo(), ("a", 32)); diff --git a/rust/kernel/num/bounded.rs b/rust/kernel/num/bounded.rs index d192610a687d..2a2b0a4bca5e 100644 --- a/rust/kernel/num/bounded.rs +++ b/rust/kernel/num/bounded.rs @@ -13,7 +13,10 @@ }; use kernel::{ - num::Integer, + num::{ + Integer, + Unsigned, // + }, prelude::*, // }; @@ -174,13 +177,16 @@ fn fits_within(value: T, num_bits: u32) -> bool { /// // `u8` (regardless of the passed value). /// // let _ = Bounded::::from(10u8); /// -/// // Booleans can be converted into single-bit `Bounded`s. +/// // Booleans can be converted into unsigned `Bounded`s. /// /// let v = Bounded::::from(false); /// assert_eq!(v.get(), 0); /// /// let v = Bounded::::from(true); /// assert_eq!(v.get(), 1); +/// +/// // This does not build because `i8` is signed. +/// // let _ = Bounded::::from(true); /// ``` /// /// Infallible conversions from a [`Bounded`] to a primitive integer are also supported, and @@ -203,12 +209,16 @@ fn fits_within(value: T, num_bits: u32) -> bool { /// let _v = Bounded::::new::<10>(); /// // assert_eq!(u8::from(_v), 10); /// -/// // Single-bit `Bounded`s can be converted into a boolean. +/// // Unsigned single-bit `Bounded`s can be converted into a boolean. /// let v = Bounded::::new::<1>(); /// assert_eq!(bool::from(v), true); /// /// let v = Bounded::::new::<0>(); /// assert_eq!(bool::from(v), false); +/// +/// // This does not build because `i8` is signed. +/// // let v = Bounded::::new::<-1>(); +/// // let _ = bool::from(v); /// ``` /// /// Fallible conversions from any primitive integer to any [`Bounded`] are also supported using the @@ -1109,31 +1119,33 @@ fn from(value: Bounded) -> $type { i8 i16 i32 i64 isize ); -// Single-bit `Bounded`s can be converted from/to a boolean. +// Unsigned single-bit `Bounded`s can be converted to a boolean. impl From> for bool where - T: Integer + Zeroable, + T: Integer + Zeroable, { fn from(value: Bounded) -> Self { value.get() != Zeroable::zeroed() } } +// Booleans can be converted to unsigned `Bounded`s. + impl From for Bounded where - T: Integer + From, + T: Integer + From, { fn from(value: bool) -> Self { - // SAFETY: A boolean can be represented using a single bit, and thus fits within any - // integer type for any `N` > 0. + // SAFETY: A boolean is represented by `0` or `1`, so it fits within any valid unsigned + // `Bounded` width. unsafe { Self::__new(T::from(value)) } } } impl Bounded where - T: Integer + Zeroable, + T: Integer + Zeroable, { /// Converts this [`Bounded`] into a [`bool`]. /// diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index 1ba1927b548e..164d9dd6fd92 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -320,9 +320,15 @@ static int __init ftrace_direct_init(void) ftrace_set_filter_ip(&direct, (unsigned long) my_ip, 0, 0); ret = register_ftrace_direct(&direct, my_tramp); - if (!ret) - simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn"); - return ret; + if (ret) + return ret; + simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn"); + if (IS_ERR(simple_tsk)) { + unregister_ftrace_direct(&direct, my_tramp, true); + return PTR_ERR(simple_tsk); + } + + return 0; } static void __exit ftrace_direct_exit(void) diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c index 7a7822dfeb50..b03766c6217b 100644 --- a/samples/ftrace/ftrace-direct-multi-modify.c +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -364,9 +364,15 @@ static int __init ftrace_direct_multi_init(void) ret = register_ftrace_direct(&direct, my_tramp); - if (!ret) - simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn"); - return ret; + if (ret) + return ret; + simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn"); + if (IS_ERR(simple_tsk)) { + unregister_ftrace_direct(&direct, my_tramp, true); + return PTR_ERR(simple_tsk); + } + + return 0; } static void __exit ftrace_direct_multi_exit(void) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index a48209591dee..4349108e75e1 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -347,7 +347,8 @@ quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_o_rs = $(rust_common_cmd) --emit=$(if $(CONFIG_RUST_INLINE_HELPERS),llvm-bc=$(patsubst %.o,%.bc,$@),obj=$@) $< \ $(if $(CONFIG_RUST_INLINE_HELPERS),;$(LLVM_LINK) --internalize --suppress-warnings $(patsubst %.o,%.bc,$@) \ $(objtree)/rust/helpers/helpers$(if $(part-of-module),_module).bc -o $(patsubst %.o,%.m.bc,$@); \ - $(CC) $(CLANG_FLAGS) $(KBUILD_CFLAGS) -Wno-override-module -c $(patsubst %.o,%.m.bc,$@) -o $@ \ + $(CC) $(CLANG_FLAGS) $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS)) \ + $(CC_FLAGS_RUST_INLINE_HELPERS) -Wno-override-module -c $(patsubst %.o,%.m.bc,$@) -o $@ \ $(cmd_ld_single)) \ $(cmd_objtool) diff --git a/scripts/coccicheck b/scripts/coccicheck index 8dd766009de1..a0a0e0f72bc7 100755 --- a/scripts/coccicheck +++ b/scripts/coccicheck @@ -11,7 +11,7 @@ DIR="$(dirname $(readlink -f $0))/.." SPATCH="`which ${SPATCH:=spatch}`" if [ ! -x "$SPATCH" ]; then - echo 'spatch is part of the Coccinelle project and is available at http://coccinelle.lip6.fr/' + echo 'spatch is part of the Coccinelle project and is available at https://coccinelle.gitlabpages.inria.fr/website' exit 1 fi @@ -229,7 +229,7 @@ coccinelle () { echo " in $FILE." echo '' echo ' More information about semantic patching is available at' - echo ' http://coccinelle.lip6.fr/' + echo ' https://coccinelle.gitlabpages.inria.fr/website' echo '' if [ "`sed -ne 's|^//#||p' $COCCI`" ] ; then diff --git a/scripts/coccinelle/api/alloc/alloc_cast.cocci b/scripts/coccinelle/api/alloc/alloc_cast.cocci index f6f0ccdb6409..a4b83cc8ea01 100644 --- a/scripts/coccinelle/api/alloc/alloc_cast.cocci +++ b/scripts/coccinelle/api/alloc/alloc_cast.cocci @@ -20,6 +20,24 @@ virtual patch virtual org virtual report +@m1@ +identifier i; +expression e; +type T; +position p1; +@@ + +#define i (T@p1 *)e + +@m2@ +identifier i; +expression e; +type T; +position p2; +@@ + +#define i(...) (T@p2 *)e + @initialize:python@ @@ import re @@ -28,15 +46,15 @@ m = re.compile(pattern) @r1 depends on context || patch@ type T; +position p != {m1.p1,m2.p2}; @@ - (T *) + (T@p *) \(kmalloc\|kzalloc\|kcalloc\|kmem_cache_alloc\|kmem_cache_zalloc\| kmem_cache_alloc_node\|kmalloc_node\|kzalloc_node\|vmalloc\|vzalloc\| dma_alloc_coherent\|devm_kmalloc\|devm_kzalloc\| - kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\|pci_alloc_consistent\| - pci_zalloc_consistent\|kmem_alloc\|kmem_zalloc\|kmem_zone_alloc\| - kmem_zone_zalloc\|vmalloc_node\|vzalloc_node\)(...) + kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\| + vmalloc_node\|vzalloc_node\)(...) //---------------------------------------------------------- // For context mode @@ -57,9 +75,8 @@ type r1.T; \(kmalloc\|kzalloc\|kcalloc\|kmem_cache_alloc\|kmem_cache_zalloc\| kmem_cache_alloc_node\|kmalloc_node\|kzalloc_node\|vmalloc\|vzalloc\| dma_alloc_coherent\|devm_kmalloc\|devm_kzalloc\| - kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\|pci_alloc_consistent\| - pci_zalloc_consistent\|kmem_alloc\|kmem_zalloc\|kmem_zone_alloc\| - kmem_zone_zalloc\|vmalloc_node\|vzalloc_node\)(...) + kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\| + vmalloc_node\|vzalloc_node\)(...) //---------------------------------------------------------- // For patch mode @@ -80,9 +97,8 @@ type r1.T; \(kmalloc\|kzalloc\|kcalloc\|kmem_cache_alloc\|kmem_cache_zalloc\| kmem_cache_alloc_node\|kmalloc_node\|kzalloc_node\|vmalloc\|vzalloc\| dma_alloc_coherent\|devm_kmalloc\|devm_kzalloc\| - kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\|pci_alloc_consistent\| - pci_zalloc_consistent\|kmem_alloc\|kmem_zalloc\|kmem_zone_alloc\| - kmem_zone_zalloc\|vmalloc_node\|vzalloc_node\)(...) + kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\| + vmalloc_node\|vzalloc_node\)(...) //---------------------------------------------------------- // For org and report mode @@ -90,16 +106,15 @@ type r1.T; @r2 depends on org || report@ type T; -position p; +position p != {m1.p1,m2.p2}; @@ (T@p *) \(kmalloc\|kzalloc\|kcalloc\|kmem_cache_alloc\|kmem_cache_zalloc\| kmem_cache_alloc_node\|kmalloc_node\|kzalloc_node\|vmalloc\|vzalloc\| dma_alloc_coherent\|devm_kmalloc\|devm_kzalloc\| - kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\|pci_alloc_consistent\| - pci_zalloc_consistent\|kmem_alloc\|kmem_zalloc\|kmem_zone_alloc\| - kmem_zone_zalloc\|vmalloc_node\|vzalloc_node\)(...) + kvmalloc\|kvzalloc\|kvmalloc_node\|kvzalloc_node\| + vmalloc_node\|vzalloc_node\)(...) @script:python depends on org@ p << r2.p; diff --git a/scripts/coccinelle/api/alloc/pool_zalloc-simple.cocci b/scripts/coccinelle/api/alloc/pool_zalloc-simple.cocci index 9c61a23b34db..07af8c7433d1 100644 --- a/scripts/coccinelle/api/alloc/pool_zalloc-simple.cocci +++ b/scripts/coccinelle/api/alloc/pool_zalloc-simple.cocci @@ -5,7 +5,7 @@ // Copyright: (C) 2015 Intel Corp. // Options: --no-includes --include-headers // -// Keywords: dma_pool_zalloc, pci_pool_zalloc +// Keywords: dma_pool_zalloc // virtual context @@ -22,7 +22,7 @@ expression x; statement S; @@ -* x = \(dma_pool_alloc\|pci_pool_alloc\)(...); +* x = dma_pool_alloc(...); if ((x==NULL) || ...) S * memset(x,0, ...); @@ -41,17 +41,6 @@ statement S; if ((x==NULL) || ...) S - memset(x,0,...); -@depends on patch@ -expression x; -expression a,b,c; -statement S; -@@ - -- x = pci_pool_alloc(a,b,c); -+ x = pci_pool_zalloc(a,b,c); - if ((x==NULL) || ...) S -- memset(x,0,...); - //---------------------------------------------------------- // For org and report mode //---------------------------------------------------------- @@ -63,7 +52,7 @@ statement S; position p; @@ - x = @p\(dma_pool_alloc\|pci_pool_alloc\)(a,b,c); + x =@p dma_pool_alloc(a,b,c); if ((x==NULL) || ...) S memset(x,0, ...); diff --git a/scripts/coccinelle/api/alloc/zalloc-simple.cocci b/scripts/coccinelle/api/alloc/zalloc-simple.cocci index d66c45356691..ae1d39e71e31 100644 --- a/scripts/coccinelle/api/alloc/zalloc-simple.cocci +++ b/scripts/coccinelle/api/alloc/zalloc-simple.cocci @@ -35,7 +35,7 @@ statement S; @@ * x = (T)\(kmalloc(E1, ...)\|vmalloc(E1)\|dma_alloc_coherent(...,E1,...)\| - kmalloc_node(E1, ...)\|kmem_cache_alloc(...)\|kmem_alloc(E1, ...)\| + kmalloc_node(E1, ...)\|kmem_cache_alloc(...)\| devm_kmalloc(...,E1,...)\|kvmalloc(E1, ...)\|kvmalloc_node(E1,...)\); if ((x==NULL) || ...) S * memset((T2)x,0,E1); @@ -88,15 +88,6 @@ statement S; - x = (T)kmem_cache_alloc(E3,E4); + x = (T)kmem_cache_zalloc(E3,E4); | -- x = kmem_alloc(E1,E2); -+ x = kmem_zalloc(E1,E2); -| -- x = (T *)kmem_alloc(E1,E2); -+ x = kmem_zalloc(E1,E2); -| -- x = (T)kmem_alloc(E1,E2); -+ x = (T)kmem_zalloc(E1,E2); -| - x = devm_kmalloc(E2,E1,E3); + x = devm_kzalloc(E2,E1,E3); | @@ -290,36 +281,6 @@ x << r4.x; msg="WARNING: kmem_cache_zalloc should be used for %s, instead of kmem_cache_alloc/memset" % (x) coccilib.report.print_report(p[0], msg) -//----------------------------------------------------------------- -@r5 depends on org || report@ -type T, T2; -expression x; -expression E1,E2; -statement S; -position p; -@@ - - x = (T)kmem_alloc@p(E1,E2); - if ((x==NULL) || ...) S - memset((T2)x,0,E1); - -@script:python depends on org@ -p << r5.p; -x << r5.x; -@@ - -msg="%s" % (x) -msg_safe=msg.replace("[","@(").replace("]",")") -coccilib.org.print_todo(p[0], msg_safe) - -@script:python depends on report@ -p << r5.p; -x << r5.x; -@@ - -msg="WARNING: kmem_zalloc should be used for %s, instead of kmem_alloc/memset" % (x) -coccilib.report.print_report(p[0], msg) - //----------------------------------------------------------------- @r6 depends on org || report@ type T, T2; diff --git a/scripts/coccinelle/api/atomic_as_refcounter.cocci b/scripts/coccinelle/api/atomic_as_refcounter.cocci index bbe5b2932933..af82b9e094aa 100644 --- a/scripts/coccinelle/api/atomic_as_refcounter.cocci +++ b/scripts/coccinelle/api/atomic_as_refcounter.cocci @@ -26,8 +26,6 @@ identifier fname6 =~ ".*call_rcu.*"; atomic_dec_and_test@p1(&(a)->x) | atomic_dec_and_lock@p1(&(a)->x, ...) -| - atomic_long_dec_and_lock@p1(&(a)->x, ...) | atomic_long_dec_and_test@p1(&(a)->x) | @@ -69,8 +67,6 @@ identifier fname =~ ".*free.*"; atomic_dec_and_test@p1(&(a)->x) | atomic_dec_and_lock@p1(&(a)->x, ...) -| - atomic_long_dec_and_lock@p1(&(a)->x, ...) | atomic_long_dec_and_test@p1(&(a)->x) | diff --git a/scripts/coccinelle/api/kfree_mismatch.cocci b/scripts/coccinelle/api/kfree_mismatch.cocci index d46a9b3eb7b3..bc90d0c071ac 100644 --- a/scripts/coccinelle/api/kfree_mismatch.cocci +++ b/scripts/coccinelle/api/kfree_mismatch.cocci @@ -29,7 +29,7 @@ position kok, vok; } else { ... E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\| - vzalloc_node\|vmalloc_exec\|vmalloc_32\| + vzalloc_node\|vmalloc_32\| vmalloc_32_user\|__vmalloc\|__vmalloc_node_range\| __vmalloc_node\)(...)@vok ... @@ -42,7 +42,7 @@ position kok, vok; if (E == NULL) { ... E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\| - vzalloc_node\|vmalloc_exec\|vmalloc_32\| + vzalloc_node\|vmalloc_32\| vmalloc_32_user\|__vmalloc\|__vmalloc_node_range\| __vmalloc_node\)(...)@vok ... @@ -68,7 +68,7 @@ position f != free.fok; * E = \(kmalloc\|kzalloc\|krealloc\|kcalloc\|kmalloc_node\| * kzalloc_node\|kmalloc_array\|kmalloc_array_node\| * kcalloc_node\)(...)@a - ... when != if (...) { ... E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\|vzalloc_node\|vmalloc_exec\|vmalloc_32\|vmalloc_32_user\|__vmalloc\|__vmalloc_node_range\|__vmalloc_node\)(...); ... } + ... when != if (...) { ... E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\|vzalloc_node\|vmalloc_32\|vmalloc_32_user\|__vmalloc\|__vmalloc_node_range\|__vmalloc_node\)(...); ... } when != is_vmalloc_addr(E) when any * \(vfree\|vfree_atomic\|kvfree\)(E)@f @@ -82,7 +82,7 @@ position f != free.fok; E = \(kmalloc\|kzalloc\|krealloc\|kcalloc\|kmalloc_node\| kzalloc_node\|kmalloc_array\|kmalloc_array_node\| kcalloc_node\)(...)@a - ... when != if (...) { ... E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\|vzalloc_node\|vmalloc_exec\|vmalloc_32\|vmalloc_32_user\|__vmalloc\|__vmalloc_node_range\|__vmalloc_node\)(...); ... } + ... when != if (...) { ... E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\|vzalloc_node\|vmalloc_32\|vmalloc_32_user\|__vmalloc\|__vmalloc_node_range\|__vmalloc_node\)(...); ... } when != is_vmalloc_addr(E) when any - \(vfree\|vfree_atomic\|kvfree\)(E)@f @@ -95,7 +95,7 @@ position f != free.fok; @@ * E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\|vzalloc_node\| -* vmalloc_exec\|vmalloc_32\|vmalloc_32_user\|__vmalloc\| +* vmalloc_32\|vmalloc_32_user\|__vmalloc\| * __vmalloc_node_range\|__vmalloc_node\)(...)@a ... when != is_vmalloc_addr(E) when any @@ -108,7 +108,7 @@ position f != free.fok; @@ E = \(vmalloc\|vzalloc\|vmalloc_user\|vmalloc_node\|vzalloc_node\| - vmalloc_exec\|vmalloc_32\|vmalloc_32_user\|__vmalloc\| + vmalloc_32\|vmalloc_32_user\|__vmalloc\| __vmalloc_node_range\|__vmalloc_node\)(...)@a ... when != is_vmalloc_addr(E) when any diff --git a/scripts/coccinelle/free/devm_free.cocci b/scripts/coccinelle/free/devm_free.cocci index 0880729badbc..947d7e685655 100644 --- a/scripts/coccinelle/free/devm_free.cocci +++ b/scripts/coccinelle/free/devm_free.cocci @@ -26,7 +26,8 @@ virtual report virtual context @r depends on context || org || report@ -expression x; +type T; +T x; @@ ( @@ -56,18 +57,26 @@ expression x; ) @safe depends on context || org || report exists@ -expression x; +r.T x; position p; @@ ( x = kmalloc(...) +| + x = kmalloc_obj(...) +| + x = kmalloc_objs(...) | x = kvasprintf(...) | x = kasprintf(...) | x = kzalloc(...) +| + x = kzalloc_obj(...) +| + x = kzalloc_objs(...) | x = kmalloc_array(...) | @@ -105,7 +114,7 @@ position p; ) @pb@ -expression r.x; +r.T r.x; position p != safe.p; @@ diff --git a/scripts/coccinelle/free/ifnulldev_put.cocci b/scripts/coccinelle/free/ifnulldev_put.cocci index 2bd2e8fae485..1430d68ff268 100644 --- a/scripts/coccinelle/free/ifnulldev_put.cocci +++ b/scripts/coccinelle/free/ifnulldev_put.cocci @@ -23,13 +23,13 @@ expression E; | dev_put(E); | - dev_put_track(E, ...); + netdev_put(E, ...); | __dev_hold(E); | dev_hold(E); | - dev_hold_track(E, ...); + netdev_hold(E, ...); ) @r depends on context || report || org @ @@ -38,18 +38,18 @@ position p; @@ * if (E != NULL) -* \(__dev_put@p\|dev_put@p\|dev_put_track@p\|__dev_hold@p\|dev_hold@p\| -* dev_hold_track@p\)(E, ...); +* \(__dev_put@p\|dev_put@p\|netdev_put@p\|__dev_hold@p\|dev_hold@p\| +* netdev_hold@p\)(E, ...); @script:python depends on org@ p << r.p; @@ -cocci.print_main("NULL check before dev_{put, hold} functions is not needed", p) +cocci.print_main("NULL check before (net)dev_{put, hold} functions is not needed", p) @script:python depends on report@ p << r.p; @@ -msg = "WARNING: NULL check before dev_{put, hold} functions is not needed." +msg = "WARNING: NULL check before (net)dev_{put, hold} functions is not needed." coccilib.report.print_report(p[0], msg) diff --git a/scripts/coccinelle/free/pci_free_consistent.cocci b/scripts/coccinelle/free/pci_free_consistent.cocci deleted file mode 100644 index e062b9ba09ff..000000000000 --- a/scripts/coccinelle/free/pci_free_consistent.cocci +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/// Find missing pci_free_consistent for every pci_alloc_consistent. -/// -// Confidence: Moderate -// Copyright: (C) 2013 Petr Strnad. -// URL: https://coccinelle.gitlabpages.inria.fr/website -// Keywords: pci_free_consistent, pci_alloc_consistent -// Options: --no-includes --include-headers - -virtual report -virtual org - -@search@ -local idexpression id; -expression x,y,z,e; -position p1,p2; -type T; -@@ - -id = pci_alloc_consistent@p1(x,y,&z) -... when != e = id -if (id == NULL || ...) { ... return ...; } -... when != pci_free_consistent(x,y,id,z) - when != if (id) { ... pci_free_consistent(x,y,id,z) ... } - when != if (y) { ... pci_free_consistent(x,y,id,z) ... } - when != e = (T)id - when exists -( -return 0; -| -return 1; -| -return id; -| -return@p2 ...; -) - -@script:python depends on report@ -p1 << search.p1; -p2 << search.p2; -@@ - -msg = "ERROR: missing pci_free_consistent; pci_alloc_consistent on line %s and return without freeing on line %s" % (p1[0].line,p2[0].line) -coccilib.report.print_report(p2[0],msg) - -@script:python depends on org@ -p1 << search.p1; -p2 << search.p2; -@@ - -msg = "ERROR: missing pci_free_consistent; pci_alloc_consistent on line %s and return without freeing on line %s" % (p1[0].line,p2[0].line) -cocci.print_main(msg,p1) -cocci.print_secs("",p2) diff --git a/scripts/coccinelle/locks/double_lock.cocci b/scripts/coccinelle/locks/double_lock.cocci index 619cfc714409..381060849a7b 100644 --- a/scripts/coccinelle/locks/double_lock.cocci +++ b/scripts/coccinelle/locks/double_lock.cocci @@ -38,7 +38,20 @@ write_lock@p1 write_trylock@p1 ) (E1@p,...); -@balanced@ +@r_candidate exists@ +expression x <= locked.E1; +expression locked.E1; +expression E2; +identifier lock; +position locked.p,p1,p2; +@@ + +lock@p1 (E1@p,...); +... when != E1 + when != \(x = E2\|&x\) +lock@p2 (E1,...); + +@balanced depends on r_candidate@ position p1 != locked.p1; position locked.p; identifier lock,unlock; diff --git a/scripts/coccinelle/locks/mini_lock.cocci b/scripts/coccinelle/locks/mini_lock.cocci index 71065d8a5d54..c65241c895ff 100644 --- a/scripts/coccinelle/locks/mini_lock.cocci +++ b/scripts/coccinelle/locks/mini_lock.cocci @@ -53,11 +53,31 @@ spin_lock_irq@p1 spin_lock_irqsave@p1 ) (E1@p,...); -@looped@ +@err_candidate exists@ +expression E1; +position prelocked.p; +position up != prelocked.p1; +position rc; +identifier lock,unlock; +@@ + +lock(E1@p,...); +... when != E1 + when any +if (...) { + ... when != E1 + return@rc ...; +} +... when != E1 + when any +unlock@up(E1,...); + +@looped exists@ +position err_candidate.rc; position r; @@ -for(...;...;...) { <+... return@r ...; ...+> } +for(...;...;...) { <+... return@rc@r ...; ...+> } @err exists@ expression E1; diff --git a/scripts/coccinelle/misc/minmax.cocci b/scripts/coccinelle/misc/minmax.cocci index ca4830ae3042..b83d4a01e47a 100644 --- a/scripts/coccinelle/misc/minmax.cocci +++ b/scripts/coccinelle/misc/minmax.cocci @@ -17,7 +17,21 @@ virtual org virtual context virtual patch -@rmax depends on !patch@ +@max_candidate disable not_int1, not_int2, neg_if_exp@ +expression E1, E2, E3, E4; +binary operator cmp = {>, >=}; +@@ + + E1 cmp E2 ? E3 : E4 + +@min_candidate disable not_int1, not_int2, neg_if_exp@ +expression E1, E2, E3, E4; +binary operator cmp = {<, <=}; +@@ + + E1 cmp E2 ? E3 : E4 + +@rmax depends on !patch && max_candidate disable not_int1, not_int2, neg_if_exp@ identifier func; expression x, y; binary operator cmp = {>, >=}; @@ -27,11 +41,23 @@ position p; func(...) { <... -* ((x) cmp@p (y) ? (x) : (y)) +* (x) cmp@p (y) ? (x) : (y) ...> } -@rmaxif depends on !patch@ +@maxif_candidate disable not_int1, not_int2, neg_if@ +expression x, y; +expression max_val; +binary operator cmp = {>, >=}; +@@ + +if ((x) cmp (y)) { + max_val = (x); +} else { + max_val = (y); +} + +@rmaxif depends on !patch && maxif_candidate disable not_int1, not_int2, neg_if@ identifier func; expression x, y; expression max_val; @@ -51,7 +77,7 @@ func(...) } // Ignore errcode returns. -@errcode@ +@errcode depends on min_candidate disable not_int1, not_int2, neg_if_exp@ position p; identifier func; expression x; @@ -65,7 +91,7 @@ func(...) ...> } -@rmin depends on !patch@ +@rmin depends on !patch && min_candidate disable not_int1, not_int2, neg_if_exp@ identifier func; expression x, y; binary operator cmp = {<, <=}; @@ -75,11 +101,23 @@ position p != errcode.p; func(...) { <... -* ((x) cmp@p (y) ? (x) : (y)) +* (x) cmp@p (y) ? (x) : (y) ...> } -@rminif depends on !patch@ +@minif_candidate disable not_int1, not_int2, neg_if@ +expression x, y; +expression min_val; +binary operator cmp = {<, <=}; +@@ + +if ((x) cmp (y)) { + min_val = (x); +} else { + min_val = (y); +} + +@rminif depends on !patch && minif_candidate disable not_int1, not_int2, neg_if@ identifier func; expression x, y; expression min_val; @@ -98,7 +136,7 @@ func(...) ...> } -@pmax depends on patch@ +@pmax depends on patch && max_candidate disable not_int1, not_int2, neg_if_exp@ identifier func; expression x, y; binary operator cmp = {>=, >}; @@ -112,7 +150,7 @@ func(...) ...> } -@pmaxif depends on patch@ +@pmaxif depends on patch && maxif_candidate disable not_int1, not_int2, neg_if@ identifier func; expression x, y; expression max_val; @@ -131,7 +169,7 @@ func(...) ...> } -@pmin depends on patch@ +@pmin depends on patch && min_candidate disable not_int1, not_int2, neg_if_exp@ identifier func; expression x, y; binary operator cmp = {<=, <}; @@ -146,7 +184,7 @@ func(...) ...> } -@pminif depends on patch@ +@pminif depends on patch && minif_candidate disable not_int1, not_int2, neg_if@ identifier func; expression x, y; expression min_val; diff --git a/scripts/coccinelle/misc/struct_size.cocci b/scripts/coccinelle/misc/struct_size.cocci index 9b02c37438e4..406884d68d43 100644 --- a/scripts/coccinelle/misc/struct_size.cocci +++ b/scripts/coccinelle/misc/struct_size.cocci @@ -29,9 +29,7 @@ f expression E1, E2; identifier m; @@ -( -* (sizeof(*E1) + (E2 * sizeof(*E1->m))) -) +* sizeof(*E1) + (E2 * sizeof(*E1->m)) //---------------------------------------------------------- // For patch mode @@ -55,9 +53,7 @@ expression E1, E2; identifier m; position p; @@ -( - (sizeof(*E1)@p + (E2 * sizeof(*E1->m))) -) + sizeof(*E1)@p + (E2 * sizeof(*E1->m)) @script:python depends on org@ p << r.p; diff --git a/scripts/nsdeps b/scripts/nsdeps index a3372166ac01..d4b5ebcc2016 100644 --- a/scripts/nsdeps +++ b/scripts/nsdeps @@ -8,7 +8,7 @@ SPATCH_REQ_VERSION="1.0.4" DIR="$(dirname $(readlink -f $0))/.." SPATCH="`which ${SPATCH:=spatch}`" if [ ! -x "$SPATCH" ]; then - echo 'spatch is part of the Coccinelle project and is available at http://coccinelle.lip6.fr/' + echo 'spatch is part of the Coccinelle project and is available at https://coccinelle.gitlabpages.inria.fr/website' exit 1 fi diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 6923036e1a2f..81c81ad983ad 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -278,7 +278,7 @@ config CC_HAS_RANDSTRUCT choice prompt "Randomize layout of sensitive kernel structures" - default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) + default RANDSTRUCT_FULL if !(RUST_IS_AVAILABLE && HAVE_RUST) && COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) default RANDSTRUCT_NONE help If you enable this, the layouts of structures that are entirely diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c index 8f57c6111e7e..bf0bf7f36970 100644 --- a/security/keys/trusted-keys/trusted_tpm1.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -18,7 +18,6 @@ #include #include #include -#include #include @@ -317,9 +316,8 @@ static int TSS_checkhmac2(unsigned char *buffer, * For key specific tpm requests, we will generate and send our * own TPM command packets using the drivers send function. */ -static int trusted_tpm_send(unsigned char *cmd, size_t buflen) +static int trusted_tpm_send(struct tpm_buf *buf) { - struct tpm_buf buf; int rc; if (!chip) @@ -329,12 +327,9 @@ static int trusted_tpm_send(unsigned char *cmd, size_t buflen) if (rc) return rc; - buf.flags = 0; - buf.length = buflen; - buf.data = cmd; - dump_tpm_buf(cmd); - rc = tpm_transmit_cmd(chip, &buf, 4, "sending data"); - dump_tpm_buf(cmd); + dump_tpm_buf(buf->data); + rc = tpm_transmit_cmd(chip, buf, 4, "sending data"); + dump_tpm_buf(buf->data); if (rc > 0) /* TPM error */ @@ -380,7 +375,7 @@ static int osap(struct tpm_buf *tb, struct osapsess *s, tpm_buf_append_u32(tb, handle); tpm_buf_append(tb, ononce, TPM_NONCE_SIZE); - ret = trusted_tpm_send(tb->data, tb->length); + ret = trusted_tpm_send(tb); if (ret < 0) return ret; @@ -404,7 +399,7 @@ static int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) return -ENODEV; tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OIAP); - ret = trusted_tpm_send(tb->data, tb->length); + ret = trusted_tpm_send(tb); if (ret < 0) return ret; @@ -513,7 +508,7 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype, tpm_buf_append_u8(tb, cont); tpm_buf_append(tb, td->pubauth, SHA1_DIGEST_SIZE); - ret = trusted_tpm_send(tb->data, tb->length); + ret = trusted_tpm_send(tb); if (ret < 0) goto out; @@ -604,7 +599,7 @@ static int tpm_unseal(struct tpm_buf *tb, tpm_buf_append_u8(tb, cont); tpm_buf_append(tb, authdata2, SHA1_DIGEST_SIZE); - ret = trusted_tpm_send(tb->data, tb->length); + ret = trusted_tpm_send(tb); if (ret < 0) { pr_info("authhmac failed (%d)\n", ret); return ret; @@ -631,23 +626,23 @@ static int tpm_unseal(struct tpm_buf *tb, static int key_seal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf tb; int ret; - ret = tpm_buf_init(&tb, 0, 0); - if (ret) - return ret; + struct tpm_buf *tb __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!tb) + return -ENOMEM; + + tpm_buf_init(tb, TPM_BUFSIZE); /* include migratable flag at end of sealed key */ p->key[p->key_len] = p->migratable; - ret = tpm_seal(&tb, o->keytype, o->keyhandle, o->keyauth, + ret = tpm_seal(tb, o->keytype, o->keyhandle, o->keyauth, p->key, p->key_len + 1, p->blob, &p->blob_len, o->blobauth, o->pcrinfo, o->pcrinfo_len); if (ret < 0) pr_info("srkseal failed (%d)\n", ret); - tpm_buf_destroy(&tb); return ret; } @@ -657,14 +652,15 @@ static int key_seal(struct trusted_key_payload *p, static int key_unseal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf tb; int ret; - ret = tpm_buf_init(&tb, 0, 0); - if (ret) - return ret; + struct tpm_buf *tb __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!tb) + return -ENOMEM; - ret = tpm_unseal(&tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, + tpm_buf_init(tb, TPM_BUFSIZE); + + ret = tpm_unseal(tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, o->blobauth, p->key, &p->key_len); if (ret < 0) pr_info("srkunseal failed (%d)\n", ret); @@ -672,7 +668,6 @@ static int key_unseal(struct trusted_key_payload *p, /* pull migratable flag out of sealed key */ p->migratable = p->key[--p->key_len]; - tpm_buf_destroy(&tb); return ret; } diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 6340823f8b53..67225dd562a9 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include @@ -234,7 +233,8 @@ int tpm2_seal_trusted(struct tpm_chip *chip, struct trusted_key_options *options) { off_t offset = TPM_HEADER_SIZE; - struct tpm_buf buf, sized; + struct tpm_buf *buf __free(kfree) = NULL; + struct tpm_buf *sized __free(kfree) = NULL; int blob_len = 0; int hash; u32 flags; @@ -255,97 +255,100 @@ int tpm2_seal_trusted(struct tpm_chip *chip, if (rc) goto out_put; - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); - if (rc) { + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { + rc = -ENOMEM; tpm2_end_auth_session(chip); goto out_put; } - rc = tpm_buf_init_sized(&sized); - if (rc) { - tpm_buf_destroy(&buf); + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); + + sized = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!sized) { + rc = -ENOMEM; tpm2_end_auth_session(chip); goto out_put; } - rc = tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); + tpm_buf_init_sized(sized, TPM_BUFSIZE); + + rc = tpm_buf_append_name(chip, buf, options->keyhandle, NULL); if (rc) goto out; - tpm_buf_append_hmac_session(chip, &buf, TPM2_SA_DECRYPT, + tpm_buf_append_hmac_session(chip, buf, TPM2_SA_DECRYPT, options->keyauth, TPM_DIGEST_SIZE); /* sensitive */ - tpm_buf_append_u16(&sized, options->blobauth_len); + tpm_buf_append_u16(sized, options->blobauth_len); if (options->blobauth_len) - tpm_buf_append(&sized, options->blobauth, options->blobauth_len); + tpm_buf_append(sized, options->blobauth, options->blobauth_len); - tpm_buf_append_u16(&sized, payload->key_len); - tpm_buf_append(&sized, payload->key, payload->key_len); - tpm_buf_append(&buf, sized.data, sized.length); + tpm_buf_append_u16(sized, payload->key_len); + tpm_buf_append(sized, payload->key, payload->key_len); + tpm_buf_append(buf, sized->data, sized->length); /* public */ - tpm_buf_reset_sized(&sized); - tpm_buf_append_u16(&sized, TPM_ALG_KEYEDHASH); - tpm_buf_append_u16(&sized, hash); + tpm_buf_reset_sized(sized); + tpm_buf_append_u16(sized, TPM_ALG_KEYEDHASH); + tpm_buf_append_u16(sized, hash); /* key properties */ flags = 0; flags |= options->policydigest_len ? 0 : TPM2_OA_USER_WITH_AUTH; flags |= payload->migratable ? 0 : (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT); - tpm_buf_append_u32(&sized, flags); + tpm_buf_append_u32(sized, flags); /* policy */ - tpm_buf_append_u16(&sized, options->policydigest_len); + tpm_buf_append_u16(sized, options->policydigest_len); if (options->policydigest_len) - tpm_buf_append(&sized, options->policydigest, options->policydigest_len); + tpm_buf_append(sized, options->policydigest, options->policydigest_len); /* public parameters */ - tpm_buf_append_u16(&sized, TPM_ALG_NULL); - tpm_buf_append_u16(&sized, 0); + tpm_buf_append_u16(sized, TPM_ALG_NULL); + tpm_buf_append_u16(sized, 0); - tpm_buf_append(&buf, sized.data, sized.length); + tpm_buf_append(buf, sized->data, sized->length); /* outside info */ - tpm_buf_append_u16(&buf, 0); + tpm_buf_append_u16(buf, 0); /* creation PCR */ - tpm_buf_append_u32(&buf, 0); + tpm_buf_append_u32(buf, 0); - if (buf.flags & TPM_BUF_OVERFLOW) { + if (buf->flags & TPM_BUF_INVALID) { rc = -E2BIG; tpm2_end_auth_session(chip); goto out; } - rc = tpm_buf_fill_hmac_session(chip, &buf); + rc = tpm_buf_fill_hmac_session(chip, buf); if (rc) goto out; - rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data"); - rc = tpm_buf_check_hmac_response(chip, &buf, rc); + rc = tpm_transmit_cmd(chip, buf, 4, "sealing data"); + rc = tpm_buf_check_hmac_response(chip, buf, rc); if (rc) goto out; - blob_len = tpm_buf_read_u32(&buf, &offset); - if (blob_len > MAX_BLOB_SIZE || buf.flags & TPM_BUF_BOUNDARY_ERROR) { + blob_len = tpm_buf_read_u32(buf, &offset); + if (blob_len > MAX_BLOB_SIZE || buf->flags & TPM_BUF_INVALID) { rc = -E2BIG; goto out; } - if (buf.length - offset < blob_len) { + if (buf->length - offset < blob_len) { rc = -EFAULT; goto out; } - blob_len = tpm2_key_encode(payload, options, &buf.data[offset], blob_len); + blob_len = tpm2_key_encode(payload, options, &buf->data[offset], blob_len); if (blob_len < 0) rc = blob_len; out: - tpm_buf_destroy(&sized); - tpm_buf_destroy(&buf); - if (!rc) payload->blob_len = blob_len; @@ -373,7 +376,7 @@ static int tpm2_load_cmd(struct tpm_chip *chip, u32 *blob_handle) { u8 *blob_ref __free(kfree) = NULL; - struct tpm_buf buf; + struct tpm_buf *buf __free(kfree) = NULL; unsigned int private_len; unsigned int public_len; unsigned int blob_len; @@ -427,39 +430,38 @@ static int tpm2_load_cmd(struct tpm_chip *chip, if (rc) return rc; - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); - if (rc) { + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { tpm2_end_auth_session(chip); - return rc; + return -ENOMEM; } - rc = tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); - if (rc) - goto out; + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); - tpm_buf_append_hmac_session(chip, &buf, 0, options->keyauth, + rc = tpm_buf_append_name(chip, buf, options->keyhandle, NULL); + if (rc) + return rc; + + tpm_buf_append_hmac_session(chip, buf, 0, options->keyauth, TPM_DIGEST_SIZE); - tpm_buf_append(&buf, blob, blob_len); + tpm_buf_append(buf, blob, blob_len); - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; + if (buf->flags & TPM_BUF_INVALID) { tpm2_end_auth_session(chip); - goto out; + return -E2BIG; } - rc = tpm_buf_fill_hmac_session(chip, &buf); + rc = tpm_buf_fill_hmac_session(chip, buf); if (rc) - goto out; + return rc; - rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob"); - rc = tpm_buf_check_hmac_response(chip, &buf, rc); + rc = tpm_transmit_cmd(chip, buf, 4, "loading blob"); + rc = tpm_buf_check_hmac_response(chip, buf, rc); if (!rc) *blob_handle = be32_to_cpup( - (__be32 *) &buf.data[TPM_HEADER_SIZE]); - -out: - tpm_buf_destroy(&buf); + (__be32 *)&buf->data[TPM_HEADER_SIZE]); return tpm_ret_to_err(rc); } @@ -482,7 +484,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, u32 blob_handle) { struct tpm_header *head; - struct tpm_buf buf; + struct tpm_buf *buf __free(kfree) = NULL; u16 data_len; int offset; u8 *data; @@ -492,18 +494,21 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, if (rc) return rc; - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); - if (rc) { + buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL); + if (!buf) { tpm2_end_auth_session(chip); - return rc; + return -ENOMEM; } - rc = tpm_buf_append_name(chip, &buf, blob_handle, NULL); + tpm_buf_init(buf, TPM_BUFSIZE); + tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); + + rc = tpm_buf_append_name(chip, buf, blob_handle, NULL); if (rc) - goto out; + return rc; if (!options->policyhandle) { - tpm_buf_append_hmac_session(chip, &buf, TPM2_SA_ENCRYPT, + tpm_buf_append_hmac_session(chip, buf, TPM2_SA_ENCRYPT, options->blobauth, options->blobauth_len); } else { @@ -518,39 +523,36 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, * could repeat our actions with the exfiltrated * password. */ - tpm2_buf_append_auth(&buf, options->policyhandle, + tpm2_buf_append_auth(buf, options->policyhandle, NULL /* nonce */, 0, 0, options->blobauth, options->blobauth_len); if (tpm2_chip_auth(chip)) { - tpm_buf_append_hmac_session(chip, &buf, TPM2_SA_ENCRYPT, NULL, 0); + tpm_buf_append_hmac_session(chip, buf, TPM2_SA_ENCRYPT, + NULL, 0); } else { - offset = buf.handles * 4 + TPM_HEADER_SIZE; - head = (struct tpm_header *)buf.data; - if (tpm_buf_length(&buf) == offset) + offset = buf->handles * 4 + TPM_HEADER_SIZE; + head = (struct tpm_header *)buf->data; + if (tpm_buf_length(buf) == offset) head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS); } } - rc = tpm_buf_fill_hmac_session(chip, &buf); + rc = tpm_buf_fill_hmac_session(chip, buf); if (rc) - goto out; + return rc; - rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); - rc = tpm_buf_check_hmac_response(chip, &buf, rc); + rc = tpm_transmit_cmd(chip, buf, 6, "unsealing"); + rc = tpm_buf_check_hmac_response(chip, buf, rc); if (!rc) { data_len = be16_to_cpup( - (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); - if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE) { - rc = -EFAULT; - goto out; - } + (__be16 *)&buf->data[TPM_HEADER_SIZE + 4]); + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE) + return -EFAULT; - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { - rc = -EFAULT; - goto out; - } - data = &buf.data[TPM_HEADER_SIZE + 6]; + if (tpm_buf_length(buf) < TPM_HEADER_SIZE + 6 + data_len) + return -EFAULT; + data = &buf->data[TPM_HEADER_SIZE + 6]; if (payload->old_format) { /* migratable flag is at the end of the key */ @@ -567,8 +569,6 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, } } -out: - tpm_buf_destroy(&buf); return tpm_ret_to_err(rc); } diff --git a/sound/aoa/soundbus/i2sbus/core.c b/sound/aoa/soundbus/i2sbus/core.c index 833c44c0a950..adf123dd79a2 100644 --- a/sound/aoa/soundbus/i2sbus/core.c +++ b/sound/aoa/soundbus/i2sbus/core.c @@ -240,6 +240,8 @@ static int i2sbus_add_dev(struct macio_dev *macio, } for (i = aoa_resource_i2smmio; i <= aoa_resource_rxdbdma; i++) { int irq = irq_of_parse_and_map(np, i); + if (!irq) + goto err; if (request_irq(irq, ints[i], 0, dev->rnames[i], dev)) goto err; dev->interrupts[i] = irq; diff --git a/sound/core/control_led.c b/sound/core/control_led.c index 8cbacee57ce7..3d13bbec1c54 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -255,6 +255,8 @@ static int snd_ctl_led_set_id(int card_number, struct snd_ctl_elem_id *id, kctl = snd_ctl_find_id(card, id); if (!kctl) return -ENOENT; + if (!kctl->info || !kctl->get) + return -EINVAL; ioff = snd_ctl_get_ioff(kctl, id); vd = &kctl->vd[ioff]; access = vd->access & SNDRV_CTL_ELEM_ACCESS_LED_MASK; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index bf504e27f73e..34b4c7d6dbe6 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -571,7 +571,6 @@ static void rawmidi_release_priv(struct snd_rawmidi_file *rfile) struct snd_rawmidi *rmidi; rmidi = rfile->rmidi; - guard(mutex)(&rmidi->open_mutex); if (rfile->input) { close_substream(rmidi, rfile->input, 1); rfile->input = NULL; @@ -585,7 +584,8 @@ static void rawmidi_release_priv(struct snd_rawmidi_file *rfile) } /* called from sound/core/seq/seq_midi.c */ -int snd_rawmidi_kernel_release(struct snd_rawmidi_file *rfile) +int snd_rawmidi_kernel_release_nested(struct snd_rawmidi_file *rfile, + int depth) { struct snd_rawmidi *rmidi; @@ -593,11 +593,13 @@ int snd_rawmidi_kernel_release(struct snd_rawmidi_file *rfile) return -ENXIO; rmidi = rfile->rmidi; + mutex_lock_nested(&rmidi->open_mutex, depth); rawmidi_release_priv(rfile); + mutex_unlock(&rmidi->open_mutex); module_put(rmidi->card->module); return 0; } -EXPORT_SYMBOL(snd_rawmidi_kernel_release); +EXPORT_SYMBOL(snd_rawmidi_kernel_release_nested); static int snd_rawmidi_release(struct inode *inode, struct file *file) { @@ -607,7 +609,8 @@ static int snd_rawmidi_release(struct inode *inode, struct file *file) rfile = file->private_data; rmidi = rfile->rmidi; - rawmidi_release_priv(rfile); + scoped_guard(mutex, &rmidi->open_mutex) + rawmidi_release_priv(rfile); kfree(rfile); module = rmidi->card->module; snd_card_file_remove(rmidi->card, file); diff --git a/sound/core/ump.c b/sound/core/ump.c index 82ad155c56e6..d183c8a000bd 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -1184,7 +1184,8 @@ static int snd_ump_legacy_close(struct snd_rawmidi_substream *substream) ump->legacy_substreams[dir][group] = NULL; if (dir == SNDRV_RAWMIDI_STREAM_OUTPUT) { if (!--ump->legacy_out_opens) - snd_rawmidi_kernel_release(&ump->legacy_out_rfile); + snd_rawmidi_kernel_release_nested(&ump->legacy_out_rfile, + SINGLE_DEPTH_NESTING); } return 0; } diff --git a/sound/drivers/mtpav.c b/sound/drivers/mtpav.c index d31eadf4be5f..1ed6d4f0cb62 100644 --- a/sound/drivers/mtpav.c +++ b/sound/drivers/mtpav.c @@ -642,9 +642,7 @@ static void snd_mtpav_free(struct snd_card *card) { struct mtpav *crd = card->private_data; - guard(spinlock_irqsave)(&crd->spinlock); - if (crd->istimer > 0) - snd_mtpav_remove_output_timer(crd); + timer_shutdown_sync(&crd->timer); } /* diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index c517334b56fd..7357dc91ac49 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -207,7 +207,7 @@ static void cx_remove(struct hda_codec *codec) snd_hda_gen_remove(codec); } -static void cx_process_headset_plugin(struct hda_codec *codec) +static void cx_process_headset_detect_plug_type(struct hda_codec *codec) { unsigned int val; unsigned int count = 0; @@ -223,11 +223,9 @@ static void cx_process_headset_plugin(struct hda_codec *codec) count++; } while (count < 3); val = snd_hda_codec_read(codec, 0x1c, 0, 0xcb0, 0x0); - if (val & 0x800) { - codec_dbg(codec, "headset plugin, type is CTIA\n"); - snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); - } else if (val & 0x400) { - codec_dbg(codec, "headset plugin, type is OMTP\n"); + if (val & 0xc00) { + codec_dbg(codec, "headset plugin, type is %s\n", + val & 0x800 ? "CTIA" : "OMTP"); snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); } else { codec_dbg(codec, "headphone plugin\n"); @@ -243,10 +241,12 @@ static void cx_update_headset_mic_vref(struct hda_codec *codec, struct hda_jack_ * Check hp&mic tag to process headset plugin & plugout. */ mic_present = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0); - if (!(mic_present & AC_PINSENSE_PRESENCE)) /* mic plugout */ + if (!(mic_present & AC_PINSENSE_PRESENCE)) { /* mic plugout */ snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20); - else - cx_process_headset_plugin(codec); + } else { + cx_process_headset_detect_plug_type(codec); + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); + } } static int cx_suspend(struct hda_codec *codec) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index cae327e1d90d..e4349743a251 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -1370,6 +1370,61 @@ static void alc269_fixup_hp_gpio_led(struct hda_codec *codec, alc_fixup_hp_gpio_led(codec, action, 0x08, 0x10); } +/* + * HP Laptop 15-fd0xxx (SSID 103c:8bb6) Speaker Mute LED fix + * + * The speaker mute LED is controlled via VREF100 on NID 0x1a. + * This pin must remain powered (D0) even during suspend, otherwise + * the LED state is lost and the pin defaults to Hi-Z on resume, + * causing the LED to stop responding to mute toggles. + * Windows keeps this pin powered unconditionally, so matching that + * behavior ensures consistent LED operation across suspend/resume. + * The mic-mute LED is controlled via GPIO 0 with active-low polarity. + */ +static unsigned int hp_8bb6_power_filter(struct hda_codec *codec, + hda_nid_t nid, + unsigned int power_state) +{ + if (nid == 0x1a) + return AC_PWRST_D0; + return snd_hda_gen_path_power_filter(codec, nid, power_state); +} + +static int hp_8bb6_speaker_mute_led_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct hda_codec *codec = dev_to_hda_codec(led_cdev->dev->parent); + unsigned int val = (brightness == LED_OFF) ? PIN_IN : PIN_VREF100; + + snd_hda_set_pin_ctl_cache(codec, 0x1a, val); + return 0; +} + +static void alc236_fixup_hp_15_fd0xxx(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + spec->micmute_led_polarity = 1; + alc_fixup_hp_gpio_led(codec, action, 0x00, 0x01); + + spec->mute_led_polarity = 0; + snd_hda_gen_add_mute_led_cdev(codec, hp_8bb6_speaker_mute_led_set); + + codec->power_filter = hp_8bb6_power_filter; + spec->no_shutup_pins = 1; + break; + + case HDA_FIXUP_ACT_INIT: + if (spec->gen.vmaster_mute.hook) + snd_hda_sync_vmaster_hook(&spec->gen.vmaster_mute); + break; + } +} + static void alc285_fixup_hp_gpio_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4089,6 +4144,7 @@ enum { ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, ALC225_FIXUP_S3_POP_NOISE, ALC700_FIXUP_INTEL_REFERENCE, + ALC700_FIXUP_INTEL_HADES_CANYON, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, ALC298_FIXUP_TPT470_DOCK_FIX, @@ -4152,6 +4208,7 @@ enum { ALC236_FIXUP_HP_GPIO_LED, ALC236_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, + ALC236_FIXUP_HP_15_FD0XXX, ALC236_FIXUP_LENOVO_INV_DMIC, ALC298_FIXUP_SAMSUNG_AMP, ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS, @@ -4297,6 +4354,7 @@ enum { ALC287_FIXUP_LENOVO_LEGION_AW88399, ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN_HEADSET, ALC285_LENOVO_DAC_RENAME, + ALC287_FIXUP_YOGA9_SPEAKER2_TO_DAC1, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -4333,6 +4391,19 @@ static void alc287_fixup_lenovo_yoga_book_9i(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +static void alc700_fixup_intel_hades_canyon(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + /* + * Windows may leave coef 0x1b bit 0x0400 cleared, causing broken + * analog playback after rebooting into Linux. Restore the bit + * during codec initialization. + */ + if (action == HDA_FIXUP_ACT_INIT) + alc_update_coef_idx(codec, 0x1b, 0x0400, 0x0400); +} + static const struct hda_fixup alc269_fixups[] = { [ALC298_FIXUP_RAZER_BLADE16_2025_PINS] = { .type = HDA_FIXUP_PINS, @@ -5411,6 +5482,10 @@ static const struct hda_fixup alc269_fixups[] = { {} } }, + [ALC700_FIXUP_INTEL_HADES_CANYON] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc700_fixup_intel_hades_canyon, + }, [ALC274_FIXUP_DELL_BIND_DACS] = { .type = HDA_FIXUP_FUNC, .v.func = alc274_fixup_bind_dacs, @@ -5913,6 +5988,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_mute_led_micmute_gpio, }, + [ALC236_FIXUP_HP_15_FD0XXX] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc236_fixup_hp_15_fd0xxx, + }, [ALC236_FIXUP_LENOVO_INV_DMIC] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_inv_dmic, @@ -7010,6 +7089,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_lenovo_dac_rename, }, + [ALC287_FIXUP_YOGA9_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC287_FIXUP_TXNW2781_I2C, + }, }; static const struct hda_quirk alc269_fixup_tbl[] = { @@ -7448,6 +7533,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bb3, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8bb4, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8bb6, "HP Laptop 15-fd0039nt", ALC236_FIXUP_HP_15_FD0XXX), SND_PCI_QUIRK(0x103c, 0x8bbe, "HP Victus 16-r0xxx (MB 8BBE)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bc8, "HP Victus 15-fa1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bcd, "HP Omen 16-xd0xxx", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT), @@ -8031,6 +8117,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3843, "Lenovo Yoga 9i / Yoga Book 9i", ALC287_FIXUP_LENOVO_YOGA_BOOK_9I), + SND_PCI_QUIRK(0x17aa, 0x3846, "Lenovo Yoga Pro 9 16IAH10", ALC287_FIXUP_YOGA9_SPEAKER2_TO_DAC1), /* Yoga Pro 7 14IMH9 shares PCI SSID 17aa:3847 with Legion 7 16ACHG6; * use codec SSID to distinguish them */ @@ -8044,14 +8131,15 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6), + SND_PCI_QUIRK(0x17aa, 0x3862, "Lenovo IdeaPad Slim 3 15ABR8", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3865, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3866, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x386a, "Lenovo Yoga 7 16IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x386e, "Yoga Pro 7 14ARP8", ALC285_FIXUP_YOGA_SPEAKER2_TO_DAC1), - HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ HDA_CODEC_QUIRK(0x17aa, 0x38a7, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ + HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), SND_PCI_QUIRK(0x17aa, 0x3874, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), @@ -8197,6 +8285,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x3031, "TongFang X6AR55xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3033, "TongFang X6SP45xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3034, "TongFang X6KK45xU", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x30ba, "TongFang XxAF5xxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -8230,6 +8319,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x2782, 0xa128, "Positivo N15RPE-S", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0xa212, "Lunnen Ground 14", ALC269VC_FIXUP_LUNNEN_GROUND_14), SND_PCI_QUIRK(0x7017, 0x2014, "Star Labs StarFighter", ALC233_FIXUP_STARLABS_STARFIGHTER), + SND_PCI_QUIRK(0x8086, 0x2073, "Intel NUC 8 Hades Canyon", + ALC700_FIXUP_INTEL_HADES_CANYON), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c index 7d1a357ed90d..d6bfd8fb20e6 100644 --- a/sound/pci/ice1712/ice1712.c +++ b/sound/pci/ice1712/ice1712.c @@ -2523,7 +2523,7 @@ static int snd_ice1712_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; - struct snd_card *card; + struct snd_card *card __free(snd_card_unref) = NULL; struct snd_ice1712 *ice; int pcm_dev = 0, err; const struct snd_ice1712_card_info * const *tbl, *c; @@ -2535,8 +2535,8 @@ static int snd_ice1712_probe(struct pci_dev *pci, return -ENOENT; } - err = snd_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE, - sizeof(*ice), &card); + err = snd_devm_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE, + sizeof(*ice), &card); if (err < 0) return err; ice = card->private_data; @@ -2640,6 +2640,7 @@ static int snd_ice1712_probe(struct pci_dev *pci, if (err < 0) return err; pci_set_drvdata(pci, card); + card = NULL; /* probe succeeded, don't release as error */ dev++; return 0; } diff --git a/sound/pci/pcxhr/pcxhr.c b/sound/pci/pcxhr/pcxhr.c index 25a640304430..60cc0721d0a6 100644 --- a/sound/pci/pcxhr/pcxhr.c +++ b/sound/pci/pcxhr/pcxhr.c @@ -1535,6 +1535,13 @@ static int pcxhr_probe(struct pci_dev *pci, mgr->pci = pci; mgr->irq = -1; + /* ISR lock */ + mutex_init(&mgr->lock); + mutex_init(&mgr->msg_lock); + + /* init setup mutex*/ + mutex_init(&mgr->setup_mutex); + if (request_threaded_irq(pci->irq, pcxhr_interrupt, pcxhr_threaded_irq, IRQF_SHARED, KBUILD_MODNAME, mgr)) { @@ -1548,13 +1555,6 @@ static int pcxhr_probe(struct pci_dev *pci, "Digigram at 0x%lx & 0x%lx, 0x%lx irq %i", mgr->port[0], mgr->port[1], mgr->port[2], mgr->irq); - /* ISR lock */ - mutex_init(&mgr->lock); - mutex_init(&mgr->msg_lock); - - /* init setup mutex*/ - mutex_init(&mgr->setup_mutex); - mgr->prmh = kmalloc(sizeof(*mgr->prmh) + sizeof(u32) * (PCXHR_SIZE_MAX_LONG_STATUS - PCXHR_SIZE_MAX_STATUS), diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c index 3021dc498c85..2d50be8190c1 100644 --- a/sound/soc/amd/acp-config.c +++ b/sound/soc/amd/acp-config.c @@ -54,7 +54,7 @@ static const struct dmi_system_id acp70_acpi_flag_override_table[] = { { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC"), - DMI_MATCH(DMI_PRODUCT_NAME, "TUF Gaming A14 FA401EA"), + DMI_MATCH(DMI_PRODUCT_NAME, "FA401EA"), }, }, { @@ -70,6 +70,13 @@ static const struct dmi_system_id acp70_acpi_flag_override_table[] = { DMI_MATCH(DMI_BOARD_NAME, "8EA1"), }, }, + { + /* HP OmniBook X Flip 16-cc0xxx */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8EA2"), + }, + }, {} }; @@ -209,6 +216,20 @@ static const struct config_entry config_table[] = { {} }, }, + { + .flags = FLAG_AMD_LEGACY, + .device = ACP_PCI_DEV_ID, + .dmi_table = (const struct dmi_system_id []) { + { + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1060"), + }, + }, + {} + }, + }, }; static int snd_amd_acp_acpi_find_config(struct pci_dev *pci) diff --git a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c index 46fff565d732..3a640e652314 100644 --- a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c +++ b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c @@ -382,6 +382,14 @@ static const struct dmi_system_id acp3x_es83xx_dmi_table[] = { }, .driver_data = (void *)(ES83XX_ENABLE_DMIC), }, + { + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1060"), + }, + .driver_data = (void *)(ES83XX_ENABLE_DMIC), + }, {} }; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 3f852393fc99..21d7ec0e7dbf 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -570,6 +570,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18 R1 AMD"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -843,6 +850,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7VE"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7UC"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/max98926.c b/sound/soc/codecs/max98926.c index 5305e1f9d97f..51a30c182167 100644 --- a/sound/soc/codecs/max98926.c +++ b/sound/soc/codecs/max98926.c @@ -360,7 +360,7 @@ static int max98926_dai_set_fmt(struct snd_soc_dai *codec_dai, regmap_write(max98926->regmap, MAX98926_FORMAT, MAX98926_DAI_DLY_MASK); regmap_update_bits(max98926->regmap, MAX98926_FORMAT, - MAX98926_DAI_BCI_MASK, invert); + MAX98926_DAI_BCI_MASK | MAX98926_DAI_WCI_MASK, invert); return 0; } diff --git a/sound/soc/codecs/rt712-sdca.c b/sound/soc/codecs/rt712-sdca.c index 2218f9918ae3..13574513b181 100644 --- a/sound/soc/codecs/rt712-sdca.c +++ b/sound/soc/codecs/rt712-sdca.c @@ -1779,6 +1779,7 @@ static void rt712_sdca_vb_io_init(struct rt712_sdca_priv *rt712) dev_dbg(dev, "%s jack/mic/amp func_status=0x%x, 0x%x, 0x%x\n", __func__, jack_func_status, mic_func_status, amp_func_status); + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, RT712_JD_CTL3, 0x7778); /* DMIC */ if ((mic_func_status & FUNCTION_NEEDS_INITIALIZATION) || (!rt712->first_hw_init)) { rt712_sdca_index_write(rt712, RT712_VENDOR_HDA_CTL, RT712_DMIC2_FU_IT_FLOAT_CTL, 0x1526); diff --git a/sound/soc/codecs/rt712-sdca.h b/sound/soc/codecs/rt712-sdca.h index 7ab7d5feb50a..46740281a5c1 100644 --- a/sound/soc/codecs/rt712-sdca.h +++ b/sound/soc/codecs/rt712-sdca.h @@ -74,6 +74,7 @@ struct rt712_dmic_kctrl_priv { #define RT712_JD_PRODUCT_NUM 0x00 #define RT712_ANALOG_BIAS_CTL3 0x04 #define RT712_JD_CTL1 0x09 +#define RT712_JD_CTL3 0x0b #define RT712_IO_CTL 0x0c #define RT712_LDO2_3_CTL1 0x0e #define RT712_PARA_VERB_CTL 0x1a diff --git a/sound/soc/codecs/rt766-sdca-sdw.c b/sound/soc/codecs/rt766-sdca-sdw.c index 5d60c3bcc6cd..8e76bf725ccc 100644 --- a/sound/soc/codecs/rt766-sdca-sdw.c +++ b/sound/soc/codecs/rt766-sdca-sdw.c @@ -233,6 +233,8 @@ static void rt766_sdca_sdw_remove(struct sdw_slave *slave) static const struct sdw_device_id rt766_sdca_id[] = { SDW_SLAVE_ENTRY_EXT(0x025d, 0x766, 0x3, 0x1, 0), SDW_SLAVE_ENTRY_EXT(0x025d, 0x767, 0x3, 0x1, 0), + SDW_SLAVE_ENTRY_EXT(0x025d, 0x766, 0x4, 0x1, 0), + SDW_SLAVE_ENTRY_EXT(0x025d, 0x767, 0x4, 0x1, 0), {}, }; MODULE_DEVICE_TABLE(sdw, rt766_sdca_id); diff --git a/sound/soc/codecs/tac5xx2-sdw.c b/sound/soc/codecs/tac5xx2-sdw.c index c062065a807d..a5f654cde69f 100644 --- a/sound/soc/codecs/tac5xx2-sdw.c +++ b/sound/soc/codecs/tac5xx2-sdw.c @@ -55,6 +55,12 @@ #define TAC_XU_BYPASS_REG(func, xu) \ SDW_SDCA_CTL(TAC_FUNCTION_ID_##func, TAC_SDCA_ENT_##xu, \ TAC_SDCA_CTL_XU_BYPASS, 0) +#define TAC_VOLUME_REG(func, fu, ch) \ + SDW_SDCA_CTL(TAC_FUNCTION_ID_##func, TAC_SDCA_ENT_##fu, \ + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_##ch) +#define TAC_GAIN_REG(func, fu, ch) \ + SDW_SDCA_CTL(TAC_FUNCTION_ID_##func, TAC_SDCA_ENT_##fu, \ + TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_##ch) /* mute registers */ #define FU21_L_MUTE_REG TAC_MUTE_REG(SA, FU21, LEFT) @@ -123,9 +129,9 @@ static const DECLARE_TLV_DB_SCALE(tac5xx2_dvc_tlv, -7200, 50, 0); #define TAC_DOUBLE_Q78_TLV(name, func_id, ent_id) \ SDCA_DOUBLE_Q78_TLV(name, \ SDW_SDCA_CTL(TAC_FUNCTION_ID_##func_id, TAC_SDCA_ENT_##ent_id, \ - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT), \ + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_LEFT), \ SDW_SDCA_CTL(TAC_FUNCTION_ID_##func_id, TAC_SDCA_ENT_##ent_id, \ - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT), \ + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT), \ TAC_DVC_MIN, TAC_DVC_MAX, TAC_DVC_STEP, tac5xx2_dvc_tlv) struct tac5xx2_prv { @@ -381,37 +387,53 @@ static const struct reg_default tac_reg_default[] = { {TAC_REG_SDW(0, 1, 0x71), 0x5}, {TAC_REG_SDW(0, 1, 0x72), 0x6}, {TAC_REG_SDW(0, 1, 0x73), 0x7}, + /* SA */ + {TAC_MUTE_REG(SA, FU21, LEFT), 0x1}, + {TAC_MUTE_REG(SA, FU21, RIGHT), 0x1}, + {TAC_VOLUME_REG(SA, FU21, LEFT), 0x9c00}, + {TAC_VOLUME_REG(SA, FU21, RIGHT), 0x9c00}, + {TAC_MUTE_REG(SA, FU23, LEFT), 0x1}, + {TAC_MUTE_REG(SA, FU23, RIGHT), 0x1}, + {TAC_GAIN_REG(SA, FU23, LEFT), 0x0}, + {TAC_GAIN_REG(SA, FU23, RIGHT), 0x0}, + /* SM */ + {TAC_USAGE_REG(SM, IT11), 0x0}, + {TAC_USAGE_REG(SM, OT113), 0x0}, + {TAC_MUTE_REG(SM, FU113, LEFT), 0x1}, + {TAC_MUTE_REG(SM, FU113, RIGHT), 0x1}, + {TAC_GAIN_REG(SM, FU113, LEFT), 0x0}, + {TAC_GAIN_REG(SM, FU113, RIGHT), 0x0}, + {TAC_MUTE_REG(SM, FU11, LEFT), 0x1}, + {TAC_MUTE_REG(SM, FU11, RIGHT), 0x1}, + {TAC_GAIN_REG(SM, FU11, LEFT), 0x0}, + {TAC_GAIN_REG(SM, FU11, RIGHT), 0x0}, + {TAC_XU_BYPASS_REG(SM, XU12), 0x1}, + {SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_CS113, + TAC_SDCA_CTL_CS_SAMP_RATE_IDX, 0), 0x0}, + /* UAJ */ + {TAC_USAGE_REG(UAJ, IT33), 0x0}, + {TAC_USAGE_REG(UAJ, IT41), 0x0}, + {TAC_USAGE_REG(UAJ, OT36), 0x0}, + {TAC_USAGE_REG(UAJ, OT45), 0x0}, + {TAC_MUTE_REG(UAJ, FU41, LEFT), 0x1}, + {TAC_MUTE_REG(UAJ, FU41, RIGHT), 0x1}, + {TAC_VOLUME_REG(UAJ, FU41, LEFT), 0x0}, + {TAC_VOLUME_REG(UAJ, FU41, RIGHT), 0x0}, + {TAC_MUTE_REG(UAJ, FU36, RIGHT), 0x1}, + {SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU36, + TAC_SDCA_CHANNEL_VOLUME, TAC_JACK_MONO_CS), 0x0}, + {TAC_XU_BYPASS_REG(UAJ, XU42), 0x0}, + {SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_CS36, + TAC_SDCA_CTL_CS_SAMP_RATE_IDX, 0), 0x0}, + {SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_CS41, + TAC_SDCA_CTL_CS_SAMP_RATE_IDX, 0), 0x0}, }; static const struct reg_sequence tac_spk_seq[] = { REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU21, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT), 0), + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_LEFT), 0), REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU21, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU23, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU23, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT), 0), -}; - -static const struct reg_sequence tac_sm_seq[] = { - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU113, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU113, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU11, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU11, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT), 0), -}; - -static const struct reg_sequence tac_uaj_seq[] = { - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU41, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU41, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT), 0), - REG_SEQ0(SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU36, - TAC_SDCA_CHANNEL_GAIN, TAC_JACK_MONO_CS), 0), + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT), 0), }; static bool tac_volatile_reg(struct device *dev, unsigned int reg) @@ -468,25 +490,25 @@ static int tac_sdca_mbq_size(struct device *dev, unsigned int reg) case SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU21, TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU23, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_LEFT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU23, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SA, TAC_SDCA_ENT_FU23, - TAC_SDCA_MASTER_GAIN, 0): + TAC_SDCA_CHANNEL_GAIN, 0): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU113, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_LEFT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU113, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU11, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_LEFT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_SM, TAC_SDCA_ENT_FU11, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU41, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_LEFT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_LEFT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU41, - TAC_SDCA_CHANNEL_GAIN, TAC_CHANNEL_RIGHT): + TAC_SDCA_CHANNEL_VOLUME, TAC_CHANNEL_RIGHT): case SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU36, - TAC_SDCA_CHANNEL_GAIN, TAC_JACK_MONO_CS): + TAC_SDCA_CHANNEL_VOLUME, TAC_JACK_MONO_CS): return 2; default: @@ -531,7 +553,7 @@ static const struct snd_kcontrol_new tac_uaj_controls[] = { TAC_DOUBLE_Q78_TLV("UAJ Playback Volume", UAJ, FU41), SDCA_SINGLE_Q78_TLV("UAJ Capture Volume", SDW_SDCA_CTL(TAC_FUNCTION_ID_UAJ, TAC_SDCA_ENT_FU36, - TAC_SDCA_CHANNEL_GAIN, TAC_JACK_MONO_CS), + TAC_SDCA_CHANNEL_VOLUME, TAC_JACK_MONO_CS), TAC_DVC_MIN, TAC_DVC_MAX, TAC_DVC_STEP, tac5xx2_dvc_tlv), }; @@ -1761,16 +1783,6 @@ static int tac_io_init(struct device *dev, struct sdw_slave *slave, bool first) goto io_init_err; } dev_dbg(dev, "smartmic init done\n"); - - if (first) { - ret = regmap_multi_reg_write(tac_dev->regmap, tac_sm_seq, - ARRAY_SIZE(tac_sm_seq)); - if (ret) { - dev_err(tac_dev->dev, - "init writes failed, err=%d", ret); - goto io_init_err; - } - } } if (tac_dev->uaj_func_data) { @@ -1783,14 +1795,6 @@ static int tac_io_init(struct device *dev, struct sdw_slave *slave, bool first) dev_dbg(dev, "uaj init done\n"); if (first) { - ret = regmap_multi_reg_write(tac_dev->regmap, tac_uaj_seq, - ARRAY_SIZE(tac_uaj_seq)); - if (ret) { - dev_err(tac_dev->dev, - "init writes failed, err=%d", ret); - goto io_init_err; - } - if (tac_dev->hs_jack) { ret = tac5xx2_jack_init(tac_dev); if (ret) { diff --git a/sound/soc/codecs/tac5xx2.h b/sound/soc/codecs/tac5xx2.h index eed8e6cf3498..a84c5ca515a7 100644 --- a/sound/soc/codecs/tac5xx2.h +++ b/sound/soc/codecs/tac5xx2.h @@ -174,14 +174,13 @@ #define TAC_SDCA_ENT_SAPU29 0x35 /* Control selector definitions */ -#define TAC_SDCA_MASTER_GAIN 0x0B #define TAC_SDCA_MASTER_MUTE 0x01 #define TAC_SDCA_CHANNEL_MUTE 0x01 -#define TAC_SDCA_CHANNEL_GAIN 0x02 +#define TAC_SDCA_CHANNEL_VOLUME 0x02 #define TAC_SDCA_POSTURENUMBER 0x10 #define TAC_SDCA_REQUESTED_PS 0x01 #define TAC_SDCA_ACTUAL_PS 0x10 -#define TAC_SDCA_CHANNEL_VOLUME 0x02 +#define TAC_SDCA_CHANNEL_GAIN 0x0B /* 2. smart mic function */ #define TAC_FUNCTION_ID_SM 0x2 diff --git a/sound/soc/codecs/tas2783-sdw.c b/sound/soc/codecs/tas2783-sdw.c index caf8fe1bf4db..eaebb0ebbe0d 100644 --- a/sound/soc/codecs/tas2783-sdw.c +++ b/sound/soc/codecs/tas2783-sdw.c @@ -1310,6 +1310,7 @@ static int tas_port_prep(struct sdw_slave *slave, struct sdw_prepare_ch *prep_ch enum sdw_port_prep_ops pre_ops) { struct device *dev = &slave->dev; + struct tas2783_prv *tas_dev = dev_get_drvdata(dev); struct sdw_dpn_prop *dpn_prop; u32 addr; int ret; @@ -1321,6 +1322,25 @@ static int tas_port_prep(struct sdw_slave *slave, struct sdw_prepare_ch *prep_ch addr = SDW_DPN_PREPARECTRL(prep_ch->num); switch (pre_ops) { case SDW_OPS_PORT_PRE_PREP: + /* + * The Function has to be powered before the port can complete + * channel preparation. hw_params() does that when a stream is + * set up, but a stream that is only re-prepared - as it is + * after the peripheral lost power in S0i3 - does not go + * through hw_params() again, and the peripheral is back at its + * PS3 reset default. Power it up here, where it is needed. + */ + scoped_guard(mutex, &tas_dev->pde_lock) + ret = regmap_write(tas_dev->regmap, + SDW_SDCA_CTL(1, TAS2783_SDCA_ENT_PDE23, + TAS2783_SDCA_CTL_REQ_POW_STATE, 0), + TAS2783_SDCA_POW_STATE_ON); + if (ret) { + dev_err(dev, "power up failed for port %d, err=%d\n", + prep_ch->num, ret); + return ret; + } + ret = sdw_write_no_pm(slave, addr, prep_ch->ch_mask); if (ret) dev_err(dev, "prep failed for port %d, err=%d\n", diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 8ae59c094878..04940879dfd8 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -244,7 +244,7 @@ config SND_SOC_MPC5200_AC97 config SND_MPC52xx_SOC_PCM030 tristate "SoC AC97 Audio support for Phytec pcm030 and WM9712" depends on PPC_MPC5200_SIMPLE - select SND_SOC_MPC5200_AC97 + depends on SND_SOC_MPC5200_AC97 select SND_SOC_WM9712 help Say Y if you want to add support for sound on the Phytec pcm030 @@ -253,7 +253,7 @@ config SND_MPC52xx_SOC_PCM030 config SND_MPC52xx_SOC_EFIKA tristate "SoC AC97 Audio support for bbplan Efika and STAC9766" depends on PPC_EFIKA - select SND_SOC_MPC5200_AC97 + depends on SND_SOC_MPC5200_AC97 select SND_SOC_STAC9766 help Say Y if you want to add support for sound on the Efika. diff --git a/sound/soc/fsl/efika-audio-fabric.c b/sound/soc/fsl/efika-audio-fabric.c index 4d3266d9cbb7..e9c728bae8b9 100644 --- a/sound/soc/fsl/efika-audio-fabric.c +++ b/sound/soc/fsl/efika-audio-fabric.c @@ -22,8 +22,6 @@ #include #include -#include "mpc5200_dma.h" - #define DRV_NAME "efika-audio-fabric" SND_SOC_DAILINK_DEFS(analog, diff --git a/sound/soc/fsl/pcm030-audio-fabric.c b/sound/soc/fsl/pcm030-audio-fabric.c index 5542c4ee6d12..a7a5dba83a2f 100644 --- a/sound/soc/fsl/pcm030-audio-fabric.c +++ b/sound/soc/fsl/pcm030-audio-fabric.c @@ -13,8 +13,6 @@ #include -#include "mpc5200_dma.h" - #define DRV_NAME "pcm030-audio-fabric" struct pcm030_audio_data { diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c index 25cd12eab4b1..6422cc1703b6 100644 --- a/sound/soc/loongson/loongson_card.c +++ b/sound/soc/loongson/loongson_card.c @@ -55,8 +55,8 @@ static const struct loongson_card_config ls2k0300_dl2k0300b_card_config = { .add_dapm_routes = true, }; -static int tegra_machine_event(struct snd_soc_dapm_widget *w, - struct snd_kcontrol *k, int event) +static int loongson_asoc_machine_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *k, int event) { struct snd_soc_card *card = snd_soc_dapm_to_card(w->dapm); struct loongson_card_data *priv = snd_soc_card_get_drvdata(card); @@ -72,9 +72,9 @@ static int tegra_machine_event(struct snd_soc_dapm_widget *w, return 0; } -static const struct snd_soc_dapm_widget loongson_aosc_dapm_widgets[] = { - SND_SOC_DAPM_HP("Headphone", tegra_machine_event), - SND_SOC_DAPM_SPK("Speaker", tegra_machine_event), +static const struct snd_soc_dapm_widget loongson_asoc_dapm_widgets[] = { + SND_SOC_DAPM_HP("Headphone", loongson_asoc_machine_event), + SND_SOC_DAPM_SPK("Speaker", loongson_asoc_machine_event), }; /* Headphones Jack */ @@ -314,8 +314,8 @@ static int loongson_asoc_card_probe(struct platform_device *pdev) card->num_links = ARRAY_SIZE(loongson_dai_links); if (ls_priv->cfg->add_dapm_widgets) { - card->dapm_widgets = loongson_aosc_dapm_widgets; - card->num_dapm_widgets = ARRAY_SIZE(loongson_aosc_dapm_widgets); + card->dapm_widgets = loongson_asoc_dapm_widgets; + card->num_dapm_widgets = ARRAY_SIZE(loongson_asoc_dapm_widgets); } snd_soc_card_set_drvdata(card, ls_priv); diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index d231024206db..d9f256d51973 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -103,14 +103,14 @@ static int qcom_snd_parse_dai_tdm_slots(struct snd_soc_pcm_runtime *rtd, int ret; if (!link_np) - return -EINVAL; + return -ENOENT; struct device_node *cpu_np __free(device_node) = of_get_child_by_name(link_np, "cpu"); struct device_node *codec_np __free(device_node) = of_get_child_by_name(link_np, "codec"); if (!cpu_np || !codec_np) - return -EINVAL; + return -ENOENT; ret = qcom_snd_parse_tdm_slot(cpu_np, cpu_cfg); if (ret) @@ -172,7 +172,7 @@ int qcom_snd_apply_dai_tdm_slots(struct snd_soc_pcm_runtime *rtd) ret = qcom_snd_get_dai_tdm_slots(rtd, &cpu_cfg, &codec_cfg); if (ret) - return ret == -EINVAL ? 0 : ret; + return ret == -ENOENT ? 0 : ret; return qcom_snd_apply_dai_tdm_slots_cfg(rtd, &cpu_cfg, &codec_cfg); } diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c index bf1f872a09f4..033197bdd870 100644 --- a/sound/soc/qcom/qdsp6/q6apm-dai.c +++ b/sound/soc/qcom/qdsp6/q6apm-dai.c @@ -216,7 +216,7 @@ static int q6apm_dai_prepare(struct snd_soc_component *component, { struct snd_pcm_runtime *runtime = substream->runtime; struct q6apm_dai_rtd *prtd = runtime->private_data; - struct audioreach_module_config cfg; + struct audioreach_module_config cfg = {}; struct device *dev = component->dev; struct q6apm_dai_data *pdata; int ret; @@ -814,7 +814,7 @@ static int q6apm_dai_compr_set_params(struct snd_soc_component *component, struct snd_compr_runtime *runtime = stream->runtime; struct q6apm_dai_rtd *prtd = runtime->private_data; struct q6apm_dai_data *pdata; - struct audioreach_module_config cfg; + struct audioreach_module_config cfg = {}; struct snd_codec *codec = ¶ms->codec; int dir = stream->direction; int ret; diff --git a/sound/soc/qcom/qdsp6/q6prm-clocks.c b/sound/soc/qcom/qdsp6/q6prm-clocks.c index f613e2aee75e..b4f9abbe02cb 100644 --- a/sound/soc/qcom/qdsp6/q6prm-clocks.c +++ b/sound/soc/qcom/qdsp6/q6prm-clocks.c @@ -64,34 +64,34 @@ static const struct q6dsp_clk_init q6prm_clks[] = { Q6PRM_CLK(LPASS_CLK_ID_WSA2_CORE_TX_MCLK), Q6PRM_CLK(LPASS_CLK_ID_WSA2_CORE_TX_2X_MCLK), Q6PRM_CLK(LPASS_CLK_ID_RX_CORE_MCLK2_2X_MCLK), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF0_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF0_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF1_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF1_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF2_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF2_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF3_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF3_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF4_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF4_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF5_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF5_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF6_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF6_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF7_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF7_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF8_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF8_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF9_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF9_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF10_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF10_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF11_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF11_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF12_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_QAIF_IF12_EBIT), - Q6PRM_CLK(LAPSS_CLK_ID_VA_QAIF_IF0_IBIT), - Q6PRM_CLK(LAPSS_CLK_ID_VA_QAIF_IF0_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF0_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF0_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF1_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF1_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF2_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF2_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF3_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF3_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF4_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF4_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF5_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF5_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF6_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF6_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF7_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF7_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF8_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF8_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF9_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF9_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF10_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF10_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF11_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF11_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF12_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_QAIF_IF12_EBIT), + Q6PRM_CLK(LPASS_CLK_ID_VA_QAIF_IF0_IBIT), + Q6PRM_CLK(LPASS_CLK_ID_VA_QAIF_IF0_EBIT), Q6DSP_VOTE_CLK(LPASS_HW_MACRO_VOTE, Q6PRM_HW_CORE_ID_LPASS, "LPASS_HW_MACRO"), Q6DSP_VOTE_CLK(LPASS_HW_DCODEC_VOTE, Q6PRM_HW_CORE_ID_DCODEC, diff --git a/sound/soc/qcom/qdsp6/q6prm.h b/sound/soc/qcom/qdsp6/q6prm.h index cca77cd92bc1..cf619ef6561a 100644 --- a/sound/soc/qcom/qdsp6/q6prm.h +++ b/sound/soc/qcom/qdsp6/q6prm.h @@ -97,34 +97,34 @@ /* Clock ID for RX CORE MCLK2 2X MCLK */ #define Q6PRM_LPASS_CLK_ID_RX_CORE_MCLK2_2X_MCLK 0x318 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF0_IBIT 0x500 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF0_EBIT 0x501 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF1_IBIT 0x502 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF1_EBIT 0x503 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF2_IBIT 0x504 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF2_EBIT 0x505 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF3_IBIT 0x506 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF3_EBIT 0x507 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF4_IBIT 0x508 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF4_EBIT 0x509 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF5_IBIT 0x50A -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF5_EBIT 0x50B -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF6_IBIT 0x50C -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF6_EBIT 0x50D -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF7_IBIT 0x50E -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF7_EBIT 0x50F -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF8_IBIT 0x510 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF8_EBIT 0x511 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF9_IBIT 0x512 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF9_EBIT 0x513 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF10_IBIT 0x514 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF10_EBIT 0x515 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF11_IBIT 0x516 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF11_EBIT 0x517 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF12_IBIT 0x518 -#define Q6PRM_LAPSS_CLK_ID_QAIF_IF12_EBIT 0x519 -#define Q6PRM_LAPSS_CLK_ID_VA_QAIF_IF0_IBIT 0x550 -#define Q6PRM_LAPSS_CLK_ID_VA_QAIF_IF0_EBIT 0x551 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF0_IBIT 0x500 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF0_EBIT 0x501 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF1_IBIT 0x502 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF1_EBIT 0x503 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF2_IBIT 0x504 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF2_EBIT 0x505 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF3_IBIT 0x506 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF3_EBIT 0x507 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF4_IBIT 0x508 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF4_EBIT 0x509 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF5_IBIT 0x50A +#define Q6PRM_LPASS_CLK_ID_QAIF_IF5_EBIT 0x50B +#define Q6PRM_LPASS_CLK_ID_QAIF_IF6_IBIT 0x50C +#define Q6PRM_LPASS_CLK_ID_QAIF_IF6_EBIT 0x50D +#define Q6PRM_LPASS_CLK_ID_QAIF_IF7_IBIT 0x50E +#define Q6PRM_LPASS_CLK_ID_QAIF_IF7_EBIT 0x50F +#define Q6PRM_LPASS_CLK_ID_QAIF_IF8_IBIT 0x510 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF8_EBIT 0x511 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF9_IBIT 0x512 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF9_EBIT 0x513 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF10_IBIT 0x514 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF10_EBIT 0x515 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF11_IBIT 0x516 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF11_EBIT 0x517 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF12_IBIT 0x518 +#define Q6PRM_LPASS_CLK_ID_QAIF_IF12_EBIT 0x519 +#define Q6PRM_LPASS_CLK_ID_VA_QAIF_IF0_IBIT 0x550 +#define Q6PRM_LPASS_CLK_ID_VA_QAIF_IF0_EBIT 0x551 #define Q6PRM_LPASS_CLK_SRC_INTERNAL 1 #define Q6PRM_LPASS_CLK_ROOT_DEFAULT 0 diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c index 1322601659d4..4d48e1012cd4 100644 --- a/sound/soc/qcom/sc8280xp.c +++ b/sound/soc/qcom/sc8280xp.c @@ -115,33 +115,42 @@ static int sc8280xp_tdm_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *codec_dai; struct qcom_snd_tdm_slot_cfg cpu_cfg; struct qcom_snd_tdm_slot_cfg codec_cfg; - unsigned int bclk_freq; + int bclk_freq; int ret; int i; ret = qcom_snd_get_dai_tdm_slots(rtd, &cpu_cfg, &codec_cfg); if (ret) - return ret == -EINVAL ? 0 : ret; + return ret == -ENOENT ? 0 : ret; if (!cpu_cfg.slots) return 0; ret = snd_soc_dai_set_fmt(cpu_dai, SND_SOC_DAIFMT_BP_FP); - if (ret) + if (ret && ret != -ENOTSUPP) return ret; + if (data->priv->codec_dai_fmt) { + for_each_rtd_codec_dais(rtd, i, codec_dai) { + ret = snd_soc_dai_set_fmt(codec_dai, + data->priv->codec_dai_fmt); + if (ret && ret != -ENOTSUPP) + return ret; + } + } + ret = qcom_snd_apply_dai_tdm_slots_cfg(rtd, &cpu_cfg, &codec_cfg); if (ret) return ret; bclk_freq = snd_soc_tdm_params_to_bclk(params, cpu_cfg.slot_width, cpu_cfg.slots, 1); - if (!bclk_freq) + if (bclk_freq <= 0) return -EINVAL; if (data->priv->mi2s_bclk_enable) { ret = snd_soc_dai_set_sysclk(cpu_dai, LPAIF_MI2S_BCLK, bclk_freq, SND_SOC_CLOCK_IN); - if (ret) { + if (ret && ret != -ENOTSUPP) { dev_err(rtd->dev, "%s: failed to set cpu sysclk: %d\n", __func__, ret); return ret; @@ -152,7 +161,7 @@ static int sc8280xp_tdm_hw_params(struct snd_pcm_substream *substream, for_each_rtd_codec_dais(rtd, i, codec_dai) { ret = snd_soc_dai_set_sysclk(codec_dai, 0, bclk_freq, SND_SOC_CLOCK_IN); - if (ret) { + if (ret && ret != -ENOTSUPP) { dev_err(rtd->dev, "%s: failed to set codec sysclk on %s: %d\n", __func__, codec_dai->name, ret); return ret; diff --git a/sound/soc/sdw_utils/soc_sdw_rt_amp.c b/sound/soc/sdw_utils/soc_sdw_rt_amp.c index 4e9b08cb653d..81d2cbac0ea3 100644 --- a/sound/soc/sdw_utils/soc_sdw_rt_amp.c +++ b/sound/soc/sdw_utils/soc_sdw_rt_amp.c @@ -252,11 +252,13 @@ int asoc_sdw_rt_amp_exit(struct snd_soc_card *card, struct snd_soc_dai_link *dai if (ctx->amp_dev1) { device_remove_software_node(ctx->amp_dev1); put_device(ctx->amp_dev1); + ctx->amp_dev1 = NULL; } if (ctx->amp_dev2) { device_remove_software_node(ctx->amp_dev2); put_device(ctx->amp_dev2); + ctx->amp_dev2 = NULL; } return 0; diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index 8a07ba2a29e5..a66dcc02fb59 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -81,6 +81,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* speaker */ .direction = {true, false}, .dai_name = "tac5xx2-aif1", + .component_name = "tac5572", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_AMP_OUT_DAI_ID, SOC_SDW_UNUSED_DAI_ID}, .init = asoc_sdw_ti_amp_init, @@ -94,6 +95,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* mic */ .direction = {false, true}, .dai_name = "tac5xx2-aif2", + .component_name = "tac5572", .dai_type = SOC_SDW_DAI_TYPE_MIC, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_DMIC_DAI_ID}, .rtd_init = asoc_sdw_ti_dmic_rtd_init, @@ -102,6 +104,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* UAJ */ .direction = {true, true}, .dai_name = "tac5xx2-aif3", + .component_name = "tac5572", .dai_type = SOC_SDW_DAI_TYPE_JACK, .dailink = {SOC_SDW_JACK_OUT_DAI_ID, SOC_SDW_JACK_IN_DAI_ID}, .controls = generic_jack_controls, @@ -122,6 +125,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* speaker with IV sense feedback */ .direction = {true, true}, .dai_name = "tac5xx2-aif1", + .component_name = "tac5672", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_AMP_OUT_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, .init = asoc_sdw_ti_amp_init, @@ -135,6 +139,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* mic */ .direction = {false, true}, .dai_name = "tac5xx2-aif2", + .component_name = "tac5672", .dai_type = SOC_SDW_DAI_TYPE_MIC, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_DMIC_DAI_ID}, .rtd_init = asoc_sdw_ti_dmic_rtd_init, @@ -143,6 +148,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* UAJ */ .direction = {true, true}, .dai_name = "tac5xx2-aif3", + .component_name = "tac5672", .dai_type = SOC_SDW_DAI_TYPE_JACK, .dailink = {SOC_SDW_JACK_OUT_DAI_ID, SOC_SDW_JACK_IN_DAI_ID}, .controls = generic_jack_controls, @@ -163,6 +169,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* speaker with echo reference feedback */ .direction = {true, true}, .dai_name = "tac5xx2-aif1", + .component_name = "tac5682", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_AMP_OUT_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, .init = asoc_sdw_ti_amp_init, @@ -176,6 +183,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* mic */ .direction = {false, true}, .dai_name = "tac5xx2-aif2", + .component_name = "tac5682", .dai_type = SOC_SDW_DAI_TYPE_MIC, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_DMIC_DAI_ID}, .rtd_init = asoc_sdw_ti_dmic_rtd_init, @@ -184,6 +192,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* UAJ */ .direction = {true, true}, .dai_name = "tac5xx2-aif3", + .component_name = "tac5682", .dai_type = SOC_SDW_DAI_TYPE_JACK, .dailink = {SOC_SDW_JACK_OUT_DAI_ID, SOC_SDW_JACK_IN_DAI_ID}, .controls = generic_jack_controls, @@ -203,6 +212,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { { .direction = {true, false}, .dai_name = "tac5xx2-aif1", + .component_name = "tas2883", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_AMP_OUT_DAI_ID, SOC_SDW_UNUSED_DAI_ID}, .init = asoc_sdw_ti_amp_init, @@ -216,6 +226,7 @@ struct asoc_sdw_codec_info codec_info_list[] = { /* mic */ .direction = {false, true}, .dai_name = "tac5xx2-aif2", + .component_name = "tas2883", .dai_type = SOC_SDW_DAI_TYPE_MIC, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_DMIC_DAI_ID}, .rtd_init = asoc_sdw_ti_dmic_rtd_init, @@ -1510,9 +1521,24 @@ int asoc_sdw_trigger(struct snd_pcm_substream *substream, int cmd) } switch (cmd) { + case SNDRV_PCM_TRIGGER_RESUME: + /* + * The peripherals lose their port configuration when the + * controller is power-gated during system suspend, and an + * application that restarts the stream with + * SNDRV_PCM_IOCTL_RESUME - which platforms advertising + * SNDRV_PCM_INFO_RESUME allow - never goes through + * .prepare() again. Prepare the stream here so that the + * ports are reprogrammed before they are enabled; + * sdw_prepare_stream() reapplies the parameters without + * recomputing them when the stream is disabled. + */ + ret = sdw_prepare_stream(sdw_stream); + if (ret) + break; + fallthrough; case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - case SNDRV_PCM_TRIGGER_RESUME: ret = sdw_enable_stream(sdw_stream); break; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index c98e917cc911..06b85313af12 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3614,7 +3614,7 @@ int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, val = snd_soc_enum_item_to_val(e, item[0]) << e->shift_l; mask = e->mask << e->shift_l; if (e->shift_l != e->shift_r) { - if (item[1] > e->items) + if (item[1] >= e->items) return -EINVAL; val |= snd_soc_enum_item_to_val(e, item[1]) << e->shift_r; mask |= e->mask << e->shift_r; diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index 3b18d90e81c3..65b7ec52a054 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -397,24 +397,8 @@ static int dmaengine_pcm_request_chan_of(struct dmaengine_pcm *pcm, if (PTR_ERR(chan) == -EPROBE_DEFER) return -EPROBE_DEFER; - bool has_fw_node = dev->of_node || is_acpi_device_node(dev->fwnode); - bool name_exists_in_fw = false; - - if (has_fw_node) - name_exists_in_fw = device_property_match_string(dev, - "dma-names", - name) >= 0; - - if (has_fw_node && name_exists_in_fw) - dev_warn(dev, "DTS/ACPI DMA channel '%s' request failed (%ld)\n", - name, PTR_ERR(chan)); - - if (has_fw_node && !name_exists_in_fw) - dev_warn(dev, "DTS/ACPI name '%s' not found, legacy failed (%ld)\n", - name, PTR_ERR(chan)); - - if (!has_fw_node) - dev_warn(dev, "Legacy DMA channel '%s' request failed (%ld)\n", + if (device_property_match_string(dev, "dma-names", name) >= 0) + dev_warn(dev, "dma-names has '%s' but request failed (%ld)\n", name, PTR_ERR(chan)); pcm->chan[i] = NULL; diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c index 7299c6bfcf15..87e898cc35e4 100644 --- a/sound/soc/tegra/tegra210_admaif.c +++ b/sound/soc/tegra/tegra210_admaif.c @@ -26,94 +26,162 @@ #define CH_RX_REG(reg, id) CH_REG(admaif->soc_data->rx_base, reg, id) -#define REG_DEFAULTS(id, rx_ctrl, tx_ctrl, tx_base, rx_base, cif_ctrl) \ +#define RX_REG_DEFAULTS(id, rx_ctrl, rx_base, cif_ctrl) \ { CH_REG(rx_base, TEGRA_ADMAIF_RX_INT_MASK, id), 0x00000001 }, \ { CH_REG(rx_base, TEGRA_ADMAIF_CH_ACIF_RX_CTRL, id), cif_ctrl }, \ - { CH_REG(rx_base, TEGRA_ADMAIF_RX_FIFO_CTRL, id), rx_ctrl }, \ + { CH_REG(rx_base, TEGRA_ADMAIF_RX_FIFO_CTRL, id), rx_ctrl } + +#define TX_REG_DEFAULTS(id, tx_ctrl, tx_base, cif_ctrl) \ { CH_REG(tx_base, TEGRA_ADMAIF_TX_INT_MASK, id), 0x00000001 }, \ { CH_REG(tx_base, TEGRA_ADMAIF_CH_ACIF_TX_CTRL, id), cif_ctrl }, \ { CH_REG(tx_base, TEGRA_ADMAIF_TX_FIFO_CTRL, id), tx_ctrl } -#define ADMAIF_REG_DEFAULTS(id, chip) \ - REG_DEFAULTS((id) - 1, \ +#define ADMAIF_RX_REG_DEFAULTS(id, chip) \ + RX_REG_DEFAULTS((id) - 1, \ chip ## _ADMAIF_RX ## id ## _FIFO_CTRL_REG_DEFAULT, \ - chip ## _ADMAIF_TX ## id ## _FIFO_CTRL_REG_DEFAULT, \ - chip ## _ADMAIF_TX_BASE, \ chip ## _ADMAIF_RX_BASE, \ chip ## _ADMAIF_CIF_REG_DEFAULT) +#define ADMAIF_TX_REG_DEFAULTS(id, chip) \ + TX_REG_DEFAULTS((id) - 1, \ + chip ## _ADMAIF_TX ## id ## _FIFO_CTRL_REG_DEFAULT, \ + chip ## _ADMAIF_TX_BASE, \ + chip ## _ADMAIF_CIF_REG_DEFAULT) + static const struct reg_default tegra186_admaif_reg_defaults[] = { - {(TEGRA_ADMAIF_GLOBAL_CG_0 + TEGRA186_ADMAIF_GLOBAL_BASE), 0x00000003}, - ADMAIF_REG_DEFAULTS(1, TEGRA186), - ADMAIF_REG_DEFAULTS(2, TEGRA186), - ADMAIF_REG_DEFAULTS(3, TEGRA186), - ADMAIF_REG_DEFAULTS(4, TEGRA186), - ADMAIF_REG_DEFAULTS(5, TEGRA186), - ADMAIF_REG_DEFAULTS(6, TEGRA186), - ADMAIF_REG_DEFAULTS(7, TEGRA186), - ADMAIF_REG_DEFAULTS(8, TEGRA186), - ADMAIF_REG_DEFAULTS(9, TEGRA186), - ADMAIF_REG_DEFAULTS(10, TEGRA186), - ADMAIF_REG_DEFAULTS(11, TEGRA186), - ADMAIF_REG_DEFAULTS(12, TEGRA186), - ADMAIF_REG_DEFAULTS(13, TEGRA186), - ADMAIF_REG_DEFAULTS(14, TEGRA186), - ADMAIF_REG_DEFAULTS(15, TEGRA186), - ADMAIF_REG_DEFAULTS(16, TEGRA186), - ADMAIF_REG_DEFAULTS(17, TEGRA186), - ADMAIF_REG_DEFAULTS(18, TEGRA186), - ADMAIF_REG_DEFAULTS(19, TEGRA186), - ADMAIF_REG_DEFAULTS(20, TEGRA186) + ADMAIF_RX_REG_DEFAULTS(1, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(2, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(3, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(4, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(5, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(6, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(7, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(8, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(9, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(10, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(11, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(12, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(13, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(14, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(15, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(16, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(17, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(18, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(19, TEGRA186), + ADMAIF_RX_REG_DEFAULTS(20, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(1, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(2, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(3, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(4, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(5, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(6, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(7, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(8, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(9, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(10, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(11, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(12, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(13, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(14, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(15, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(16, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(17, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(18, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(19, TEGRA186), + ADMAIF_TX_REG_DEFAULTS(20, TEGRA186), + {(TEGRA_ADMAIF_GLOBAL_CG_0 + TEGRA186_ADMAIF_GLOBAL_BASE), 0x00000003} }; static const struct reg_default tegra210_admaif_reg_defaults[] = { - {(TEGRA_ADMAIF_GLOBAL_CG_0 + TEGRA210_ADMAIF_GLOBAL_BASE), 0x00000003}, - ADMAIF_REG_DEFAULTS(1, TEGRA210), - ADMAIF_REG_DEFAULTS(2, TEGRA210), - ADMAIF_REG_DEFAULTS(3, TEGRA210), - ADMAIF_REG_DEFAULTS(4, TEGRA210), - ADMAIF_REG_DEFAULTS(5, TEGRA210), - ADMAIF_REG_DEFAULTS(6, TEGRA210), - ADMAIF_REG_DEFAULTS(7, TEGRA210), - ADMAIF_REG_DEFAULTS(8, TEGRA210), - ADMAIF_REG_DEFAULTS(9, TEGRA210), - ADMAIF_REG_DEFAULTS(10, TEGRA210) + ADMAIF_RX_REG_DEFAULTS(1, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(2, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(3, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(4, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(5, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(6, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(7, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(8, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(9, TEGRA210), + ADMAIF_RX_REG_DEFAULTS(10, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(1, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(2, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(3, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(4, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(5, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(6, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(7, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(8, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(9, TEGRA210), + ADMAIF_TX_REG_DEFAULTS(10, TEGRA210), + {(TEGRA_ADMAIF_GLOBAL_CG_0 + TEGRA210_ADMAIF_GLOBAL_BASE), 0x00000003} }; static const struct reg_default tegra264_admaif_reg_defaults[] = { - {(TEGRA_ADMAIF_GLOBAL_CG_0 + TEGRA264_ADMAIF_GLOBAL_BASE), 0x00000003}, - ADMAIF_REG_DEFAULTS(1, TEGRA264), - ADMAIF_REG_DEFAULTS(2, TEGRA264), - ADMAIF_REG_DEFAULTS(3, TEGRA264), - ADMAIF_REG_DEFAULTS(4, TEGRA264), - ADMAIF_REG_DEFAULTS(5, TEGRA264), - ADMAIF_REG_DEFAULTS(6, TEGRA264), - ADMAIF_REG_DEFAULTS(7, TEGRA264), - ADMAIF_REG_DEFAULTS(8, TEGRA264), - ADMAIF_REG_DEFAULTS(9, TEGRA264), - ADMAIF_REG_DEFAULTS(10, TEGRA264), - ADMAIF_REG_DEFAULTS(11, TEGRA264), - ADMAIF_REG_DEFAULTS(12, TEGRA264), - ADMAIF_REG_DEFAULTS(13, TEGRA264), - ADMAIF_REG_DEFAULTS(14, TEGRA264), - ADMAIF_REG_DEFAULTS(15, TEGRA264), - ADMAIF_REG_DEFAULTS(16, TEGRA264), - ADMAIF_REG_DEFAULTS(17, TEGRA264), - ADMAIF_REG_DEFAULTS(18, TEGRA264), - ADMAIF_REG_DEFAULTS(19, TEGRA264), - ADMAIF_REG_DEFAULTS(20, TEGRA264), - ADMAIF_REG_DEFAULTS(21, TEGRA264), - ADMAIF_REG_DEFAULTS(22, TEGRA264), - ADMAIF_REG_DEFAULTS(23, TEGRA264), - ADMAIF_REG_DEFAULTS(24, TEGRA264), - ADMAIF_REG_DEFAULTS(25, TEGRA264), - ADMAIF_REG_DEFAULTS(26, TEGRA264), - ADMAIF_REG_DEFAULTS(27, TEGRA264), - ADMAIF_REG_DEFAULTS(28, TEGRA264), - ADMAIF_REG_DEFAULTS(29, TEGRA264), - ADMAIF_REG_DEFAULTS(30, TEGRA264), - ADMAIF_REG_DEFAULTS(31, TEGRA264), - ADMAIF_REG_DEFAULTS(32, TEGRA264) + ADMAIF_RX_REG_DEFAULTS(1, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(2, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(3, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(4, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(5, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(6, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(7, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(8, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(9, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(10, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(11, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(12, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(13, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(14, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(15, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(16, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(17, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(18, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(19, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(20, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(21, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(22, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(23, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(24, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(25, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(26, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(27, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(28, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(29, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(30, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(31, TEGRA264), + ADMAIF_RX_REG_DEFAULTS(32, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(1, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(2, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(3, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(4, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(5, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(6, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(7, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(8, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(9, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(10, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(11, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(12, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(13, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(14, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(15, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(16, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(17, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(18, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(19, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(20, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(21, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(22, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(23, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(24, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(25, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(26, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(27, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(28, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(29, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(30, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(31, TEGRA264), + ADMAIF_TX_REG_DEFAULTS(32, TEGRA264), + {(TEGRA_ADMAIF_GLOBAL_CG_0 + TEGRA264_ADMAIF_GLOBAL_BASE), 0x00000003} }; static bool tegra_admaif_wr_reg(struct device *dev, unsigned int reg) diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c index 84506576437d..79a2f898ea28 100644 --- a/sound/soc/tegra/tegra210_i2s.c +++ b/sound/soc/tegra/tegra210_i2s.c @@ -23,7 +23,7 @@ static const struct reg_default tegra210_i2s_reg_defaults[] = { { TEGRA210_I2S_RX_CIF_CTRL, 0x00007700 }, { TEGRA210_I2S_TX_INT_MASK, 0x00000003 }, { TEGRA210_I2S_TX_CIF_CTRL, 0x00007700 }, - { TEGRA210_I2S_ENABLE, 0x1 }, + { TEGRA210_I2S_ENABLE, 0x0 }, { TEGRA210_I2S_CG, 0x1 }, { TEGRA210_I2S_TIMING, 0x0000001f }, /* @@ -42,7 +42,7 @@ static const struct reg_default tegra264_i2s_reg_defaults[] = { { TEGRA264_I2S_TX_INT_MASK, 0x00000003 }, { TEGRA264_I2S_TX_CIF_CTRL, 0x00003f00 }, { TEGRA264_I2S_TX_FIFO_RD_ACCESS_MODE, 0x1 }, - { TEGRA264_I2S_ENABLE, 0x1 }, + { TEGRA264_I2S_ENABLE, 0x0 }, { TEGRA264_I2S_CG, 0x1 }, { TEGRA264_I2S_TIMING, 0x0000001f }, }; @@ -201,9 +201,21 @@ static int tegra210_i2s_runtime_resume(struct device *dev) } regcache_cache_only(i2s->regmap, false); - regcache_sync(i2s->regmap); + err = regcache_sync(i2s->regmap); + if (err) + goto err; + + err = regmap_write(i2s->regmap, i2s->soc_data->enable_reg, I2S_EN); + if (err) + goto err; return 0; + +err: + regcache_cache_only(i2s->regmap, true); + clk_disable_unprepare(i2s->clk_i2s); + + return err; } static void tegra210_i2s_set_data_offset(struct tegra210_i2s *i2s, @@ -1133,6 +1145,7 @@ static const struct tegra_i2s_soc_data soc_data_tegra210 = { .regmap_conf = &tegra210_regmap_conf, .i2s_cmpnt = &tegra210_i2s_cmpnt, .max_ch = TEGRA210_I2S_MAX_CHANNEL, + .enable_reg = TEGRA210_I2S_ENABLE, .tx_offset = TEGRA210_I2S_TX_OFFSET, .i2s_ctrl_offset = TEGRA210_I2S_CTRL_OFFSET, .fsync_width_mask = I2S_CTRL_FSYNC_WIDTH_MASK, @@ -1144,6 +1157,7 @@ static const struct tegra_i2s_soc_data soc_data_tegra264 = { .regmap_conf = &tegra264_regmap_conf, .i2s_cmpnt = &tegra264_i2s_cmpnt, .max_ch = TEGRA264_I2S_MAX_CHANNEL, + .enable_reg = TEGRA264_I2S_ENABLE, .tx_offset = TEGRA264_I2S_TX_OFFSET, .i2s_ctrl_offset = TEGRA264_I2S_CTRL_OFFSET, .fsync_width_mask = TEGRA264_I2S_CTRL_FSYNC_WIDTH_MASK, diff --git a/sound/soc/tegra/tegra210_i2s.h b/sound/soc/tegra/tegra210_i2s.h index 42be2137342c..82292f96ab36 100644 --- a/sound/soc/tegra/tegra210_i2s.h +++ b/sound/soc/tegra/tegra210_i2s.h @@ -150,6 +150,7 @@ struct tegra_i2s_soc_data { const struct regmap_config *regmap_conf; const struct snd_soc_component_driver *i2s_cmpnt; unsigned int max_ch; + unsigned int enable_reg; unsigned int tx_offset; unsigned int i2s_ctrl_offset; unsigned int fsync_width_mask; diff --git a/sound/soc/tegra/tegra210_mbdrc.c b/sound/soc/tegra/tegra210_mbdrc.c index f5d4a93dd6f1..1d78b4c1cc88 100644 --- a/sound/soc/tegra/tegra210_mbdrc.c +++ b/sound/soc/tegra/tegra210_mbdrc.c @@ -20,33 +20,33 @@ #define MBDRC_FILTER_REG(reg, id) \ ((reg) + ((id) * TEGRA210_MBDRC_FILTER_PARAM_STRIDE)) -#define MBDRC_FILTER_REG_DEFAULTS(id) \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_IIR_CFG, id), 0x00000005}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_IN_ATTACK, id), 0x3e48590c}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_IN_RELEASE, id), 0x08414e9f}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_FAST_ATTACK, id), 0x7fffffff}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_IN_THRESHOLD, id), 0x06145082}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_OUT_THRESHOLD, id), 0x060d379b}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_RATIO_1ST, id), 0x0000a000}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_RATIO_2ND, id), 0x00002000}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_RATIO_3RD, id), 0x00000b33}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_RATIO_4TH, id), 0x00000800}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_RATIO_5TH, id), 0x0000019a}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_MAKEUP_GAIN, id), 0x00000002}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_INIT_GAIN, id), 0x00066666}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_GAIN_ATTACK, id), 0x00d9ba0e}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_GAIN_RELEASE, id), 0x3e48590c}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_FAST_RELEASE, id), 0x7ffff26a}, \ - { MBDRC_FILTER_REG(TEGRA210_MBDRC_CFG_RAM_CTRL, id), 0x4000} +#define MBDRC_FILTER_PARAM_REG_DEFAULTS(reg, val) \ + { MBDRC_FILTER_REG(reg, 0), val}, \ + { MBDRC_FILTER_REG(reg, 1), val}, \ + { MBDRC_FILTER_REG(reg, 2), val} static const struct reg_default tegra210_mbdrc_reg_defaults[] = { { TEGRA210_MBDRC_CFG, 0x0030de51}, { TEGRA210_MBDRC_CHANNEL_MASK, 0x00000003}, { TEGRA210_MBDRC_FAST_FACTOR, 0x30000800}, - MBDRC_FILTER_REG_DEFAULTS(0), - MBDRC_FILTER_REG_DEFAULTS(1), - MBDRC_FILTER_REG_DEFAULTS(2), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_IIR_CFG, 0x00000005), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_IN_ATTACK, 0x3e48590c), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_IN_RELEASE, 0x08414e9f), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_FAST_ATTACK, 0x7fffffff), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_IN_THRESHOLD, 0x06145082), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_OUT_THRESHOLD, 0x060d379b), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_RATIO_1ST, 0x0000a000), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_RATIO_2ND, 0x00002000), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_RATIO_3RD, 0x00000b33), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_RATIO_4TH, 0x00000800), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_RATIO_5TH, 0x0000019a), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_MAKEUP_GAIN, 0x00000002), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_INIT_GAIN, 0x00066666), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_GAIN_ATTACK, 0x00d9ba0e), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_GAIN_RELEASE, 0x3e48590c), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_FAST_RELEASE, 0x7ffff26a), + MBDRC_FILTER_PARAM_REG_DEFAULTS(TEGRA210_MBDRC_CFG_RAM_CTRL, 0x4000), }; /* Default MBDRC parameters */ diff --git a/sound/soc/tegra/tegra210_mixer.c b/sound/soc/tegra/tegra210_mixer.c index 8eb4e54b954b..96259a6cbc59 100644 --- a/sound/soc/tegra/tegra210_mixer.c +++ b/sound/soc/tegra/tegra210_mixer.c @@ -57,7 +57,7 @@ static const struct reg_default tegra210_mixer_reg_defaults[] = { MIXER_TX_REG_DEFAULTS(3), MIXER_TX_REG_DEFAULTS(4), - { TEGRA210_MIXER_ENABLE, 0x1 }, + { TEGRA210_MIXER_ENABLE, 0x0 }, { TEGRA210_MIXER_CG, 0x00000001}, { TEGRA210_MIXER_GAIN_CFG_RAM_CTRL, 0x00004000}, { TEGRA210_MIXER_PEAKM_RAM_CTRL, 0x00004000}, @@ -86,11 +86,15 @@ static int tegra210_mixer_runtime_suspend(struct device *dev) static int tegra210_mixer_runtime_resume(struct device *dev) { struct tegra210_mixer *mixer = dev_get_drvdata(dev); + int err; regcache_cache_only(mixer->regmap, false); - regcache_sync(mixer->regmap); + err = regcache_sync(mixer->regmap); + if (err) + return err; - return 0; + return regmap_write(mixer->regmap, TEGRA210_MIXER_ENABLE, + TEGRA210_MIXER_EN); } static int tegra210_mixer_write_ram(struct tegra210_mixer *mixer, diff --git a/sound/usb/card.c b/sound/usb/card.c index 24112e491779..9307da95efbe 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -1282,8 +1282,11 @@ static int usb_audio_resume(struct usb_interface *intf) list_for_each_entry(as, &chip->pcm_list, list) { err = snd_usb_pcm_resume(as); - if (err < 0) - goto err_out; + if (err < 0) { + if (!chip->system_suspend) + goto err_out; + goto out; + } } /* @@ -1292,8 +1295,11 @@ static int usb_audio_resume(struct usb_interface *intf) */ list_for_each_entry(mixer, &chip->mixer_list, list) { err = snd_usb_mixer_resume(mixer); - if (err < 0) - goto err_out; + if (err < 0) { + if (!chip->system_suspend) + goto err_out; + goto out; + } } list_for_each(p, &chip->midi_list) { diff --git a/sound/usb/midi.c b/sound/usb/midi.c index f8996416c3be..8a9bc37f0b6e 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -875,6 +875,8 @@ static void snd_usbmidi_novation_output(struct snd_usb_midi_out_endpoint *ep, if (!ep->ports[0].active) return; + if (ep->max_transfer < 3) + return; transfer_buffer = urb->transfer_buffer; count = snd_rawmidi_transmit(ep->ports[0].substream, &transfer_buffer[2], diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 5de182181ede..ecaa8bc08d7c 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1237,21 +1237,27 @@ static void init_cur_mix_raw(struct usb_mixer_elem_info *cval, int ch, int idx) } /* - * Additional checks for sticky mixers + * Additional checks for sticky GET_CUR * - * Some devices' volume control mixers are sticky, which accept SET_CUR but - * do absolutely nothing. + * Some devices' volume control mixers have sticky GET_CUR, which implies either + * stubbed SET_CUR or broken GET_CUR. For the former case, the mixer accepts + * SET_CUR but do absolutely nothing, so falling back to soft mixer is the only + * way to control the volume. For the latter case, the mixer has effective + * SET_CUR despite GET_CUR being constant, and the mixer is usable as long as we + * always provide mixer value from the ceche. * * Check the return values of GET_CUR with different SET_CUR values. Consider - * the mixer as sticky if GET_CUR always returns a constant value. + * GET_CUR as sticky if GET_CUR always returns a constant value. * - * Some devices have effective SET_CUR despite GET_CUR being constant. Do not - * consider the mixer as sticky if a quirk flag indicates that. + * Unfortunately, we can't distinguish between stubbed SET_CUR and broken + * GET_CUR with simple read-back tests. Disabling the mixer regardless and + * forcing userspace to use soft mixer instead can lead to audible distortion at + * low volume on some wireless headphones, probably due to their poorly- + * performed lossy codec. * - * Gate the registration of sticky mixers to prevent confusing userspace, so - * that they won't cause ineffective volume control. However, for mixers with - * effective SET_CUR but broken GET_CUR, the registration can continue normally - * but further GET_CUR requests will be gated. + * Instead, mark GET_CUR as broken regardless and only provide mixer value from + * the cache. Users may opt into soft mixer in userspace audio stack if they + * need it. */ static int check_sticky_volume_control(struct usb_mixer_elem_info *cval, int channel, int saved) @@ -1271,24 +1277,13 @@ static int check_sticky_volume_control(struct usb_mixer_elem_info *cval, return 0; } - if (cval->head.mixer->chip->quirk_flags & QUIRK_FLAG_MIXER_GET_CUR_BROKEN) { - usb_audio_info(cval->head.mixer->chip, - "%d:%d: broken mixer GET_CUR (%d/%d/%d => %d)\n", - cval->head.id, mixer_ctrl_intf(cval->head.mixer), - cval->min, cval->max, cval->res, saved); - - cval->get_cur_broken = 1; - return -ENXIO; - } - - usb_audio_err(cval->head.mixer->chip, - "%d:%d: sticky mixer values (%d/%d/%d => %d), disabling\n", - cval->head.id, mixer_ctrl_intf(cval->head.mixer), - cval->min, cval->max, cval->res, saved); usb_audio_info(cval->head.mixer->chip, - "check MIXER_GET_CUR_BROKEN if you believe the mixer is non-sticky"); + "%d:%d: broken mixer GET_CUR (%d/%d/%d => %d)\n", + cval->head.id, mixer_ctrl_intf(cval->head.mixer), + cval->min, cval->max, cval->res, saved); - return -ENODEV; + cval->get_cur_broken = 1; + return -ENXIO; } /* @@ -1385,8 +1380,6 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, goto no_checks; ret = check_sticky_volume_control(cval, minchn, saved); - if (ret == -ENODEV) - goto sticky; if (ret) goto no_checks; @@ -1454,34 +1447,15 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, } } - return 0; - -sticky: /* - * It makes no sense to restore the saved value for a sticky mixer, - * since setting any value is a no-op. - * - * However, in some rare cases, SET_CUR is effective despite GET_CUR - * always returns a constant value. These mixers are not sticky, but - * there's no way to distinguish them. Without any additional - * information, the best thing we can do is to set the mixer value to - * the maximum before bailing out, so that a soft mixer can still reach - * the maximum hardware volume if the mixer turns out to be non-sticky. - * Meanwhile, all channels must be synchronized to prevent imbalance - * volume. + * When GET_CUR is sticky, the saved value is bogus, so mixer values set + * by the sanity checks must be discarded through init_cur_mix_raw(). + * After that, we can clear the flag as per QUIRK_FLAG_MIXER_GET_CUR_OK. */ - if (!cval->cmask) { - snd_usb_set_cur_mix_value(cval, 0, 0, cval->max); - } else { - idx = 0; - for (i = 0; i < MAX_CHANNELS; i++) { - if (cval->cmask & BIT(i)) { - snd_usb_set_cur_mix_value(cval, i + 1, idx, cval->max); - idx++; - } - } - } - return ret; + if (cval->head.mixer->chip->quirk_flags & QUIRK_FLAG_MIXER_GET_CUR_OK) + cval->get_cur_broken = 0; + + return 0; } #define get_min_max(cval, def) get_min_max_with_quirks(cval, def, NULL) diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 8046d5987d5b..ace4ccad8f51 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -505,13 +505,13 @@ static const struct usbmix_connector_map gigabyte_b450_connector_map[] = { {} }; -/* Audient iD14: FU 12 advertises Volume on only 4 of its 6 logical channels - * and sits on the monitor mixer branch, but it is traced through to the - * Speaker output terminal and gets named "Speaker Playback Volume". Userspace - * then adopts it as the stream's hardware volume, and any setting below 0 dB - * attenuates some channels but not others (20 dB imbalance at 80%). Give it a - * non-standard name so that it is no longer taken for the stream's master - * volume, while remaining reachable for anyone who wants the monitor gain. +/* Audient iD14 MkI and MkII: FU 12 sits on the monitor mixer branch but is + * traced through to the Speaker output terminal, so it is named "Speaker + * Playback Volume". On MkII it controls only 4 of 6 playback channels. MkI + * testing found asymmetric attenuation within the main stereo pair. Userspace + * adopts this control as the stream's hardware volume, causing imbalance below + * 0 dB. Give it a non-standard name so that userspace no longer treats it as + * the stream master, while keeping the monitor gain reachable. */ static const struct usbmix_name_map audient_id14_map[] = { { 12, "Monitor Mix Playback" }, /* FU, partial coverage */ @@ -602,7 +602,12 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = maya44_map, }, { - /* Audient iD14 */ + /* Audient iD14 MkI */ + .id = USB_ID(0x2708, 0x0002), + .map = audient_id14_map, + }, + { + /* Audient iD14 MkII */ .id = USB_ID(0x2708, 0x0008), .map = audient_id14_map, }, diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 0a3d39b8385b..dd02c6294edf 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -1814,6 +1814,28 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + /* + * M-Audio Venom + * + * The AudioControl interface times out on every GET_CUR request, + * which adds around 47 seconds to the card registration and + * freezes the device, blocking streaming. + * Using an explicit composite quirk to skip the mixer entirely. + */ + USB_DEVICE_VENDOR_SPEC(0x0763, 0x2084), + QUIRK_DRIVER_INFO { + .vendor_name = "M-Audio", + .product_name = "Venom", + QUIRK_DATA_COMPOSITE { + { QUIRK_DATA_IGNORE(0) }, + { QUIRK_DATA_STANDARD_AUDIO(1) }, + { QUIRK_DATA_STANDARD_AUDIO(2) }, + { QUIRK_DATA_STANDARD_MIDI(3) }, + QUIRK_COMPOSITE_END + } + } +}, /* Casio devices */ { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index eb1750def067..91938172912a 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2215,10 +2215,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x03f0, 0x654a, /* HP 320 FHD Webcam */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), - DEVICE_FLG(0x040b, 0x0897, /* Weltrend Semiconductor, sold as Redragon H510-PRO Wireless headset */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x041e, 0x3000, /* Creative SB Extigy */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x041e, 0x324d, /* Creative Sound Blaster Play! 3 */ + QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), DEVICE_FLG(0x041e, 0x4080, /* Creative Live Cam VF0610 */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x045e, 0x083c, /* MS USB Link headset */ @@ -2256,8 +2256,9 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { DEVICE_FLG(0x046d, 0x0a8f, /* Logitech H390 headset */ QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), - DEVICE_FLG(0x046d, 0x0af7, /* Logitech PRO X 2 LIGHTSPEED */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN), + DEVICE_FLG(0x046d, 0x0aba, /* Logitech PRO X Wireless */ + QUIRK_FLAG_MIXER_GET_CUR_OK | + QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), DEVICE_FLG(0x0499, 0x1506, /* Yamaha THR5 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ @@ -2329,9 +2330,11 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0763, 0x2080, /* M-Audio Fast Track Ultra */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN | QUIRK_FLAG_GENERIC_IMPLICIT_FB), + QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0763, 0x2081, /* M-Audio Fast Track Ultra */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN | QUIRK_FLAG_GENERIC_IMPLICIT_FB), + QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x0763, 0x2084, /* M-Audio Venom */ + QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_DISABLE_AUTOSUSPEND), DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */ @@ -2370,8 +2373,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x1038, 0x1294, /* SteelSeries Arctis Pro Wireless */ QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), - DEVICE_FLG(0x1038, 0x2232, /* SteelSeries Arctis Nova 5 */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x12d1, 0x3a07, /* HUAWEI USB-C HEADSET */ @@ -2379,8 +2380,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), - DEVICE_FLG(0x1377, 0x6004, /* Sennheiser MOMENTUM 3 */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */ @@ -2393,6 +2392,9 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IFB_SILENCE_ON_EMPTY), DEVICE_FLG(0x13e5, 0x0001, /* Serato Phono */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x152a, 0x85dd, /* SMSL USB DAC */ + QUIRK_FLAG_DSD_RAW | QUIRK_FLAG_DISABLE_AUTOSUSPEND | + QUIRK_FLAG_SKIP_IFACE_SETUP), DEVICE_FLG(0x152a, 0x880a, /* NeuralDSP Quad Cortex */ 0), /* Doesn't have the vendor quirk which would otherwise apply */ DEVICE_FLG(0x1532, 0x055e, /* Razer Nommo V2 X */ @@ -2505,8 +2507,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d99, 0x0026, /* HECATE G2 GAMING HEADSET */ QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), - DEVICE_FLG(0x2d99, 0xa024, /* Edifier MF200 */ - QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x2fc6, 0xf06b, /* MOONDROP Moonriver2 Ti */ QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x2fc6, 0xf0b5, /* iBasso DC-Elite */ @@ -2647,7 +2647,7 @@ static const char *const snd_usb_audio_quirk_flag_names[] = { QUIRK_STRING_ENTRY(MIXER_PLAYBACK_LINEAR_VOL), QUIRK_STRING_ENTRY(MIXER_CAPTURE_LINEAR_VOL), QUIRK_STRING_ENTRY(IFB_SILENCE_ON_EMPTY), - QUIRK_STRING_ENTRY(MIXER_GET_CUR_BROKEN), + QUIRK_STRING_ENTRY(MIXER_GET_CUR_OK), QUIRK_STRING_ENTRY(PLAYBACK_URB_FIXUP), QUIRK_STRING_ENTRY(ALWAYS_SET_RATE), NULL diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index c49709d7ad25..24436473931d 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -243,24 +243,18 @@ extern bool snd_usb_skip_validation; * from snd_usb_handle_sync_urb. Instead fall through and enqueue a * packet_info containing only size-0 packets, so the OUT ring keeps * moving (emits silence). Needed by Behringer Flow 8 (1397:050c). - * QUIRK_FLAG_MIXER_GET_CUR_BROKEN - * Some mixers are sticky, which means that setting their current volume is a - * no-op, and reading the current volume returns a constant value. The sticky - * check disables these mixers to prevent confusing userspace. However, some - * devices do have a tunable volume despite the reported current volume being - * constant. As the sticky check can't distinguish between the two categories, - * setting this flag tells that the device should fall into the second - * category when GET_CUR returns a constant value, resulting in the sticky - * check being non-fatal and only disabling GET_CUR instead of the whole mixer. - * The current volume will then be provided by the internal cache that stores - * the last set volume + * QUIRK_FLAG_MIXER_GET_CUR_OK + * On some devices, whether their GET_CUR being sticky depends on whether + * hotpluggable components are present. When the hotpluggable components are + * missing on probe, their GET_CUR behavior is classified as broken. Set the + * flag to prevent the heuristics from gating GET_CUR. * QUIRK_FLAG_PLAYBACK_URB_FIXUP * Set URB_ISO_ASAP flag for isochronous URBs and force nurbs to MAX_URBS. * This is needed for devices that exhibit boot-time audio stuttering due * to insufficient buffer depth combined with xHCI scheduling variability. * The larger buffer (MAX_URBS = 12, ~64ms) absorbs system scheduling * jitter during boot, while URB_ISO_ASAP ensures consistent xHCI scheduling. - * QUIRK_FLAG_ALWAYS_SET_RATE: + * QUIRK_FLAG_ALWAYS_SET_RATE * Issue SET_CUR for the sample rate even when the clock already reports the * requested rate. A device advertising a single rate is otherwise never sent * the request at all, and some require it before streaming will start. @@ -297,10 +291,10 @@ enum { QUIRK_TYPE_MIXER_PLAYBACK_LINEAR_VOL = 27, QUIRK_TYPE_MIXER_CAPTURE_LINEAR_VOL = 28, QUIRK_TYPE_IFB_SILENCE_ON_EMPTY = 29, - QUIRK_TYPE_MIXER_GET_CUR_BROKEN = 30, + QUIRK_TYPE_MIXER_GET_CUR_OK = 30, QUIRK_TYPE_PLAYBACK_URB_FIXUP = 31, QUIRK_TYPE_ALWAYS_SET_RATE = 32, -/* Please also edit snd_usb_audio_quirk_flag_names */ +/* Please also edit snd_usb_audio_quirk_flag_names and alsa-configuration.rst */ }; #define QUIRK_FLAG(x) BIT_U64(QUIRK_TYPE_ ## x) @@ -335,7 +329,7 @@ enum { #define QUIRK_FLAG_MIXER_PLAYBACK_LINEAR_VOL QUIRK_FLAG(MIXER_PLAYBACK_LINEAR_VOL) #define QUIRK_FLAG_MIXER_CAPTURE_LINEAR_VOL QUIRK_FLAG(MIXER_CAPTURE_LINEAR_VOL) #define QUIRK_FLAG_IFB_SILENCE_ON_EMPTY QUIRK_FLAG(IFB_SILENCE_ON_EMPTY) -#define QUIRK_FLAG_MIXER_GET_CUR_BROKEN QUIRK_FLAG(MIXER_GET_CUR_BROKEN) +#define QUIRK_FLAG_MIXER_GET_CUR_OK QUIRK_FLAG(MIXER_GET_CUR_OK) #define QUIRK_FLAG_PLAYBACK_URB_FIXUP QUIRK_FLAG(PLAYBACK_URB_FIXUP) #define QUIRK_FLAG_ALWAYS_SET_RATE QUIRK_FLAG(ALWAYS_SET_RATE) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index df04e6be2f66..464f6c9d9ff0 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -196,6 +196,7 @@ static bool is_rust_noreturn(const struct symbol *func) return str_ends_with(func->name, "_4core3num20from_str_radix_panic") || str_ends_with(func->name, "_4core3num22from_ascii_radix_panic") || str_ends_with(func->name, "_4core3num28from_ascii_bytes_radix_panic") || + str_ends_with(func->name, "_4core3str16slice_error_fail") || str_ends_with(func->name, "_4core5sliceSp15copy_from_slice17len_mismatch_fail") || str_ends_with(func->name, "_4core6option13expect_failed") || str_ends_with(func->name, "_4core6option13unwrap_failed") || diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 979d4cabfaf9..76f5e025e107 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -48,6 +48,7 @@ extern int LINUX_KERNEL_VERSION __kconfig; extern const char CONFIG_CC_VERSION_TEXT[64] __kconfig __weak; extern const char CONFIG_LOCALVERSION[64] __kconfig __weak; +extern bool CONFIG_PREEMPT_RCU __kconfig __weak; /* * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can @@ -97,6 +98,7 @@ s32 scx_bpf_pick_any_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; +struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym __weak; struct rq *scx_bpf_locked_rq(void) __ksym; struct task_struct *scx_bpf_cpu_curr(s32 cpu) __ksym __weak; struct task_struct *scx_bpf_tid_to_task(u64 tid) __ksym __weak; @@ -527,32 +529,103 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) return (const struct cpumask *)mask; } +/* + * True if the non-sleepable BPF trampoline prolog (__bpf_prog_enter) calls + * migrate_disable() for the current task. Recorded once by + * scx_lib_init_probe, an fentry program on bpf_scx_reg() that fires during + * the natural scheduler-attach call chain (auto-attached by scx_ops_attach!). + * + * Defaults to true (conservative). Over-reporting in is_migration_disabled() + * causes local-only dispatch, which is safe. Under-reporting can crash the + * scheduler, so we err high if the probe somehow fails to run. + */ +bool __scx_prolog_disables_migration __weak = true; + +/* + * scx_lib_init_probe - non-sleepable prolog probe. + * + * Attached to bpf_scx_reg(), the .reg callback in bpf_sched_ext_ops + * (kernel/sched/ext.c). The kernel's struct_ops machinery invokes + * bpf_scx_reg when userspace creates the scheduler link, before + * ops.init() fires. Its address is taken in the vtable, so the symbol + * is non-inlinable and has been stable since introduction. + * + * Entering via fentry runs us through __bpf_prog_enter -- the + * non-sleepable prolog that consumers of is_migration_disabled() live + * under. + * + * Loud warning: the prolog adds at most 1 to migration_disabled. + * Reading > 1 means something upstream in the + * bpf_struct_ops_link_create -> bpf_scx_reg path disabled migration + * before the prolog ran, invalidating the probe; audit and adjust. + */ +SEC("fentry/bpf_scx_reg") __weak +int scx_lib_init_probe(void *ctx) +{ + if (bpf_core_field_exists(((struct task_struct *)0)->migration_disabled)) { + const struct task_struct *p = bpf_get_current_task_btf(); + unsigned int md = p->migration_disabled; + + if (md > 1) + bpf_printk("scx_lib_init_probe: unexpected migration_disabled=%u " + "upstream of BPF prolog; probe result unreliable", + md); + + __scx_prolog_disables_migration = md > 0; + } + return 0; +} + /* * Return true if task @p cannot migrate to a different CPU, false * otherwise. + * + * IMPORTANT: designed for NON-SLEEPABLE BPF contexts only. Sleepable + * contexts (BPF_STRUCT_OPS_SLEEPABLE, SEC("syscall"), + * SEC("fentry.s/...")) enter via __bpf_prog_enter_sleepable() or + * __bpf_prog_enter_sleepable_recur(), both of which unconditionally + * call migrate_disable(); this helper can yield a false negative for + * p == current there, which can crash the scheduler. */ static inline bool is_migration_disabled(const struct task_struct *p) { /* - * Testing p->migration_disabled in a BPF code is tricky because the - * migration is _always_ disabled while running the BPF code. - * The prolog (__bpf_prog_enter) and epilog (__bpf_prog_exit) for BPF - * code execution disable and re-enable the migration of the current - * task, respectively. So, the _current_ task of the sched_ext ops is - * always migration-disabled. Moreover, p->migration_disabled could be - * two or greater when a sched_ext ops BPF code (e.g., ops.tick) is - * executed in the middle of the other BPF code execution. + * Testing p->migration_disabled in BPF is tricky because the BPF prolog + * (__bpf_prog_enter) may call migrate_disable() for the current task, + * making migration_disabled == 1 even for tasks that are not truly + * migration-disabled. * - * Therefore, we should decide that the _current_ task is - * migration-disabled only when its migration_disabled count is greater - * than one. In other words, when p->migration_disabled == 1, there is - * an ambiguity, so we should check if @p is the current task or not. + * Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for + * trampoline.c"), the BPF prolog calls migrate_disable() only when + * CONFIG_PREEMPT_RCU is enabled. Two fast paths cover the common cases: + * + * 1) CONFIG_PREEMPT_RCU: prolog always calls migrate_disable(), so + * migration_disabled == 1 for the current task is ambiguous. + * Disambiguate by checking p == current. + * + * 2) v6.18+ without CONFIG_PREEMPT_RCU: prolog never calls + * migrate_disable(), so migration_disabled == 1 is unambiguously + * a real migrate_disable() call. + * + * A slow path handles pre-v6.18 kernels without CONFIG_PREEMPT_RCU, + * where the prolog historically called migrate_disable() unconditionally + * but a cherry-picked downstream kernel may not. The runtime-probed flag + * __scx_prolog_disables_migration (set by scx_lib_init_probe) distinguishes + * the two cases without relying on the kernel version alone. */ if (bpf_core_field_exists(p->migration_disabled)) { - if (p->migration_disabled == 1) - return bpf_get_current_task_btf() != p; - else - return p->migration_disabled; + if (p->migration_disabled == 1) { + /* Fast path: prolog always disables migration */ + if (CONFIG_PREEMPT_RCU) + return bpf_get_current_task_btf() != p; + /* Fast path: prolog never disables migration */ + if (LINUX_KERNEL_VERSION >= KERNEL_VERSION(6, 18, 0)) + return true; + /* Slow path: pre-v6.18, !PREEMPT_RCU - use runtime flag */ + return __scx_prolog_disables_migration ? + bpf_get_current_task_btf() != p : true; + } + return p->migration_disabled; } return false; } @@ -1021,7 +1094,20 @@ static inline u64 scx_clock_task(u32 cpu) { struct rq___local *rq = get_current_rq(cpu); - /* Equivalent to the kernel's rq_clock_task(). */ + /* + * Equivalent to the kernel's rq_clock_task(): wall-clock time minus + * cumulative IRQ time (CONFIG_IRQ_TIME_ACCOUNTING) and hypervisor + * steal time (CONFIG_PARAVIRT_TIME_ACCOUNTING). Without those configs, + * it equals rq->clock. + * + * Conceptually this clock advances during idle (the idle task counts + * as a running task), but rq->clock_task is only updated on scheduling + * events. With NO_HZ_IDLE (the default), the periodic tick is stopped + * on idle CPUs, so rq->clock_task is not refreshed while a CPU is + * idle. Reading this clock for a remote idle CPU from a BPF timer + * callback returns the value from when the CPU last went idle, making + * the delta over an idle interval effectively zero. + */ return rq ? rq->clock_task : 0; } @@ -1032,9 +1118,23 @@ static inline u64 scx_clock_pelt(u32 cpu) /* * Equivalent to the kernel's rq_clock_pelt(): subtracts * lost_idle_time from clock_pelt to absorb the jump that occurs - * when clock_pelt resyncs with clock_task at idle exit. The result - * is a continuous, capacity-invariant clock safe for both task - * execution time stamping and cross-idle measurements. + * when clock_pelt resyncs with clock_task at idle exit. The intent + * is a continuous, capacity- and frequency-invariant clock that is + * frozen during idle, IRQ, and hypervisor steal. + * + * However, like scx_clock_task(), this clock has a stale-read issue + * for remote idle CPUs with NO_HZ_IDLE (the default). clock_pelt + * itself advances at wall-clock rate (hardware-clock based), but + * lost_idle_time is only updated via update_rq_clock_pelt(), which + * requires update_rq_clock() to be called. With NO_HZ_IDLE, the + * periodic tick is stopped on idle CPUs, so lost_idle_time is not + * refreshed during idle. Reading this clock for a remote idle CPU + * from a BPF timer callback therefore returns a value that drifts + * at wall-clock rate -- the same stale behaviour as scx_clock_task(). + * + * Without NO_HZ_IDLE, periodic ticks keep lost_idle_time nearly in + * sync (stale by at most one tick period, ~1 ms), so the result is + * accurate. */ return rq ? (rq->clock_pelt - rq->lost_idle_time) : 0; } diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index 3ab642f92c8a..6944221f96cc 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -92,15 +92,20 @@ int bpf_cpumask_populate(struct bpf_cpumask *dst, void *src, size_t src__sz) __k /* * v6.19: Introduce lockless peek API for user DSQs. + * v7.1: Fix scx_bpf_dsq_peek() spuriously returning NULL on non-empty + * FIFO DSQs (2f2ea7709266). * - * Preserve the following macro until v6.21. + * The kfunc exists from v6.19 but can return NULL for a non-empty FIFO DSQ + * before the v7.1 fix. Require kernel version >= 7.1.0 before calling it; + * otherwise fall through to the bpf_iter_scx_dsq fallback below. */ static inline struct task_struct *__COMPAT_scx_bpf_dsq_peek(u64 dsq_id) { struct task_struct *p = NULL; struct bpf_iter_scx_dsq it; - if (bpf_ksym_exists(scx_bpf_dsq_peek)) + if (bpf_ksym_exists(scx_bpf_dsq_peek) && + LINUX_KERNEL_VERSION >= KERNEL_VERSION(7, 1, 0)) return scx_bpf_dsq_peek(dsq_id); if (!bpf_iter_scx_dsq_new(&it, dsq_id, 0)) p = bpf_iter_scx_dsq_next(&it); @@ -238,6 +243,26 @@ static inline bool __COMPAT_is_enq_cpu_selected(u64 enq_flags) scx_bpf_pick_any_cpu_node(cpus_allowed, node, flags) : \ scx_bpf_pick_any_cpu(cpus_allowed, flags)) +/* + * v6.18: Add a helper to retrieve the current task running on a CPU. + * + * The kernel tree dropped this helper and scx_bpf_cpu_rq(), but schedulers in + * this tree still support pre-v6.18 kernels where scx_bpf_cpu_curr() doesn't + * resolve and the scx_bpf_cpu_rq() fallback still exists. Keep it until + * pre-v6.18 kernels fall out of the support window. + */ +static inline struct task_struct *__COMPAT_scx_bpf_cpu_curr(int cpu) +{ + struct rq *rq; + + if (bpf_ksym_exists(scx_bpf_cpu_curr)) + return scx_bpf_cpu_curr(cpu); + + rq = scx_bpf_cpu_rq(cpu); + + return rq ? rq->curr : NULL; +} + /* * v6.19: To work around BPF maximum parameter limit, the following kfuncs are * replaced with variants that pack scalar arguments in a struct. Wrappers are @@ -378,6 +403,17 @@ static inline void scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime) p->scx.dsq_vtime = vtime; } +/* + * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This + * will eventually deprecate scx_bpf_reenqueue_local(). + */ +void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak; + +static inline bool __COMPAT_has_generic_reenq(void) +{ + return bpf_ksym_exists(scx_bpf_dsq_reenq___compat); +} + /* * v6.19: The new void variant can be called from anywhere while the older v1 * variant can only be called from ops.cpu_release(). The double ___ prefixes on @@ -395,21 +431,31 @@ static inline bool __COMPAT_scx_bpf_reenqueue_local_from_anywhere(void) static inline void scx_bpf_reenqueue_local(void) { - if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) + if (__COMPAT_has_generic_reenq()) + scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0); + else if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) scx_bpf_reenqueue_local___v2___compat(); else scx_bpf_reenqueue_local___v1(); } -/* - * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This - * will eventually deprecate scx_bpf_reenqueue_local(). - */ -void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak; - -static inline bool __COMPAT_has_generic_reenq(void) +static inline int scx_bpf_reenqueue_local_from_anywhere(void) { - return bpf_ksym_exists(scx_bpf_dsq_reenq___compat); + /* + * The generic reenq kfunc and the v2 reenqueue-local variant can both be + * called from anywhere; v1 cannot. Test each ksym in its own branch with a + * distinct call: combining them with || would fold into a bitwise OR of the + * two ksym addresses, which the verifier rejects. + */ + if (__COMPAT_has_generic_reenq()) { + scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0); + return 0; + } + if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) { + scx_bpf_reenqueue_local___v2___compat(); + return 0; + } + return -EOPNOTSUPP; } static inline void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags) diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index d2e4384df5af..7c12df45fdba 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -10,9 +10,14 @@ #include #include #include +#include +#include #include +#include #include +#include "enums_abi.autogen.h" + struct btf *__COMPAT_vmlinux_btf __attribute__((weak)); static inline void __COMPAT_load_vmlinux_btf(void) @@ -23,6 +28,85 @@ static inline void __COMPAT_load_vmlinux_btf(void) } } +/* + * Recover the true value of a 64-bit enum enumerator whose kernel BTF entry + * was truncated to its low 32 bits. + * + * Kernels whose BTF was generated without BTF_KIND_ENUM64 support encode + * 64-bit enums as 8-byte BTF_KIND_ENUM entries whose enumerator values only + * carry the low 32 bits. This happens with pahole < 1.24, which predates + * ENUM64, and with pahole passing --skip_encoding_btf_enum64 (e.g. Google's + * Container-Optimized OS / GKE kernels deliberately pass it for backward + * compatibility with older BTF consumers). The high bits + * can't be recovered from kernel BTF, so substitute the value from the + * vmlinux.h this tree was built against, cross-checked against the low 32 + * bits the kernel did provide. + * + * Note that this is a best-effort recovery, not a ground truth. The + * substitution assumes the running kernel agrees with this tree's vmlinux.h + * on the high 32 bits, but only the low 32 bits can actually be verified. + * The cross-check is vacuous for enumerators whose value has no low bits + * set (e.g. SCX_DSQ_FLAG_BUILTIN, __SCX_ENQ_INTERNAL_MASK, + * SCX_ENQ_CLEAR_OPSS, SCX_ECODE_*): their lo32 is 0 and matches anything, + * so those substitutions rest entirely on the high bits never moving. An + * enumerator missing from the table (a kernel newer than this tree's + * vmlinux.h, or a stale autogen table) can't be recovered at all. If a + * substitution is ever wrong, the scheduler operates on bogus values (e.g. + * dispatching to nonexistent DSQ ids or silently dropping flags) and can + * wildly malfunction, which is why the mismatch and table-miss paths refuse + * instead of guessing. + */ +static inline bool __COMPAT_recover_truncated_enum64(const char *type, + const char *name, + u32 lo32, u64 *v) +{ + static bool warned; + size_t i; + + for (i = 0; i < sizeof(__scx_enum_abi_vals) / sizeof(__scx_enum_abi_vals[0]); i++) { + const struct __scx_enum_abi_val *e = &__scx_enum_abi_vals[i]; + + if (strcmp(e->type, type) || strcmp(e->name, name)) + continue; + + if (e->val <= (u64)UINT32_MAX) { + *v = lo32; + return true; + } + + if ((u32)e->val != lo32) { + fprintf(stderr, "ERROR: kernel BTF value of %s::%s (0x%x) doesn't match the low 32 bits of the vmlinux.h value (0x%llx); refusing to substitute\n", + type, name, lo32, (unsigned long long)e->val); + return false; + } + + if (!warned) { + fprintf(stderr, + "WARNING: kernel BTF lacks BTF_KIND_ENUM64 encoding (generated by\n" + "WARNING: pahole < 1.24 or with --skip_encoding_btf_enum64), so 64-bit\n" + "WARNING: scx enum values are truncated to their low 32 bits in kernel\n" + "WARNING: BTF. Substituting the full 64-bit values from the vmlinux.h\n" + "WARNING: this binary was built against, cross-checked against the low\n" + "WARNING: 32 bits the kernel does provide. The high 32 bits cannot be\n" + "WARNING: verified: if the running kernel's actual values differ from\n" + "WARNING: the build-time vmlinux.h (e.g. an enum that moved in a newer\n" + "WARNING: kernel), the scheduler will operate on bogus values, such as\n" + "WARNING: dispatching to nonexistent DSQ ids, and can wildly malfunction.\n"); + warned = true; + } + *v = e->val; + return true; + } + + /* + * Unknown enumerator (likely a stale autogen table). Fail + * pessimistically to avoid returning an invalid value. + */ + fprintf(stderr, "ERROR: kernel BTF truncates 64-bit enum %s::%s to 0x%x; 64-bit variant not found in vmlinux.h\n", + type, name, lo32); + return false; +} + static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v) { const struct btf_type *t; @@ -46,6 +130,19 @@ static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off); SCX_BUG_ON(!n, "btf__name_by_offset()"); if (!strcmp(n, name)) { + /* + * Try to recover a 64-bit enum from an 8-byte + * BTF_KIND_ENUM that was encoded without ENUM64 + * support (old pahole or + * --skip_encoding_btf_enum64). Only scx_* + * types are covered by the substitution table; + * non-scx types fall through to the raw value + * so this generic utility keeps working for + * them. + */ + if (t->size == 8 && !strncmp(type, "scx_", 4)) + return __COMPAT_recover_truncated_enum64(type, name, + (u32)e[i].val, v); *v = e[i].val; return true; } diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h index 19aa1de3e700..63b6b14b19bd 100644 --- a/tools/sched_ext/include/scx/enum_defs.autogen.h +++ b/tools/sched_ext/include/scx/enum_defs.autogen.h @@ -56,6 +56,10 @@ #define HAVE_SCX_DEQ_SLEEP #define HAVE_SCX_DEQ_CORE_SCHED_EXEC #define HAVE_SCX_DEQ_SCHED_CHANGE +#define HAVE_SCX_DSP_NONE +#define HAVE_SCX_DSP_LOCAL +#define HAVE_SCX_DSP_PREV +#define HAVE_SCX_DSP_RETRY #define HAVE_SCX_DSQ_FLAG_BUILTIN #define HAVE_SCX_DSQ_FLAG_LOCAL_ON #define HAVE_SCX_DSQ_INVALID @@ -188,7 +192,6 @@ #define HAVE_SCX_RQ_SUB_IDLE_RENOTIFY #define HAVE_SCX_RQ_ROOT_IDLE_RENOTIFY #define HAVE_SCX_RQ_IN_WAKEUP -#define HAVE_SCX_RQ_IN_BALANCE #define HAVE_SCX_RQ_IN_DISPATCH #define HAVE_SCX_SCHED_PCPU_BYPASSING #define HAVE_SCX_SLICE_OOB_DUR_BITS diff --git a/tools/sched_ext/include/scx/enums_abi.autogen.h b/tools/sched_ext/include/scx/enums_abi.autogen.h new file mode 100644 index 000000000000..d53899764f5a --- /dev/null +++ b/tools/sched_ext/include/scx/enums_abi.autogen.h @@ -0,0 +1,223 @@ +/* + * WARNING: This file is autogenerated from gen_enum_defs.py [1]. + * + * scx enumerator values from the vmlinux.h this tree is built against. + * Used as the substitution source when the running kernel's BTF lacks + * BTF_KIND_ENUM64 encoding and 64-bit enum values are truncated. + * + * [1] https://github.com/sched-ext/scx/blob/main/scripts/gen_enum_defs.py + */ + +#ifndef __ENUMS_ABI_AUTOGEN_H__ +#define __ENUMS_ABI_AUTOGEN_H__ + +struct __scx_enum_abi_val { + const char *type; + const char *name; + u64 val; +}; + +static const struct __scx_enum_abi_val __scx_enum_abi_vals[] + __attribute__((unused)) = { + { "scx_arena_consts", "SCX_ARENA_MIN_ORDER", 0x3LLU }, + { "scx_arena_consts", "SCX_ARENA_GROW_PAGES", 0x4LLU }, + { "scx_cap_flags", "__SCX_CAP_ENQ_IMMED", 0x0LLU }, + { "scx_cap_flags", "__SCX_CAP_ENQ", 0x1LLU }, + { "scx_cap_flags", "__SCX_CAP_PREEMPT", 0x2LLU }, + { "scx_cap_flags", "__SCX_CAP_PERF", 0x3LLU }, + { "scx_cap_flags", "__SCX_NR_CAPS", 0x4LLU }, + { "scx_cap_flags", "__SCX_CAP_ALL", 0xfLLU }, + { "scx_cap_flags", "SCX_CAP_ENQ_IMMED", 0x1LLU }, + { "scx_cap_flags", "SCX_CAP_ENQ", 0x2LLU }, + { "scx_cap_flags", "SCX_CAP_PREEMPT", 0x4LLU }, + { "scx_cap_flags", "SCX_CAP_PERF", 0x8LLU }, + { "scx_cap_flags", "SCX_CAP_BASE", 0x1LLU }, + { "scx_cap_flags", "SCX_CAPS_REENQ_ON_LOSS", 0x3LLU }, + { "scx_cid_consts", "SCX_CID_SHARD_SIZE_DFL", 0x18LLU }, + { "scx_cid_consts", "SCX_CID_SHARD_MAX_CPUS", 0x200LLU }, + { "scx_consts", "SCX_DSP_DFL_MAX_BATCH", 0x20LLU }, + { "scx_consts", "SCX_DSP_MAX_LOOPS", 0x20LLU }, + { "scx_consts", "SCX_WATCHDOG_MAX_TIMEOUT", 0x7530LLU }, + { "scx_consts", "SCX_RESCUE_DFL_BW_PPT", 0x14LLU }, + { "scx_consts", "SCX_RESCUE_MAX_BW_PPT", 0xfaLLU }, + { "scx_consts", "SCX_RESCUE_DISABLE", 0xffffffffLLU }, + { "scx_consts", "SCX_RESCUE_DFL_QUANTUM_US", 0x1388LLU }, + { "scx_consts", "SCX_RESCUE_MIN_QUANTUM_US", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_MAX_QUANTUM_US", 0x186a0LLU }, + { "scx_consts", "SCX_RESCUE_MIN_SLICE_US", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_OVERLOAD_MULT", 0x10LLU }, + { "scx_consts", "SCX_RESCUE_MIN_OVERLOAD_MS", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_MAX_OVERLOAD_MS", 0x3a98LLU }, + { "scx_consts", "SCX_TID_CHUNK", 0x400LLU }, + { "scx_consts", "SCX_EXIT_BT_LEN", 0x40LLU }, + { "scx_consts", "SCX_EXIT_MSG_LEN", 0x400LLU }, + { "scx_consts", "SCX_EXIT_DUMP_DFL_LEN", 0x8000LLU }, + { "scx_consts", "SCX_CPUPERF_ONE", 0x400LLU }, + { "scx_consts", "SCX_TASK_ITER_BATCH", 0x20LLU }, + { "scx_consts", "SCX_BYPASS_HOST_NTH", 0x2LLU }, + { "scx_consts", "SCX_BYPASS_LB_DFL_INTV_US", 0x7a120LLU }, + { "scx_consts", "SCX_BYPASS_LB_DONOR_PCT", 0x7dLLU }, + { "scx_consts", "SCX_BYPASS_LB_MIN_DELTA_DIV", 0x4LLU }, + { "scx_consts", "SCX_BYPASS_LB_BATCH", 0x100LLU }, + { "scx_consts", "SCX_REENQ_MAX_REPEAT", 0x100LLU }, + { "scx_consts", "SCX_SUB_MAX_DEPTH", 0x4LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_RT", 0x0LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_DL", 0x1LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_STOP", 0x2LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_UNKNOWN", 0x3LLU }, + { "scx_deq_flags", "SCX_DEQ_SLEEP", 0x1LLU }, + { "scx_deq_flags", "SCX_DEQ_CORE_SCHED_EXEC", 0x100000000LLU }, + { "scx_deq_flags", "SCX_DEQ_SCHED_CHANGE", 0x200000000LLU }, + { "scx_dsp_verdict", "SCX_DSP_NONE", 0x0LLU }, + { "scx_dsp_verdict", "SCX_DSP_LOCAL", 0x1LLU }, + { "scx_dsp_verdict", "SCX_DSP_PREV", 0x2LLU }, + { "scx_dsp_verdict", "SCX_DSP_RETRY", 0x3LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_FLAG_BUILTIN", 0x8000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_FLAG_LOCAL_ON", 0x4000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_INVALID", 0x8000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_GLOBAL", 0x8000000000000001LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL", 0x8000000000000002LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_BYPASS", 0x8000000000000003LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_REJECT", 0x8000000000000004LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_RESCUE", 0x8000000000000005LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL_ON", 0xc000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL_CPU_MASK", 0xffffffffLLU }, + { "scx_dsq_iter_flags", "SCX_DSQ_ITER_REV", 0x10000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_SLICE", 0x40000000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_VTIME", 0x80000000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_USER_FLAGS", 0x10000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_ALL_FLAGS", 0xc0010000LLU }, + { "scx_dsq_lnode_flags", "SCX_DSQ_LNODE_ITER_CURSOR", 0x1LLU }, + { "scx_dsq_lnode_flags", "__SCX_DSQ_LNODE_PRIV_SHIFT", 0x10LLU }, + { "scx_enable_state", "SCX_ENABLING", 0x0LLU }, + { "scx_enable_state", "SCX_ENABLED", 0x1LLU }, + { "scx_enable_state", "SCX_DISABLING", 0x2LLU }, + { "scx_enable_state", "SCX_DISABLED", 0x3LLU }, + { "scx_enq_flags", "SCX_ENQ_WAKEUP", 0x1LLU }, + { "scx_enq_flags", "SCX_ENQ_HEAD", 0x10000LLU }, + { "scx_enq_flags", "SCX_ENQ_CPU_SELECTED", 0x100000LLU }, + { "scx_enq_flags", "SCX_ENQ_PREEMPT", 0x100000000LLU }, + { "scx_enq_flags", "SCX_ENQ_IMMED", 0x200000000LLU }, + { "scx_enq_flags", "SCX_ENQ_RESCUE", 0x400000000LLU }, + { "scx_enq_flags", "SCX_ENQ_REENQ", 0x10000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_LAST", 0x20000000000LLU }, + { "scx_enq_flags", "__SCX_ENQ_INTERNAL_MASK", 0xff00000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_CLEAR_OPSS", 0x100000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_DSQ_PRIQ", 0x200000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_NESTED", 0x400000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_GDSQ_FALLBACK", 0x800000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_IGNORE_CAPS", 0x1000000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_APPLY_SLICE", 0x2000000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_SLICE_DFL", 0x4000000000000000LLU }, + { "scx_ent_dsq_flags", "SCX_TASK_DSQ_ON_PRIQ", 0x1LLU }, + { "scx_ent_flags", "SCX_TASK_QUEUED", 0x1LLU }, + { "scx_ent_flags", "SCX_TASK_IN_CUSTODY", 0x2LLU }, + { "scx_ent_flags", "SCX_TASK_RESET_RUNNABLE_AT", 0x4LLU }, + { "scx_ent_flags", "SCX_TASK_DEQD_FOR_SLEEP", 0x8LLU }, + { "scx_ent_flags", "SCX_TASK_SUB_INIT", 0x10LLU }, + { "scx_ent_flags", "SCX_TASK_IMMED", 0x20LLU }, + { "scx_ent_flags", "SCX_TASK_PROTECTED", 0x40LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_SHIFT", 0x8LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_BITS", 0x3LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_MASK", 0x700LLU }, + { "scx_ent_flags", "SCX_TASK_NONE", 0x0LLU }, + { "scx_ent_flags", "SCX_TASK_INIT_BEGIN", 0x100LLU }, + { "scx_ent_flags", "SCX_TASK_INIT", 0x200LLU }, + { "scx_ent_flags", "SCX_TASK_READY", 0x300LLU }, + { "scx_ent_flags", "SCX_TASK_ENABLED", 0x400LLU }, + { "scx_ent_flags", "SCX_TASK_DEAD", 0x500LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_SHIFT", 0xcLLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_BITS", 0x3LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_MASK", 0x7000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_NONE", 0x0LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_KFUNC", 0x1000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_IMMED", 0x2000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_PREEMPTED", 0x3000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_CAP", 0x4000LLU }, + { "scx_ent_flags", "SCX_TASK_CURSOR", 0xffffffff80000000LLU }, + { "scx_exit_code", "SCX_ECODE_RSN_HOTPLUG", 0x100000000LLU }, + { "scx_exit_code", "SCX_ECODE_RSN_CGROUP_OFFLINE", 0x200000000LLU }, + { "scx_exit_code", "SCX_ECODE_ACT_RESTART", 0x1000000000000LLU }, + { "scx_exit_flags", "SCX_EFLAG_INITIALIZED", 0x1LLU }, + { "scx_exit_kind", "SCX_EXIT_NONE", 0x0LLU }, + { "scx_exit_kind", "SCX_EXIT_DONE", 0x1LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG", 0x40LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG_BPF", 0x41LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG_KERN", 0x42LLU }, + { "scx_exit_kind", "SCX_EXIT_SYSRQ", 0x43LLU }, + { "scx_exit_kind", "SCX_EXIT_PARENT", 0x44LLU }, + { "scx_exit_kind", "SCX_EXIT_PARENT_KILL", 0x45LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR", 0x400LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_BPF", 0x401LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_STALL", 0x402LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_REENQ", 0x403LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_RESCUE", 0x404LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_UNLOCKED", 0x1LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_INIT_CIDS", 0x2LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_CPU_RELEASE", 0x4LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_DISPATCH", 0x8LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_ENQUEUE", 0x10LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_SELECT_CPU", 0x20LLU }, + { "scx_kick_flags", "SCX_KICK_IDLE", 0x1LLU }, + { "scx_kick_flags", "SCX_KICK_PREEMPT", 0x2LLU }, + { "scx_kick_flags", "SCX_KICK_WAIT", 0x4LLU }, + { "scx_opi", "SCX_OPI_BEGIN", 0x0LLU }, + { "scx_opi", "SCX_OPI_NORMAL_BEGIN", 0x0LLU }, + { "scx_opi", "SCX_OPI_NORMAL_END", 0x21LLU }, + { "scx_opi", "SCX_OPI_CPU_HOTPLUG_BEGIN", 0x21LLU }, + { "scx_opi", "SCX_OPI_CPU_HOTPLUG_END", 0x23LLU }, + { "scx_opi", "SCX_OPI_END", 0x23LLU }, + { "scx_ops_flags", "SCX_OPS_KEEP_BUILTIN_IDLE", 0x1LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_LAST", 0x2LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_EXITING", 0x4LLU }, + { "scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL", 0x8LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_MIGRATION_DISABLED", 0x10LLU }, + { "scx_ops_flags", "SCX_OPS_ALLOW_QUEUED_WAKEUP", 0x20LLU }, + { "scx_ops_flags", "SCX_OPS_BUILTIN_IDLE_PER_NODE", 0x40LLU }, + { "scx_ops_flags", "SCX_OPS_ALWAYS_ENQ_IMMED", 0x80LLU }, + { "scx_ops_flags", "SCX_OPS_TID_TO_TASK", 0x100LLU }, + { "scx_ops_flags", "SCX_OPS_ALL_FLAGS", 0x1ffLLU }, + { "scx_ops_flags", "__SCX_OPS_INTERNAL_MASK", 0xff00000000000000LLU }, + { "scx_ops_flags", "SCX_OPS_HAS_CPU_PREEMPT", 0x100000000000000LLU }, + { "scx_ops_state", "SCX_OPSS_NONE", 0x0LLU }, + { "scx_ops_state", "SCX_OPSS_QUEUEING", 0x1LLU }, + { "scx_ops_state", "SCX_OPSS_QUEUED", 0x2LLU }, + { "scx_ops_state", "SCX_OPSS_DISPATCHING", 0x3LLU }, + { "scx_ops_state", "SCX_OPSS_QSEQ_SHIFT", 0x2LLU }, + { "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_CORE", 0x1LLU }, + { "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_IN_NODE", 0x2LLU }, + { "scx_public_consts", "SCX_OPS_NAME_LEN", 0x80LLU }, + { "scx_public_consts", "SCX_SLICE_DFL", 0x1312d00LLU }, + { "scx_public_consts", "SCX_SLICE_BYPASS", 0x4c4b40LLU }, + { "scx_public_consts", "SCX_SLICE_INF", 0xffffffffffffffffLLU }, + { "scx_reenq_flags", "SCX_REENQ_ANY", 0x1LLU }, + { "scx_reenq_flags", "SCX_REENQ_CAP_REVOKE", 0x2LLU }, + { "scx_reenq_flags", "__SCX_REENQ_FILTER_MASK", 0xffffLLU }, + { "scx_reenq_flags", "__SCX_REENQ_USER_MASK", 0x1LLU }, + { "scx_reenq_flags", "SCX_REENQ_TSR_RQ_OPEN", 0x100000000LLU }, + { "scx_reenq_flags", "SCX_REENQ_TSR_NOT_FIRST", 0x200000000LLU }, + { "scx_reenq_flags", "__SCX_REENQ_TSR_MASK", 0xf00000000LLU }, + { "scx_rq_flags", "SCX_RQ_ONLINE", 0x1LLU }, + { "scx_rq_flags", "SCX_RQ_CAN_STOP_TICK", 0x2LLU }, + { "scx_rq_flags", "SCX_RQ_CLK_VALID", 0x20LLU }, + { "scx_rq_flags", "SCX_RQ_BAL_CB_PENDING", 0x40LLU }, + { "scx_rq_flags", "SCX_RQ_SUB_IDLE_RENOTIFY", 0x80LLU }, + { "scx_rq_flags", "SCX_RQ_ROOT_IDLE_RENOTIFY", 0x100LLU }, + { "scx_rq_flags", "SCX_RQ_IN_WAKEUP", 0x10000LLU }, + { "scx_rq_flags", "SCX_RQ_IN_DISPATCH", 0x20000LLU }, + { "scx_sched_pcpu_flags", "SCX_SCHED_PCPU_BYPASSING", 0x1LLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_BITS", 0x2bLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_BITS", 0x14LLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_MASK", 0x7ffffffffffLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_SHIFT", 0x2bLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_MASK", 0xfffffLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_PENDING", 0x8000000000000000LLU }, + { "scx_tg_flags", "SCX_TG_ONLINE", 0x1LLU }, + { "scx_tg_flags", "SCX_TG_INITED", 0x2LLU }, + { "scx_tg_flags", "SCX_TG_SUB_INIT", 0x4LLU }, + { "scx_wake_flags", "SCX_WAKE_FORK", 0x4LLU }, + { "scx_wake_flags", "SCX_WAKE_TTWU", 0x8LLU }, + { "scx_wake_flags", "SCX_WAKE_SYNC", 0x10LLU }, +}; + +#endif /* __ENUMS_ABI_AUTOGEN_H__ */ diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c index 64dd60b3e922..65dae9e45400 100644 --- a/tools/sched_ext/scx_central.bpf.c +++ b/tools/sched_ext/scx_central.bpf.c @@ -299,6 +299,7 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) u64 now = scx_bpf_now(); u64 nr_to_kick = nr_queued; s32 i, curr_cpu; + int ret; curr_cpu = bpf_get_smp_processor_id(); if (timer_pinned && (curr_cpu != central_cpu)) { @@ -332,7 +333,10 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT); } - bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, + timer_pinned ? BPF_F_TIMER_CPU_PIN : 0); + if (ret) + scx_bpf_error("bpf_timer_start failed (%d)", ret); __sync_fetch_and_add(&nr_timers, 1); return 0; } diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index 64cf4dd964d6..454ebb820c5e 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -937,7 +937,7 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to))) return; - delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now); + delta = (s64)(p->scx.dsq_vtime - from_cgc->tvtime_now); scx_bpf_task_set_dsq_vtime(p, to_cgc->tvtime_now + delta); } diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 5bb8b90a275a..9f6e61d7ca07 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -1246,7 +1246,8 @@ static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer) scx_read_event(&events, SCX_EV_BYPASS_ACTIVATE)); } - bpf_timer_start(timer, ONE_SEC_IN_NS, 0); + if (bpf_timer_start(timer, ONE_SEC_IN_NS, 0)) + scx_bpf_error("failed to re-arm stats timer"); return 0; } @@ -1268,7 +1269,8 @@ struct { static int lowpri_timerfn(void *map, int *key, struct bpf_timer *timer) { scx_bpf_dsq_reenq(LOWPRI_DSQ, 0); - bpf_timer_start(timer, LOWPRI_INTV_NS, 0); + if (bpf_timer_start(timer, LOWPRI_INTV_NS, 0)) + scx_bpf_error("failed to re-arm lowpri timer"); return 0; } @@ -1747,7 +1749,8 @@ static void rr_advance(void) static int round_robin_timerfn(void *map, int *key, struct bpf_timer *timer) { rr_advance(); - bpf_timer_start(timer, round_robin_ns, 0); + if (bpf_timer_start(timer, round_robin_ns, 0)) + scx_bpf_error("failed to re-arm round-robin timer"); return 0; } diff --git a/tools/testing/selftests/arm64/config b/tools/testing/selftests/arm64/config new file mode 100644 index 000000000000..0fa975585392 --- /dev/null +++ b/tools/testing/selftests/arm64/config @@ -0,0 +1,17 @@ +CONFIG_ARM64_BTI=y +CONFIG_ARM64_GCS=y +CONFIG_ARM64_MTE=y +CONFIG_ARM64_POE=y +CONFIG_ARM64_PTR_AUTH=y +CONFIG_ARM64_SME=y +CONFIG_ARM64_SVE=y +CONFIG_ARM64_TAGGED_ADDR_ABI=y +CONFIG_HUGETLBFS=y +CONFIG_KSM=y +CONFIG_PROC_FS=y +CONFIG_SECCOMP=y +CONFIG_SECCOMP_FILTER=y +CONFIG_SHMEM=y +CONFIG_SYSCTL=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y diff --git a/tools/testing/selftests/arm64/mte/check_buffer_fill.c b/tools/testing/selftests/arm64/mte/check_buffer_fill.c index ff4e07503349..039b1d7d8566 100644 --- a/tools/testing/selftests/arm64/mte/check_buffer_fill.c +++ b/tools/testing/selftests/arm64/mte/check_buffer_fill.c @@ -406,6 +406,8 @@ int main(int argc, char *argv[]) size_t page_size = getpagesize(); int item = ARRAY_SIZE(sizes); + ksft_print_header(); + sizes[item - 3] = page_size - 1; sizes[item - 2] = page_size; sizes[item - 1] = page_size + 1; diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c index 5e97ee792e4d..e6a8acca2a94 100644 --- a/tools/testing/selftests/arm64/mte/check_child_memory.c +++ b/tools/testing/selftests/arm64/mte/check_child_memory.c @@ -146,6 +146,8 @@ int main(int argc, char *argv[]) int err; int item = ARRAY_SIZE(sizes); + ksft_print_header(); + page_size = getpagesize(); if (!page_size) { ksft_print_msg("ERR: Unable to get page size\n"); diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c index 325bca0de0f6..d23f154d3288 100644 --- a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c +++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c @@ -131,6 +131,7 @@ int main(int argc, char *argv[]) if (err) return err; + ksft_print_header(); ksft_set_plan(1); evaluate_test(mte_gcr_fork_test(), diff --git a/tools/testing/selftests/arm64/mte/check_hugetlb_options.c b/tools/testing/selftests/arm64/mte/check_hugetlb_options.c index aad1234c7e0f..23e4a7a9950c 100644 --- a/tools/testing/selftests/arm64/mte/check_hugetlb_options.c +++ b/tools/testing/selftests/arm64/mte/check_hugetlb_options.c @@ -230,6 +230,8 @@ int main(int argc, char *argv[]) void *map_ptr; unsigned long map_size; + ksft_print_header(); + err = mte_default_setup(); if (err) return err; diff --git a/tools/testing/selftests/arm64/mte/check_ksm_options.c b/tools/testing/selftests/arm64/mte/check_ksm_options.c index 0cf5faef1724..4855b737d550 100644 --- a/tools/testing/selftests/arm64/mte/check_ksm_options.c +++ b/tools/testing/selftests/arm64/mte/check_ksm_options.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -22,6 +23,20 @@ static size_t page_sz; static unsigned long ksm_sysfs[5]; +static bool has_merge_across_nodes; + +static bool merge_across_nodes_available(void) +{ + const char *path = PATH_KSM "merge_across_nodes"; + + if (!access(path, R_OK | W_OK)) + return true; + if (errno == ENOENT) + return false; + + ksft_exit_skip("Unable to read and write %s: %s\n", path, + strerror(errno)); +} static unsigned long read_sysfs(char *str) { @@ -56,8 +71,10 @@ static void write_sysfs(char *str, unsigned long val) static void mte_ksm_setup(void) { - ksm_sysfs[0] = read_sysfs(PATH_KSM "merge_across_nodes"); - write_sysfs(PATH_KSM "merge_across_nodes", 1); + if (has_merge_across_nodes) { + ksm_sysfs[0] = read_sysfs(PATH_KSM "merge_across_nodes"); + write_sysfs(PATH_KSM "merge_across_nodes", 1); + } ksm_sysfs[1] = read_sysfs(PATH_KSM "sleep_millisecs"); write_sysfs(PATH_KSM "sleep_millisecs", 0); ksm_sysfs[2] = read_sysfs(PATH_KSM "run"); @@ -70,7 +87,8 @@ static void mte_ksm_setup(void) static void mte_ksm_restore(void) { - write_sysfs(PATH_KSM "merge_across_nodes", ksm_sysfs[0]); + if (has_merge_across_nodes) + write_sysfs(PATH_KSM "merge_across_nodes", ksm_sysfs[0]); write_sysfs(PATH_KSM "sleep_millisecs", ksm_sysfs[1]); write_sysfs(PATH_KSM "run", ksm_sysfs[2]); write_sysfs(PATH_KSM "max_page_sharing", ksm_sysfs[3]); @@ -132,9 +150,16 @@ int main(int argc, char *argv[]) { int err; + ksft_print_header(); + err = mte_default_setup(); if (err) return err; + + if (geteuid() != 0) + ksft_exit_skip("Please run the test as root\n"); + + has_merge_across_nodes = merge_across_nodes_available(); page_sz = getpagesize(); if (!page_sz) { ksft_print_msg("ERR: Unable to get page size\n"); diff --git a/tools/testing/selftests/arm64/mte/check_mmap_options.c b/tools/testing/selftests/arm64/mte/check_mmap_options.c index c100af3012cb..492f2cd41f43 100644 --- a/tools/testing/selftests/arm64/mte/check_mmap_options.c +++ b/tools/testing/selftests/arm64/mte/check_mmap_options.c @@ -945,6 +945,8 @@ int main(int argc, char *argv[]) }, }; + ksft_print_header(); + err = mte_default_setup(); if (err) return err; diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c index f7f320defa7b..d16a91117eef 100644 --- a/tools/testing/selftests/arm64/mte/check_prctl.c +++ b/tools/testing/selftests/arm64/mte/check_prctl.c @@ -119,7 +119,7 @@ int main(void) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(mte_modes)); + ksft_set_plan(ARRAY_SIZE(mte_modes) + 1); check_basic_read(); for (i = 0; i < ARRAY_SIZE(mte_modes); i++) diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c index 4b764f2a8185..6b4fa6705d7c 100644 --- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c +++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c @@ -175,6 +175,8 @@ int main(int argc, char *argv[]) { int err; + ksft_print_header(); + err = mte_default_setup(); if (err) return err; diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c index fb7936c4e097..af343aa61732 100644 --- a/tools/testing/selftests/arm64/mte/check_user_mem.c +++ b/tools/testing/selftests/arm64/mte/check_user_mem.c @@ -201,6 +201,8 @@ int main(int argc, char *argv[]) int tag_offsets[] = {page_sz, MT_GRANULE_SIZE}; char test_name[TEST_NAME_MAX]; + ksft_print_header(); + page_sz = getpagesize(); if (!page_sz) { ksft_print_msg("ERR: Unable to get page size\n"); diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index e9bee164bb70..20d2b63774c3 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -919,7 +919,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) { if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME)) ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n"); @@ -932,6 +931,7 @@ int main(int argc, char *argv[]) ksft_exit_skip("Failed to set memory controller\n"); post_v2_setup: + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index f9f7017d9299..735a53bb222b 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -832,7 +832,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -840,6 +839,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpu")) ksft_exit_skip("Failed to set cpu controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c index 8c2d4d4ef1fc..3dfadd280c1c 100644 --- a/tools/testing/selftests/cgroup/test_cpuset.c +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -497,7 +497,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -505,6 +504,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpuset")) ksft_exit_skip("Failed to set cpuset controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index da8f7b920178..131d8b4551ef 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -797,7 +797,6 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) - HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -835,11 +834,6 @@ check_isolcpus() ISOLCPUS= EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN - # - # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS - # - [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 - # # Use the sched domain in debugfs to check isolated CPUs, if available # @@ -1161,6 +1155,63 @@ test_isolated() pause 0.05 } +# +# Select an online CPU isolated from scheduler domains at boot. +# $1: test name used in the skip message +# +get_boot_isolated_cpu() +{ + TEST_NAME=$1 + BOOT_ISOLATED_FILE=/sys/devices/system/cpu/isolated + + [[ -r $BOOT_ISOLATED_FILE ]] || { + echo "$TEST_NAME test SKIPPED: boot isolation state unavailable" + return 1 + } + BOOT_CPUS=$(cat $BOOT_ISOLATED_FILE) + [[ -n "$BOOT_CPUS" ]] || { + echo "$TEST_NAME test SKIPPED: no boot-isolated CPU" + return 1 + } + + BOOT_CPU=$(echo "$BOOT_CPUS" | sed -e 's/[,-].*//') + CPU_ONLINE=/sys/devices/system/cpu/cpu${BOOT_CPU}/online + [[ ! -e $CPU_ONLINE || $(cat $CPU_ONLINE) -eq 1 ]] || { + echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is offline" + return 1 + } +} + +# +# A CPU isolated at boot must stay isolated after it is released by a dynamic +# isolated partition. +# +test_boot_isolated() +{ + TEST_NAME="Boot-isolated CPU partition release" + get_boot_isolated_cpu "$TEST_NAME" || return 0 + echo "Running $TEST_NAME test ..." + + cd $CGROUP2/test + echo member > cpuset.cpus.partition + echo $BOOT_CPU > cpuset.cpus + [[ $(cat cpuset.cpus.effective) = "$BOOT_CPU" ]] || { + echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is unavailable" + echo "" > cpuset.cpus + cd $CGROUP2 + return 0 + } + test_partition isolated + test_partition member + check_isolcpus "." || { + echo "Boot-isolated CPU $BOOT_CPU was lost after partition release" + exit 1 + } + echo "" > cpuset.cpus + cd $CGROUP2 + echo "$TEST_NAME test PASSED." +} + # # Wait for inotify event for the given file and read it # $1: cgroup file to wait for @@ -1232,5 +1283,6 @@ trap cleanup 0 2 3 6 run_state_test TEST_MATRIX run_remote_state_test REMOTE_TEST_MATRIX test_isolated +test_boot_isolated test_inotify echo "All tests PASSED." diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 0569e93fa6b0..f28bb02e9783 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -1491,9 +1491,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index f6cd23a8ecc7..bac1ddd8cb94 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include "kselftest.h" @@ -261,6 +262,59 @@ static int test_cgkill_forkbomb(const char *root) return ret; } +/* + * Test that a cgroup that was killed in the past can still be the target + * of clone3(CLONE_INTO_CGROUP): writing cgroup.kill must only kill the + * tasks in the cgroup at the time of the write, not tasks cloned into + * it afterwards. + */ +static int test_cgkill_clone_into_killed(const char *root) +{ + pid_t pid; + int cgroup_fd = -EBADF; + int ret = KSFT_FAIL; + char *cgroup = NULL; + + cgroup = cg_name(root, "cg_test_clone_into_killed"); + if (!cgroup) + goto cleanup; + + if (cg_create(cgroup)) + goto cleanup; + + /* Kill the cgroup while it is still empty. */ + if (cg_write(cgroup, "cgroup.kill", "1")) + goto cleanup; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + goto cleanup; + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) { + if (errno == ENOSYS) + ret = KSFT_SKIP; + goto cleanup; + } + + if (pid == 0) + exit(EXIT_SUCCESS); + + /* The child must not be SIGKILLed; it has to exit cleanly. */ + if (clone_reap(pid, WEXITED) != EXIT_SUCCESS) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (cgroup_fd >= 0) + close(cgroup_fd); + if (cgroup) + cg_destroy(cgroup); + free(cgroup); + return ret; +} + #define T(x) { x, #x } struct cgkill_test { int (*fn)(const char *root); @@ -269,6 +323,7 @@ struct cgkill_test { T(test_cgkill_simple), T(test_cgkill_tree), T(test_cgkill_forkbomb), + T(test_cgkill_clone_into_killed), }; #undef T @@ -278,9 +333,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 1db0ba1226b9..437f2d35f205 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -145,7 +145,7 @@ static int cg_run_in_subcgroups(const char *parent, return -1; } - if (cg_run(child, fn, NULL)) { + if (cg_run(child, fn, arg)) { cg_destroy(child); free(child); return -1; @@ -426,7 +426,6 @@ int main(int argc, char **argv) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -441,6 +440,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 0ebf796f3cff..3a84d068fbf3 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -1798,7 +1798,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -1823,6 +1822,7 @@ int main(int argc, char **argv) ksft_exit_skip("Failed to query cgroup mount option\n"); has_localevents = proc_status; + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c index 9a387c815d2c..710109b53dfe 100644 --- a/tools/testing/selftests/cgroup/test_pids.c +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -148,7 +148,6 @@ int main(int argc, char **argv) char root[PATH_MAX]; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -163,6 +162,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+pids")) ksft_exit_skip("Failed to set pids controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (int i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index f7b4c4370db6..609c48f38524 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -819,7 +819,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -836,6 +835,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 0f5c178bc224..517c09d60bef 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -28,6 +28,7 @@ TEST_PROGS := \ double_udp_encap.sh \ drop_monitor_tests.sh \ ecmp_rehash.sh \ + exception_cache.sh \ fcnal-ipv4.sh \ fcnal-ipv6.sh \ fcnal-other.sh \ diff --git a/tools/testing/selftests/net/exception_cache.sh b/tools/testing/selftests/net/exception_cache.sh new file mode 100755 index 000000000000..8d3eed5c532a --- /dev/null +++ b/tools/testing/selftests/net/exception_cache.sh @@ -0,0 +1,521 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that the state of the route exception cache after an ICMP error is +# processed does not depend on whether the quoted packet was matched to a +# socket. Otherwise, an off-path attacker can probe the cache to discover the +# ephemeral port used by a connected UDP socket. +# +# When the quoted packet is not matched to a socket, the same exception is +# created as when it is matched, so that neither its presence nor its contents +# reveal the result of socket matching. +# +# +----+ +# +---------| r1 | +# | +----+ +# +----+ +--------+ | .1 +# | h1 |---| bridge | | 198.51.100.0/30 +# +----+ +--------+ | 2001:db8:2::/64 +# .1 | | .2 +# | +----+ +----+ +# +---------| r2 |-----------| h2 | +# .2 .3 +----+ .1 .2 +----+ +# 203.0.113.0/24 +# 2001:db8:3::/64 +# 192.0.2.0/24 +# 2001:db8:1::/64 +# +# Traffic from h1 to h2 is routed via r1, which reaches h2's network via r2 +# over the point-to-point link. The MTU of the r2 - h2 link is lowered so that +# r2 emits ICMP errors towards h1. +# +# For the redirect tests r1's route to h2's network is replaced with one via r2 +# on the shared segment, so that r1 forwards the packet back to the segment it +# arrived from and emits a redirect towards h1. +# +# The packets that provoke the ICMP errors are injected with a packet socket so +# that no socket is ever associated with them. A socket is created separately, +# with socat, when a test needs the ICMP error to be matched. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2329 +source lib.sh + +require_command jq +require_command mausezahn +require_command nstat +require_command socat + +ALL_TESTS=" + pmtu_no_socket_ipv4 + pmtu_no_socket_ipv6 + pmtu_socket_ipv4 + pmtu_socket_ipv6 + pmtu_omit_ipv4 + pmtu_omit_ipv6 + redirect_no_socket_ipv4 + redirect_no_socket_ipv6 + redirect_socket_ipv4 + redirect_socket_ipv6 +" + +# Shared segment. +H1_ADDR4=192.0.2.1 +R1_ADDR4=192.0.2.2 +R2_ADDR4=192.0.2.3 +H1_ADDR6=2001:db8:1::1 +R1_ADDR6=2001:db8:1::2 +R2_ADDR6=2001:db8:1::3 + +# r1 - r2 link. +R2_R1_ADDR4=198.51.100.2 +R2_R1_ADDR6=2001:db8:2::2 + +# r2 - h2 link. +H2_ADDR4=203.0.113.2 +H2_NET4=203.0.113.0/24 +H2_ADDR6=2001:db8:3::2 +H2_NET6=2001:db8:3::/64 + +SPORT=12345 +DPORT=54321 + +# The MTU of the shared segment and of the r1 - r2 link. Large enough for the +# injected packets to reach r2 intact. +SEGMENT_MTU=2000 +# Size of the injected packets. The PMTU tests need a size that exceeds every +# MTU used for the r2 - h2 link, so that r2 responds with an ICMP error. The +# redirect tests need a size that does not, otherwise r2 would respond with an +# ICMP error in addition to the redirect emitted by r1. +PMTU_PACKET_SIZE=1800 +REDIRECT_PACKET_SIZE=100 + +# The MTUs used for the r2 - h2 link. All of them must be at least +# IPV6_MIN_MTU, otherwise IPv6 silently ignores the error instead of creating +# an exception. +MTU_MID=1400 +MTU_LOW=1300 + +# Values for the IP{,V6}_MTU_DISCOVER socket option. +PMTUDISC_DONT=0 +PMTUDISC_OMIT=5 + +SOCAT_PID= + +linklocal_get() +{ + local ns=$1; shift + local dev=$1; shift + + ip -n "$ns" -j -6 addr show dev "$dev" | \ + jq -r '.[]["addr_info"][] | select(.scope == "link") | .local' +} + +linklocal_exists() +{ + local ns=$1; shift + local dev=$1; shift + + [ -n "$(linklocal_get "$ns" "$dev")" ] +} + +family_vars_set() +{ + local family=$1; shift + + FAMILY=$family + + if [ "$family" -eq 4 ]; then + H1_ADDR=$H1_ADDR4 + H2_ADDR=$H2_ADDR4 + MZ_FAMILY_OPT=() + # Without the Don't Fragment bit set r2 fragments the packet + # instead of reporting the MTU of the next hop. + MZ_IP_OPTS="df," + SOCAT_DST="UDP4-CONNECT:$H2_ADDR4:$DPORT" + SOCAT_BIND="bind=$H1_ADDR4:$SPORT" + SOCAT_PMTUDISC="ip-mtu-discover" + else + H1_ADDR=$H1_ADDR6 + H2_ADDR=$H2_ADDR6 + MZ_FAMILY_OPT=(-6) + MZ_IP_OPTS= + SOCAT_DST="UDP6-CONNECT:[$H2_ADDR6]:$DPORT" + SOCAT_BIND="bind=[$H1_ADDR6]:$SPORT" + SOCAT_PMTUDISC="ipv6-mtu-discover" + fi +} + +topology_setup() +{ + local ns + + setup_ns h1 r1 r2 h2 sw + defer cleanup_all_ns + + # Link-local addresses are generated from the MAC address and read + # back during setup, so request that generation mode explicitly and + # make the addresses available as soon as the devices are brought up. + for ns in "$h1" "$r1" "$r2" "$h2" "$sw"; do + ip netns exec "$ns" sysctl -qw \ + net.ipv6.conf.default.addr_gen_mode=0 \ + net.ipv6.conf.default.accept_dad=0 \ + net.ipv6.conf.all.accept_dad=0 + done + + ip -n "$sw" link add name br0 type bridge + ip -n "$sw" link set dev br0 mtu "$SEGMENT_MTU" up + + ip -n "$h1" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp1 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r1" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp2 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r2" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp3 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r1" link add name eth1 mtu "$SEGMENT_MTU" type veth \ + peer name eth1 mtu "$SEGMENT_MTU" netns "$r2" + ip -n "$r2" link add name eth2 type veth peer name eth0 netns "$h2" + + ip -n "$sw" link set dev swp1 master br0 up + ip -n "$sw" link set dev swp2 master br0 up + ip -n "$sw" link set dev swp3 master br0 up + + ip -n "$h1" link set dev eth0 up + ip -n "$r1" link set dev eth0 up + ip -n "$r1" link set dev eth1 up + ip -n "$r2" link set dev eth0 up + ip -n "$r2" link set dev eth1 up + ip -n "$r2" link set dev eth2 up + ip -n "$h2" link set dev eth0 up + + ip -n "$h1" address add "$H1_ADDR4/24" dev eth0 + ip -n "$r1" address add "$R1_ADDR4/24" dev eth0 + ip -n "$r2" address add "$R2_ADDR4/24" dev eth0 + ip -n "$r1" address add 198.51.100.1/30 dev eth1 + ip -n "$r2" address add "$R2_R1_ADDR4/30" dev eth1 + ip -n "$r2" address add 203.0.113.1/24 dev eth2 + ip -n "$h2" address add "$H2_ADDR4/24" dev eth0 + + ip -n "$h1" -6 address add "$H1_ADDR6/64" dev eth0 nodad + ip -n "$r1" -6 address add "$R1_ADDR6/64" dev eth0 nodad + ip -n "$r2" -6 address add "$R2_ADDR6/64" dev eth0 nodad + ip -n "$r1" -6 address add 2001:db8:2::1/64 dev eth1 nodad + ip -n "$r2" -6 address add "$R2_R1_ADDR6/64" dev eth1 nodad + ip -n "$r2" -6 address add 2001:db8:3::1/64 dev eth2 nodad + ip -n "$h2" -6 address add "$H2_ADDR6/64" dev eth0 nodad + + ip netns exec "$r1" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "$r1" sysctl -qw net.ipv4.conf.all.send_redirects=1 + ip netns exec "$r1" sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec "$r2" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "$r2" sysctl -qw net.ipv6.conf.all.forwarding=1 + + ip netns exec "$h1" sysctl -qw net.ipv4.conf.all.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv4.conf.eth0.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv6.conf.all.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv6.conf.eth0.accept_redirects=1 + + slowwait 5 linklocal_exists "$r1" eth0 + check_err $? "r1: link-local address was not generated" + slowwait 5 linklocal_exists "$r2" eth0 + check_err $? "r2: link-local address was not generated" + + R1_LLADDR=$(linklocal_get "$r1" eth0) + R2_LLADDR=$(linklocal_get "$r2" eth0) + R1_MAC=$(ip -n "$r1" -j link show dev eth0 | jq -r '.[]["address"]') + R2_MAC=$(ip -n "$r2" -j link show dev eth0 | jq -r '.[]["address"]') + + ip -n "$h1" route add "$H2_NET4" via "$R1_ADDR4" dev eth0 + ip -n "$h1" -6 route add "$H2_NET6" via "$R1_LLADDR" dev eth0 + ip -n "$r1" route add "$H2_NET4" via "$R2_R1_ADDR4" dev eth1 + ip -n "$r1" -6 route add "$H2_NET6" via "$R2_R1_ADDR6" dev eth1 + ip -n "$h2" route add default via 203.0.113.1 dev eth0 + ip -n "$h2" -6 route add default via 2001:db8:3::1 dev eth0 + + far_mtu_set "$MTU_MID" +} + +# Make r1 forward towards h2's network over the segment it receives the packet +# from, so that it emits a redirect towards h1. +redirect_route_set() +{ + ip -n "$r1" route replace "$H2_NET4" via "$R2_ADDR4" dev eth0 + ip -n "$r1" -6 route replace "$H2_NET6" via "$R2_LLADDR" dev eth0 + + # __ip_do_redirect() only creates an exception if the new gateway is + # already a valid neighbour. Otherwise it merely triggers address + # resolution. IPv6 resolves the target itself, in rt6_do_redirect(). + ip -n "$h1" neigh replace "$R2_ADDR4" lladdr "$R2_MAC" dev eth0 \ + nud permanent +} + +far_mtu_set() +{ + local mtu=$1; shift + + ip -n "$r2" link set dev eth2 mtu "$mtu" + ip -n "$h2" link set dev eth0 mtu "$mtu" +} + +socket_is_open() +{ + ip netns exec "$h1" ss -uHn "sport = :$SPORT" | grep -q . +} + +socket_start() +{ + # Disable PMTU discovery by default so that ICMP errors are not + # reported to the socket. Otherwise socat would exit when the first one + # arrives and later packets in the same test would not be matched to a + # socket. The exception is still created, as ip{,6}_sk_accept_pmtu() + # only rejects IP{,V6}_PMTUDISC_{INTERFACE,OMIT}. + local pmtudisc=${1:-$PMTUDISC_DONT} + + # Send socat's diagnostics to /dev/null. It reports the ICMP errors + # that reach the socket, which is exactly what the tests provoke. + ip netns exec "$h1" socat -u -lf/dev/null \ + "$SOCAT_DST,$SOCAT_BIND,$SOCAT_PMTUDISC=$pmtudisc" \ + OPEN:/dev/null,wronly=1 & + SOCAT_PID=$! + defer socket_stop + + slowwait 5 socket_is_open + check_err $? "socket did not open" +} + +socket_stop() +{ + [ -z "$SOCAT_PID" ] && return 0 + + kill "$SOCAT_PID" &> /dev/null + wait "$SOCAT_PID" 2> /dev/null + SOCAT_PID= +} + +# Inject a packet towards h2 with a packet socket. No socket is associated with +# it, so an ICMP error quoting it is matched to a socket only if one was +# created separately with the same source port. +packet_send() +{ + local size=$1; shift + + ip netns exec "$h1" mausezahn "${MZ_FAMILY_OPT[@]}" eth0 \ + -a own -b "$R1_MAC" -A "$H1_ADDR" -B "$H2_ADDR" \ + -t udp "${MZ_IP_OPTS}sp=$SPORT,dp=$DPORT" \ + -p "$size" -c 1 -q +} + +exception_show() +{ + if [ "$FAMILY" -eq 4 ]; then + # IPv4 exceptions without a bound route are not dumped, but + # "route get" reports the exception and binds a route to it. + ip -n "$h1" route get "$H2_ADDR" + else + # IPv6 does not report a cache indication in "route get" + # output, so dump the exceptions instead. + ip -n "$h1" -6 route show cache | grep -F "$H2_ADDR" || true + fi +} + +exception_mtu_get() +{ + exception_show | grep -o "mtu [0-9]*" | cut -d ' ' -f 2 +} + +exception_gw_get() +{ + exception_show | grep -o "via [0-9a-f.:]*" | cut -d ' ' -f 2 +} + +exception_mtu_check() +{ + local expected=$1; shift + + [ "$(exception_mtu_get)" = "$expected" ] +} + +icmp_errors_get() +{ + local ctr=IcmpInDestUnreachs + + [ "$FAMILY" -eq 6 ] && ctr=Icmp6InPktTooBigs + + ip netns exec "$h1" nstat -asz "$ctr" | \ + awk -v ctr="$ctr" '$1 == ctr { print $2 }' +} + +exception_pmtu_check() +{ + local mtu=$1; shift + local desc=$1; shift + + busywait "$BUSYWAIT_TIMEOUT" exception_mtu_check "$mtu" + check_err $? "$desc: exception does not carry an MTU of $mtu" +} + +pmtu_no_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "No socket" + + log_test "IPv$family: PMTU: exception without a matching socket" +} + +pmtu_no_socket_ipv4() +{ + pmtu_no_socket 4 +} + +pmtu_no_socket_ipv6() +{ + pmtu_no_socket 6 +} + +pmtu_socket() +{ + local family=$1; shift + local t0 + + RET=0 + family_vars_set "$family" + topology_setup + socket_start + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "Matching socket" + + # A lower PMTU replaces the one currently stored in the exception. + far_mtu_set "$MTU_LOW" + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_LOW" "Lower PMTU" + + # A higher PMTU is ignored, so the exception is left as it is. Wait + # for the error to be received, as otherwise the check below would + # pass even if it never was. + far_mtu_set "$MTU_MID" + t0=$(icmp_errors_get) + packet_send "$PMTU_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" until_counter_is ">= $((t0 + 1))" \ + icmp_errors_get > /dev/null + check_err $? "Higher PMTU: ICMP error was not received" + + exception_mtu_check "$MTU_LOW" + check_err $? "Higher PMTU: exception does not carry an MTU of $MTU_LOW" + + log_test "IPv$family: PMTU: exception with a matching socket" +} + +pmtu_socket_ipv4() +{ + pmtu_socket 4 +} + +pmtu_socket_ipv6() +{ + pmtu_socket 6 +} + +pmtu_omit() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + socket_start "$PMTUDISC_OMIT" + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "PMTU discovery disabled" + + log_test "IPv$family: PMTU: exception with a socket ignoring it" +} + +pmtu_omit_ipv4() +{ + pmtu_omit 4 +} + +pmtu_omit_ipv6() +{ + pmtu_omit 6 +} + +exception_gw_check() +{ + local expected=$1; shift + + [ -n "$expected" ] && [ "$(exception_gw_get)" = "$expected" ] +} + +redirect_gw_new() +{ + if [ "$FAMILY" -eq 4 ]; then + echo "$R2_ADDR4" + else + echo "$R2_LLADDR" + fi +} + +redirect_no_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + redirect_route_set + + packet_send "$REDIRECT_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)" + check_err $? "No socket: exception does not carry the new gateway" + + log_test "IPv$family: Redirect: exception without a matching socket" +} + +redirect_no_socket_ipv4() +{ + redirect_no_socket 4 +} + +redirect_no_socket_ipv6() +{ + redirect_no_socket 6 +} + +redirect_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + redirect_route_set + socket_start + + packet_send "$REDIRECT_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)" + check_err $? "Matching socket: exception does not carry the new gateway" + + log_test "IPv$family: Redirect: exception with a matching socket" +} + +redirect_socket_ipv4() +{ + redirect_socket 4 +} + +redirect_socket_ipv6() +{ + redirect_socket 6 +} + +trap defer_scopes_cleanup EXIT +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh index 58da5de99ac4..f9600aabd4a2 100755 --- a/tools/testing/selftests/net/test_vxlan_mdb.sh +++ b/tools/testing/selftests/net/test_vxlan_mdb.sh @@ -685,6 +685,9 @@ star_g_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $grp dst $vtep_ip src_vni 10010" log_test $? 255 "Invalid source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $all_zeros_grp dst $vtep_ip src_vni 10010" + log_test $? 255 "All-zeros source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent source_list $src1 dst $vtep_ip src_vni 10010" log_test $? 255 "Source list without filter mode" } @@ -784,6 +787,9 @@ sg_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $grp permanent dst $vtep_ip src_vni 10010" log_test $? 255 "(S, G) with an invalid source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $all_zeros_grp permanent dst $vtep_ip src_vni 10010" + log_test $? 255 "(S, G) with an all-zeros source" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $all_zeros_grp src $src permanent dst $vtep_ip src_vni 10010" log_test $? 255 "All-zeros group with source" } diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json index b2ca9d4e991b..e2b03f2b5e89 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -353,5 +353,28 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "70fd", + "name": "Add u32 filter when node ID pool is exhausted (4096th filter rejected)", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY clsact", + "bash -c 'for i in {1..4095}; do echo filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0; done | $TC -b -'" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0", + "expExitCode": "2", + "verifyCmd": "$TC -d filter show dev $DUMMY ingress", + "matchPattern": "fh 800::", + "matchCount": "4095", + "teardown": [ + "$TC qdisc del dev $DUMMY clsact" + ] } ] diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index 31afc24ef17b..9313ebe0c525 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -78,6 +78,12 @@ def cpumask_str(cpumask): wq_type_len = 9 +def wq_attrs(wq): + try: + return wq.attrs + except AttributeError: + return wq.unbound_attrs + def wq_type_str(wq): if wq.flags & WQ_BH: return f'{"bh":{wq_type_len}}' @@ -85,7 +91,7 @@ def wq_type_str(wq): if wq.flags & WQ_ORDERED: return f'{"ordered":{wq_type_len}}' else: - if wq.attrs.affn_strict: + if wq_attrs(wq).affn_strict: return f'{"unbound,S":{wq_type_len}}' else: return f'{"unbound":{wq_type_len}}' @@ -206,7 +212,7 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='') if wq.flags & WQ_UNBOUND: - print(f' {cpumask_str(wq.attrs.cpumask):{ucpus_len}}', end='') + print(f' {cpumask_str(wq_attrs(wq).cpumask):{ucpus_len}}', end='') else: print(f' {"":{ucpus_len}}', end='')