diff options
1124 files changed, 21387 insertions, 16063 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index f627e705e663..b268e3e18b4a 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -512,3 +512,19 @@ Date: July 2021 Contact: "Daeho Jeong" <daehojeong@google.com> Description: You can control the multiplier value of bdi device readahead window size between 2 (default) and 256 for POSIX_FADV_SEQUENTIAL advise option. + +What: /sys/fs/f2fs/<disk>/max_fragment_chunk +Date: August 2021 +Contact: "Daeho Jeong" <daehojeong@google.com> +Description: With "mode=fragment:block" mount options, we can scatter block allocation. + f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole + in the length of 1..<max_fragment_hole> by turns. This value can be set + between 1..512 and the default value is 4. + +What: /sys/fs/f2fs/<disk>/max_fragment_hole +Date: August 2021 +Contact: "Daeho Jeong" <daehojeong@google.com> +Description: With "mode=fragment:block" mount options, we can scatter block allocation. + f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole + in the length of 1..<max_fragment_hole> by turns. This value can be set + between 1..512 and the default value is 4. diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index 0febe458597c..cf1eeefdfc32 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -61,8 +61,9 @@ arg3: ``pid`` of the task for which the operation applies. arg4: - ``pid_type`` for which the operation applies. It is of type ``enum pid_type``. - For example, if arg4 is ``PIDTYPE_TGID``, then the operation of this command + ``pid_type`` for which the operation applies. It is one of + ``PR_SCHED_CORE_SCOPE_``-prefixed macro constants. For example, if arg4 + is ``PR_SCHED_CORE_SCOPE_THREAD_GROUP``, then the operation of this command will be performed for all tasks in the task group of ``pid``. arg5: diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0905d2cdb2d5..9725c546a0d4 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3253,6 +3253,19 @@ driver. A non-zero value sets the minimum interval in seconds between layoutstats transmissions. + nfsd.inter_copy_offload_enable = + [NFSv4.2] When set to 1, the server will support + server-to-server copies for which this server is + the destination of the copy. + + nfsd.nfsd4_ssc_umount_timeout = + [NFSv4.2] When used as the destination of a + server-to-server copy, knfsd temporarily mounts + the source server. It caches the mount in case + it will be needed again, and discards it if not + used for the number of milliseconds specified by + this parameter. + nfsd.nfs4_disable_idmapping= [NFSv4] When set to the default of '1', the NFSv4 server will return only numeric uids and gids to @@ -3260,6 +3273,7 @@ and gids from such clients. This is intended to ease migration from NFSv2/v3. + nmi_backtrace.backtrace_idle [KNL] Dump stacks even of idle CPUs in response to an NMI stack-backtrace request. @@ -6379,6 +6393,13 @@ improve timer resolution at the expense of processing more timer interrupts. + xen.balloon_boot_timeout= [XEN] + The time (in seconds) to wait before giving up to boot + in case initial ballooning fails to free enough memory. + Applies only when running as HVM or PVH guest and + started with less memory configured than allowed at + max. Default is 180. + xen.event_eoi_delay= [XEN] How long to delay EOI handling in case of event storms (jiffies). Default is 10. diff --git a/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml b/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml index e17143cac316..252085a0cf65 100644 --- a/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml +++ b/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml @@ -42,6 +42,9 @@ properties: "#clock-cells": const: 1 + "#reset-cells": + const: 1 + required: - compatible - reg @@ -57,4 +60,5 @@ examples: reg = <0x10000000 0x1000>; clocks = <&hfclk>, <&rtcclk>; #clock-cells = <1>; + #reset-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/clock/silabs,si5351.txt b/Documentation/devicetree/bindings/clock/silabs,si5351.txt index 8fe6f80afade..bfda6af76bee 100644 --- a/Documentation/devicetree/bindings/clock/silabs,si5351.txt +++ b/Documentation/devicetree/bindings/clock/silabs,si5351.txt @@ -2,7 +2,7 @@ Binding for Silicon Labs Si5351a/b/c programmable i2c clock generator. Reference [1] Si5351A/B/C Data Sheet - https://www.silabs.com/Support%20Documents/TechnicalDocs/Si5351.pdf + https://www.skyworksinc.com/-/media/Skyworks/SL/documents/public/data-sheets/Si5351-B.pdf The Si5351a/b/c are programmable i2c clock generators with up to 8 output clocks. Si5351a also has a reduced pin-count package (MSOP10) where only diff --git a/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml b/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml index c3930edc410f..9a0cc7341630 100644 --- a/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml +++ b/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml @@ -23,6 +23,7 @@ properties: - socionext,uniphier-ld11-clock - socionext,uniphier-ld20-clock - socionext,uniphier-pxs3-clock + - socionext,uniphier-nx1-clock - description: Media I/O (MIO) clock, SD clock enum: - socionext,uniphier-ld4-mio-clock @@ -33,6 +34,7 @@ properties: - socionext,uniphier-ld11-mio-clock - socionext,uniphier-ld20-sd-clock - socionext,uniphier-pxs3-sd-clock + - socionext,uniphier-nx1-sd-clock - description: Peripheral clock enum: - socionext,uniphier-ld4-peri-clock @@ -43,6 +45,10 @@ properties: - socionext,uniphier-ld11-peri-clock - socionext,uniphier-ld20-peri-clock - socionext,uniphier-pxs3-peri-clock + - socionext,uniphier-nx1-peri-clock + - description: SoC-glue clock + enum: + - socionext,uniphier-pro4-sg-clock "#clock-cells": const: 1 diff --git a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml index 304a1367faaa..1faae3e323a4 100644 --- a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml +++ b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml @@ -49,11 +49,26 @@ properties: properties: port@0: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base description: | For LVDS encoders, port 0 is the parallel input For LVDS decoders, port 0 is the LVDS input + properties: + endpoint: + $ref: /schemas/media/video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-mapping: + enum: + - jeida-18 + - jeida-24 + - vesa-24 + description: | + The color signals mapping order. See details in + Documentation/devicetree/bindings/display/panel/lvds.yaml + port@1: $ref: /schemas/graph.yaml#/properties/port description: | @@ -71,6 +86,22 @@ properties: power-supply: true +if: + not: + properties: + compatible: + contains: + const: lvds-decoder +then: + properties: + ports: + properties: + port@0: + properties: + endpoint: + properties: + data-mapping: false + required: - compatible - ports diff --git a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml index fce82b605c8b..cdaf7a7a8f88 100644 --- a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml @@ -40,6 +40,9 @@ properties: vdd33-supply: description: Regulator for 3.3V digital core power. + aux-bus: + $ref: /schemas/display/dp-aux-bus.yaml# + ports: $ref: /schemas/graph.yaml#/properties/ports @@ -98,7 +101,21 @@ examples: reg = <1>; ps8640_out: endpoint { remote-endpoint = <&panel_in>; - }; + }; + }; + }; + + aux-bus { + panel { + compatible = "boe,nv133fhm-n62"; + power-supply = <&pp3300_dx_edp>; + backlight = <&backlight>; + + port { + panel_in: endpoint { + remote-endpoint = <&ps8640_out>; + }; + }; }; }; }; diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index 335776c45474..f3c9395d23b6 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -166,6 +166,8 @@ properties: - innolux,at070tn92 # Innolux G070Y2-L01 7" WVGA (800x480) TFT LCD panel - innolux,g070y2-l01 + # Innolux G070Y2-T02 7" WVGA (800x480) TFT LCD TTL panel + - innolux,g070y2-t02 # Innolux Corporation 10.1" G101ICE-L01 WXGA (1280x800) LVDS panel - innolux,g101ice-l01 # Innolux Corporation 12.1" WXGA (1280x800) TFT LCD panel @@ -309,6 +311,8 @@ properties: - urt,umsh-8596md-11t - urt,umsh-8596md-19t - urt,umsh-8596md-20t + # Vivax TPC-9150 tablet 9.0" WSVGA TFT LCD panel + - vivax,tpc9150-panel # VXT 800x480 color TFT LCD panel - vxt,vl050-8048nt-c01 # Winstar Display Corporation 3.5" QVGA (320x240) TFT LCD panel @@ -317,6 +321,7 @@ properties: - yes-optoelectronics,ytc700tlag-05-201c backlight: true + ddc-i2c-bus: true enable-gpios: true port: true power-supply: true diff --git a/Documentation/devicetree/bindings/display/panel/sharp,ls060t1sx01.yaml b/Documentation/devicetree/bindings/display/panel/sharp,ls060t1sx01.yaml new file mode 100644 index 000000000000..271c097cc9a4 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/sharp,ls060t1sx01.yaml @@ -0,0 +1,56 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/sharp,ls060t1sx01.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Sharp Microelectronics 6.0" FullHD TFT LCD panel + +maintainers: + - Dmitry Baryskov <dmitry.baryshkov@linaro.org> + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + const: sharp,ls060t1sx01 + + reg: true + backlight: true + reset-gpios: true + port: true + + avdd-supply: + description: handle of the regulator that provides the positive supply voltage + avee-supply: + description: handle of the regulator that provides the negative supply voltage + vddi-supply: + description: handle of the regulator that provides the I/O supply voltage + vddh-supply: + description: handle of the regulator that provides the analog supply voltage + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "sharp,ls060t1sx01"; + reg = <0>; + avdd-supply = <&pm8941_l22>; + backlight = <&backlight>; + reset-gpios = <&pm8916_gpios 25 GPIO_ACTIVE_LOW>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt b/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt index cf5b9e44432c..6e9a5497b3f2 100644 --- a/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt +++ b/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt @@ -15,6 +15,8 @@ Required properties: the secure world. - qcom,controlled-remotely : optional, indicates that the bam is controlled by remote proccessor i.e. execution environment. +- qcom,powered-remotely : optional, indicates that the bam is powered up by + a remote processor but must be initialized by the local processor. - num-channels : optional, indicates supported number of DMA channels in a remotely controlled bam. - qcom,num-ees : optional, indicates supported number of Execution Environments diff --git a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml index 7afc9f2be13a..e66ef2da7879 100644 --- a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml +++ b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml @@ -8,6 +8,7 @@ title: NXP i.MX8 DSP core maintainers: - Daniel Baluta <daniel.baluta@nxp.com> + - Shengjiu Wang <shengjiu.wang@nxp.com> description: | Some boards from i.MX8 family contain a DSP core used for @@ -19,6 +20,10 @@ properties: - fsl,imx8qxp-dsp - fsl,imx8qm-dsp - fsl,imx8mp-dsp + - fsl,imx8qxp-hifi4 + - fsl,imx8qm-hifi4 + - fsl,imx8mp-hifi4 + - fsl,imx8ulp-hifi4 reg: maxItems: 1 @@ -28,37 +33,53 @@ properties: - description: ipg clock - description: ocram clock - description: core clock + - description: debug interface clock + - description: message unit clock + minItems: 3 clock-names: items: - const: ipg - const: ocram - const: core + - const: debug + - const: mu + minItems: 3 power-domains: description: List of phandle and PM domain specifier as documented in Documentation/devicetree/bindings/power/power_domain.txt + minItems: 1 maxItems: 4 mboxes: description: List of <&phandle type channel> - 2 channels for TXDB, 2 channels for RXDB + or - 1 channel for TX, 1 channel for RX, 1 channel for RXDB (see mailbox/fsl,mu.txt) + minItems: 3 maxItems: 4 mbox-names: - items: - - const: txdb0 - - const: txdb1 - - const: rxdb0 - - const: rxdb1 + minItems: 3 + maxItems: 4 memory-region: description: phandle to a node describing reserved memory (System RAM memory) used by DSP (see bindings/reserved-memory/reserved-memory.txt) - maxItems: 1 + minItems: 1 + maxItems: 4 + + firmware-name: + description: | + Default name of the firmware to load to the remote processor. + + fsl,dsp-ctrl: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Phandle to syscon block which provide access for processor enablement required: - compatible @@ -70,6 +91,58 @@ required: - mbox-names - memory-region +allOf: + - if: + properties: + compatible: + contains: + enum: + - fsl,imx8qxp-dsp + - fsl,imx8qm-dsp + - fsl,imx8qxp-hifi4 + - fsl,imx8qm-hifi4 + then: + properties: + power-domains: + minItems: 4 + else: + properties: + power-domains: + maxItems: 1 + + - if: + properties: + compatible: + contains: + enum: + - fsl,imx8qxp-hifi4 + - fsl,imx8qm-hifi4 + - fsl,imx8mp-hifi4 + - fsl,imx8ulp-hifi4 + then: + properties: + memory-region: + minItems: 4 + mboxes: + maxItems: 3 + mbox-names: + items: + - const: tx + - const: rx + - const: rxdb + else: + properties: + memory-region: + maxItems: 1 + mboxes: + minItems: 4 + mbox-names: + items: + - const: txdb0 + - const: txdb1 + - const: rxdb0 + - const: rxdb1 + additionalProperties: false examples: @@ -91,3 +164,41 @@ examples: mboxes = <&lsio_mu13 2 0>, <&lsio_mu13 2 1>, <&lsio_mu13 3 0>, <&lsio_mu13 3 1>; memory-region = <&dsp_reserved>; }; + - | + #include <dt-bindings/clock/imx8mp-clock.h> + dsp_reserved: dsp@92400000 { + reg = <0x92400000 0x1000000>; + no-map; + }; + dsp_vdev0vring0: vdev0vring0@942f0000 { + reg = <0x942f0000 0x8000>; + no-map; + }; + dsp_vdev0vring1: vdev0vring1@942f8000 { + reg = <0x942f8000 0x8000>; + no-map; + }; + dsp_vdev0buffer: vdev0buffer@94300000 { + compatible = "shared-dma-pool"; + reg = <0x94300000 0x100000>; + no-map; + }; + + dsp: dsp@3b6e8000 { + compatible = "fsl,imx8mp-hifi4"; + reg = <0x3b6e8000 0x88000>; + clocks = <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_DSP_ROOT>, + <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_OCRAMA_IPG>, + <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_DSP_ROOT>, + <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_DSPDBG_ROOT>; + clock-names = "ipg", "ocram", "core", "debug"; + firmware-name = "imx/dsp/hifi4.bin"; + power-domains = <&audiomix_pd>; + mbox-names = "tx", "rx", "rxdb"; + mboxes = <&mu2 0 0>, + <&mu2 1 0>, + <&mu2 3 0>; + memory-region = <&dsp_vdev0buffer>, <&dsp_vdev0vring0>, + <&dsp_vdev0vring1>, <&dsp_reserved>; + fsl,dsp-ctrl = <&audio_blk_ctrl>; + }; diff --git a/Documentation/devicetree/bindings/input/cypress-sf.yaml b/Documentation/devicetree/bindings/input/cypress-sf.yaml new file mode 100644 index 000000000000..c0b051466272 --- /dev/null +++ b/Documentation/devicetree/bindings/input/cypress-sf.yaml @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/cypress-sf.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Cypress StreetFighter touchkey controller + +maintainers: + - Yassine Oudjana <y.oudjana@protonmail.com> + +allOf: + - $ref: input.yaml# + +properties: + compatible: + const: cypress,sf3155 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + avdd-supply: + description: Regulator for AVDD analog voltage + + vdd-supply: + description: Regulator for VDD digital voltage + + linux,keycodes: + minItems: 1 + maxItems: 8 + +required: + - compatible + - reg + - interrupts + - avdd-supply + - vdd-supply + +additionalProperties: false + +examples: + - | + #include <dt-bindings/input/input.h> + #include <dt-bindings/interrupt-controller/irq.h> + i2c { + #address-cells = <1>; + #size-cells = <0>; + + touchkey@28 { + compatible = "cypress,sf3155"; + reg = <0x28>; + interrupt-parent = <&msmgpio>; + interrupts = <77 IRQ_TYPE_EDGE_FALLING>; + avdd-supply = <&vreg_l6a_1p8>; + vdd-supply = <&vdd_3v2_tp>; + linux,keycodes = <KEY_BACK KEY_MENU>; + }; + }; diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml index fa0f37a90ac9..d5d6bced3148 100644 --- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml +++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml @@ -19,6 +19,7 @@ properties: - microchip,cap1106 - microchip,cap1126 - microchip,cap1188 + - microchip,cap1206 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/opp/opp-v2-base.yaml b/Documentation/devicetree/bindings/opp/opp-v2-base.yaml index ae3ae4d39843..15a76bcd6d42 100644 --- a/Documentation/devicetree/bindings/opp/opp-v2-base.yaml +++ b/Documentation/devicetree/bindings/opp/opp-v2-base.yaml @@ -33,7 +33,7 @@ properties: type: boolean patternProperties: - '^opp-?[0-9]+$': + '^opp(-?[0-9]+)*$': type: object description: One or more OPP nodes describing voltage-current-frequency combinations. diff --git a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml index 81ccb2110162..1f5c6384182e 100644 --- a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml @@ -35,9 +35,11 @@ properties: - renesas,tpu-r8a7794 # R-Car E2 - renesas,tpu-r8a7795 # R-Car H3 - renesas,tpu-r8a7796 # R-Car M3-W + - renesas,tpu-r8a77961 # R-Car M3-W+ - renesas,tpu-r8a77965 # R-Car M3-N - renesas,tpu-r8a77970 # R-Car V3M - renesas,tpu-r8a77980 # R-Car V3H + - renesas,tpu-r8a779a0 # R-Car V3U - const: renesas,tpu reg: diff --git a/Documentation/devicetree/bindings/remoteproc/amlogic,meson-mx-ao-arc.yaml b/Documentation/devicetree/bindings/remoteproc/amlogic,meson-mx-ao-arc.yaml new file mode 100644 index 000000000000..d892d29a656b --- /dev/null +++ b/Documentation/devicetree/bindings/remoteproc/amlogic,meson-mx-ao-arc.yaml @@ -0,0 +1,87 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/remoteproc/amlogic,meson-mx-ao-arc.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Amlogic Meson AO ARC Remote Processor bindings + +description: + Amlogic Meson6, Meson8, Meson8b and Meson8m2 SoCs embed an ARC core + controller for always-on operations, typically used for managing + system suspend. Meson6 and older use a ARC core based on the ARCv1 + ISA, while Meson8, Meson8b and Meson8m2 use an ARC EM4 (ARCv2 ISA) + core. + +maintainers: + - Martin Blumenstingl <martin.blumenstingl@googlemail.com> + +properties: + compatible: + items: + - enum: + - amlogic,meson8-ao-arc + - amlogic,meson8b-ao-arc + - const: amlogic,meson-mx-ao-arc + + firmware-name: + $ref: /schemas/types.yaml#/definitions/string + description: + The name of the firmware which should be loaded for this remote + processor. + + reg: + description: + Address ranges of the remap and CPU control addresses for the + remote processor. + minItems: 2 + + reg-names: + items: + - const: remap + - const: cpu + + resets: + minItems: 1 + + clocks: + minItems: 1 + + sram: + $ref: /schemas/types.yaml#/definitions/phandle + description: + phandles to a reserved SRAM region which is used as the memory of + the ARC core. The region should be defined as child nodes of the + AHB SRAM node as per the generic bindings in + Documentation/devicetree/bindings/sram/sram.yaml + + amlogic,secbus2: + $ref: /schemas/types.yaml#/definitions/phandle + description: + A phandle to the SECBUS2 region which contains some configuration + bits of this remote processor + +required: + - compatible + - reg + - reg-names + - resets + - clocks + - sram + - amlogic,secbus2 + +additionalProperties: false + +examples: + - | + remoteproc@1c { + compatible= "amlogic,meson8-ao-arc", "amlogic,meson-mx-ao-arc"; + reg = <0x1c 0x8>, <0x38 0x8>; + reg-names = "remap", "cpu"; + resets = <&media_cpu_reset>; + clocks = <&media_cpu_clock>; + sram = <&ahb_sram_ao_arc>; + amlogic,secbus2 = <&secbus2>; + }; + +... diff --git a/Documentation/devicetree/bindings/remoteproc/mtk,scp.txt b/Documentation/devicetree/bindings/remoteproc/mtk,scp.txt deleted file mode 100644 index 3f5f78764b60..000000000000 --- a/Documentation/devicetree/bindings/remoteproc/mtk,scp.txt +++ /dev/null @@ -1,36 +0,0 @@ -Mediatek SCP Bindings ----------------------------------------- - -This binding provides support for ARM Cortex M4 Co-processor found on some -Mediatek SoCs. - -Required properties: -- compatible Should be "mediatek,mt8183-scp" -- reg Should contain the address ranges for memory regions: - SRAM, CFG, and L1TCM. -- reg-names Contains the corresponding names for the memory regions: - "sram", "cfg", and "l1tcm". -- clocks Clock for co-processor (See: ../clock/clock-bindings.txt) -- clock-names Contains the corresponding name for the clock. This - should be named "main". - -Subnodes --------- - -Subnodes of the SCP represent rpmsg devices. The names of the devices are not -important. The properties of these nodes are defined by the individual bindings -for the rpmsg devices - but must contain the following property: - -- mtk,rpmsg-name Contains the name for the rpmsg device. Used to match - the subnode to rpmsg device announced by SCP. - -Example: - - scp: scp@10500000 { - compatible = "mediatek,mt8183-scp"; - reg = <0 0x10500000 0 0x80000>, - <0 0x105c0000 0 0x5000>; - reg-names = "sram", "cfg"; - clocks = <&infracfg CLK_INFRA_SCPSYS>; - clock-names = "main"; - }; diff --git a/Documentation/devicetree/bindings/remoteproc/mtk,scp.yaml b/Documentation/devicetree/bindings/remoteproc/mtk,scp.yaml new file mode 100644 index 000000000000..d21a25ee96e6 --- /dev/null +++ b/Documentation/devicetree/bindings/remoteproc/mtk,scp.yaml @@ -0,0 +1,92 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/remoteproc/mtk,scp.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Mediatek SCP Bindings + +maintainers: + - Tinghan Shen <tinghan.shen@mediatek.com> + +description: + This binding provides support for ARM Cortex M4 Co-processor found on some + Mediatek SoCs. + +properties: + compatible: + enum: + - mediatek,mt8183-scp + - mediatek,mt8192-scp + - mediatek,mt8195-scp + + reg: + description: + Should contain the address ranges for memory regions SRAM, CFG, and + L1TCM. + maxItems: 3 + + reg-names: + items: + - const: sram + - const: cfg + - const: l1tcm + + clocks: + description: + Clock for co-processor (see ../clock/clock-bindings.txt). + Required by mt8183 and mt8192. + maxItems: 1 + + clock-names: + const: main + +required: + - compatible + - reg + - reg-names + +if: + properties: + compatible: + enum: + - mediatek,mt8183-scp + - mediatek,mt8192-scp +then: + required: + - clocks + - clock-names + +additionalProperties: + type: object + description: + Subnodes of the SCP represent rpmsg devices. The names of the devices + are not important. The properties of these nodes are defined by the + individual bindings for the rpmsg devices. + properties: + mediatek,rpmsg-name: + $ref: /schemas/types.yaml#/definitions/string-array + description: + Contains the name for the rpmsg device. Used to match + the subnode to rpmsg device announced by SCP. + + required: + - mediatek,rpmsg-name + +examples: + - | + #include <dt-bindings/clock/mt8183-clk.h> + + scp@10500000 { + compatible = "mediatek,mt8183-scp"; + reg = <0x10500000 0x80000>, + <0x10700000 0x8000>, + <0x10720000 0xe0000>; + reg-names = "sram", "cfg", "l1tcm"; + clocks = <&infracfg CLK_INFRA_SCPSYS>; + clock-names = "main"; + + cros_ec { + mediatek,rpmsg-name = "cros-ec-rpmsg"; + }; + }; diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml index 0c112f3264a9..63e06d93bca3 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml @@ -25,6 +25,7 @@ properties: - qcom,qcs404-cdsp-pas - qcom,qcs404-wcss-pas - qcom,sc7180-mpss-pas + - qcom,sc7280-mpss-pas - qcom,sc8180x-adsp-pas - qcom,sc8180x-cdsp-pas - qcom,sc8180x-mpss-pas @@ -93,6 +94,10 @@ properties: maxItems: 1 description: Reference to the reserved-memory for the Hexagon core + qcom,qmp: + $ref: /schemas/types.yaml#/definitions/phandle + description: Reference to the AOSS side-channel message RAM. + qcom,smem-states: $ref: /schemas/types.yaml#/definitions/phandle-array description: States used by the AP to signal the Hexagon core @@ -147,6 +152,7 @@ allOf: - qcom,msm8998-adsp-pas - qcom,qcs404-adsp-pas - qcom,qcs404-wcss-pas + - qcom,sc7280-mpss-pas - qcom,sc8180x-adsp-pas - qcom,sc8180x-cdsp-pas - qcom,sc8180x-mpss-pas @@ -292,6 +298,7 @@ allOf: contains: enum: - qcom,sc7180-mpss-pas + - qcom,sc7280-mpss-pas - qcom,sc8180x-mpss-pas - qcom,sdx55-mpss-pas - qcom,sm8150-mpss-pas @@ -369,13 +376,11 @@ allOf: properties: power-domains: items: - - description: Load State power domain - description: CX power domain - description: MX power domain - description: MSS power domain power-domain-names: items: - - const: load_state - const: cx - const: mx - const: mss @@ -391,43 +396,21 @@ allOf: properties: power-domains: items: - - description: Load State power domain - description: CX power domain - power-domain-names: - items: - - const: load_state - - const: cx - if: properties: compatible: contains: enum: + - qcom,sc7280-mpss-pas + - qcom,sdx55-mpss-pas - qcom,sm8150-mpss-pas - qcom,sm8350-mpss-pas then: properties: power-domains: items: - - description: Load State power domain - - description: CX power domain - - description: MSS power domain - power-domain-names: - items: - - const: load_state - - const: cx - - const: mss - - - if: - properties: - compatible: - contains: - enum: - - qcom,sdx55-mpss-pas - then: - properties: - power-domains: - items: - description: CX power domain - description: MSS power domain power-domain-names: @@ -451,12 +434,10 @@ allOf: properties: power-domains: items: - - description: Load State power domain - description: LCX power domain - description: LMX power domain power-domain-names: items: - - const: load_state - const: lcx - const: lmx @@ -470,12 +451,10 @@ allOf: properties: power-domains: items: - - description: Load State power domain - description: CX power domain - description: MXC power domain power-domain-names: items: - - const: load_state - const: cx - const: mxc @@ -500,6 +479,7 @@ allOf: contains: enum: - qcom,sc7180-mpss-pas + - qcom,sc7280-mpss-pas then: properties: resets: @@ -511,6 +491,25 @@ allOf: - const: mss_restart - const: pdc_reset + - if: + properties: + compatible: + contains: + enum: + - qcom,msm8974-adsp-pil + - qcom,msm8996-adsp-pil + - qcom,msm8996-slpi-pil + - qcom,msm8998-adsp-pas + - qcom,msm8998-slpi-pas + - qcom,qcs404-adsp-pas + - qcom,qcs404-cdsp-pas + - qcom,qcs404-wcss-pas + - qcom,sdm660-adsp-pas + - qcom,sdx55-mpss-pas + then: + properties: + qcom,qmp: false + examples: - | #include <dt-bindings/clock/qcom,rpmcc.h> diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt b/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt index 69c49c7b2cff..8f1507052afd 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt +++ b/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt @@ -15,6 +15,7 @@ on the Qualcomm Hexagon core. "qcom,msm8996-mss-pil" "qcom,msm8998-mss-pil" "qcom,sc7180-mss-pil" + "qcom,sc7280-mss-pil" "qcom,sdm845-mss-pil" - reg: @@ -47,6 +48,7 @@ on the Qualcomm Hexagon core. qcom,msm8996-mss-pil: qcom,msm8998-mss-pil: qcom,sc7180-mss-pil: + qcom,sc7280-mss-pil: qcom,sdm845-mss-pil: must be "wdog", "fatal", "ready", "handover", "stop-ack", "shutdown-ack" @@ -87,6 +89,8 @@ on the Qualcomm Hexagon core. qcom,sc7180-mss-pil: must be "iface", "bus", "xo", "snoc_axi", "mnoc_axi", "nav" + qcom,sc7280-mss-pil: + must be "iface", "xo", "snoc_axi", "offline", "pka" qcom,sdm845-mss-pil: must be "iface", "bus", "mem", "xo", "gpll0_mss", "snoc_axi", "mnoc_axi", "prng" @@ -98,7 +102,7 @@ on the Qualcomm Hexagon core. reference to the list of 3 reset-controllers for the wcss sub-system reference to the list of 2 reset-controllers for the modem - sub-system on SC7180, SDM845 SoCs + sub-system on SC7180, SC7280, SDM845 SoCs - reset-names: Usage: required @@ -107,7 +111,7 @@ on the Qualcomm Hexagon core. must be "wcss_aon_reset", "wcss_reset", "wcss_q6_reset" for the wcss sub-system must be "mss_restart", "pdc_reset" for the modem - sub-system on SC7180, SDM845 SoCs + sub-system on SC7180, SC7280, SDM845 SoCs For devices where the mba and mpss sub-nodes are not specified, mba/mpss region should be referenced as follows: @@ -173,8 +177,16 @@ For the compatible string below the following supplies are required: qcom,msm8998-mss-pil: must be "cx", "mx" qcom,sc7180-mss-pil: + must be "cx", "mx", "mss" + qcom,sc7280-mss-pil: + must be "cx", "mss" qcom,sdm845-mss-pil: - must be "cx", "mx", "mss", "load_state" + must be "cx", "mx", "mss" + +- qcom,qmp: + Usage: optional + Value type: <phandle> + Definition: reference to the AOSS side-channel message RAM. - qcom,smem-states: Usage: required @@ -193,6 +205,9 @@ For the compatible string below the following supplies are required: Definition: a phandle reference to a syscon representing TCSR followed by the three offsets within syscon for q6, modem and nc halt registers. + a phandle reference to a syscon representing TCSR followed + by the four offsets within syscon for q6, modem, nc and vq6 + halt registers on SC7280 SoCs. For the compatible strings below the following phandle references are required: "qcom,sc7180-mss-pil" @@ -203,6 +218,24 @@ For the compatible strings below the following phandle references are required: by the offset within syscon for conn_box_spare0 register used by the modem sub-system running on SC7180 SoC. +For the compatible strings below the following phandle references are required: + "qcom,sc7280-mss-pil" +- qcom,ext-regs: + Usage: required + Value type: <prop-encoded-array> + Definition: two phandle references to syscons representing TCSR_REG and + TCSR register space followed by the two offsets within the syscon + to force_clk_en/rscc_disable and axim1_clk_off/crypto_clk_off + registers respectively. + +- qcom,qaccept-regs: + Usage: required + Value type: <prop-encoded-array> + Definition: a phandle reference to a syscon representing TCSR followed + by the three offsets within syscon for mdm, cx and axi + qaccept registers used by the modem sub-system running on + SC7280 SoC. + The Hexagon node must contain iommus property as described in ../iommu/iommu.txt on platforms which do not have TrustZone. diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml index 6070456a7b67..5ec6505ac408 100644 --- a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml +++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml @@ -133,9 +133,7 @@ unevaluatedProperties: false examples: - | - / { - model = "Texas Instruments K3 J721E SoC"; - compatible = "ti,j721e"; + soc { #address-cells = <2>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml index 130fbaacc4b1..eeef255c4045 100644 --- a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml +++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml @@ -230,9 +230,7 @@ additionalProperties: false examples: - | - / { - model = "Texas Instruments K3 AM654 SoC"; - compatible = "ti,am654-evm", "ti,am654"; + soc { #address-cells = <2>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml b/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml new file mode 100644 index 000000000000..114199cf4d28 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml @@ -0,0 +1,49 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/mstar,msc313-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Mstar MSC313e RTC Device Tree Bindings + +allOf: + - $ref: "rtc.yaml#" + +maintainers: + - Daniel Palmer <daniel@0x0f.com> + - Romain Perier <romain.perier@gmail.com> + +properties: + compatible: + enum: + - mstar,msc313-rtc + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + start-year: true + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + - clocks + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + rtc@2400 { + compatible = "mstar,msc313-rtc"; + reg = <0x2400 0x40>; + clocks = <&xtal_div2>; + interrupts-extended = <&intc_irq GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>; + }; +... diff --git a/Documentation/devicetree/bindings/rtc/nxp,pcf85063.txt b/Documentation/devicetree/bindings/rtc/nxp,pcf85063.txt index 627bb533eff7..6439682c9319 100644 --- a/Documentation/devicetree/bindings/rtc/nxp,pcf85063.txt +++ b/Documentation/devicetree/bindings/rtc/nxp,pcf85063.txt @@ -13,10 +13,19 @@ Optional property: expressed in femto Farad (fF). Valid values are 7000 and 12500. Default value (if no value is specified) is 7000fF. +Optional child node: +- clock: Provide this if the square wave pin is used as boot-enabled fixed clock. + Example: pcf85063: rtc@51 { compatible = "nxp,pcf85063"; reg = <0x51>; quartz-load-femtofarads = <12500>; + + clock { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + }; }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 983f5e4afbc5..66d6432fd781 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -1286,6 +1286,8 @@ patternProperties: description: Vitesse Semiconductor Corporation "^vivante,.*": description: Vivante Corporation + "^vivax,.*": + description: Vivax brand by M SAN Grupa d.o.o. "^vocore,.*": description: VoCore Studio "^voipac,.*": diff --git a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml index 9aa3c313c49f..44cad9427ae6 100644 --- a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml @@ -24,16 +24,33 @@ properties: - allwinner,sun50i-a100-wdt - allwinner,sun50i-h6-wdt - allwinner,sun50i-h616-wdt + - allwinner,sun50i-r329-wdt + - allwinner,sun50i-r329-wdt-reset - const: allwinner,sun6i-a31-wdt - items: - const: allwinner,suniv-f1c100s-wdt - const: allwinner,sun4i-a10-wdt + - const: allwinner,sun20i-d1-wdt + - items: + - const: allwinner,sun20i-d1-wdt-reset + - const: allwinner,sun20i-d1-wdt reg: maxItems: 1 clocks: - maxItems: 1 + minItems: 1 + maxItems: 2 + items: + - description: High-frequency oscillator input, divided internally + - description: Low-frequency oscillator input, only found on some variants + + clock-names: + minItems: 1 + maxItems: 2 + items: + - const: hosc + - const: losc interrupts: maxItems: 1 @@ -44,6 +61,35 @@ required: - clocks - interrupts +if: + properties: + compatible: + contains: + enum: + - allwinner,sun20i-d1-wdt + - allwinner,sun20i-d1-wdt-reset + - allwinner,sun50i-r329-wdt + - allwinner,sun50i-r329-wdt-reset + +then: + properties: + clocks: + minItems: 2 + + clock-names: + minItems: 2 + + required: + - clock-names + +else: + properties: + clocks: + maxItems: 1 + + clock-names: + maxItems: 1 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt b/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt index a4e31ce96e0e..0114871f887a 100644 --- a/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt +++ b/Documentation/devicetree/bindings/watchdog/mtk-wdt.txt @@ -22,6 +22,7 @@ Required properties: - reg : Specifies base physical address and size of the registers. Optional properties: +- mediatek,disable-extrst: disable send output reset signal - interrupts: Watchdog pre-timeout (bark) interrupt. - timeout-sec: contains the watchdog timeout in seconds. - #reset-cells: Should be 1. @@ -31,6 +32,7 @@ Example: watchdog: watchdog@10007000 { compatible = "mediatek,mt8183-wdt", "mediatek,mt6589-wdt"; + mediatek,disable-extrst; reg = <0 0x10007000 0 0x100>; interrupts = <GIC_SPI 139 IRQ_TYPE_NONE>; timeout-sec = <10>; diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index 6f3c6e91346d..d7b84695f56a 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -197,10 +197,29 @@ fault_type=%d Support configuring fault injection type, should be FAULT_DISCARD 0x000002000 FAULT_WRITE_IO 0x000004000 FAULT_SLAB_ALLOC 0x000008000 + FAULT_DQUOT_INIT 0x000010000 =================== =========== mode=%s Control block allocation mode which supports "adaptive" and "lfs". In "lfs" mode, there should be no random writes towards main area. + "fragment:segment" and "fragment:block" are newly added here. + These are developer options for experiments to simulate filesystem + fragmentation/after-GC situation itself. The developers use these + modes to understand filesystem fragmentation/after-GC condition well, + and eventually get some insights to handle them better. + In "fragment:segment", f2fs allocates a new segment in ramdom + position. With this, we can simulate the after-GC condition. + In "fragment:block", we can scatter block allocation with + "max_fragment_chunk" and "max_fragment_hole" sysfs nodes. + We added some randomness to both chunk and hole size to make + it close to realistic IO pattern. So, in this mode, f2fs will allocate + 1..<max_fragment_chunk> blocks in a chunk and make a hole in the + length of 1..<max_fragment_hole> by turns. With this, the newly + allocated blocks will be scattered throughout the whole partition. + Note that "fragment:block" implicitly enables "fragment:segment" + option for more randomness. + Please, use these options for your experiments and we strongly + recommend to re-format the filesystem after using these options. io_bits=%u Set the bit size of write IO requests. It should be set with "mode=lfs". usrquota Enable plain user disk quota accounting. diff --git a/Documentation/filesystems/nfs/index.rst b/Documentation/filesystems/nfs/index.rst index 65805624e39b..288d8ddb2bc6 100644 --- a/Documentation/filesystems/nfs/index.rst +++ b/Documentation/filesystems/nfs/index.rst @@ -11,3 +11,4 @@ NFS rpc-server-gss nfs41-server knfsd-stats + reexport diff --git a/Documentation/filesystems/nfs/reexport.rst b/Documentation/filesystems/nfs/reexport.rst new file mode 100644 index 000000000000..ff9ae4a46530 --- /dev/null +++ b/Documentation/filesystems/nfs/reexport.rst @@ -0,0 +1,113 @@ +Reexporting NFS filesystems +=========================== + +Overview +-------- + +It is possible to reexport an NFS filesystem over NFS. However, this +feature comes with a number of limitations. Before trying it, we +recommend some careful research to determine whether it will work for +your purposes. + +A discussion of current known limitations follows. + +"fsid=" required, crossmnt broken +--------------------------------- + +We require the "fsid=" export option on any reexport of an NFS +filesystem. You can use "uuidgen -r" to generate a unique argument. + +The "crossmnt" export does not propagate "fsid=", so it will not allow +traversing into further nfs filesystems; if you wish to export nfs +filesystems mounted under the exported filesystem, you'll need to export +them explicitly, assigning each its own unique "fsid= option. + +Reboot recovery +--------------- + +The NFS protocol's normal reboot recovery mechanisms don't work for the +case when the reexport server reboots. Clients will lose any locks +they held before the reboot, and further IO will result in errors. +Closing and reopening files should clear the errors. + +Filehandle limits +----------------- + +If the original server uses an X byte filehandle for a given object, the +reexport server's filehandle for the reexported object will be X+22 +bytes, rounded up to the nearest multiple of four bytes. + +The result must fit into the RFC-mandated filehandle size limits: + ++-------+-----------+ +| NFSv2 | 32 bytes | ++-------+-----------+ +| NFSv3 | 64 bytes | ++-------+-----------+ +| NFSv4 | 128 bytes | ++-------+-----------+ + +So, for example, you will only be able to reexport a filesystem over +NFSv2 if the original server gives you filehandles that fit in 10 +bytes--which is unlikely. + +In general there's no way to know the maximum filehandle size given out +by an NFS server without asking the server vendor. + +But the following table gives a few examples. The first column is the +typical length of the filehandle from a Linux server exporting the given +filesystem, the second is the length after that nfs export is reexported +by another Linux host: + ++--------+-------------------+----------------+ +| | filehandle length | after reexport | ++========+===================+================+ +| ext4: | 28 bytes | 52 bytes | ++--------+-------------------+----------------+ +| xfs: | 32 bytes | 56 bytes | ++--------+-------------------+----------------+ +| btrfs: | 40 bytes | 64 bytes | ++--------+-------------------+----------------+ + +All will therefore fit in an NFSv3 or NFSv4 filehandle after reexport, +but none are reexportable over NFSv2. + +Linux server filehandles are a bit more complicated than this, though; +for example: + + - The (non-default) "subtreecheck" export option generally + requires another 4 to 8 bytes in the filehandle. + - If you export a subdirectory of a filesystem (instead of + exporting the filesystem root), that also usually adds 4 to 8 + bytes. + - If you export over NFSv2, knfsd usually uses a shorter + filesystem identifier that saves 8 bytes. + - The root directory of an export uses a filehandle that is + shorter. + +As you can see, the 128-byte NFSv4 filehandle is large enough that +you're unlikely to have trouble using NFSv4 to reexport any filesystem +exported from a Linux server. In general, if the original server is +something that also supports NFSv3, you're *probably* OK. Re-exporting +over NFSv3 may be dicier, and reexporting over NFSv2 will probably +never work. + +For more details of Linux filehandle structure, the best reference is +the source code and comments; see in particular: + + - include/linux/exportfs.h:enum fid_type + - include/uapi/linux/nfsd/nfsfh.h:struct nfs_fhbase_new + - fs/nfsd/nfsfh.c:set_version_and_fsid_type + - fs/nfs/export.c:nfs_encode_fh + +Open DENY bits ignored +---------------------- + +NFS since NFSv4 supports ALLOW and DENY bits taken from Windows, which +allow you, for example, to open a file in a mode which forbids other +read opens or write opens. The Linux client doesn't use them, and the +server's support has always been incomplete: they are enforced only +against other NFS users, not against processes accessing the exported +filesystem locally. A reexport server will also not pass them along to +the original server, so they will not be enforced between clients of +different reexport servers. diff --git a/Documentation/firmware-guide/acpi/index.rst b/Documentation/firmware-guide/acpi/index.rst index a99ee402b212..b053b0c3d696 100644 --- a/Documentation/firmware-guide/acpi/index.rst +++ b/Documentation/firmware-guide/acpi/index.rst @@ -26,5 +26,6 @@ ACPI Support acpi-lid lpit video_extension + non-d0-probe extcon-intel-int3496 intel-pmc-mux diff --git a/Documentation/firmware-guide/acpi/non-d0-probe.rst b/Documentation/firmware-guide/acpi/non-d0-probe.rst new file mode 100644 index 000000000000..7afd16701a02 --- /dev/null +++ b/Documentation/firmware-guide/acpi/non-d0-probe.rst @@ -0,0 +1,78 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================== +Probing devices in other D states than 0 +======================================== + +Introduction +============ + +In some cases it may be preferred to leave certain devices powered off for the +entire system bootup if powering on these devices has adverse side effects, +beyond just powering on the said device. + +How it works +============ + +The _DSC (Device State for Configuration) object that evaluates to an integer +may be used to tell Linux the highest allowed D state for a device during +probe. The support for _DSC requires support from the kernel bus type if the +bus driver normally sets the device in D0 state for probe. + +The downside of using _DSC is that as the device is not powered on, even if +there's a problem with the device, the driver likely probes just fine but the +first user will find out the device doesn't work, instead of a failure at probe +time. This feature should thus be used sparingly. + +I²C +--- + +If an I²C driver indicates its support for this by setting the +I2C_DRV_ACPI_WAIVE_D0_PROBE flag in struct i2c_driver.flags field and the +_DSC object evaluates to integer higher than the D state of the device, +the device will not be powered on (put in D0 state) for probe. + +D states +-------- + +The D states and thus also the allowed values for _DSC are listed below. Refer +to [1] for more information on device power states. + +.. code-block:: text + + Number State Description + 0 D0 Device fully powered on + 1 D1 + 2 D2 + 3 D3hot + 4 D3cold Off + +References +========== + +[1] https://uefi.org/specifications/ACPI/6.4/02_Definition_of_Terms/Definition_of_Terms.html#device-power-state-definitions + +Example +======= + +An ASL example describing an ACPI device using _DSC object to tell Operating +System the device should remain powered off during probe looks like this. Some +objects not relevant from the example point of view have been omitted. + +.. code-block:: text + + Device (CAM0) + { + Name (_HID, "SONY319A") + Name (_UID, Zero) + Name (_CRS, ResourceTemplate () + { + I2cSerialBus(0x0020, ControllerInitiated, 0x00061A80, + AddressingMode7Bit, "\\_SB.PCI0.I2C0", + 0x00, ResourceConsumer) + }) + Method (_DSC, 0, NotSerialized) + { + Return (0x4) + } + } diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index 6613543955e9..60d1d7ee0719 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -314,16 +314,19 @@ Level: Advanced Garbage collect fbdev scrolling acceleration -------------------------------------------- -Scroll acceleration is disabled in fbcon by hard-wiring p->scrollmode = -SCROLL_REDRAW. There's a ton of code this will allow us to remove: +Scroll acceleration has been disabled in fbcon. Now it works as the old +SCROLL_REDRAW mode. A ton of code was removed in fbcon.c and the hook bmove was +removed from fbcon_ops. +Remaining tasks: -- lots of code in fbcon.c - -- a bunch of the hooks in fbcon_ops, maybe the remaining hooks could be called +- a bunch of the hooks in fbcon_ops could be removed or simplified by calling directly instead of the function table (with a switch on p->rotate) - fb_copyarea is unused after this, and can be deleted from all drivers +- after that, fb_copyarea can be deleted from fb_ops in include/linux/fb.h as + well as cfb_copyarea + Note that not all acceleration code can be deleted, since clearing and cursor support is still accelerated, which might be good candidates for further deletion projects. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index c61cc0219f4c..c04431144f7a 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1004,13 +1004,11 @@ udp_l3mdev_accept - BOOLEAN udp_mem - vector of 3 INTEGERs: min, pressure, max Number of pages allowed for queueing by all UDP sockets. - min: Below this number of pages UDP is not bothered about its - memory appetite. When amount of memory allocated by UDP exceeds - this number, UDP starts to moderate memory usage. + min: Number of pages allowed for queueing by all UDP sockets. pressure: This value was introduced to follow format of tcp_mem. - max: Number of pages allowed for queueing by all UDP sockets. + max: This value was introduced to follow format of tcp_mem. Default is calculated at boot time from amount of available memory. diff --git a/Documentation/security/SCTP.rst b/Documentation/security/SCTP.rst index 0bcf6c1245ee..d5fd6ccc3dcb 100644 --- a/Documentation/security/SCTP.rst +++ b/Documentation/security/SCTP.rst @@ -26,11 +26,11 @@ described in the `SCTP SELinux Support`_ chapter. security_sctp_assoc_request() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Passes the ``@ep`` and ``@chunk->skb`` of the association INIT packet to the +Passes the ``@asoc`` and ``@chunk->skb`` of the association INIT packet to the security module. Returns 0 on success, error on failure. :: - @ep - pointer to sctp endpoint structure. + @asoc - pointer to sctp association structure. @skb - pointer to skbuff of association packet. @@ -117,9 +117,9 @@ Called whenever a new socket is created by **accept**\(2) calls **sctp_peeloff**\(3). :: - @ep - pointer to current sctp endpoint structure. + @asoc - pointer to current sctp association structure. @sk - pointer to current sock structure. - @sk - pointer to new sock structure. + @newsk - pointer to new sock structure. security_inet_conn_established() @@ -151,9 +151,9 @@ establishing an association. INIT ---------------------------------------------> sctp_sf_do_5_1B_init() Respond to an INIT chunk. - SCTP peer endpoint "A" is - asking for an association. Call - security_sctp_assoc_request() + SCTP peer endpoint "A" is asking + for a temporary association. + Call security_sctp_assoc_request() to set the peer label if first association. If not first association, check @@ -163,9 +163,12 @@ establishing an association. | discard the packet. | COOKIE ECHO ------------------------------------------> - | - | - | + sctp_sf_do_5_1D_ce() + Respond to an COOKIE ECHO chunk. + Confirm the cookie and create a + permanent association. + Call security_sctp_assoc_request() to + do the same as for INIT chunk Response. <------------------------------------------- COOKIE ACK | | sctp_sf_do_5_1E_ca | @@ -200,22 +203,22 @@ hooks with the SELinux specifics expanded below:: security_sctp_assoc_request() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Passes the ``@ep`` and ``@chunk->skb`` of the association INIT packet to the +Passes the ``@asoc`` and ``@chunk->skb`` of the association INIT packet to the security module. Returns 0 on success, error on failure. :: - @ep - pointer to sctp endpoint structure. + @asoc - pointer to sctp association structure. @skb - pointer to skbuff of association packet. The security module performs the following operations: - IF this is the first association on ``@ep->base.sk``, then set the peer + IF this is the first association on ``@asoc->base.sk``, then set the peer sid to that in ``@skb``. This will ensure there is only one peer sid - assigned to ``@ep->base.sk`` that may support multiple associations. + assigned to ``@asoc->base.sk`` that may support multiple associations. - ELSE validate the ``@ep->base.sk peer_sid`` against the ``@skb peer sid`` + ELSE validate the ``@asoc->base.sk peer_sid`` against the ``@skb peer sid`` to determine whether the association should be allowed or denied. - Set the sctp ``@ep sid`` to socket's sid (from ``ep->base.sk``) with + Set the sctp ``@asoc sid`` to socket's sid (from ``asoc->base.sk``) with MLS portion taken from ``@skb peer sid``. This will be used by SCTP TCP style sockets and peeled off connections as they cause a new socket to be generated. @@ -259,13 +262,13 @@ security_sctp_sk_clone() Called whenever a new socket is created by **accept**\(2) (i.e. a TCP style socket) or when a socket is 'peeled off' e.g userspace calls **sctp_peeloff**\(3). ``security_sctp_sk_clone()`` will set the new -sockets sid and peer sid to that contained in the ``@ep sid`` and -``@ep peer sid`` respectively. +sockets sid and peer sid to that contained in the ``@asoc sid`` and +``@asoc peer sid`` respectively. :: - @ep - pointer to current sctp endpoint structure. + @asoc - pointer to current sctp association structure. @sk - pointer to current sock structure. - @sk - pointer to new sock structure. + @newsk - pointer to new sock structure. security_inet_conn_established() diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 3b093d6dbe22..aeeb071c7688 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6911,6 +6911,20 @@ MAP_SHARED mmap will result in an -EINVAL return. When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to perform a bulk copy of tags to/from the guest. +7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM +------------------------------------- + +Architectures: x86 SEV enabled +Type: vm +Parameters: args[0] is the fd of the source vm +Returns: 0 on success + +This capability enables userspace to migrate the encryption context from the VM +indicated by the fd to the VM this is called on. + +This is intended to support intra-host migration of VMs between userspace VMMs, +upgrading the VMM process without interrupting the guest. + 8. Other capabilities. ====================== diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index a14c2938e7af..f2a59ed82ed3 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -360,7 +360,7 @@ between device driver specific code and shared common code: system memory page, locks the page with ``lock_page()``, and fills in the ``dst`` array entry with:: - dst[i] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + dst[i] = migrate_pfn(page_to_pfn(dpage)); Now that the driver knows that this page is being migrated, it can invalidate device private MMU mappings and copy device private memory diff --git a/MAINTAINERS b/MAINTAINERS index a2bd991db512..41ec20b7ec35 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -872,9 +872,10 @@ F: Documentation/devicetree/bindings/thermal/amazon,al-thermal.txt F: drivers/thermal/thermal_mmio.c AMAZON ETHERNET DRIVERS -M: Netanel Belgazal <netanel@amazon.com> +M: Shay Agroskin <shayagr@amazon.com> M: Arthur Kiyanovski <akiyano@amazon.com> -R: Guy Tzalik <gtzalik@amazon.com> +R: David Arinzon <darinzon@amazon.com> +R: Noam Dagan <ndagan@amazon.com> R: Saeed Bishara <saeedb@amazon.com> L: netdev@vger.kernel.org S: Supported @@ -2282,6 +2283,7 @@ F: arch/arm/boot/dts/mstar-* F: arch/arm/mach-mstar/ F: drivers/clk/mstar/ F: drivers/gpio/gpio-msc313.c +F: drivers/rtc/rtc-msc313.c F: drivers/watchdog/msc313e_wdt.c F: include/dt-bindings/clock/mstar-* F: include/dt-bindings/gpio/msc313-gpio.h @@ -4457,7 +4459,7 @@ CHIPONE ICN8318 I2C TOUCHSCREEN DRIVER M: Hans de Goede <hdegoede@redhat.com> L: linux-input@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt +F: Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml F: drivers/input/touchscreen/chipone_icn8318.c CHIPONE ICN8505 I2C TOUCHSCREEN DRIVER @@ -4468,14 +4470,12 @@ F: drivers/input/touchscreen/chipone_icn8505.c CHROME HARDWARE PLATFORM SUPPORT M: Benson Leung <bleung@chromium.org> -M: Enric Balletbo i Serra <enric.balletbo@collabora.com> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chrome-platform/linux.git F: drivers/platform/chrome/ CHROMEOS EC CODEC DRIVER M: Cheng-Yi Chiang <cychiang@chromium.org> -R: Enric Balletbo i Serra <enric.balletbo@collabora.com> R: Guenter Roeck <groeck@chromium.org> S: Maintained F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml @@ -4483,13 +4483,23 @@ F: sound/soc/codecs/cros_ec_codec.* CHROMEOS EC SUBDRIVERS M: Benson Leung <bleung@chromium.org> -M: Enric Balletbo i Serra <enric.balletbo@collabora.com> R: Guenter Roeck <groeck@chromium.org> S: Maintained F: drivers/power/supply/cros_usbpd-charger.c N: cros_ec N: cros-ec +CHROMEOS EC USB TYPE-C DRIVER +M: Prashant Malani <pmalani@chromium.org> +S: Maintained +F: drivers/platform/chrome/cros_ec_typec.c + +CHROMEOS EC USB PD NOTIFY DRIVER +M: Prashant Malani <pmalani@chromium.org> +S: Maintained +F: drivers/platform/chrome/cros_usbpd_notify.c +F: include/linux/platform_data/cros_usbpd_notify.h + CHRONTEL CH7322 CEC DRIVER M: Joe Tessler <jrt@google.com> L: linux-media@vger.kernel.org @@ -4666,11 +4676,10 @@ COCCINELLE/Semantic Patches (SmPL) M: Julia Lawall <Julia.Lawall@inria.fr> M: Gilles Muller <Gilles.Muller@inria.fr> M: Nicolas Palix <nicolas.palix@imag.fr> -M: Michal Marek <michal.lkml@markovi.net> -L: cocci@systeme.lip6.fr (moderated for non-subscribers) +L: cocci@inria.fr (moderated for non-subscribers) S: Supported -W: http://coccinelle.lip6.fr/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git misc +W: https://coccinelle.gitlabpages.inria.fr/website/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jlawall/linux.git F: Documentation/dev-tools/coccinelle.rst F: scripts/coccicheck F: scripts/coccinelle/ @@ -5195,6 +5204,13 @@ L: linux-input@vger.kernel.org S: Maintained F: drivers/input/touchscreen/cy8ctma140.c +CYPRESS STREETFIGHTER TOUCHKEYS DRIVER +M: Yassine Oudjana <y.oudjana@protonmail.com> +L: linux-input@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/input/cypress-sf.yaml +F: drivers/input/keyboard/cypress-sf.c + CYTTSP TOUCHSCREEN DRIVER M: Linus Walleij <linus.walleij@linaro.org> L: linux-input@vger.kernel.org @@ -8053,9 +8069,10 @@ F: drivers/media/usb/go7007/ GOODIX TOUCHSCREEN M: Bastien Nocera <hadess@hadess.net> +M: Hans de Goede <hdegoede@redhat.com> L: linux-input@vger.kernel.org S: Maintained -F: drivers/input/touchscreen/goodix.c +F: drivers/input/touchscreen/goodix* GOOGLE ETHERNET DRIVERS M: Jeroen de Borst <jeroendb@google.com> @@ -10790,11 +10807,6 @@ F: drivers/ata/ F: include/linux/ata.h F: include/linux/libata.h -LIBLOCKDEP -M: Sasha Levin <alexander.levin@microsoft.com> -S: Maintained -F: tools/lib/lockdep/ - LIBNVDIMM BLK: MMIO-APERTURE DRIVER M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> @@ -16162,7 +16174,7 @@ M: Bjorn Andersson <bjorn.andersson@linaro.org> M: Mathieu Poirier <mathieu.poirier@linaro.org> L: linux-remoteproc@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rproc-next +T: git https://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux.git rproc-next F: Documentation/ABI/testing/sysfs-class-remoteproc F: Documentation/devicetree/bindings/remoteproc/ F: Documentation/staging/remoteproc.rst @@ -16176,7 +16188,7 @@ M: Bjorn Andersson <bjorn.andersson@linaro.org> M: Mathieu Poirier <mathieu.poirier@linaro.org> L: linux-remoteproc@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rpmsg-next +T: git https://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux.git rpmsg-next F: Documentation/ABI/testing/sysfs-bus-rpmsg F: Documentation/staging/rpmsg.rst F: drivers/rpmsg/ diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 3793876f42d9..8e90052f6f05 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -294,7 +294,7 @@ int elf_check_arch(const struct elf32_hdr *x) eflags = x->e_flags; if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) { pr_err("ABI mismatch - you need newer toolchain\n"); - force_sigsegv(SIGSEGV); + force_fatal_sig(SIGSEGV); return 0; } diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index 24c19d63ff0a..dfeed440254a 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -77,16 +77,6 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, ®s->ARM_r0 + 1, 5 * sizeof(args[0])); } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - regs->ARM_ORIG_r0 = args[0]; - args++; - - memcpy(®s->ARM_r0 + 1, args, 5 * sizeof(args[0])); -} - static inline int syscall_get_arch(struct task_struct *task) { /* ARM tasks don't change audit architectures on the fly. */ diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c index 4b1619584b23..5ad0d6c56d56 100644 --- a/arch/arm/mm/kasan_init.c +++ b/arch/arm/mm/kasan_init.c @@ -32,7 +32,7 @@ pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss; static __init void *kasan_alloc_block(size_t size) { return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_KASAN, NUMA_NO_NODE); + MEMBLOCK_ALLOC_NOLEAKTRACE, NUMA_NO_NODE); } static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 7f1c106b746f..7619fbffcea2 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -442,7 +442,6 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op); EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); -EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw); EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist); diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S index b11bba542fac..f794dac9859a 100644 --- a/arch/arm/xen/hypercall.S +++ b/arch/arm/xen/hypercall.S @@ -88,7 +88,6 @@ HYPERCALL2(hvm_op); HYPERCALL2(memory_op); HYPERCALL2(physdev_op); HYPERCALL3(vcpu_op); -HYPERCALL1(tmem_op); HYPERCALL1(platform_op_raw); HYPERCALL2(multicall); HYPERCALL2(vm_assist); diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index a305ce256090..d52a0b269ee8 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -68,6 +68,7 @@ #define ESR_ELx_EC_MAX (0x3F) #define ESR_ELx_EC_SHIFT (26) +#define ESR_ELx_EC_WIDTH (6) #define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT) #define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4be8486042a7..2a5f7f38006f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -584,7 +584,7 @@ struct kvm_vcpu_stat { u64 exits; }; -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); +void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 84fbb52b4224..c4ba047a82d2 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -67,9 +67,15 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * page table entry, taking care of 52-bit addresses. */ #ifdef CONFIG_ARM64_PA_BITS_52 -#define __pte_to_phys(pte) \ - ((pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << 36)) -#define __phys_to_pte_val(phys) (((phys) | ((phys) >> 36)) & PTE_ADDR_MASK) +static inline phys_addr_t __pte_to_phys(pte_t pte) +{ + return (pte_val(pte) & PTE_ADDR_LOW) | + ((pte_val(pte) & PTE_ADDR_HIGH) << 36); +} +static inline pteval_t __phys_to_pte_val(phys_addr_t phys) +{ + return (phys | (phys >> 36)) & PTE_ADDR_MASK; +} #else #define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK) #define __phys_to_pte_val(phys) (phys) diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 03e20895453a..4cfe9b49709b 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -73,16 +73,6 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, ®s->regs[1], 5 * sizeof(args[0])); } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - regs->orig_x0 = args[0]; - args++; - - memcpy(®s->regs[1], args, 5 * sizeof(args[0])); -} - /* * We don't care about endianness (__AUDIT_ARCH_LE bit) here because * AArch64 has the same system calls both on little- and big- endian. diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index ecbdff795f5e..6f3e677d88f1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -573,15 +573,19 @@ static const struct arm64_ftr_bits ftr_raz[] = { ARM64_FTR_END, }; -#define ARM64_FTR_REG_OVERRIDE(id, table, ovr) { \ +#define __ARM64_FTR_REG_OVERRIDE(id_str, id, table, ovr) { \ .sys_id = id, \ .reg = &(struct arm64_ftr_reg){ \ - .name = #id, \ + .name = id_str, \ .override = (ovr), \ .ftr_bits = &((table)[0]), \ }} -#define ARM64_FTR_REG(id, table) ARM64_FTR_REG_OVERRIDE(id, table, &no_override) +#define ARM64_FTR_REG_OVERRIDE(id, table, ovr) \ + __ARM64_FTR_REG_OVERRIDE(#id, id, table, ovr) + +#define ARM64_FTR_REG(id, table) \ + __ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override) struct arm64_ftr_override __ro_after_init id_aa64mmfr1_override; struct arm64_ftr_override __ro_after_init id_aa64pfr1_override; @@ -2864,6 +2868,7 @@ bool this_cpu_has_cap(unsigned int n) return false; } +EXPORT_SYMBOL_GPL(this_cpu_has_cap); /* * This helper function is used in a narrow window when, diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 945e6bb326e3..700767dfd221 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,7 +23,7 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # potential future proofing if we end up with internal calls to the exported # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ +ldflags-y := -shared -soname=linux-vdso.so.1 --hash-style=sysv \ -Bsymbolic --build-id=sha1 -n $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index c8fec493a450..6c01b63ff56d 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -102,7 +102,7 @@ VDSO_AFLAGS += -D__ASSEMBLY__ # From arm vDSO Makefile VDSO_LDFLAGS += -Bsymbolic --no-undefined -soname=linux-vdso.so.1 VDSO_LDFLAGS += -z max-page-size=4096 -z common-page-size=4096 -VDSO_LDFLAGS += -nostdlib -shared --hash-style=sysv --build-id=sha1 +VDSO_LDFLAGS += -shared --hash-style=sysv --build-id=sha1 # Borrow vdsomunge.c from the arm vDSO diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index f5490afe1ebf..2f03cbfefe67 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1389,12 +1389,9 @@ long kvm_arch_vm_ioctl(struct file *filp, return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); } case KVM_ARM_PREFERRED_TARGET: { - int err; struct kvm_vcpu_init init; - err = kvm_vcpu_preferred_target(&init); - if (err) - return err; + kvm_vcpu_preferred_target(&init); if (copy_to_user(argp, &init, sizeof(init))) return -EFAULT; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5ce26bedf23c..e116c7767730 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -869,13 +869,10 @@ u32 __attribute_const__ kvm_target_cpu(void) return KVM_ARM_TARGET_GENERIC_V8; } -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) +void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) { u32 target = kvm_target_cpu(); - if (target < 0) - return -ENODEV; - memset(init, 0, sizeof(*init)); /* @@ -885,8 +882,6 @@ int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) * target type. */ init->target = (__u32)target; - - return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 9aa9b73475c9..b6b6801d96d5 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -44,7 +44,7 @@ el1_sync: // Guest trapped into EL2 mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH cmp x0, #ESR_ELx_EC_HVC64 ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 0c6116d34e18..3d613e721a75 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -141,7 +141,7 @@ SYM_FUNC_END(__host_hvc) .L__vect_start\@: stp x0, x1, [sp, #-16]! mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH cmp x0, #ESR_ELx_EC_HVC64 b.eq __host_hvc b __host_exit diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 862c7b514e20..578f71798c2e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -178,7 +178,7 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, phys = kvm_pte_to_phys(pte); if (!addr_is_memory(phys)) - return 0; + return -EINVAL; /* * Adjust the host stage-2 mappings to match the ownership attributes @@ -207,8 +207,18 @@ static int finalize_host_mappings(void) .cb = finalize_host_mappings_walker, .flags = KVM_PGTABLE_WALK_LEAF, }; + int i, ret; + + for (i = 0; i < hyp_memblock_nr; i++) { + struct memblock_region *reg = &hyp_memory[i]; + u64 start = (u64)hyp_phys_to_virt(reg->base); + + ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker); + if (ret) + return ret; + } - return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker); + return 0; } void __noreturn __pkvm_init_finalise(void) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 3787ee6fb1a2..792cf6e6ac92 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -474,7 +474,7 @@ bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -/** +/* * Handler for protected VM restricted exceptions. * * Inject an undefined exception into the guest and return true to indicate that diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 5b996ca4d996..c12cd700598f 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -36,7 +36,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) { void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_KASAN, node); + MEMBLOCK_ALLOC_NOLEAKTRACE, node); if (!p) panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n", __func__, PAGE_SIZE, PAGE_SIZE, node, @@ -49,7 +49,8 @@ static phys_addr_t __init kasan_alloc_raw_page(int node) { void *p = memblock_alloc_try_nid_raw(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_KASAN, node); + MEMBLOCK_ALLOC_NOLEAKTRACE, + node); if (!p) panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n", __func__, PAGE_SIZE, PAGE_SIZE, node, @@ -309,7 +310,7 @@ void __init kasan_init(void) kasan_init_depth(); #if defined(CONFIG_KASAN_GENERIC) /* CONFIG_KASAN_SW_TAGS also requires kasan_init_sw_tags(). */ - pr_info("KernelAddressSanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized (generic)\n"); #endif } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index d77bf06d6a6d..acfae9b41cc8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -96,7 +96,8 @@ static phys_addr_t __init early_pgtable_alloc(int shift) phys_addr_t phys; void *ptr; - phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); + phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0, + MEMBLOCK_ALLOC_NOLEAKTRACE); if (!phys) panic("Failed to allocate page table page\n"); diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S index 5b09aca55108..9d01361696a1 100644 --- a/arch/arm64/xen/hypercall.S +++ b/arch/arm64/xen/hypercall.S @@ -80,7 +80,6 @@ HYPERCALL2(hvm_op); HYPERCALL2(memory_op); HYPERCALL2(physdev_op); HYPERCALL3(vcpu_op); -HYPERCALL1(tmem_op); HYPERCALL1(platform_op_raw); HYPERCALL2(multicall); HYPERCALL2(vm_assist); diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h index f624fa3bbc22..0de5734950bf 100644 --- a/arch/csky/include/asm/syscall.h +++ b/arch/csky/include/asm/syscall.h @@ -59,15 +59,6 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, memcpy(args, ®s->a1, 5 * sizeof(args[0])); } -static inline void -syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - const unsigned long *args) -{ - regs->orig_a0 = args[0]; - args++; - memcpy(®s->a1, args, 5 * sizeof(regs->a1)); -} - static inline int syscall_get_arch(struct task_struct *task) { diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h index 0d23c0049301..2b02a3fb862a 100644 --- a/arch/ia64/include/asm/syscall.h +++ b/arch/ia64/include/asm/syscall.h @@ -55,21 +55,8 @@ static inline void syscall_set_return_value(struct task_struct *task, } } -extern void ia64_syscall_get_set_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned long *args, int rw); -static inline void syscall_get_arguments(struct task_struct *task, - struct pt_regs *regs, - unsigned long *args) -{ - ia64_syscall_get_set_arguments(task, regs, args, 0); -} - -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - unsigned long *args) -{ - ia64_syscall_get_set_arguments(task, regs, args, 1); -} +extern void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, unsigned long *args); static inline int syscall_get_arch(struct task_struct *task) { diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index df28c7dd164f..6a1439eaa050 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -2001,17 +2001,16 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *tsk) return &user_ia64_view; } -struct syscall_get_set_args { +struct syscall_get_args { unsigned int i; unsigned int n; unsigned long *args; struct pt_regs *regs; - int rw; }; -static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data) +static void syscall_get_args_cb(struct unw_frame_info *info, void *data) { - struct syscall_get_set_args *args = data; + struct syscall_get_args *args = data; struct pt_regs *pt = args->regs; unsigned long *krbs, cfm, ndirty, nlocals, nouts; int i, count; @@ -2042,37 +2041,31 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data) /* Iterate over outs. */ for (i = 0; i < count; i++) { int j = ndirty + nlocals + i + args->i; - if (args->rw) - *ia64_rse_skip_regs(krbs, j) = args->args[i]; - else - args->args[i] = *ia64_rse_skip_regs(krbs, j); + args->args[i] = *ia64_rse_skip_regs(krbs, j); } - if (!args->rw) { - while (i < args->n) { - args->args[i] = 0; - i++; - } + while (i < args->n) { + args->args[i] = 0; + i++; } } -void ia64_syscall_get_set_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned long *args, int rw) +void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, unsigned long *args) { - struct syscall_get_set_args data = { + struct syscall_get_args data = { .i = 0, .n = 6, .args = args, .regs = regs, - .rw = rw, }; if (task == current) - unw_init_running(syscall_get_set_args_cb, &data); + unw_init_running(syscall_get_args_cb, &data); else { struct unw_frame_info ufi; memset(&ufi, 0, sizeof(ufi)); unw_init_from_blocked_task(&ufi, task); - syscall_get_set_args_cb(&ufi, &data); + syscall_get_args_cb(&ufi, &data); } } diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index 277d61a09463..0d00ef5117dc 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -53,17 +53,6 @@ config M68000 System-On-Chip devices (eg 68328, 68302, etc). It does not contain a paging MMU. -config MCPU32 - bool - select CPU_HAS_NO_BITFIELDS - select CPU_HAS_NO_CAS - select CPU_HAS_NO_UNALIGNED - select CPU_NO_EFFICIENT_FFS - help - The Freescale (was then Motorola) CPU32 is a CPU core that is - based on the 68020 processor. For the most part it is used in - System-On-Chip parts, and does not contain a paging MMU. - config M68020 bool "68020 support" depends on MMU diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index 36fa0c3ef129..eeab4f3e6c19 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -203,6 +203,7 @@ config INIT_LCD config MEMORY_RESERVE int "Memory reservation (MiB)" depends on (UCSIMM || UCDIMM) + default 0 help Reserve certain memory regions on 68x328 based boards. diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 7b414099e5fc..7b93e1fd8ffa 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -451,7 +451,7 @@ static inline unsigned long ffz(unsigned long word) * generic functions for those. */ #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \ - !defined(CONFIG_M68000) && !defined(CONFIG_MCPU32) + !defined(CONFIG_M68000) static inline unsigned long __ffs(unsigned long x) { __asm__ __volatile__ ("bitrev %0; ff1 %0" diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 9718ce94cc84..99058a6da956 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1145,7 +1145,7 @@ asmlinkage void set_esp0(unsigned long ssp) */ asmlinkage void fpsp040_die(void) { - force_sigsegv(SIGSEGV); + force_fatal_sig(SIGSEGV); } #ifdef CONFIG_M68KFPU_EMU diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h index 3a6924f3cbde..5eb3f624cc59 100644 --- a/arch/microblaze/include/asm/syscall.h +++ b/arch/microblaze/include/asm/syscall.h @@ -58,28 +58,6 @@ static inline microblaze_reg_t microblaze_get_syscall_arg(struct pt_regs *regs, return ~0; } -static inline void microblaze_set_syscall_arg(struct pt_regs *regs, - unsigned int n, - unsigned long val) -{ - switch (n) { - case 5: - regs->r10 = val; - case 4: - regs->r9 = val; - case 3: - regs->r8 = val; - case 2: - regs->r7 = val; - case 1: - regs->r6 = val; - case 0: - regs->r5 = val; - default: - BUG(); - } -} - static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) @@ -91,17 +69,6 @@ static inline void syscall_get_arguments(struct task_struct *task, *args++ = microblaze_get_syscall_arg(regs, i++); } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - unsigned int i = 0; - unsigned int n = 6; - - while (n--) - microblaze_set_syscall_arg(regs, i++, *args++); -} - asmlinkage unsigned long do_syscall_trace_enter(struct pt_regs *regs); asmlinkage void do_syscall_trace_leave(struct pt_regs *regs); diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 2c57994b5217..30193bcf9caa 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -37,4 +37,4 @@ platform-$(CONFIG_MACH_TX49XX) += txx9/ platform-$(CONFIG_MACH_VR41XX) += vr41xx/ # include the platform specific files -include $(patsubst %, $(srctree)/arch/mips/%/Platform, $(platform-y)) +include $(patsubst %/, $(srctree)/arch/mips/%/Platform, $(platform-y)) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 86510741d49d..de60ad190057 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -292,6 +292,8 @@ config BMIPS_GENERIC select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN select USB_OHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN select HARDIRQS_SW_RESEND + select HAVE_PCI + select PCI_DRIVERS_GENERIC help Build a generic DT-based kernel image that boots on select BCM33xx cable modem chips, BCM63xx DSL chips, and BCM7xxx set-top @@ -333,6 +335,9 @@ config BCM63XX select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select SYS_HAS_EARLY_PRINTK + select SYS_HAS_CPU_BMIPS32_3300 + select SYS_HAS_CPU_BMIPS4350 + select SYS_HAS_CPU_BMIPS4380 select SWAP_IO_SPACE select GPIOLIB select MIPS_L1_CACHE_SHIFT_4 diff --git a/arch/mips/Makefile b/arch/mips/Makefile index e036fc025ccc..ace7f033de07 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -253,7 +253,9 @@ endif # # Board-dependent options and extra files # +ifdef need-compiler include $(srctree)/arch/mips/Kbuild.platforms +endif ifdef CONFIG_PHYSICAL_START load-y = $(CONFIG_PHYSICAL_START) diff --git a/arch/mips/boot/compressed/.gitignore b/arch/mips/boot/compressed/.gitignore deleted file mode 100644 index d358395614c9..000000000000 --- a/arch/mips/boot/compressed/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -ashldi3.c -bswapsi.c diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 3548b3b45269..2861a05c2e0c 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -50,19 +50,9 @@ vmlinuzobjs-$(CONFIG_MIPS_ALCHEMY) += $(obj)/uart-alchemy.o vmlinuzobjs-$(CONFIG_ATH79) += $(obj)/uart-ath79.o endif -extra-y += uart-ath79.c -$(obj)/uart-ath79.c: $(srctree)/arch/mips/ath79/early_printk.c - $(call cmd,shipped) - vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o -extra-y += ashldi3.c -$(obj)/ashldi3.c: $(obj)/%.c: $(srctree)/lib/%.c FORCE - $(call if_changed,shipped) - -extra-y += bswapsi.c -$(obj)/bswapsi.c: $(obj)/%.c: $(srctree)/arch/mips/lib/%.c FORCE - $(call if_changed,shipped) +vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o targets := $(notdir $(vmlinuzobjs-y)) diff --git a/arch/mips/boot/compressed/ashldi3.c b/arch/mips/boot/compressed/ashldi3.c new file mode 100644 index 000000000000..f7bf6a7aae31 --- /dev/null +++ b/arch/mips/boot/compressed/ashldi3.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../../../lib/ashldi3.c" diff --git a/arch/mips/boot/compressed/bswapdi.c b/arch/mips/boot/compressed/bswapdi.c new file mode 100644 index 000000000000..acb28aebb025 --- /dev/null +++ b/arch/mips/boot/compressed/bswapdi.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/bswapdi.c" diff --git a/arch/mips/boot/compressed/bswapsi.c b/arch/mips/boot/compressed/bswapsi.c new file mode 100644 index 000000000000..fdb9c6476904 --- /dev/null +++ b/arch/mips/boot/compressed/bswapsi.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/bswapsi.c" diff --git a/arch/mips/boot/compressed/uart-ath79.c b/arch/mips/boot/compressed/uart-ath79.c new file mode 100644 index 000000000000..d686820921be --- /dev/null +++ b/arch/mips/boot/compressed/uart-ath79.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../ath79/early_printk.c" diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig index 625bd2d7e685..5956fb95c19f 100644 --- a/arch/mips/configs/bmips_stb_defconfig +++ b/arch/mips/configs/bmips_stb_defconfig @@ -1,6 +1,7 @@ # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_NO_HZ=y +CONFIG_HZ=1000 CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set @@ -8,17 +9,34 @@ CONFIG_EXPERT=y CONFIG_BMIPS_GENERIC=y CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_HIGHMEM=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_NR_CPUS=4 +CONFIG_CC_STACKPROTECTOR_STRONG=y # CONFIG_SECCOMP is not set CONFIG_MIPS_O32_FP64_SUPPORT=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +CONFIG_RD_XZ=y +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCIEASPM_POWERSAVE=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCIE_BRCMSTB=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y -CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y CONFIG_BMIPS_CPUFREQ=y # CONFIG_BLK_DEV_BSG is not set CONFIG_NET=y @@ -32,32 +50,99 @@ CONFIG_INET=y # CONFIG_INET_DIAG is not set CONFIG_CFG80211=y CONFIG_NL80211_TESTMODE=y +CONFIG_WIRELESS=y CONFIG_MAC80211=y +CONFIG_NL80211=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set +CONFIG_BRCMSTB_GISB_ARB=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +CONFIG_INET_UDP_DIAG=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_BIC=y +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +# CONFIG_IPV6 is not set +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_BRIDGE=y +CONFIG_BRIDGE_NETFILTER=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_NET_DSA=y +CONFIG_NET_SWITCHDEV=y +CONFIG_DMA_CMA=y +CONFIG_CMA_ALIGNMENT=12 +CONFIG_SPI=y +CONFIG_SPI_BRCMSTB=y CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y +CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y +CONFIG_MTD_CFI_STAA=y +CONFIG_MTD_ROM=y +CONFIG_MTD_ABSENT=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_M25P80=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_BRCMNAND=y +CONFIG_MTD_SPI_NOR=y +# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_GLUEBI=y +CONFIG_PROC_DEVICETREE=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_BLK_DEV is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_MULTI_LUN=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y +CONFIG_VLAN_8021Q=y +CONFIG_MACVLAN=y CONFIG_BCMGENET=y CONFIG_USB_USBNET=y -# CONFIG_INPUT is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y # CONFIG_SERIO is not set -# CONFIG_VT is not set +CONFIG_VT=y +CONFIG_VT_HW_CONSOLE_BINDING=y +# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_BRCMSTB=y CONFIG_POWER_RESET_SYSCON=y CONFIG_POWER_SUPPLY=y # CONFIG_HWMON is not set @@ -69,22 +154,76 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_SOC_BRCMSTB=y +CONFIG_MMC=y +CONFIG_MMC_BLOCK_MINORS=16 +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y # CONFIG_DNOTIFY is not set +CONFIG_PROC_KCORE=y +CONFIG_CIFS=y +CONFIG_JBD2_DEBUG=y CONFIG_FUSE_FS=y +CONFIG_FHANDLE=y +CONFIG_CGROUPS=y +CONFIG_CUSE=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=y +CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y -CONFIG_PROC_KCORE=y CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_UBIFS_FS=y +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y CONFIG_NFS_FS=y -CONFIG_CIFS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y -# CONFIG_CRYPTO_HW is not set CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG=y +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_INFO_REDUCED is not set CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEBUG_USER=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon" +# CONFIG_MIPS_CMDLINE_FROM_DTB is not set +CONFIG_MIPS_CMDLINE_DTB_EXTEND=y +# CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER is not set +# CONFIG_CRYPTO_HW is not set +CONFIG_DT_BCM974XX=y +CONFIG_FW_CFE=y +CONFIG_ATA=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_BRCMSTB=y +CONFIG_GENERIC_PHY=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SYSFS=y +CONFIG_PHY_BRCM_USB=y +CONFIG_PHY_BRCM_SATA=y +CONFIG_PM_RUNTIME=y +CONFIG_PM_DEBUG=y +CONFIG_SYSVIPC=y +CONFIG_FUNCTION_GRAPH_TRACER=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index eaad0ed4b523..a8a30bb1dee8 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -117,21 +117,21 @@ static void __init dec_be_init(void) { switch (mips_machtype) { case MACH_DS23100: /* DS2100/DS3100 Pmin/Pmax */ - board_be_handler = dec_kn01_be_handler; + mips_set_be_handler(dec_kn01_be_handler); busirq_handler = dec_kn01_be_interrupt; busirq_flags |= IRQF_SHARED; dec_kn01_be_init(); break; case MACH_DS5000_1XX: /* DS5000/1xx 3min */ case MACH_DS5000_XX: /* DS5000/xx Maxine */ - board_be_handler = dec_kn02xa_be_handler; + mips_set_be_handler(dec_kn02xa_be_handler); busirq_handler = dec_kn02xa_be_interrupt; dec_kn02xa_be_init(); break; case MACH_DS5000_200: /* DS5000/200 3max */ case MACH_DS5000_2X0: /* DS5000/240 3max+ */ case MACH_DS5900: /* DS5900 bigmax */ - board_be_handler = dec_ecc_be_handler; + mips_set_be_handler(dec_ecc_be_handler); busirq_handler = dec_ecc_be_interrupt; dec_ecc_be_init(); break; diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h index b710e76c9c65..15cde638b407 100644 --- a/arch/mips/include/asm/traps.h +++ b/arch/mips/include/asm/traps.h @@ -15,7 +15,7 @@ #define MIPS_BE_FATAL 2 /* treat as an unrecoverable error */ extern void (*board_be_init)(void); -extern int (*board_be_handler)(struct pt_regs *regs, int is_fixup); +void mips_set_be_handler(int (*handler)(struct pt_regs *reg, int is_fixup)); extern void (*board_nmi_handler_setup)(void); extern void (*board_ejtag_handler_setup)(void); diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index 12e58053544f..cbf6db98cfb3 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -29,8 +29,8 @@ #define EX2(a,b) \ 9: a,##b; \ .section __ex_table,"a"; \ - PTR 9b,bad_stack; \ - PTR 9b+4,bad_stack; \ + PTR 9b,fault; \ + PTR 9b+4,fault; \ .previous .set mips1 diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 2afa3eef486a..5512cd586e6e 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -240,12 +240,3 @@ SYSCALL_DEFINE3(cachectl, char *, addr, int, nbytes, int, op) { return -ENOSYS; } - -/* - * If we ever come here the user sp is bad. Zap the process right away. - * Due to the bad stack signaling wouldn't work. - */ -asmlinkage void bad_stack(void) -{ - do_exit(SIGSEGV); -} diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 6f07362de5ce..d26b0fb8ea06 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -103,13 +103,19 @@ extern asmlinkage void handle_reserved(void); extern void tlb_do_page_fault_0(void); void (*board_be_init)(void); -int (*board_be_handler)(struct pt_regs *regs, int is_fixup); +static int (*board_be_handler)(struct pt_regs *regs, int is_fixup); void (*board_nmi_handler_setup)(void); void (*board_ejtag_handler_setup)(void); void (*board_bind_eic_interrupt)(int irq, int regset); void (*board_ebase_setup)(void); void(*board_cache_error_setup)(void); +void mips_set_be_handler(int (*handler)(struct pt_regs *regs, int is_fixup)) +{ + board_be_handler = handler; +} +EXPORT_SYMBOL_GPL(mips_set_be_handler); + static void show_raw_backtrace(unsigned long reg29, const char *loglvl, bool user) { diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c index dc0110a607a5..afe8a61078e4 100644 --- a/arch/mips/sgi-ip22/ip22-berr.c +++ b/arch/mips/sgi-ip22/ip22-berr.c @@ -112,5 +112,5 @@ static int ip22_be_handler(struct pt_regs *regs, int is_fixup) void __init ip22_be_init(void) { - board_be_handler = ip22_be_handler; + mips_set_be_handler(ip22_be_handler); } diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c index c61362d9ea95..16ca470deb80 100644 --- a/arch/mips/sgi-ip22/ip28-berr.c +++ b/arch/mips/sgi-ip22/ip28-berr.c @@ -468,7 +468,7 @@ static int ip28_be_handler(struct pt_regs *regs, int is_fixup) void __init ip22_be_init(void) { - board_be_handler = ip28_be_handler; + mips_set_be_handler(ip28_be_handler); } int ip28_show_be_info(struct seq_file *m) diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c index 5a38ae6bdfa9..923a63a51cda 100644 --- a/arch/mips/sgi-ip27/ip27-berr.c +++ b/arch/mips/sgi-ip27/ip27-berr.c @@ -85,7 +85,7 @@ void __init ip27_be_init(void) int cpu = LOCAL_HUB_L(PI_CPU_NUM); int cpuoff = cpu << 8; - board_be_handler = ip27_be_handler; + mips_set_be_handler(ip27_be_handler); LOCAL_HUB_S(PI_ERR_INT_PEND, cpu ? PI_ERR_CLEAR_ALL_B : PI_ERR_CLEAR_ALL_A); diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c index c860f95ab7ed..478b63b4c808 100644 --- a/arch/mips/sgi-ip32/ip32-berr.c +++ b/arch/mips/sgi-ip32/ip32-berr.c @@ -34,5 +34,5 @@ static int ip32_be_handler(struct pt_regs *regs, int is_fixup) void __init ip32_be_init(void) { - board_be_handler = ip32_be_handler; + mips_set_be_handler(ip32_be_handler); } diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index f07b15dd1c1a..72a31eeeebba 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -122,7 +122,7 @@ void __init plat_mem_setup(void) #error invalid SiByte board configuration #endif - board_be_handler = swarm_be_handler; + mips_set_be_handler(swarm_be_handler); if (xicor_probe()) swarm_rtc_type = RTC_XICOR; diff --git a/arch/mips/txx9/generic/setup_tx4927.c b/arch/mips/txx9/generic/setup_tx4927.c index 46e9c4101386..63f9725b2eb0 100644 --- a/arch/mips/txx9/generic/setup_tx4927.c +++ b/arch/mips/txx9/generic/setup_tx4927.c @@ -80,7 +80,7 @@ static int tx4927_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4927_be_init(void) { - board_be_handler = tx4927_be_handler; + mips_set_be_handler(tx4927_be_handler); } static struct resource tx4927_sdram_resource[4]; diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c index 17395d5d15ca..ba646548c5f6 100644 --- a/arch/mips/txx9/generic/setup_tx4938.c +++ b/arch/mips/txx9/generic/setup_tx4938.c @@ -82,7 +82,7 @@ static int tx4938_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4938_be_init(void) { - board_be_handler = tx4938_be_handler; + mips_set_be_handler(tx4938_be_handler); } static struct resource tx4938_sdram_resource[4]; diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index bf8a3cdababf..f5f59b7401a3 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -86,7 +86,7 @@ static int tx4939_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4939_be_init(void) { - board_be_handler = tx4939_be_handler; + mips_set_be_handler(tx4939_be_handler); } static struct resource tx4939_sdram_resource[4]; diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 1b2ea34c3d3b..d65f55f67e19 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -57,7 +57,7 @@ endif # VDSO linker flags. ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ - $(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared \ + $(filter -E%,$(KBUILD_CFLAGS)) -shared \ -G 0 --eh-frame-hdr --hash-style=sysv --build-id=sha1 -T CFLAGS_REMOVE_vdso.o = $(CC_FLAGS_FTRACE) diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h index 7b5180d78e20..90aa56c94af1 100644 --- a/arch/nds32/include/asm/syscall.h +++ b/arch/nds32/include/asm/syscall.h @@ -132,28 +132,6 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, memcpy(args, ®s->uregs[0] + 1, 5 * sizeof(args[0])); } -/** - * syscall_set_arguments - change system call parameter value - * @task: task of interest, must be in system call entry tracing - * @regs: task_pt_regs() of @task - * @args: array of argument values to store - * - * Changes 6 arguments to the system call. The first argument gets value - * @args[0], and so on. - * - * It's only valid to call this when @task is stopped for tracing on - * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT. - */ -static inline void -syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - const unsigned long *args) -{ - regs->orig_r0 = args[0]; - args++; - - memcpy(®s->uregs[0] + 1, args, 5 * sizeof(args[0])); -} - static inline int syscall_get_arch(struct task_struct *task) { diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index f06421c645af..ca75d475eda4 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -118,7 +118,7 @@ DEFINE_SPINLOCK(die_lock); /* * This function is protected against re-entrancy. */ -void die(const char *str, struct pt_regs *regs, int err) +void __noreturn die(const char *str, struct pt_regs *regs, int err) { struct task_struct *tsk = current; static int die_counter; diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c index f02524eb6d56..1d139b117168 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -13,7 +13,7 @@ #include <asm/tlbflush.h> -extern void die(const char *str, struct pt_regs *regs, long err); +extern void __noreturn die(const char *str, struct pt_regs *regs, long err); /* * This is useful to dump out the page tables associated with @@ -299,10 +299,6 @@ no_context: show_pte(mm, addr); die("Oops", regs, error_code); - bust_spinlocks(0); - do_exit(SIGKILL); - - return; /* * We ran out of memory, or some other thing happened to us that made diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h index 526449edd768..fff52205fb65 100644 --- a/arch/nios2/include/asm/syscall.h +++ b/arch/nios2/include/asm/syscall.h @@ -58,17 +58,6 @@ static inline void syscall_get_arguments(struct task_struct *task, *args = regs->r9; } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, const unsigned long *args) -{ - regs->r4 = *args++; - regs->r5 = *args++; - regs->r6 = *args++; - regs->r7 = *args++; - regs->r8 = *args++; - regs->r9 = *args; -} - static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_NIOS2; diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h index e6383be2a195..903ed882bdec 100644 --- a/arch/openrisc/include/asm/syscall.h +++ b/arch/openrisc/include/asm/syscall.h @@ -57,13 +57,6 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, memcpy(args, ®s->gpr[3], 6 * sizeof(args[0])); } -static inline void -syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - const unsigned long *args) -{ - memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); -} - static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_OPENRISC; diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index aa1e709405ac..0898cb159fac 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -197,7 +197,7 @@ void nommu_dump_state(struct pt_regs *regs, } /* This is normally the 'Oops' routine */ -void die(const char *str, struct pt_regs *regs, long err) +void __noreturn die(const char *str, struct pt_regs *regs, long err) { console_verbose(); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index c730d1a51686..f0fa6394a58e 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -32,7 +32,7 @@ unsigned long pte_errors; /* updated by do_page_fault() */ */ volatile pgd_t *current_pgd[NR_CPUS]; -extern void die(char *, struct pt_regs *, long); +extern void __noreturn die(char *, struct pt_regs *, long); /* * This routine handles page faults. It determines the address, @@ -248,8 +248,6 @@ no_context: die("Oops", regs, write_acc); - do_exit(SIGKILL); - /* * We ran out of memory, or some other thing happened to us that made * us unable to handle the page fault gracefully. diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index c60ebd04b2ed..52d05b465e3e 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -103,16 +103,6 @@ static inline void syscall_get_arguments(struct task_struct *task, } } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); - - /* Also copy the first argument into orig_gpr3 */ - regs->orig_gpr3 = args[0]; -} - static inline int syscall_get_arch(struct task_struct *task) { if (is_32bit_task()) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 38c3eae40c14..00a9c9cd6d42 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1062,8 +1062,10 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, * or if another thread unmaps the region containing the context. * We kill the task with a SIGSEGV in this situation. */ - if (do_setcontext(new_ctx, regs, 0)) - do_exit(SIGSEGV); + if (do_setcontext(new_ctx, regs, 0)) { + force_fatal_sig(SIGSEGV); + return -EFAULT; + } set_thread_flag(TIF_RESTOREALL); return 0; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 9f471b4a11e3..ef518535d436 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -703,15 +703,18 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, * We kill the task with a SIGSEGV in this situation. */ - if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) - do_exit(SIGSEGV); + if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) { + force_fatal_sig(SIGSEGV); + return -EFAULT; + } set_current_blocked(&set); if (!user_read_access_begin(new_ctx, ctx_size)) return -EFAULT; if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) { user_read_access_end(); - do_exit(SIGSEGV); + force_fatal_sig(SIGSEGV); + return -EFAULT; } user_read_access_end(); diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index a7061ee3b157..28c436df9935 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -560,7 +560,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, gpa, 0, page_shift); if (ret == U_SUCCESS) - *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + *mig.dst = migrate_pfn(pfn); else { unlock_page(dpage); __free_page(dpage); @@ -774,7 +774,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, } } - *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + *mig.dst = migrate_pfn(page_to_pfn(dpage)); migrate_vma_pages(&mig); out_finalize: migrate_vma_finalize(&mig); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a34c531be4e7..821252b65f89 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -62,6 +62,7 @@ config RISCV select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT + select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 7f19b784e649..5927c94302b8 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -136,3 +136,13 @@ zinstall: install-image = Image.gz install zinstall: $(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \ $(boot)/$(install-image) System.map "$(INSTALL_PATH)" + +PHONY += rv32_randconfig +rv32_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \ + -f $(srctree)/Makefile randconfig + +PHONY += rv64_randconfig +rv64_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \ + -f $(srctree)/Makefile randconfig diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index b254c60589a1..fc1e5869df1b 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -9,10 +9,8 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "Microchip PolarFire-SoC Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit"; + compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs"; aliases { ethernet0 = &emac1; @@ -35,9 +33,6 @@ reg = <0x0 0x80000000 0x0 0x40000000>; clocks = <&clkcfg 26>; }; - - soc { - }; }; &serial0 { @@ -56,8 +51,17 @@ status = "okay"; }; -&sdcard { +&mmc { status = "okay"; + + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + card-detect-delay = <200>; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; }; &emac0 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index 9d2fbbc1f777..c9f6d205d2ba 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -6,8 +6,8 @@ / { #address-cells = <2>; #size-cells = <2>; - model = "Microchip MPFS Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit"; + model = "Microchip PolarFire SoC"; + compatible = "microchip,mpfs"; chosen { }; @@ -161,7 +161,7 @@ }; clint@2000000 { - compatible = "sifive,clint0"; + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; reg = <0x0 0x2000000 0x0 0xC000>; interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 &cpu1_intc 3 &cpu1_intc 7 @@ -172,7 +172,7 @@ plic: interrupt-controller@c000000 { #interrupt-cells = <1>; - compatible = "sifive,plic-1.0.0"; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; reg = <0x0 0xc000000 0x0 0x4000000>; riscv,ndev = <186>; interrupt-controller; @@ -262,39 +262,13 @@ status = "disabled"; }; - emmc: mmc@20008000 { - compatible = "cdns,sd4hc"; + /* Common node entry for emmc/sd */ + mmc: mmc@20008000 { + compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc"; reg = <0x0 0x20008000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <88 89>; - pinctrl-names = "default"; clocks = <&clkcfg 6>; - bus-width = <4>; - cap-mmc-highspeed; - mmc-ddr-3_3v; - max-frequency = <200000000>; - non-removable; - no-sd; - no-sdio; - voltage-ranges = <3300 3300>; - status = "disabled"; - }; - - sdcard: sdhc@20008000 { - compatible = "cdns,sd4hc"; - reg = <0x0 0x20008000 0x0 0x1000>; - interrupt-parent = <&plic>; - interrupts = <88>; - pinctrl-names = "default"; - clocks = <&clkcfg 6>; - bus-width = <4>; - disable-wp; - cap-sd-highspeed; - card-detect-delay = <200>; - sd-uhs-sdr12; - sd-uhs-sdr25; - sd-uhs-sdr50; - sd-uhs-sdr104; max-frequency = <200000000>; status = "disabled"; }; diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 7db861053483..0655b5c4201d 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -141,7 +141,7 @@ ranges; plic0: interrupt-controller@c000000 { #interrupt-cells = <1>; - compatible = "sifive,plic-1.0.0"; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; reg = <0x0 0xc000000 0x0 0x4000000>; riscv,ndev = <53>; interrupt-controller; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 60846e88ae4b..ba304d4c455c 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -8,10 +8,9 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "SiFive HiFive Unleashed A00"; - compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000"; + compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000", + "sifive,fu540"; chosen { stdout-path = "serial0"; @@ -26,9 +25,6 @@ reg = <0x0 0x80000000 0x2 0x00000000>; }; - soc { - }; - hfclk: hfclk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -63,7 +59,7 @@ &qspi0 { status = "okay"; flash@0 { - compatible = "issi,is25wp256", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; m25p,fast-read; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 2e4ea84f27e7..4f66919215f6 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -8,8 +8,6 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "SiFive HiFive Unmatched A00"; compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000", "sifive,fu740"; @@ -27,9 +25,6 @@ reg = <0x0 0x80000000 0x4 0x00000000>; }; - soc { - }; - hfclk: hfclk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -211,7 +206,7 @@ &qspi0 { status = "okay"; flash@0 { - compatible = "issi,is25wp256", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; m25p,fast-read; diff --git a/arch/riscv/configs/32-bit.config b/arch/riscv/configs/32-bit.config new file mode 100644 index 000000000000..43f41323b67e --- /dev/null +++ b/arch/riscv/configs/32-bit.config @@ -0,0 +1,2 @@ +CONFIG_ARCH_RV32I=y +CONFIG_32BIT=y diff --git a/arch/riscv/configs/64-bit.config b/arch/riscv/configs/64-bit.config new file mode 100644 index 000000000000..313edc554d84 --- /dev/null +++ b/arch/riscv/configs/64-bit.config @@ -0,0 +1,2 @@ +CONFIG_ARCH_RV64I=y +CONFIG_64BIT=y diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 4ebc80315f01..c252fd5706d2 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -72,9 +72,10 @@ CONFIG_GPIOLIB=y CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y -CONFIG_DRM=y -CONFIG_DRM_RADEON=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_DRM=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_NOUVEAU=m +CONFIG_DRM_VIRTIO_GPU=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 109c97e991a6..b3e5ff0125fe 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -157,6 +157,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define page_to_bus(page) (page_to_phys(page)) #define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) + #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) \ (((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 39b550310ec6..bf204e7c1f74 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -75,7 +75,8 @@ #endif #ifdef CONFIG_XIP_KERNEL -#define XIP_OFFSET SZ_8M +#define XIP_OFFSET SZ_32M +#define XIP_OFFSET_MASK (SZ_32M - 1) #else #define XIP_OFFSET 0 #endif @@ -97,7 +98,8 @@ #ifdef CONFIG_XIP_KERNEL #define XIP_FIXUP(addr) ({ \ uintptr_t __a = (uintptr_t)(addr); \ - (__a >= CONFIG_XIP_PHYS_ADDR && __a < CONFIG_XIP_PHYS_ADDR + SZ_16M) ? \ + (__a >= CONFIG_XIP_PHYS_ADDR && \ + __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ? \ __a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\ __a; \ }) diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 34fbb3ea21d5..7ac6a0e275f2 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -64,15 +64,6 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, ®s->a1, 5 * sizeof(args[0])); } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - regs->orig_a0 = args[0]; - args++; - memcpy(®s->a1, args, 5 * sizeof(regs->a1)); -} - static inline int syscall_get_arch(struct task_struct *task) { #ifdef CONFIG_64BIT diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 208e31bc5d1c..bc6f75f3a199 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -8,30 +8,19 @@ #ifndef _ASM_RISCV_VDSO_H #define _ASM_RISCV_VDSO_H - -/* - * All systems with an MMU have a VDSO, but systems without an MMU don't - * support shared libraries and therefor don't have one. - */ -#ifdef CONFIG_MMU - -#include <linux/types.h> /* * All systems with an MMU have a VDSO, but systems without an MMU don't * support shared libraries and therefor don't have one. */ #ifdef CONFIG_MMU -#define __VVAR_PAGES 1 +#define __VVAR_PAGES 2 #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> #define VDSO_SYMBOL(base, name) \ (void __user *)((unsigned long)(base) + __vdso_##name##_offset) - -#endif /* CONFIG_MMU */ - #endif /* !__ASSEMBLY__ */ #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index f839f16e0d2a..77d9c2f721c4 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -76,6 +76,13 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) return _vdso_data; } +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +{ + return _timens_data; +} +#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 25ec50573957..f52f01ecbeea 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -20,10 +20,20 @@ REG_L t0, _xip_fixup add \reg, \reg, t0 .endm +.macro XIP_FIXUP_FLASH_OFFSET reg + la t1, __data_loc + li t0, XIP_OFFSET_MASK + and t1, t1, t0 + li t1, XIP_OFFSET + sub t0, t0, t1 + sub \reg, \reg, t0 +.endm _xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET #else .macro XIP_FIXUP_OFFSET reg .endm +.macro XIP_FIXUP_FLASH_OFFSET reg +.endm #endif /* CONFIG_XIP_KERNEL */ __HEAD @@ -267,6 +277,7 @@ pmp_done: la a3, hart_lottery mv a2, a3 XIP_FIXUP_OFFSET a2 + XIP_FIXUP_FLASH_OFFSET a3 lw t1, (a3) amoswap.w t0, t1, (a2) /* first time here if hart_lottery in RAM is not set */ @@ -305,6 +316,7 @@ clear_bss_done: XIP_FIXUP_OFFSET sp #ifdef CONFIG_BUILTIN_DTB la a0, __dtb_start + XIP_FIXUP_OFFSET a0 #else mv a0, s1 #endif /* CONFIG_BUILTIN_DTB */ diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index ee5878d968cc..9c842c41684a 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -12,7 +12,7 @@ static void default_power_off(void) wait_for_interrupt(); } -void (*pm_power_off)(void) = default_power_off; +void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); void machine_restart(char *cmd) @@ -23,10 +23,16 @@ void machine_restart(char *cmd) void machine_halt(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } void machine_power_off(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index b70956d80408..a9436a65161a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <asm/page.h> #include <asm/vdso.h> +#include <linux/time_namespace.h> #ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> @@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[]; enum vvar_pages { VVAR_DATA_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, VVAR_NR_PAGES, }; #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) -static unsigned int vdso_pages __ro_after_init; -static struct page **vdso_pagelist __ro_after_init; - /* * The vDSO data page. */ @@ -42,83 +41,228 @@ static union { } vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; -static int __init vdso_init(void) +struct __vdso_info { + const char *name; + const char *vdso_code_start; + const char *vdso_code_end; + unsigned long vdso_pages; + /* Data Mapping */ + struct vm_special_mapping *dm; + /* Code Mapping */ + struct vm_special_mapping *cm; +}; + +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, +}; + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static int __init __vdso_init(void) { unsigned int i; + struct page **vdso_pagelist; + unsigned long pfn; - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; - vdso_pagelist = - kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); - if (unlikely(vdso_pagelist == NULL)) { - pr_err("vdso: pagelist allocation failed\n"); - return -ENOMEM; + if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { + pr_err("vDSO is not a valid ELF object!\n"); + return -EINVAL; } - for (i = 0; i < vdso_pages; i++) { - struct page *pg; + vdso_info.vdso_pages = ( + vdso_info.vdso_code_end - + vdso_info.vdso_code_start) >> + PAGE_SHIFT; + + vdso_pagelist = kcalloc(vdso_info.vdso_pages, + sizeof(struct page *), + GFP_KERNEL); + if (vdso_pagelist == NULL) + return -ENOMEM; + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_info.vdso_code_start); + + for (i = 0; i < vdso_info.vdso_pages; i++) + vdso_pagelist[i] = pfn_to_page(pfn + i); + + vdso_info.cm->pages = vdso_pagelist; + + return 0; +} + +#ifdef CONFIG_TIME_NS +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page); +} + +/* + * The vvar mapping contains data for a specific time namespace, so when a task + * changes namespace we must unmap its vvar data for the old namespace. + * Subsequent faults will map in data for the new namespace. + * + * For more details see timens_setup_vdso_data(). + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + mmap_read_lock(mm); - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); - vdso_pagelist[i] = pg; + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; + + if (vma_is_special_mapping(vma, vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); } - vdso_pagelist[i] = virt_to_page(vdso_data); + mmap_read_unlock(mm); return 0; } + +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops. + * For more details check_vma_flags() and __access_remote_vm() + */ + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} +#else +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *timens_page = find_timens_vvar_page(vma); + unsigned long pfn; + + switch (vmf->pgoff) { + case VVAR_DATA_PAGE_OFFSET: + if (timens_page) + pfn = page_to_pfn(timens_page); + else + pfn = sym_to_pfn(vdso_data); + break; +#ifdef CONFIG_TIME_NS + case VVAR_TIMENS_PAGE_OFFSET: + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (!timens_page) + return VM_FAULT_SIGBUS; + pfn = sym_to_pfn(vdso_data); + break; +#endif /* CONFIG_TIME_NS */ + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; + +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { + [RV_VDSO_MAP_VVAR] = { + .name = "[vvar]", + .fault = vvar_fault, + }, + [RV_VDSO_MAP_VDSO] = { + .name = "[vdso]", + .mremap = vdso_mremap, + }, +}; + +static int __init vdso_init(void) +{ + vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; + vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; + + return __vdso_init(); +} arch_initcall(vdso_init); -int arch_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp) +static int __setup_additional_pages(struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp) { - struct mm_struct *mm = current->mm; - unsigned long vdso_base, vdso_len; - int ret; + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; + vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + VVAR_SIZE; - if (mmap_write_lock_killable(mm)) - return -EINTR; - - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { - ret = vdso_base; - goto end; + ret = ERR_PTR(vdso_base); + goto up_fail; } - mm->context.vdso = NULL; - ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); - if (unlikely(ret)) - goto end; + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); + if (IS_ERR(ret)) + goto up_fail; + vdso_base += VVAR_SIZE; + mm->context.vdso = (void *)vdso_base; ret = - install_special_mapping(mm, vdso_base + VVAR_SIZE, - vdso_pages << PAGE_SHIFT, + _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_pagelist); + vdso_info.cm); - if (unlikely(ret)) - goto end; + if (IS_ERR(ret)) + goto up_fail; - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - mm->context.vdso = (void *)vdso_base + VVAR_SIZE; + return 0; -end: - mmap_write_unlock(mm); - return ret; +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); } -const char *arch_vma_name(struct vm_area_struct *vma) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) - return "[vdso]"; - if (vma->vm_mm && (vma->vm_start == - (long)vma->vm_mm->context.vdso - VVAR_SIZE)) - return "[vdso_data]"; - return NULL; + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp); + mmap_write_unlock(mm); + + return ret; } diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e9111f700af0..01d94aae5bf5 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv) SECTIONS { PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 9c9f35091ef0..f5ed08262139 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -64,8 +64,11 @@ SECTIONS /* * From this point, stuff is considered writable and will be copied to RAM */ - __data_loc = ALIGN(16); /* location in file */ - . = LOAD_OFFSET + XIP_OFFSET; /* location in memory */ + __data_loc = ALIGN(PAGE_SIZE); /* location in file */ + . = KERNEL_LINK_ADDR + XIP_OFFSET; /* location in memory */ + +#undef LOAD_OFFSET +#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK)) _sdata = .; /* Start of data section */ _data = .; @@ -96,7 +99,6 @@ SECTIONS KEEP(*(__soc_builtin_dtb_table)) __soc_builtin_dtb_table_end = .; } - PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(8); .alternative : { @@ -122,6 +124,8 @@ SECTIONS BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + PERCPU_SECTION(L1_CACHE_BYTES) + .rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) { *(.rel.dyn*) } diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index ee3459cb6750..ea54cc0c9106 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -233,8 +233,10 @@ static int __init asids_init(void) local_flush_tlb_all(); /* Pre-compute ASID details */ - num_asids = 1 << asid_bits; - asid_mask = num_asids - 1; + if (asid_bits) { + num_asids = 1 << asid_bits; + asid_mask = num_asids - 1; + } /* * Use ASID allocator only if number of HW ASIDs are @@ -255,7 +257,7 @@ static int __init asids_init(void) pr_info("ASID allocator using %lu bits (%lu entries)\n", asid_bits, num_asids); } else { - pr_info("ASID allocator disabled\n"); + pr_info("ASID allocator disabled (%lu bits)\n", asid_bits); } return 0; diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c index 18bf338303b6..ddb7d3b99e89 100644 --- a/arch/riscv/mm/extable.c +++ b/arch/riscv/mm/extable.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/uaccess.h> -#ifdef CONFIG_BPF_JIT +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I) int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs); #endif @@ -23,7 +23,7 @@ int fixup_exception(struct pt_regs *regs) if (!fixup) return 0; -#ifdef CONFIG_BPF_JIT +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I) if (regs->epc >= BPF_JIT_REGION_START && regs->epc < BPF_JIT_REGION_END) return rv_bpf_fixup_exception(fixup, regs); #endif diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index c0cddf0fc22d..24b2b8044602 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -41,7 +41,7 @@ phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); #ifdef CONFIG_XIP_KERNEL -extern char _xiprom[], _exiprom[]; +extern char _xiprom[], _exiprom[], __data_loc; #endif unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] @@ -454,10 +454,9 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) /* called from head.S with MMU off */ asmlinkage void __init __copy_data(void) { - void *from = (void *)(&_sdata); - void *end = (void *)(&_end); + void *from = (void *)(&__data_loc); void *to = (void *)CONFIG_PHYS_RAM_BASE; - size_t sz = (size_t)(end - from + 1); + size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata)); memcpy(to, from, sz); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 2ca345c7b0bf..f2a779c7e225 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -460,6 +460,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) #define BPF_FIXUP_REG_MASK GENMASK(31, 27) int rv_bpf_fixup_exception(const struct exception_table_entry *ex, + struct pt_regs *regs); +int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs) { off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup); diff --git a/arch/s390/include/asm/kdebug.h b/arch/s390/include/asm/kdebug.h index d5327f064799..4377238e4752 100644 --- a/arch/s390/include/asm/kdebug.h +++ b/arch/s390/include/asm/kdebug.h @@ -23,6 +23,6 @@ enum die_val { DIE_NMI_IPI, }; -extern void die(struct pt_regs *, const char *); +extern void __noreturn die(struct pt_regs *, const char *); #endif diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 6b3c366af78e..90824be5ce9a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -210,9 +210,11 @@ int zpci_deconfigure_device(struct zpci_dev *zdev); void zpci_device_reserved(struct zpci_dev *zdev); bool zpci_is_device_configured(struct zpci_dev *zdev); +int zpci_hot_reset_device(struct zpci_dev *zdev); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); void zpci_remove_reserved_devices(void); +void zpci_update_fh(struct zpci_dev *zdev, u32 fh); /* CLP */ int clp_setup_writeback_mio(void); @@ -294,8 +296,10 @@ void zpci_debug_exit(void); void zpci_debug_init_device(struct zpci_dev *, const char *); void zpci_debug_exit_device(struct zpci_dev *); -/* Error reporting */ +/* Error handling */ int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *); +int zpci_clear_error_state(struct zpci_dev *zdev); +int zpci_reset_load_store_blocked(struct zpci_dev *zdev); #ifdef CONFIG_NUMA diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index b3dd883699e7..27e3d804b311 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -78,18 +78,6 @@ static inline void syscall_get_arguments(struct task_struct *task, args[0] = regs->orig_gpr2 & mask; } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - unsigned int n = 6; - - while (n-- > 0) - if (n > 0) - regs->gprs[2 + n] = args[n]; - regs->orig_gpr2 = args[0]; -} - static inline int syscall_get_arch(struct task_struct *task) { #ifdef CONFIG_COMPAT diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 85f326e258df..0681c55e831d 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -192,7 +192,7 @@ void show_regs(struct pt_regs *regs) static DEFINE_SPINLOCK(die_lock); -void die(struct pt_regs *regs, const char *str) +void __noreturn die(struct pt_regs *regs, const char *str) { static int die_counter; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 6f431fa9e4d7..ee8707abdb6a 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -687,8 +687,10 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags) false); if (cfdiag_diffctr(cpuhw, event->hw.config_base)) cfdiag_push_sample(event, cpuhw); - } else + } else if (cpuhw->flags & PMU_F_RESERVED) { + /* Only update when PMU not hotplugged off */ hw_perf_event_update(event); + } hwc->state |= PERF_HES_UPTODATE; } } diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 6c6f7dcce1a5..035705c9f23e 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -84,7 +84,7 @@ static void default_trap_handler(struct pt_regs *regs) { if (user_mode(regs)) { report_user_fault(regs, SIGSEGV, 0); - do_exit(SIGSEGV); + force_fatal_sig(SIGSEGV); } else die(regs, "Unknown program exception"); } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 212632d57db9..d30f5986fa85 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -260,7 +260,6 @@ static noinline void do_no_context(struct pt_regs *regs) " in virtual user address space\n"); dump_fault_info(regs); die(regs, "Oops"); - do_exit(SIGKILL); } static noinline void do_low_address(struct pt_regs *regs) @@ -270,7 +269,6 @@ static noinline void do_low_address(struct pt_regs *regs) if (regs->psw.mask & PSW_MASK_PSTATE) { /* Low-address protection hit in user mode 'cannot happen'. */ die (regs, "Low-address protection"); - do_exit(SIGKILL); } do_no_context(regs); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 872d772b73d2..2f9b78fa82a5 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -481,6 +481,34 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } +static void zpci_do_update_iomap_fh(struct zpci_dev *zdev, u32 fh) +{ + int bar, idx; + + spin_lock(&zpci_iomap_lock); + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + if (!zdev->bars[bar].size) + continue; + idx = zdev->bars[bar].map_idx; + if (!zpci_iomap_start[idx].count) + continue; + WRITE_ONCE(zpci_iomap_start[idx].fh, zdev->fh); + } + spin_unlock(&zpci_iomap_lock); +} + +void zpci_update_fh(struct zpci_dev *zdev, u32 fh) +{ + if (!fh || zdev->fh == fh) + return; + + zdev->fh = fh; + if (zpci_use_mio(zdev)) + return; + if (zdev->has_resources && zdev_enabled(zdev)) + zpci_do_update_iomap_fh(zdev, fh); +} + static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, unsigned long size, unsigned long flags) { @@ -668,7 +696,7 @@ int zpci_enable_device(struct zpci_dev *zdev) if (clp_enable_fh(zdev, &fh, ZPCI_NR_DMA_SPACES)) rc = -EIO; else - zdev->fh = fh; + zpci_update_fh(zdev, fh); return rc; } @@ -679,14 +707,14 @@ int zpci_disable_device(struct zpci_dev *zdev) cc = clp_disable_fh(zdev, &fh); if (!cc) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); } else if (cc == CLP_RC_SETPCIFN_ALRDY) { pr_info("Disabling PCI function %08x had no effect as it was already disabled\n", zdev->fid); /* Function is already disabled - update handle */ rc = clp_refresh_fh(zdev->fid, &fh); if (!rc) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); rc = -EINVAL; } } else { @@ -696,6 +724,65 @@ int zpci_disable_device(struct zpci_dev *zdev) } /** + * zpci_hot_reset_device - perform a reset of the given zPCI function + * @zdev: the slot which should be reset + * + * Performs a low level reset of the zPCI function. The reset is low level in + * the sense that the zPCI function can be reset without detaching it from the + * common PCI subsystem. The reset may be performed while under control of + * either DMA or IOMMU APIs in which case the existing DMA/IOMMU translation + * table is reinstated at the end of the reset. + * + * After the reset the functions internal state is reset to an initial state + * equivalent to its state during boot when first probing a driver. + * Consequently after reset the PCI function requires re-initialization via the + * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors() + * and enabling the function via e.g.pci_enablde_device_flags().The caller + * must guard against concurrent reset attempts. + * + * In most cases this function should not be called directly but through + * pci_reset_function() or pci_reset_bus() which handle the save/restore and + * locking. + * + * Return: 0 on success and an error value otherwise + */ +int zpci_hot_reset_device(struct zpci_dev *zdev) +{ + int rc; + + zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh); + if (zdev_enabled(zdev)) { + /* Disables device access, DMAs and IRQs (reset state) */ + rc = zpci_disable_device(zdev); + /* + * Due to a z/VM vs LPAR inconsistency in the error state the + * FH may indicate an enabled device but disable says the + * device is already disabled don't treat it as an error here. + */ + if (rc == -EINVAL) + rc = 0; + if (rc) + return rc; + } + + rc = zpci_enable_device(zdev); + if (rc) + return rc; + + if (zdev->dma_table) + rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + (u64)zdev->dma_table); + else + rc = zpci_dma_init_device(zdev); + if (rc) { + zpci_disable_device(zdev); + return rc; + } + + return 0; +} + +/** * zpci_create_device() - Create a new zpci_dev and add it to the zbus * @fid: Function ID of the device to be created * @fh: Current Function Handle of the device to be created @@ -776,7 +863,7 @@ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh) { int rc; - zdev->fh = fh; + zpci_update_fh(zdev, fh); /* the PCI function will be scanned once function 0 appears */ if (!zdev->zbus->bus) return 0; @@ -903,6 +990,59 @@ int zpci_report_error(struct pci_dev *pdev, } EXPORT_SYMBOL(zpci_report_error); +/** + * zpci_clear_error_state() - Clears the zPCI error state of the device + * @zdev: The zdev for which the zPCI error state should be reset + * + * Clear the zPCI error state of the device. If clearing the zPCI error state + * fails the device is left in the error state. In this case it may make sense + * to call zpci_io_perm_failure() on the associated pdev if it exists. + * + * Returns: 0 on success, -EIO otherwise + */ +int zpci_clear_error_state(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_ERROR); + struct zpci_fib fib = {0}; + u8 status; + int cc; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + zpci_dbg(3, "ces fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status); + return -EIO; + } + + return 0; +} + +/** + * zpci_reset_load_store_blocked() - Re-enables L/S from error state + * @zdev: The zdev for which to unblock load/store access + * + * Re-enables load/store access for a PCI function in the error state while + * keeping DMA blocked. In this state drivers can poke MMIO space to determine + * if error recovery is possible while catching any rogue DMA access from the + * device. + * + * Returns: 0 on success, -EIO otherwise + */ +int zpci_reset_load_store_blocked(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_BLOCK); + struct zpci_fib fib = {0}; + u8 status; + int cc; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + zpci_dbg(3, "rls fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status); + return -EIO; + } + + return 0; +} + static int zpci_mem_init(void) { BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 6a5bfa9dc1f2..2e3e5b278925 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -47,18 +47,223 @@ struct zpci_ccdf_avail { u16 pec; /* PCI event code */ } __packed; +static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res) +{ + switch (ers_res) { + case PCI_ERS_RESULT_CAN_RECOVER: + case PCI_ERS_RESULT_RECOVERED: + case PCI_ERS_RESULT_NEED_RESET: + return false; + default: + return true; + } +} + +static bool is_passed_through(struct zpci_dev *zdev) +{ + return zdev->s390_domain; +} + +static bool is_driver_supported(struct pci_driver *driver) +{ + if (!driver || !driver->err_handler) + return false; + if (!driver->err_handler->error_detected) + return false; + if (!driver->err_handler->slot_reset) + return false; + if (!driver->err_handler->resume) + return false; + return true; +} + +static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + + ers_res = driver->err_handler->error_detected(pdev, pdev->error_state); + if (ers_result_indicates_abort(ers_res)) + pr_info("%s: Automatic recovery failed after initial reporting\n", pci_name(pdev)); + else if (ers_res == PCI_ERS_RESULT_NEED_RESET) + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + + return ers_res; +} + +static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct zpci_dev *zdev = to_zpci(pdev); + int rc; + + pr_info("%s: Unblocking device access for examination\n", pci_name(pdev)); + rc = zpci_reset_load_store_blocked(zdev); + if (rc) { + pr_err("%s: Unblocking device access failed\n", pci_name(pdev)); + /* Let's try a full reset instead */ + return PCI_ERS_RESULT_NEED_RESET; + } + + if (driver->err_handler->mmio_enabled) { + ers_res = driver->err_handler->mmio_enabled(pdev); + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after MMIO re-enable\n", + pci_name(pdev)); + return ers_res; + } else if (ers_res == PCI_ERS_RESULT_NEED_RESET) { + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + return ers_res; + } + } + + pr_debug("%s: Unblocking DMA\n", pci_name(pdev)); + rc = zpci_clear_error_state(zdev); + if (!rc) { + pdev->error_state = pci_channel_io_normal; + } else { + pr_err("%s: Unblocking DMA failed\n", pci_name(pdev)); + /* Let's try a full reset instead */ + return PCI_ERS_RESULT_NEED_RESET; + } + + return ers_res; +} + +static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + + pr_info("%s: Initiating reset\n", pci_name(pdev)); + if (zpci_hot_reset_device(to_zpci(pdev))) { + pr_err("%s: The reset request failed\n", pci_name(pdev)); + return ers_res; + } + pdev->error_state = pci_channel_io_normal; + ers_res = driver->err_handler->slot_reset(pdev); + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev)); + return ers_res; + } + + return ers_res; +} + +/* zpci_event_attempt_error_recovery - Try to recover the given PCI function + * @pdev: PCI function to recover currently in the error state + * + * We follow the scheme outlined in Documentation/PCI/pci-error-recovery.rst. + * With the simplification that recovery always happens per function + * and the platform determines which functions are affected for + * multi-function devices. + */ +static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct pci_driver *driver; + + /* + * Ensure that the PCI function is not removed concurrently, no driver + * is unbound or probed and that userspace can't access its + * configuration space while we perform recovery. + */ + pci_dev_lock(pdev); + if (pdev->error_state == pci_channel_io_perm_failure) { + ers_res = PCI_ERS_RESULT_DISCONNECT; + goto out_unlock; + } + pdev->error_state = pci_channel_io_frozen; + + if (is_passed_through(to_zpci(pdev))) { + pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", + pci_name(pdev)); + goto out_unlock; + } + + driver = to_pci_driver(pdev->dev.driver); + if (!is_driver_supported(driver)) { + if (!driver) + pr_info("%s: Cannot be recovered because no driver is bound to the device\n", + pci_name(pdev)); + else + pr_info("%s: The %s driver bound to the device does not support error recovery\n", + pci_name(pdev), + driver->name); + goto out_unlock; + } + + ers_res = zpci_event_notify_error_detected(pdev, driver); + if (ers_result_indicates_abort(ers_res)) + goto out_unlock; + + if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { + ers_res = zpci_event_do_error_state_clear(pdev, driver); + if (ers_result_indicates_abort(ers_res)) + goto out_unlock; + } + + if (ers_res == PCI_ERS_RESULT_NEED_RESET) + ers_res = zpci_event_do_reset(pdev, driver); + + if (ers_res != PCI_ERS_RESULT_RECOVERED) { + pr_err("%s: Automatic recovery failed; operator intervention is required\n", + pci_name(pdev)); + goto out_unlock; + } + + pr_info("%s: The device is ready to resume operations\n", pci_name(pdev)); + if (driver->err_handler->resume) + driver->err_handler->resume(pdev); +out_unlock: + pci_dev_unlock(pdev); + + return ers_res; +} + +/* zpci_event_io_failure - Report PCI channel failure state to driver + * @pdev: PCI function for which to report + * @es: PCI channel failure state to report + */ +static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es) +{ + struct pci_driver *driver; + + pci_dev_lock(pdev); + pdev->error_state = es; + /** + * While vfio-pci's error_detected callback notifies user-space QEMU + * reacts to this by freezing the guest. In an s390 environment PCI + * errors are rarely fatal so this is overkill. Instead in the future + * we will inject the error event and let the guest recover the device + * itself. + */ + if (is_passed_through(to_zpci(pdev))) + goto out; + driver = to_pci_driver(pdev->dev.driver); + if (driver && driver->err_handler && driver->err_handler->error_detected) + driver->err_handler->error_detected(pdev, pdev->error_state); +out: + pci_dev_unlock(pdev); +} + static void __zpci_event_error(struct zpci_ccdf_err *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; + pci_ers_result_t ers_res; zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("error CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); - if (zdev) - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (zdev) { + zpci_update_fh(zdev, ccdf->fh); + if (zdev->zbus->bus) + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + } pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); @@ -66,7 +271,20 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) if (!pdev) return; - pdev->error_state = pci_channel_io_perm_failure; + switch (ccdf->pec) { + case 0x003a: /* Service Action or Error Recovery Successful */ + ers_res = zpci_event_attempt_error_recovery(pdev); + if (ers_res != PCI_ERS_RESULT_RECOVERED) + zpci_event_io_failure(pdev, pci_channel_io_perm_failure); + break; + default: + /* + * Mark as frozen not permanently failed because the device + * could be subsequently recovered by the platform. + */ + zpci_event_io_failure(pdev, pci_channel_io_frozen); + break; + } pci_dev_put(pdev); } @@ -78,7 +296,7 @@ void zpci_event_error(void *data) static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); /* Give the driver a hint that the function is * already unusable. */ @@ -121,7 +339,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY); else - zdev->fh = ccdf->fh; + zpci_update_fh(zdev, ccdf->fh); break; case 0x0303: /* Deconfiguration requested */ if (zdev) { @@ -130,7 +348,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) */ if (zdev->state != ZPCI_FN_STATE_CONFIGURED) break; - zdev->fh = ccdf->fh; + zpci_update_fh(zdev, ccdf->fh); zpci_deconfigure_device(zdev); } break; diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 2e43996159f0..28d863aaafea 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -163,7 +163,7 @@ static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr, unsigned long len) { struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; - u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len); + u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len); return __zpci_load(data, req, ZPCI_OFFSET(addr)); } @@ -244,7 +244,7 @@ static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data, unsigned long len) { struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; - u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len); + u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len); return __zpci_store(data, req, ZPCI_OFFSET(addr)); } diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 3823e159bf74..954bb7a83124 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -387,6 +387,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs); } +void arch_restore_msi_irqs(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + if (!zdev->irqs_registered) + zpci_set_irq(zdev); + default_restore_msi_irqs(pdev); +} + static struct airq_struct zpci_airq = { .handler = zpci_floating_irq_handler, .isc = PCI_ISC, diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h index cb51a7528384..d87738eebe30 100644 --- a/arch/sh/include/asm/syscall_32.h +++ b/arch/sh/include/asm/syscall_32.h @@ -57,18 +57,6 @@ static inline void syscall_get_arguments(struct task_struct *task, args[0] = regs->regs[4]; } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - regs->regs[1] = args[5]; - regs->regs[0] = args[4]; - regs->regs[7] = args[3]; - regs->regs[6] = args[2]; - regs->regs[5] = args[1]; - regs->regs[4] = args[0]; -} - static inline int syscall_get_arch(struct task_struct *task) { int arch = AUDIT_ARCH_SH; diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c index ae354a2931e7..fd6db0ab1928 100644 --- a/arch/sh/kernel/cpu/fpu.c +++ b/arch/sh/kernel/cpu/fpu.c @@ -62,18 +62,20 @@ void fpu_state_restore(struct pt_regs *regs) } if (!tsk_used_math(tsk)) { - local_irq_enable(); + int ret; /* * does a slab alloc which can sleep */ - if (init_fpu(tsk)) { + local_irq_enable(); + ret = init_fpu(tsk); + local_irq_disable(); + if (ret) { /* * ran out of memory! */ - do_group_exit(SIGKILL); + force_sig(SIGKILL); return; } - local_irq_disable(); } grab_fpu(regs); diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index e76b22157099..cbe3201d4f21 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -20,7 +20,7 @@ static DEFINE_SPINLOCK(die_lock); -void die(const char *str, struct pt_regs *regs, long err) +void __noreturn die(const char *str, struct pt_regs *regs, long err) { static int die_counter; diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 88a1f453d73e..1e1aa75df3ca 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -238,8 +238,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, show_fault_oops(regs, address); die("Oops", regs, error_code); - bust_spinlocks(0); - do_exit(SIGKILL); } static void diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h index 62a5a78804c4..20c109ac8cc9 100644 --- a/arch/sparc/include/asm/syscall.h +++ b/arch/sparc/include/asm/syscall.h @@ -117,16 +117,6 @@ static inline void syscall_get_arguments(struct task_struct *task, } } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - unsigned int i; - - for (i = 0; i < 6; i++) - regs->u_regs[UREG_I0 + i] = args[i]; -} - static inline int syscall_get_arch(struct task_struct *task) { #if defined(CONFIG_SPARC64) && defined(CONFIG_COMPAT) diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 02f3ad55dfe3..cd677bc564a7 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -244,7 +244,7 @@ static int setup_frame(struct ksignal *ksig, struct pt_regs *regs, get_sigframe(ksig, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) { - do_exit(SIGILL); + force_fatal_sig(SIGILL); return -EINVAL; } @@ -336,7 +336,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs, sf = (struct rt_signal_frame __user *) get_sigframe(ksig, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) { - do_exit(SIGILL); + force_fatal_sig(SIGILL); return -EINVAL; } diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c index 69a6ba6e9293..bbbd40cc6b28 100644 --- a/arch/sparc/kernel/windows.c +++ b/arch/sparc/kernel/windows.c @@ -121,8 +121,10 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who) if ((sp & 7) || copy_to_user((char __user *) sp, &tp->reg_window[window], - sizeof(struct reg_window32))) - do_exit(SIGILL); + sizeof(struct reg_window32))) { + force_fatal_sig(SIGILL); + return; + } } tp->w_saved = 0; } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index fa858626b85b..90dc4ae315c8 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -248,7 +248,6 @@ no_context: } unhandled_fault(address, tsk, regs); - do_exit(SIGKILL); /* * We ran out of memory, or some other thing happened to us that made diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 0dce4b7ff73e..912205787161 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -266,7 +266,7 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign default: printk(KERN_ERR "TSB[%s:%d]: Impossible TSB size %lu, killing process.\n", current->comm, current->pid, tsb_bytes); - do_exit(SIGSEGV); + BUG(); } tte |= pte_sz_bits(page_sz); diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h index 2984feb9d576..172b74143c4b 100644 --- a/arch/um/include/asm/syscall-generic.h +++ b/arch/um/include/asm/syscall-generic.h @@ -62,20 +62,6 @@ static inline void syscall_get_arguments(struct task_struct *task, *args = UPT_SYSCALL_ARG6(r); } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - struct uml_pt_regs *r = ®s->regs; - - UPT_SYSCALL_ARG1(r) = *args++; - UPT_SYSCALL_ARG2(r) = *args++; - UPT_SYSCALL_ARG3(r) = *args++; - UPT_SYSCALL_ARG4(r) = *args++; - UPT_SYSCALL_ARG5(r) = *args++; - UPT_SYSCALL_ARG6(r) = *args; -} - /* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */ #endif /* __UM_SYSCALL_GENERIC_H */ diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 3198c4767387..c32efb09db21 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -158,7 +158,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip) void fatal_sigsegv(void) { - force_sigsegv(SIGSEGV); + force_fatal_sig(SIGSEGV); do_signal(¤t->thread.regs); /* * This is to tell gcc that we're not returning - do_signal diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 1b40b9297083..0b6b277ee050 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -226,7 +226,8 @@ bool emulate_vsyscall(unsigned long error_code, if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); - do_exit(SIGSYS); + force_fatal_sig(SIGSYS); + return true; } regs->orig_ax = -1; if (tmp) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2acf37cc1991..e5d8700319cc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -38,7 +38,6 @@ #define __KVM_HAVE_ARCH_VCPU_DEBUGFS #define KVM_MAX_VCPUS 1024 -#define KVM_SOFT_MAX_VCPUS 710 /* * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs @@ -725,6 +724,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + u32 kvm_cpuid_base; u64 reserved_gpa_bits; int maxphyaddr; @@ -748,7 +748,7 @@ struct kvm_vcpu_arch { u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_pfn_cache cache; + struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; @@ -1034,6 +1034,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_IRQWIN 3 #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 +#define APICV_INHIBIT_REASON_BLOCKIRQ 6 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1476,6 +1477,7 @@ struct kvm_x86_ops { int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 69299878b200..56935ebb1dfe 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -83,6 +83,18 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } +static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + long ret; + + asm volatile("vmmcall" + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3) + : "memory"); + return ret; +} + #ifdef CONFIG_KVM_GUEST void kvmclock_init(void); void kvmclock_disable(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 2d4f5c17d79c..e2c6f433ed10 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -44,6 +44,8 @@ void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, + bool enc); void __init mem_encrypt_free_decrypted_mem(void); @@ -78,6 +80,8 @@ static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +static inline void __init +early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cebec95a7124..21c4a694ca11 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -97,6 +97,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) PVOP_VCALL1(mmu.exit_mmap, mm); } +static inline void notify_page_enc_status_changed(unsigned long pfn, + int npages, bool enc) +{ + PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc); +} + #ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index d9d6b0203ec4..a69012e1903f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -168,6 +168,7 @@ struct pv_mmu_ops { /* Hook for intercepting the destruction of an mm_struct. */ void (*exit_mmap)(struct mm_struct *mm); + void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc); #ifdef CONFIG_PARAVIRT_XXL struct paravirt_callee_save read_cr2; @@ -577,7 +578,9 @@ void paravirt_leave_lazy_mmu(void); void paravirt_flush_lazy_mmu(void); void _paravirt_nop(void); +void paravirt_BUG(void); u64 _paravirt_ident_64(u64); +unsigned long paravirt_ret0(void); #define paravirt_nop ((void *)_paravirt_nop) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 191878a65c61..355d38c0cf60 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -806,11 +806,14 @@ static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } #endif +#define for_each_possible_hypervisor_cpuid_base(function) \ + for (function = 0x40000000; function < 0x40010000; function += 0x100) + static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { uint32_t base, eax, signature[3]; - for (base = 0x40000000; base < 0x40010000; base += 0x100) { + for_each_possible_hypervisor_cpuid_base(base) { cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); if (!memcmp(sig, signature, 12) && diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 43fa081a1adb..872617542bbc 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -83,6 +83,7 @@ int set_pages_rw(struct page *page, int numpages); int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); bool kernel_page_present(struct page *page); +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc); extern int kernel_set_to_readonly; diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f7e2d82d24fb..5b85987a5e97 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -87,15 +87,6 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, ®s->bx, 6 * sizeof(args[0])); } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - unsigned int i, unsigned int n, - const unsigned long *args) -{ - BUG_ON(i + n > 6); - memcpy(®s->bx + i, args, n * sizeof(args[0])); -} - static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_I386; @@ -127,30 +118,6 @@ static inline void syscall_get_arguments(struct task_struct *task, } } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ -# ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) { - regs->bx = *args++; - regs->cx = *args++; - regs->dx = *args++; - regs->si = *args++; - regs->di = *args++; - regs->bp = *args; - } else -# endif - { - regs->di = *args++; - regs->si = *args++; - regs->dx = *args++; - regs->r10 = *args++; - regs->r8 = *args++; - regs->r9 = *args; - } -} - static inline int syscall_get_arch(struct task_struct *task) { /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 4a7ff8b0db20..0575f5863b7f 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -248,6 +248,7 @@ privcmd_call(unsigned int call, return res; } +#ifdef CONFIG_XEN_PV static inline int HYPERVISOR_set_trap_table(struct trap_info *table) { @@ -281,6 +282,107 @@ HYPERVISOR_callback_op(int cmd, void *arg) } static inline int +HYPERVISOR_set_debugreg(int reg, unsigned long value) +{ + return _hypercall2(int, set_debugreg, reg, value); +} + +static inline unsigned long +HYPERVISOR_get_debugreg(int reg) +{ + return _hypercall1(unsigned long, get_debugreg, reg); +} + +static inline int +HYPERVISOR_update_descriptor(u64 ma, u64 desc) +{ + return _hypercall2(int, update_descriptor, ma, desc); +} + +static inline int +HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, + unsigned long flags) +{ + return _hypercall3(int, update_va_mapping, va, new_val.pte, flags); +} + +static inline int +HYPERVISOR_set_segment_base(int reg, unsigned long value) +{ + return _hypercall2(int, set_segment_base, reg, value); +} + +static inline void +MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) +{ + mcl->op = __HYPERVISOR_fpu_taskswitch; + mcl->args[0] = set; + + trace_xen_mc_entry(mcl, 1); +} + +static inline void +MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, + pte_t new_val, unsigned long flags) +{ + mcl->op = __HYPERVISOR_update_va_mapping; + mcl->args[0] = va; + mcl->args[1] = new_val.pte; + mcl->args[2] = flags; + + trace_xen_mc_entry(mcl, 3); +} + +static inline void +MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, + struct desc_struct desc) +{ + mcl->op = __HYPERVISOR_update_descriptor; + mcl->args[0] = maddr; + mcl->args[1] = *(unsigned long *)&desc; + + trace_xen_mc_entry(mcl, 2); +} + +static inline void +MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, + int count, int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmu_update; + mcl->args[0] = (unsigned long)req; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; + + trace_xen_mc_entry(mcl, 4); +} + +static inline void +MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmuext_op; + mcl->args[0] = (unsigned long)op; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; + + trace_xen_mc_entry(mcl, 4); +} + +static inline void +MULTI_stack_switch(struct multicall_entry *mcl, + unsigned long ss, unsigned long esp) +{ + mcl->op = __HYPERVISOR_stack_switch; + mcl->args[0] = ss; + mcl->args[1] = esp; + + trace_xen_mc_entry(mcl, 2); +} +#endif + +static inline int HYPERVISOR_sched_op(int cmd, void *arg) { return _hypercall2(int, sched_op, cmd, arg); @@ -308,26 +410,6 @@ HYPERVISOR_platform_op(struct xen_platform_op *op) return _hypercall1(int, platform_op, op); } -static __always_inline int -HYPERVISOR_set_debugreg(int reg, unsigned long value) -{ - return _hypercall2(int, set_debugreg, reg, value); -} - -static __always_inline unsigned long -HYPERVISOR_get_debugreg(int reg) -{ - return _hypercall1(unsigned long, get_debugreg, reg); -} - -static inline int -HYPERVISOR_update_descriptor(u64 ma, u64 desc) -{ - if (sizeof(u64) == sizeof(long)) - return _hypercall2(int, update_descriptor, ma, desc); - return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); -} - static inline long HYPERVISOR_memory_op(unsigned int cmd, void *arg) { @@ -341,18 +423,6 @@ HYPERVISOR_multicall(void *call_list, uint32_t nr_calls) } static inline int -HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, - unsigned long flags) -{ - if (sizeof(new_val) == sizeof(long)) - return _hypercall3(int, update_va_mapping, va, - new_val.pte, flags); - else - return _hypercall4(int, update_va_mapping, va, - new_val.pte, new_val.pte >> 32, flags); -} - -static inline int HYPERVISOR_event_channel_op(int cmd, void *arg) { return _hypercall2(int, event_channel_op, cmd, arg); @@ -394,14 +464,6 @@ HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args) return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); } -#ifdef CONFIG_X86_64 -static inline int -HYPERVISOR_set_segment_base(int reg, unsigned long value) -{ - return _hypercall2(int, set_segment_base, reg, value); -} -#endif - static inline int HYPERVISOR_suspend(unsigned long start_info_mfn) { @@ -423,13 +485,6 @@ HYPERVISOR_hvm_op(int op, void *arg) } static inline int -HYPERVISOR_tmem_op( - struct tmem_op *op) -{ - return _hypercall1(int, tmem_op, op); -} - -static inline int HYPERVISOR_xenpmu_op(unsigned int op, void *arg) { return _hypercall2(int, xenpmu_op, op, arg); @@ -446,88 +501,4 @@ HYPERVISOR_dm_op( return ret; } -static inline void -MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) -{ - mcl->op = __HYPERVISOR_fpu_taskswitch; - mcl->args[0] = set; - - trace_xen_mc_entry(mcl, 1); -} - -static inline void -MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, - pte_t new_val, unsigned long flags) -{ - mcl->op = __HYPERVISOR_update_va_mapping; - mcl->args[0] = va; - if (sizeof(new_val) == sizeof(long)) { - mcl->args[1] = new_val.pte; - mcl->args[2] = flags; - } else { - mcl->args[1] = new_val.pte; - mcl->args[2] = new_val.pte >> 32; - mcl->args[3] = flags; - } - - trace_xen_mc_entry(mcl, sizeof(new_val) == sizeof(long) ? 3 : 4); -} - -static inline void -MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, - struct desc_struct desc) -{ - mcl->op = __HYPERVISOR_update_descriptor; - if (sizeof(maddr) == sizeof(long)) { - mcl->args[0] = maddr; - mcl->args[1] = *(unsigned long *)&desc; - } else { - u32 *p = (u32 *)&desc; - - mcl->args[0] = maddr; - mcl->args[1] = maddr >> 32; - mcl->args[2] = *p++; - mcl->args[3] = *p; - } - - trace_xen_mc_entry(mcl, sizeof(maddr) == sizeof(long) ? 2 : 4); -} - -static inline void -MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, - int count, int *success_count, domid_t domid) -{ - mcl->op = __HYPERVISOR_mmu_update; - mcl->args[0] = (unsigned long)req; - mcl->args[1] = count; - mcl->args[2] = (unsigned long)success_count; - mcl->args[3] = domid; - - trace_xen_mc_entry(mcl, 4); -} - -static inline void -MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count, - int *success_count, domid_t domid) -{ - mcl->op = __HYPERVISOR_mmuext_op; - mcl->args[0] = (unsigned long)op; - mcl->args[1] = count; - mcl->args[2] = (unsigned long)success_count; - mcl->args[3] = domid; - - trace_xen_mc_entry(mcl, 4); -} - -static inline void -MULTI_stack_switch(struct multicall_entry *mcl, - unsigned long ss, unsigned long esp) -{ - mcl->op = __HYPERVISOR_stack_switch; - mcl->args[0] = ss; - mcl->args[1] = esp; - - trace_xen_mc_entry(mcl, 2); -} - #endif /* _ASM_X86_XEN_HYPERCALL_H */ diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index ff4b52e37e60..4957f59deb40 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,4 +62,8 @@ void xen_arch_register_cpu(int num); void xen_arch_unregister_cpu(int num); #endif +#ifdef CONFIG_PVH +void __init xen_pvh_init(struct boot_params *boot_params); +#endif + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 4557f7cb0fa6..9015b888edd6 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -22,25 +22,6 @@ static inline int __init pci_xen_initial_domain(void) return -1; } #endif -#ifdef CONFIG_XEN_DOM0 -int xen_find_device_domain_owner(struct pci_dev *dev); -int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); -int xen_unregister_device_domain_owner(struct pci_dev *dev); -#else -static inline int xen_find_device_domain_owner(struct pci_dev *dev) -{ - return -1; -} -static inline int xen_register_device_domain_owner(struct pci_dev *dev, - uint16_t domain) -{ - return -1; -} -static inline int xen_unregister_device_domain_owner(struct pci_dev *dev) -{ - return -1; -} -#endif #if defined(CONFIG_PCI_MSI) #if defined(CONFIG_PCI_XEN) diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 5146bbab84d4..6e64b27b2c1e 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -8,6 +8,7 @@ * should be used to determine that a VM is running under KVM. */ #define KVM_CPUID_SIGNATURE 0x40000000 +#define KVM_SIGNATURE "KVMKVMKVM\0\0\0" /* This CPUID returns two feature bitmaps in eax, edx. Before enabling * a particular paravirtualization, the appropriate feature bit should diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index d1d49e3d536b..3b58d8703094 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -77,9 +77,6 @@ asmlinkage noinstr void __noreturn doublefault_shim(void) * some way to reconstruct CR3. We could make a credible guess based * on cpu_tlbstate, but that would be racy and would not account for * PTI. - * - * Instead, don't bother. We can return through - * rewind_stack_do_exit() instead. */ panic("cannot return from double fault\n"); } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8863d1941f1b..59abbdad7729 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -28,6 +28,7 @@ #include <linux/swait.h> #include <linux/syscore_ops.h> #include <linux/cc_platform.h> +#include <linux/efi.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -41,6 +42,7 @@ #include <asm/ptrace.h> #include <asm/reboot.h> #include <asm/svm.h> +#include <asm/e820/api.h> DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -434,6 +436,8 @@ static void kvm_guest_cpu_offline(bool shutdown) kvm_disable_steal_time(); if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) wrmsrl(MSR_KVM_PV_EOI_EN, 0); + if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) + wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0); kvm_pv_disable_apf(); if (!shutdown) apf_task_wake_all(); @@ -548,6 +552,55 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) __send_ipi_mask(local_mask, vector); } +static int __init setup_efi_kvm_sev_migration(void) +{ + efi_char16_t efi_sev_live_migration_enabled[] = L"SevLiveMigrationEnabled"; + efi_guid_t efi_variable_guid = AMD_SEV_MEM_ENCRYPT_GUID; + efi_status_t status; + unsigned long size; + bool enabled; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) || + !kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) + return 0; + + if (!efi_enabled(EFI_BOOT)) + return 0; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + pr_info("%s : EFI runtime services are not enabled\n", __func__); + return 0; + } + + size = sizeof(enabled); + + /* Get variable contents into buffer */ + status = efi.get_variable(efi_sev_live_migration_enabled, + &efi_variable_guid, NULL, &size, &enabled); + + if (status == EFI_NOT_FOUND) { + pr_info("%s : EFI live migration variable not found\n", __func__); + return 0; + } + + if (status != EFI_SUCCESS) { + pr_info("%s : EFI variable retrieval failed\n", __func__); + return 0; + } + + if (enabled == 0) { + pr_info("%s: live migration disabled in EFI\n", __func__); + return 0; + } + + pr_info("%s : live migration enabled in EFI\n", __func__); + wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY); + + return 1; +} + +late_initcall(setup_efi_kvm_sev_migration); + /* * Set the IPI entry points */ @@ -756,7 +809,7 @@ static noinline uint32_t __kvm_cpuid_base(void) return 0; /* So we don't blow up on old processors */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); + return hypervisor_cpuid_base(KVM_SIGNATURE, 0); return 0; } @@ -806,8 +859,62 @@ static bool __init kvm_msi_ext_dest_id(void) return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID); } +static void kvm_sev_hc_page_enc_status(unsigned long pfn, int npages, bool enc) +{ + kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, pfn << PAGE_SHIFT, npages, + KVM_MAP_GPA_RANGE_ENC_STAT(enc) | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); +} + static void __init kvm_init_platform(void) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && + kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) { + unsigned long nr_pages; + int i; + + pv_ops.mmu.notify_page_enc_status_changed = + kvm_sev_hc_page_enc_status; + + /* + * Reset the host's shared pages list related to kernel + * specific page encryption status settings before we load a + * new kernel by kexec. Reset the page encryption status + * during early boot intead of just before kexec to avoid SMP + * races during kvm_pv_guest_cpu_reboot(). + * NOTE: We cannot reset the complete shared pages list + * here as we need to retain the UEFI/OVMF firmware + * specific settings. + */ + + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; + + if (entry->type != E820_TYPE_RAM) + continue; + + nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE); + + kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, entry->addr, + nr_pages, + KVM_MAP_GPA_RANGE_ENCRYPTED | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); + } + + /* + * Ensure that _bss_decrypted section is marked as decrypted in the + * shared pages list. + */ + nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted, + PAGE_SIZE); + early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted, + nr_pages, 0); + + /* + * If not booted using EFI, enable Live migration support. + */ + if (!efi_enabled(EFI_BOOT)) + wrmsrl(MSR_KVM_MIGRATION_CONTROL, + KVM_MIGRATION_READY); + } kvmclock_init(); x86_platform.apic_post_init = kvm_apic_init; } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index ebc45360ffd4..7f7636aac620 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -46,6 +46,17 @@ asm (".pushsection .entry.text, \"ax\"\n" ".type _paravirt_nop, @function\n\t" ".popsection"); +/* stub always returning 0. */ +asm (".pushsection .entry.text, \"ax\"\n" + ".global paravirt_ret0\n" + "paravirt_ret0:\n\t" + "xor %" _ASM_AX ", %" _ASM_AX ";\n\t" + "ret\n\t" + ".size paravirt_ret0, . - paravirt_ret0\n\t" + ".type paravirt_ret0, @function\n\t" + ".popsection"); + + void __init default_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", @@ -53,7 +64,7 @@ void __init default_banner(void) } /* Undefined instruction for dealing with missing ops pointers. */ -static void paravirt_BUG(void) +noinstr void paravirt_BUG(void) { BUG(); } @@ -326,6 +337,7 @@ struct paravirt_patch_template pv_ops = { (void (*)(struct mmu_gather *, void *))tlb_remove_page, .mmu.exit_mmap = paravirt_nop, + .mmu.notify_page_enc_status_changed = paravirt_nop, #ifdef CONFIG_PARAVIRT_XXL .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2), diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index e5a7a10a0164..cce1c89cb7df 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -106,10 +106,8 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) */ local_irq_enable(); - if (!vm86 || !vm86->user_vm86) { - pr_alert("no user_vm86: BAD\n"); - do_exit(SIGSEGV); - } + BUG_ON(!vm86); + set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); user = vm86->user_vm86; @@ -142,6 +140,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) user_access_end(); +exit_vm86: preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; tsk->thread.sysenter_cs = __KERNEL_CS; @@ -161,7 +160,8 @@ Efault_end: user_access_end(); Efault: pr_alert("could not access userspace vm86 info\n"); - do_exit(SIGSEGV); + force_fatal_sig(SIGSEGV); + goto exit_vm86; } static int do_vm86_irq_handling(int subfunction, int irqnumber); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2d70edb0f323..e19dabf1848b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -99,11 +99,45 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) { - struct kvm_cpuid_entry2 *best; + u32 function; + struct kvm_cpuid_entry2 *entry; + + vcpu->arch.kvm_cpuid_base = 0; + + for_each_possible_hypervisor_cpuid_base(function) { + entry = kvm_find_cpuid_entry(vcpu, function, 0); - best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + if (entry) { + u32 signature[3]; + + signature[0] = entry->ebx; + signature[1] = entry->ecx; + signature[2] = entry->edx; + + BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE)); + if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) { + vcpu->arch.kvm_cpuid_base = function; + break; + } + } + } +} + +struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) +{ + u32 base = vcpu->arch.kvm_cpuid_base; + + if (!base) + return NULL; + + return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0); +} + +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu); /* * save the feature bitmap to avoid cpuid lookup for every PV @@ -142,7 +176,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + best = kvm_find_kvm_cpuid_features(vcpu); if (kvm_hlt_in_guest(vcpu->kvm) && best && (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); @@ -239,6 +273,26 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); } +static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, + int nent) +{ + int r; + + r = kvm_check_cpuid(e2, nent); + if (r) + return r; + + kvfree(vcpu->arch.cpuid_entries); + vcpu->arch.cpuid_entries = e2; + vcpu->arch.cpuid_nent = nent; + + kvm_update_kvm_cpuid_base(vcpu); + kvm_update_cpuid_runtime(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); + + return 0; +} + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -275,18 +329,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, e2[i].padding[2] = 0; } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - goto out_free_cpuid; - } - - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); out_free_cpuid: kvfree(e); @@ -310,20 +355,11 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return PTR_ERR(e2); } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - return r; - } - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); - - return 0; + return r; } int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, @@ -871,8 +907,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case KVM_CPUID_SIGNATURE: { - static const char signature[12] = "KVMKVMKVM\0\0"; - const u32 *sigptr = (const u32 *)signature; + const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; entry->ebx = sigptr[0]; entry->ecx = sigptr[1]; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4f15c0165c05..4a555f32885a 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1472,7 +1472,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) { hv_vcpu->hv_vapic = data; - if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0)) + if (kvm_lapic_set_pv_eoi(vcpu, 0, 0)) return 1; break; } @@ -1490,7 +1490,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; hv_vcpu->hv_vapic = data; kvm_vcpu_mark_page_dirty(vcpu, gfn); - if (kvm_lapic_enable_pv_eoi(vcpu, + if (kvm_lapic_set_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED, sizeof(struct hv_vp_assist_page))) return 1; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d6ac32f3f650..759952dd1222 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2856,25 +2856,30 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) return 0; } -int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) { u64 addr = data & ~KVM_MSR_ENABLED; struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data; unsigned long new_len; + int ret; if (!IS_ALIGNED(addr, 4)) return 1; - vcpu->arch.pv_eoi.msr_val = data; - if (!pv_eoi_enabled(vcpu)) - return 0; + if (data & KVM_MSR_ENABLED) { + if (addr == ghc->gpa && len <= ghc->len) + new_len = ghc->len; + else + new_len = len; - if (addr == ghc->gpa && len <= ghc->len) - new_len = ghc->len; - else - new_len = len; + ret = kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); + if (ret) + return ret; + } + + vcpu->arch.pv_eoi.msr_val = data; - return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); + return 0; } int kvm_apic_accept_events(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index d7c25d0c1354..2b44e533fc8d 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -127,7 +127,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 323b5057d08f..33794379949e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3191,17 +3191,17 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) new_spte |= PT_WRITABLE_MASK; /* - * Do not fix write-permission on the large spte. Since - * we only dirty the first page into the dirty-bitmap in + * Do not fix write-permission on the large spte when + * dirty logging is enabled. Since we only dirty the + * first page into the dirty-bitmap in * fast_pf_fix_direct_spte(), other pages are missed * if its slot has dirty logging enabled. * * Instead, we let the slow page fault path create a * normal spte to fix the access. - * - * See the comments in kvm_arch_commit_memory_region(). */ - if (sp->role.level > PG_LEVEL_4K) + if (sp->role.level > PG_LEVEL_4K && + kvm_slot_dirty_track_enabled(fault->slot)) break; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7c5dd83e52de..a54c3491af42 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -897,7 +897,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, struct tdp_iter *iter) { - struct kvm_mmu_page *sp = sptep_to_sp(iter->sptep); + struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(iter->sptep)); u64 new_spte; int ret = RET_PF_FIXED; bool wrprot = false; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 0772bad9165c..09873f6488f7 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -319,7 +319,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) } /* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 0e4f2b1fa9fb..59d6b76203d5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -32,7 +32,7 @@ struct kvm_pmu_ops { struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); - int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); + bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -149,7 +149,7 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); +bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8052d92069e0..affc0ea98d30 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -904,7 +904,8 @@ bool svm_check_apicv_inhibit_reasons(ulong bit) BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_X2APIC); + BIT(APICV_INHIBIT_REASON_X2APIC) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ); return supported & BIT(bit); } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index fdf587f19c5f..871c426ec389 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -181,14 +181,13 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER); } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); idx &= ~(3u << 30); - return (idx >= pmu->nr_arch_gp_counters); + return idx < pmu->nr_arch_gp_counters; } /* idx is the ECX register of RDPMC instruction */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1964b9a174be..902c52a8dd0c 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -120,16 +120,26 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) return true; } +static int sev_misc_cg_try_charge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + return misc_cg_try_charge(type, sev->misc_cg, 1); +} + +static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + misc_cg_uncharge(type, sev->misc_cg, 1); +} + static int sev_asid_new(struct kvm_sev_info *sev) { int asid, min_asid, max_asid, ret; bool retry = true; - enum misc_res_type type; - type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); - ret = misc_cg_try_charge(type, sev->misc_cg, 1); + ret = sev_misc_cg_try_charge(sev); if (ret) { put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; @@ -162,7 +172,7 @@ again: return asid; e_uncharge: - misc_cg_uncharge(type, sev->misc_cg, 1); + sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; return ret; @@ -179,7 +189,6 @@ static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; int cpu; - enum misc_res_type type; mutex_lock(&sev_bitmap_lock); @@ -192,8 +201,7 @@ static void sev_asid_free(struct kvm_sev_info *sev) mutex_unlock(&sev_bitmap_lock); - type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; - misc_cg_uncharge(type, sev->misc_cg, 1); + sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; } @@ -590,7 +598,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) * traditional VMSA as it has been built so far (in prep * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. */ - memcpy(svm->vmsa, save, sizeof(*save)); + memcpy(svm->sev_es.vmsa, save, sizeof(*save)); return 0; } @@ -612,11 +620,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, * the VMSA memory content (i.e it will write the same memory region * with the guest's key), so invalidate it first. */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE); vmsa.reserved = 0; vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; - vmsa.address = __sme_pa(svm->vmsa); + vmsa.address = __sme_pa(svm->sev_es.vmsa); vmsa.len = PAGE_SIZE; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); if (ret) @@ -1536,6 +1544,201 @@ static bool cmd_allowed_from_miror(u32 cmd_id) return false; } +static int sev_lock_for_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + /* + * Bail if this VM is already involved in a migration to avoid deadlock + * between two VMs trying to migrate to/from each other. + */ + if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + return -EBUSY; + + mutex_lock(&kvm->lock); + + return 0; +} + +static void sev_unlock_after_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + mutex_unlock(&kvm->lock); + atomic_set_release(&sev->migration_in_progress, 0); +} + + +static int sev_lock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, j; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable(&vcpu->mutex)) + goto out_unlock; + } + + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} + +static void sev_unlock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_unlock(&vcpu->mutex); + } +} + +static void sev_migrate_from(struct kvm_sev_info *dst, + struct kvm_sev_info *src) +{ + dst->active = true; + dst->asid = src->asid; + dst->handle = src->handle; + dst->pages_locked = src->pages_locked; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + + INIT_LIST_HEAD(&dst->regions_list); + list_replace_init(&src->regions_list, &dst->regions_list); +} + +static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) +{ + int i; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; + + if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) + return -EINVAL; + + kvm_for_each_vcpu(i, src_vcpu, src) { + if (!src_vcpu->arch.guest_state_protected) + return -EINVAL; + } + + kvm_for_each_vcpu(i, src_vcpu, src) { + src_svm = to_svm(src_vcpu); + dst_vcpu = kvm_get_vcpu(dst, i); + dst_svm = to_svm(dst_vcpu); + + /* + * Transfer VMSA and GHCB state to the destination. Nullify and + * clear source fields as appropriate, the state now belongs to + * the destination. + */ + memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es)); + dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa; + dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa; + dst_vcpu->arch.guest_state_protected = true; + + memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es)); + src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE; + src_svm->vmcb->control.vmsa_pa = INVALID_PAGE; + src_vcpu->arch.guest_state_protected = false; + } + to_kvm_svm(src)->sev_info.es_active = false; + to_kvm_svm(dst)->sev_info.es_active = true; + + return 0; +} + +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *src_sev, *cg_cleanup_sev; + struct file *source_kvm_file; + struct kvm *source_kvm; + bool charged = false; + int ret; + + ret = sev_lock_for_migration(kvm); + if (ret) + return ret; + + if (sev_guest(kvm)) { + ret = -EINVAL; + goto out_unlock; + } + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = source_kvm_file->private_data; + ret = sev_lock_for_migration(source_kvm); + if (ret) + goto out_fput; + + if (!sev_guest(source_kvm)) { + ret = -EINVAL; + goto out_source; + } + + src_sev = &to_kvm_svm(source_kvm)->sev_info; + dst_sev->misc_cg = get_current_misc_cg(); + cg_cleanup_sev = dst_sev; + if (dst_sev->misc_cg != src_sev->misc_cg) { + ret = sev_misc_cg_try_charge(dst_sev); + if (ret) + goto out_dst_cgroup; + charged = true; + } + + ret = sev_lock_vcpus_for_migration(kvm); + if (ret) + goto out_dst_cgroup; + ret = sev_lock_vcpus_for_migration(source_kvm); + if (ret) + goto out_dst_vcpu; + + if (sev_es_guest(source_kvm)) { + ret = sev_es_migrate_from(kvm, source_kvm); + if (ret) + goto out_source_vcpu; + } + sev_migrate_from(dst_sev, src_sev); + kvm_vm_dead(source_kvm); + cg_cleanup_sev = src_sev; + ret = 0; + +out_source_vcpu: + sev_unlock_vcpus_for_migration(source_kvm); +out_dst_vcpu: + sev_unlock_vcpus_for_migration(kvm); +out_dst_cgroup: + /* Operates on the source on success, on the destination on failure. */ + if (charged) + sev_misc_cg_uncharge(cg_cleanup_sev); + put_misc_cg(cg_cleanup_sev->misc_cg); + cg_cleanup_sev->misc_cg = NULL; +out_source: + sev_unlock_after_migration(source_kvm); +out_fput: + if (source_kvm_file) + fput(source_kvm_file); +out_unlock: + sev_unlock_after_migration(kvm); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -2038,16 +2241,16 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE); - __free_page(virt_to_page(svm->vmsa)); + sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + __free_page(virt_to_page(svm->sev_es.vmsa)); - if (svm->ghcb_sa_free) - kfree(svm->ghcb_sa); + if (svm->sev_es.ghcb_sa_free) + kfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) { - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -2073,7 +2276,7 @@ static void dump_ghcb(struct vcpu_svm *svm) static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; /* * The GHCB protocol so far allows for the following data @@ -2093,7 +2296,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 exit_code; /* @@ -2140,7 +2343,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) struct ghcb *ghcb; u64 exit_code = 0; - ghcb = svm->ghcb; + ghcb = svm->sev_es.ghcb; /* Only GHCB Usage code 0 is supported */ if (ghcb->ghcb_usage) @@ -2258,33 +2461,34 @@ vmgexit_err: void sev_es_unmap_ghcb(struct vcpu_svm *svm) { - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - if (svm->ghcb_sa_free) { + if (svm->sev_es.ghcb_sa_free) { /* * The scratch area lives outside the GHCB, so there is a * buffer that, depending on the operation performed, may * need to be synced, then freed. */ - if (svm->ghcb_sa_sync) { + if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->ghcb), - svm->ghcb_sa, svm->ghcb_sa_len); - svm->ghcb_sa_sync = false; + ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.ghcb_sa, + svm->sev_es.ghcb_sa_len); + svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->ghcb_sa); - svm->ghcb_sa = NULL; - svm->ghcb_sa_free = false; + kfree(svm->sev_es.ghcb_sa); + svm->sev_es.ghcb_sa = NULL; + svm->sev_es.ghcb_sa_free = false; } - trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb); + trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb); sev_es_sync_to_ghcb(svm); - kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true); - svm->ghcb = NULL; + kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map, true); + svm->sev_es.ghcb = NULL; } void pre_sev_run(struct vcpu_svm *svm, int cpu) @@ -2314,7 +2518,7 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; @@ -2350,7 +2554,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) return false; } - scratch_va = (void *)svm->ghcb; + scratch_va = (void *)svm->sev_es.ghcb; scratch_va += (scratch_gpa_beg - control->ghcb_gpa); } else { /* @@ -2380,12 +2584,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) * the vCPU next time (i.e. a read was requested so the data * must be written back to the guest memory). */ - svm->ghcb_sa_sync = sync; - svm->ghcb_sa_free = true; + svm->sev_es.ghcb_sa_sync = sync; + svm->sev_es.ghcb_sa_free = true; } - svm->ghcb_sa = scratch_va; - svm->ghcb_sa_len = len; + svm->sev_es.ghcb_sa = scratch_va; + svm->sev_es.ghcb_sa_len = len; return true; } @@ -2504,15 +2708,15 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) return -EINVAL; } - if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) { + if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); return -EINVAL; } - svm->ghcb = svm->ghcb_map.hva; - ghcb = svm->ghcb_map.hva; + svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; + ghcb = svm->sev_es.ghcb_map.hva; trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); @@ -2535,7 +2739,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = kvm_sev_es_mmio_read(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_MMIO_WRITE: if (!setup_vmgexit_scratch(svm, false, control->exit_info_2)) @@ -2544,7 +2748,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = kvm_sev_es_mmio_write(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET); @@ -2604,7 +2808,8 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) if (!setup_vmgexit_scratch(svm, in, bytes)) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in); + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, + count, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) @@ -2619,7 +2824,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) * VMCB page. Do not include the encryption mask on the VMSA physical * address since hardware will access it using the guest key. */ - svm->vmcb->control.vmsa_pa = __pa(svm->vmsa); + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); @@ -2691,8 +2896,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) struct vcpu_svm *svm = to_svm(vcpu); /* First SIPI: Use the values as initially set by the VMM */ - if (!svm->received_first_sipi) { - svm->received_first_sipi = true; + if (!svm->sev_es.received_first_sipi) { + svm->sev_es.received_first_sipi = true; return; } @@ -2701,8 +2906,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a * non-zero value. */ - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - ghcb_set_sw_exit_info_2(svm->ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b36ca4e476c2..5630c241d5f6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1452,7 +1452,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm_switch_vmcb(svm, &svm->vmcb01); if (vmsa_page) - svm->vmsa = page_address(vmsa_page); + svm->sev_es.vmsa = page_address(vmsa_page); svm->guest_state_loaded = false; @@ -2835,11 +2835,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { struct vcpu_svm *svm = to_svm(vcpu); - if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->ghcb)) + if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb)) return kvm_complete_insn_gp(vcpu, err); - ghcb_set_sw_exit_info_1(svm->ghcb, 1); - ghcb_set_sw_exit_info_2(svm->ghcb, + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, X86_TRAP_GP | SVM_EVTINJ_TYPE_EXEPT | SVM_EVTINJ_VALID); @@ -3121,11 +3121,6 @@ static int invpcid_interception(struct kvm_vcpu *vcpu) type = svm->vmcb->control.exit_info_2; gva = svm->vmcb->control.exit_info_1; - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return kvm_handle_invpcid(vcpu, type, gva); } @@ -4701,6 +4696,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_unreg_region = svm_unregister_enc_region, .vm_copy_enc_context_from = svm_vm_copy_asid_from, + .vm_move_enc_context_from = svm_vm_migrate_from, .can_emulate_instruction = svm_can_emulate_instruction, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5e9510d4574e..437e68504e66 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -80,6 +80,7 @@ struct kvm_sev_info { u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ + atomic_t migration_in_progress; }; struct kvm_svm { @@ -123,6 +124,20 @@ struct svm_nested_state { bool initialized; }; +struct vcpu_sev_es_state { + /* SEV-ES support */ + struct vmcb_save_area *vmsa; + struct ghcb *ghcb; + struct kvm_host_map ghcb_map; + bool received_first_sipi; + + /* SEV-ES scratch area support */ + void *ghcb_sa; + u32 ghcb_sa_len; + bool ghcb_sa_sync; + bool ghcb_sa_free; +}; + struct vcpu_svm { struct kvm_vcpu vcpu; /* vmcb always points at current_vmcb->ptr, it's purely a shorthand. */ @@ -186,17 +201,7 @@ struct vcpu_svm { DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); } shadow_msr_intercept; - /* SEV-ES support */ - struct vmcb_save_area *vmsa; - struct ghcb *ghcb; - struct kvm_host_map ghcb_map; - bool received_first_sipi; - - /* SEV-ES scratch area support */ - void *ghcb_sa; - u32 ghcb_sa_len; - bool ghcb_sa_sync; - bool ghcb_sa_free; + struct vcpu_sev_es_state sev_es; bool guest_state_loaded; }; @@ -558,6 +563,7 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd); +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd); void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b4ee5e9f9e20..b213ca966d41 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -525,67 +525,19 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, } /* - * Check if MSR is intercepted for L01 MSR bitmap. + * For x2APIC MSRs, ignore the vmcs01 bitmap. L1 can enable x2APIC without L1 + * itself utilizing x2APIC. All MSRs were previously set to be intercepted, + * only the "disable intercept" case needs to be handled. */ -static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int type) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); + if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr); - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; -} - -/* - * If a msr is allowed by L0, we should check whether it is allowed by L1. - * The corresponding bit will be cleared unless both of L0 and L1 allow it. - */ -static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, - unsigned long *msr_bitmap_nested, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x000 / f)) - /* read-low */ - __clear_bit(msr, msr_bitmap_nested + 0x000 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0x800 / f)) - /* write-low */ - __clear_bit(msr, msr_bitmap_nested + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x400 / f)) - /* read-high */ - __clear_bit(msr, msr_bitmap_nested + 0x400 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0xc00 / f)) - /* write-high */ - __clear_bit(msr, msr_bitmap_nested + 0xc00 / f); - - } + if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr); } static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) @@ -600,6 +552,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) } } +#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw) \ +static inline \ +void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx, \ + unsigned long *msr_bitmap_l1, \ + unsigned long *msr_bitmap_l0, u32 msr) \ +{ \ + if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) || \ + vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr)) \ + vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr); \ + else \ + vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr); \ +} +BUILD_NVMX_MSR_INTERCEPT_HELPER(read) +BUILD_NVMX_MSR_INTERCEPT_HELPER(write) + +static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx, + unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int types) +{ + if (types & MSR_TYPE_R) + nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); + if (types & MSR_TYPE_W) + nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -607,10 +587,11 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + struct vcpu_vmx *vmx = to_vmx(vcpu); int msr; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; - struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map; + unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || @@ -625,7 +606,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, /* * To keep the control flow simple, pay eight 8-byte writes (sixteen * 4-byte writes on 32-bit systems) up front to enable intercepts for - * the x2APIC MSR range and selectively disable them below. + * the x2APIC MSR range and selectively toggle those relevant to L2. */ enable_x2apic_msr_intercepts(msr_bitmap_l0); @@ -644,61 +625,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, } } - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_R | MSR_TYPE_W); if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); } } - /* KVM unconditionally exposes the FS/GS base MSRs to L1. */ + /* + * Always check vmcs01's bitmap to honor userspace MSR filters and any + * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through. + */ #ifdef CONFIG_X86_64 - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_FS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_FS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_GS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); - /* - * Checking the L0->L1 bitmap is trying to verify two things: - * - * 1. L0 gave a permission to L1 to actually passthrough the MSR. This - * ensures that we do not accidentally generate an L02 MSR bitmap - * from the L12 MSR bitmap that is too permissive. - * 2. That L1 or L2s have actually used the MSR. This avoids - * unnecessarily merging of the bitmap if the MSR is unused. This - * works properly because we only update the L01 MSR bitmap lazily. - * So even if L0 should pass L1 these MSRs, the L01 bitmap is only - * updated to reflect this when L1 (or its L2s) actually write to - * the MSR. - */ - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_R | MSR_TYPE_W); - - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_PRED_CMD, - MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, MSR_TYPE_W); - kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); return true; } @@ -5379,7 +5343,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - int i, r; + int i, r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || @@ -5392,7 +5356,8 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; @@ -5459,7 +5424,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) u64 gla; } operand; u16 vpid02; - int r; + int r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -5472,7 +5437,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.vpid_caps & VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index b8e0d21b7c8a..1b7456b2177b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -118,16 +118,15 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); idx &= ~(3u << 30); - return (!fixed && idx >= pmu->nr_arch_gp_counters) || - (fixed && idx >= pmu->nr_arch_fixed_counters); + return fixed ? idx < pmu->nr_arch_fixed_counters + : idx < pmu->nr_arch_gp_counters; } static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 76861b66bbcf..ba66c171d951 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -769,24 +769,13 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) /* * Check if MSR is intercepted for currently loaded MSR bitmap. */ -static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) + if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, + MSR_IA32_SPEC_CTRL); } static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, @@ -3697,46 +3686,6 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -static void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - -static void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5494,6 +5443,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) u64 pcid; u64 gla; } operand; + int gpr_index; if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -5501,12 +5451,8 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); - - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); /* According to the Intel instruction reference, the memory operand * is read even if it isn't needed (e.g., for type==all) @@ -6749,7 +6695,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); @@ -7563,7 +7509,8 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_HYPERV); + BIT(APICV_INHIBIT_REASON_HYPERV) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ); return supported & BIT(bit); } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e7db42e3b0ce..a4ead6023133 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -400,6 +400,34 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +/* + * Note, early Intel manuals have the write-low and read-high bitmap offsets + * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and + * 0xc0000000-0xc0001fff. The former (low) uses bytes 0-0x3ff for reads and + * 0x800-0xbff for writes. The latter (high) uses 0x400-0x7ff for reads and + * 0xc00-0xfff for writes. MSRs not covered by either of the ranges always + * VM-Exit. + */ +#define __BUILD_VMX_MSR_BITMAP_HELPER(rtype, action, bitop, access, base) \ +static inline rtype vmx_##action##_msr_bitmap_##access(unsigned long *bitmap, \ + u32 msr) \ +{ \ + int f = sizeof(unsigned long); \ + \ + if (msr <= 0x1fff) \ + return bitop##_bit(msr, bitmap + base / f); \ + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) \ + return bitop##_bit(msr & 0x1fff, bitmap + (base + 0x400) / f); \ + return (rtype)true; \ +} +#define BUILD_VMX_MSR_BITMAP_HELPERS(ret_type, action, bitop) \ + __BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, read, 0x0) \ + __BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 0x800) + +BUILD_VMX_MSR_BITMAP_HELPERS(bool, test, test) +BUILD_VMX_MSR_BITMAP_HELPERS(void, clear, __clear) +BUILD_VMX_MSR_BITMAP_HELPERS(void, set, __set) + static inline u8 vmx_get_rvi(void) { return vmcs_read16(GUEST_INTR_STATUS) & 0xff; @@ -522,4 +550,9 @@ static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu) void dump_vmcs(struct kvm_vcpu *vcpu); +static inline int vmx_get_instr_info_reg2(u32 vmx_instr_info) +{ + return (vmx_instr_info >> 28) & 0xf; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c1c4e2b05a63..dc7eb5fddfd3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3260,8 +3260,11 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + u64 steal; + u32 version; if (kvm_xen_msr_enabled(vcpu->kvm)) { kvm_xen_runstate_set_running(vcpu); @@ -3271,47 +3274,86 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - /* -EAGAIN is returned in atomic context so we can just return. */ - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, - &map, &vcpu->arch.st.cache, false)) + if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { + gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + + /* We rely on the fact that it fits in a single page. */ + BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + kvm_is_error_hva(ghc->hva) || !ghc->memslot) + return; + } + st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { - u8 st_preempted = xchg(&st->preempted, 0); + u8 st_preempted = 0; + int err = -EFAULT; + + if (!user_access_begin(st, sizeof(*st))) + return; + + asm volatile("1: xchgb %0, %2\n" + "xor %1, %1\n" + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+r" (st_preempted), + "+&r" (err) + : "m" (st->preempted)); + if (err) + goto out; + + user_access_end(); + + vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + + if (!user_access_begin(st, sizeof(*st))) + goto dirty; } else { - st->preempted = 0; - } + if (!user_access_begin(st, sizeof(*st))) + return; - vcpu->arch.st.preempted = 0; + unsafe_put_user(0, &st->preempted, out); + vcpu->arch.st.preempted = 0; + } - if (st->version & 1) - st->version += 1; /* first time write, random junk */ + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); smp_wmb(); - st->steal += current->sched_info.run_delay - + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); - smp_wmb(); - - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); + out: + user_access_end(); + dirty: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3517,7 +3559,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return 1; - if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8))) + if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8))) return 1; break; @@ -4137,7 +4179,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); break; case KVM_CAP_NR_VCPUS: - r = KVM_SOFT_MAX_VCPUS; + r = num_online_cpus(); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -4351,8 +4393,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + static const u8 preempted = KVM_VCPU_PREEMPTED; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4360,16 +4404,23 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, - &vcpu->arch.st.cache, true)) + /* This happens on process exit */ + if (unlikely(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) + return; - st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + st = (struct kvm_steal_time __user *)ghc->hva; + BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) + vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -5728,6 +5779,12 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: + r = -EINVAL; + if (kvm_x86_ops.vm_move_enc_context_from) + r = kvm_x86_ops.vm_move_enc_context_from( + kvm, cap->args[0]); + return r; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; @@ -7328,7 +7385,9 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc); + if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc)) + return 0; + return -EINVAL; } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -9552,7 +9611,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) { + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } @@ -10564,6 +10623,24 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return ret; } +static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) +{ + bool inhibit = false; + struct kvm_vcpu *vcpu; + int i; + + down_write(&kvm->arch.apicv_update_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { + inhibit = true; + break; + } + } + __kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ); + up_write(&kvm->arch.apicv_update_lock); +} + int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { @@ -10616,6 +10693,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, static_call(kvm_x86_update_exception_bitmap)(vcpu); + kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); + r = 0; out: @@ -10859,11 +10938,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; int idx; - kvm_release_pfn(cache->pfn, cache->dirty, cache); - kvmclock_reset(vcpu); static_call(kvm_x86_vcpu_free)(vcpu); @@ -12275,7 +12351,8 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return kvm_skip_emulated_instruction(vcpu); default: - BUG(); /* We have already checked above that type <= 3 */ + kvm_inject_gp(vcpu, 0); + return 1; } } EXPORT_SYMBOL_GPL(kvm_handle_invpcid); diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 23d54b810f08..35487305d8af 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -229,28 +229,75 @@ void __init sev_setup_arch(void) swiotlb_adjust_size(size); } -static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) { - pgprot_t old_prot, new_prot; - unsigned long pfn, pa, size; - pte_t new_pte; + unsigned long pfn = 0; + pgprot_t prot; switch (level) { case PG_LEVEL_4K: pfn = pte_pfn(*kpte); - old_prot = pte_pgprot(*kpte); + prot = pte_pgprot(*kpte); break; case PG_LEVEL_2M: pfn = pmd_pfn(*(pmd_t *)kpte); - old_prot = pmd_pgprot(*(pmd_t *)kpte); + prot = pmd_pgprot(*(pmd_t *)kpte); break; case PG_LEVEL_1G: pfn = pud_pfn(*(pud_t *)kpte); - old_prot = pud_pgprot(*(pud_t *)kpte); + prot = pud_pgprot(*(pud_t *)kpte); break; default: - return; + WARN_ONCE(1, "Invalid level for kpte\n"); + return 0; + } + + if (ret_prot) + *ret_prot = prot; + + return pfn; +} + +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc) +{ +#ifdef CONFIG_PARAVIRT + unsigned long sz = npages << PAGE_SHIFT; + unsigned long vaddr_end = vaddr + sz; + + while (vaddr < vaddr_end) { + int psize, pmask, level; + unsigned long pfn; + pte_t *kpte; + + kpte = lookup_address(vaddr, &level); + if (!kpte || pte_none(*kpte)) { + WARN_ONCE(1, "kpte lookup for vaddr\n"); + return; + } + + pfn = pg_level_to_pfn(level, kpte, NULL); + if (!pfn) + continue; + + psize = page_level_size(level); + pmask = page_level_mask(level); + + notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc); + + vaddr = (vaddr & pmask) + psize; } +#endif +} + +static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +{ + pgprot_t old_prot, new_prot; + unsigned long pfn, pa, size; + pte_t new_pte; + + pfn = pg_level_to_pfn(level, kpte, &old_prot); + if (!pfn) + return; new_prot = old_prot; if (enc) @@ -286,12 +333,13 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) static int __init early_set_memory_enc_dec(unsigned long vaddr, unsigned long size, bool enc) { - unsigned long vaddr_end, vaddr_next; + unsigned long vaddr_end, vaddr_next, start; unsigned long psize, pmask; int split_page_size_mask; int level, ret; pte_t *kpte; + start = vaddr; vaddr_next = vaddr; vaddr_end = vaddr + size; @@ -346,6 +394,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr, ret = 0; + notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); out: __flush_tlb_all(); return ret; @@ -361,6 +410,11 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) return early_set_memory_enc_dec(vaddr, size, true); } +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +{ + notify_range_enc_status_changed(vaddr, npages, enc); +} + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 934dc5b2df36..b4072115c8ef 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2023,6 +2023,12 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) */ cpa_flush(&cpa, 0); + /* + * Notify hypervisor that a given memory range is mapped encrypted + * or decrypted. + */ + notify_range_enc_status_changed(addr, numpages, enc); + return ret; } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 5debe4ac6f81..12da00558631 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -23,6 +23,7 @@ #include <xen/features.h> #include <xen/events.h> +#include <xen/pci.h> #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> @@ -585,78 +586,3 @@ int __init pci_xen_initial_domain(void) } #endif -#ifdef CONFIG_XEN_DOM0 - -struct xen_device_domain_owner { - domid_t domain; - struct pci_dev *dev; - struct list_head list; -}; - -static DEFINE_SPINLOCK(dev_domain_list_spinlock); -static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list); - -static struct xen_device_domain_owner *find_device(struct pci_dev *dev) -{ - struct xen_device_domain_owner *owner; - - list_for_each_entry(owner, &dev_domain_list, list) { - if (owner->dev == dev) - return owner; - } - return NULL; -} - -int xen_find_device_domain_owner(struct pci_dev *dev) -{ - struct xen_device_domain_owner *owner; - int domain = -ENODEV; - - spin_lock(&dev_domain_list_spinlock); - owner = find_device(dev); - if (owner) - domain = owner->domain; - spin_unlock(&dev_domain_list_spinlock); - return domain; -} -EXPORT_SYMBOL_GPL(xen_find_device_domain_owner); - -int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain) -{ - struct xen_device_domain_owner *owner; - - owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL); - if (!owner) - return -ENODEV; - - spin_lock(&dev_domain_list_spinlock); - if (find_device(dev)) { - spin_unlock(&dev_domain_list_spinlock); - kfree(owner); - return -EEXIST; - } - owner->domain = domain; - owner->dev = dev; - list_add_tail(&owner->list, &dev_domain_list); - spin_unlock(&dev_domain_list_spinlock); - return 0; -} -EXPORT_SYMBOL_GPL(xen_register_device_domain_owner); - -int xen_unregister_device_domain_owner(struct pci_dev *dev) -{ - struct xen_device_domain_owner *owner; - - spin_lock(&dev_domain_list_spinlock); - owner = find_device(dev); - if (!owner) { - spin_unlock(&dev_domain_list_spinlock); - return -ENODEV; - } - list_del(&owner->list); - spin_unlock(&dev_domain_list_spinlock); - kfree(owner); - return 0; -} -EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner); -#endif /* CONFIG_XEN_DOM0 */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 95d970359e17..30c6e986a6cd 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,25 +31,10 @@ EXPORT_SYMBOL_GPL(hypercall_page); * Pointer to the xen_vcpu_info structure or * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info - * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point - * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to - * acknowledge pending events. - * Also more subtly it is used by the patched version of irq enable/disable - * e.g. xen_irq_enable_direct and xen_iret in PV mode. - * - * The desire to be able to do those mask/unmask operations as a single - * instruction by using the per-cpu offset held in %gs is the real reason - * vcpu info is in a per-cpu pointer and the original reason for this - * hypercall. - * + * but during boot it is switched to point to xen_vcpu_info. + * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events. */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); - -/* - * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info - * hypercall. This can be used both in PV and PVHVM mode. The structure - * overrides the default per_cpu(xen_vcpu, cpu) value. - */ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ @@ -84,21 +69,6 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; -/* - * Flag to determine whether vcpu info placement is available on all - * VCPUs. We assume it is to start with, and then set it to zero on - * the first failure. This is because it can succeed on some VCPUs - * and not others, since it can involve hypervisor memory allocation, - * or because the guest failed to guarantee all the appropriate - * constraints on all VCPUs (ie buffer can't cross a page boundary). - * - * Note that any particular CPU may be using a placed vcpu structure, - * but we can only optimise if the all are. - * - * 0: not available, 1: available - */ -int xen_have_vcpu_info_placement = 1; - static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); @@ -124,10 +94,8 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), return rc >= 0 ? 0 : rc; } -static int xen_vcpu_setup_restore(int cpu) +static void xen_vcpu_setup_restore(int cpu) { - int rc = 0; - /* Any per_cpu(xen_vcpu) is stale, so reset it */ xen_vcpu_info_reset(cpu); @@ -136,11 +104,8 @@ static int xen_vcpu_setup_restore(int cpu) * be handled by hotplug. */ if (xen_pv_domain() || - (xen_hvm_domain() && cpu_online(cpu))) { - rc = xen_vcpu_setup(cpu); - } - - return rc; + (xen_hvm_domain() && cpu_online(cpu))) + xen_vcpu_setup(cpu); } /* @@ -150,7 +115,7 @@ static int xen_vcpu_setup_restore(int cpu) */ void xen_vcpu_restore(void) { - int cpu, rc; + int cpu; for_each_possible_cpu(cpu) { bool other_cpu = (cpu != smp_processor_id()); @@ -170,20 +135,9 @@ void xen_vcpu_restore(void) if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_runstate_info(cpu); - rc = xen_vcpu_setup_restore(cpu); - if (rc) - pr_emerg_once("vcpu restore failed for cpu=%d err=%d. " - "System will hang.\n", cpu, rc); - /* - * In case xen_vcpu_setup_restore() fails, do not bring up the - * VCPU. This helps us avoid the resulting OOPS when the VCPU - * accesses pvclock_vcpu_time via xen_vcpu (which is NULL.) - * Note that this does not improve the situation much -- now the - * VM hangs instead of OOPSing -- with the VCPUs that did not - * fail, spinning in stop_machine(), waiting for the failed - * VCPUs to come up. - */ - if (other_cpu && is_up && (rc == 0) && + xen_vcpu_setup_restore(cpu); + + if (other_cpu && is_up && HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL)) BUG(); } @@ -200,7 +154,7 @@ void xen_vcpu_info_reset(int cpu) } } -int xen_vcpu_setup(int cpu) +void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; int err; @@ -221,44 +175,26 @@ int xen_vcpu_setup(int cpu) */ if (xen_hvm_domain()) { if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu)) - return 0; + return; } - if (xen_have_vcpu_info_placement) { - vcpup = &per_cpu(xen_vcpu_info, cpu); - info.mfn = arbitrary_virt_to_mfn(vcpup); - info.offset = offset_in_page(vcpup); - - /* - * Check to see if the hypervisor will put the vcpu_info - * structure where we want it, which allows direct access via - * a percpu-variable. - * N.B. This hypercall can _only_ be called once per CPU. - * Subsequent calls will error out with -EINVAL. This is due to - * the fact that hypervisor has no unregister variant and this - * hypercall does not allow to over-write info.mfn and - * info.offset. - */ - err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, - xen_vcpu_nr(cpu), &info); - - if (err) { - pr_warn_once("register_vcpu_info failed: cpu=%d err=%d\n", - cpu, err); - xen_have_vcpu_info_placement = 0; - } else { - /* - * This cpu is using the registered vcpu info, even if - * later ones fail to. - */ - per_cpu(xen_vcpu, cpu) = vcpup; - } - } + vcpup = &per_cpu(xen_vcpu_info, cpu); + info.mfn = arbitrary_virt_to_mfn(vcpup); + info.offset = offset_in_page(vcpup); - if (!xen_have_vcpu_info_placement) - xen_vcpu_info_reset(cpu); + /* + * N.B. This hypercall can _only_ be called once per CPU. + * Subsequent calls will error out with -EINVAL. This is due to + * the fact that hypervisor has no unregister variant and this + * hypercall does not allow to over-write info.mfn and + * info.offset. + */ + err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu), + &info); + if (err) + panic("register_vcpu_info failed: cpu=%d err=%d\n", cpu, err); - return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0); + per_cpu(xen_vcpu, cpu) = vcpup; } void __init xen_banner(void) diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index e68ea5f4ad1c..42300941ec29 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -163,9 +163,9 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); else per_cpu(xen_vcpu_id, cpu) = cpu; - rc = xen_vcpu_setup(cpu); - if (rc || !xen_have_vector_callback) - return rc; + xen_vcpu_setup(cpu); + if (!xen_have_vector_callback) + return 0; if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 4f63117f09bb..5004feb16783 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -27,7 +27,6 @@ #include <linux/export.h> #include <linux/mm.h> #include <linux/page-flags.h> -#include <linux/highmem.h> #include <linux/pci.h> #include <linux/gfp.h> #include <linux/edd.h> @@ -993,31 +992,13 @@ void __init xen_setup_vcpu_info_placement(void) for_each_possible_cpu(cpu) { /* Set up direct vCPU id mapping for PV guests. */ per_cpu(xen_vcpu_id, cpu) = cpu; - - /* - * xen_vcpu_setup(cpu) can fail -- in which case it - * falls back to the shared_info version for cpus - * where xen_vcpu_nr(cpu) < MAX_VIRT_CPUS. - * - * xen_cpu_up_prepare_pv() handles the rest by failing - * them in hotplug. - */ - (void) xen_vcpu_setup(cpu); + xen_vcpu_setup(cpu); } - /* - * xen_vcpu_setup managed to place the vcpu_info within the - * percpu area for all cpus, so make use of it. - */ - if (xen_have_vcpu_info_placement) { - pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); - pv_ops.irq.irq_disable = - __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); - pv_ops.irq.irq_enable = - __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); - pv_ops.mmu.read_cr2 = - __PV_IS_CALLEE_SAVE(xen_read_cr2_direct); - } + pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); + pv_ops.irq.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); + pv_ops.irq.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); + pv_ops.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2_direct); } static const struct pv_info xen_info __initconst = { @@ -1247,12 +1228,6 @@ asmlinkage __visible void __init xen_start_kernel(void) __supported_pte_mask &= ~_PAGE_GLOBAL; __default_kernel_pte_mask &= ~_PAGE_GLOBAL; - /* - * Prevent page tables from being allocated in highmem, even - * if CONFIG_HIGHPTE is enabled. - */ - __userpte_alloc_gfp &= ~__GFP_HIGHMEM; - /* Get mfn list */ xen_build_dynamic_phys_to_machine(); diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 4fe387e520af..06c3c2fb4b06 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -24,60 +24,6 @@ noinstr void xen_force_evtchn_callback(void) (void)HYPERVISOR_xen_version(0, NULL); } -asmlinkage __visible noinstr unsigned long xen_save_fl(void) -{ - struct vcpu_info *vcpu; - unsigned long flags; - - vcpu = this_cpu_read(xen_vcpu); - - /* flag has opposite sense of mask */ - flags = !vcpu->evtchn_upcall_mask; - - /* convert to IF type flag - -0 -> 0x00000000 - -1 -> 0xffffffff - */ - return (-flags) & X86_EFLAGS_IF; -} -__PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl, ".noinstr.text"); - -asmlinkage __visible noinstr void xen_irq_disable(void) -{ - /* There's a one instruction preempt window here. We need to - make sure we're don't switch CPUs between getting the vcpu - pointer and updating the mask. */ - preempt_disable(); - this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1; - preempt_enable_no_resched(); -} -__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable, ".noinstr.text"); - -asmlinkage __visible noinstr void xen_irq_enable(void) -{ - struct vcpu_info *vcpu; - - /* - * We may be preempted as soon as vcpu->evtchn_upcall_mask is - * cleared, so disable preemption to ensure we check for - * events on the VCPU we are still running on. - */ - preempt_disable(); - - vcpu = this_cpu_read(xen_vcpu); - vcpu->evtchn_upcall_mask = 0; - - /* Doesn't matter if we get preempted here, because any - pending event will get dealt with anyway. */ - - barrier(); /* unmask then check (avoid races) */ - if (unlikely(vcpu->evtchn_upcall_pending)) - xen_force_evtchn_callback(); - - preempt_enable(); -} -__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable, ".noinstr.text"); - static void xen_safe_halt(void) { /* Blocking includes an implicit local_irq_enable(). */ @@ -96,10 +42,10 @@ static void xen_halt(void) static const typeof(pv_ops) xen_irq_ops __initconst = { .irq = { - - .save_fl = PV_CALLEE_SAVE(xen_save_fl), - .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), - .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), + /* Initial interrupt flag handling only called while interrupts off. */ + .save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0), + .irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop), + .irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG), .safe_halt = xen_safe_halt, .halt = xen_halt, diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index cdbf4822f431..00354866921b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -41,7 +41,6 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ #include <linux/sched/mm.h> -#include <linux/highmem.h> #include <linux/debugfs.h> #include <linux/bug.h> #include <linux/vmalloc.h> @@ -86,8 +85,10 @@ #include "mmu.h" #include "debugfs.h" +#ifdef CONFIG_X86_VSYSCALL_EMULATION /* l3 pud for userspace vsyscall mapping */ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; +#endif /* * Protects atomic reservation decrease/increase against concurrent increases. @@ -241,9 +242,11 @@ static void xen_set_pmd(pmd_t *ptr, pmd_t val) * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. */ -void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) +void __init set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) { - set_pte_vaddr(vaddr, mfn_pte(mfn, flags)); + if (HYPERVISOR_update_va_mapping(vaddr, mfn_pte(mfn, flags), + UVMF_INVLPG)) + BUG(); } static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) @@ -789,7 +792,9 @@ static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, static void __init xen_after_bootmem(void) { static_branch_enable(&xen_struct_pages_ready); +#ifdef CONFIG_X86_VSYSCALL_EMULATION SetPagePinned(virt_to_page(level3_user_vsyscall)); +#endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1192,6 +1197,13 @@ static void __init xen_pagetable_p2m_setup(void) static void __init xen_pagetable_init(void) { + /* + * The majority of further PTE writes is to pagetables already + * announced as such to Xen. Hence it is more efficient to use + * hypercalls for these updates. + */ + pv_ops.mmu.set_pte = __xen_set_pte; + paging_init(); xen_post_allocator_init(); @@ -1421,10 +1433,18 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) * * Many of these PTE updates are done on unpinned and writable pages * and doing a hypercall for these is unnecessary and expensive. At - * this point it is not possible to tell if a page is pinned or not, - * so always write the PTE directly and rely on Xen trapping and + * this point it is rarely possible to tell if a page is pinned, so + * mostly write the PTE directly and rely on Xen trapping and * emulating any updates as necessary. */ +static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +{ + if (unlikely(is_early_ioremap_ptep(ptep))) + __xen_set_pte(ptep, pte); + else + native_set_pte(ptep, pte); +} + __visible pte_t xen_make_pte_init(pteval_t pte) { unsigned long pfn; @@ -1446,11 +1466,6 @@ __visible pte_t xen_make_pte_init(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); -static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) -{ - __xen_set_pte(ptep, pte); -} - /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1750,7 +1765,6 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(init_top_pgt, PAGE_KERNEL_RO); set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); @@ -1767,6 +1781,13 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Unpin Xen-provided one */ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); +#ifdef CONFIG_X86_VSYSCALL_EMULATION + /* Pin user vsyscall L3 */ + set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, + PFN_DOWN(__pa_symbol(level3_user_vsyscall))); +#endif + /* * At this stage there can be no user pgd, and no page structure to * attach it to, so make sure we just set kernel pgd. @@ -1999,6 +2020,7 @@ static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) { pte_t pte; + unsigned long vaddr; phys >>= PAGE_SHIFT; @@ -2039,15 +2061,15 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) break; } - __native_set_fixmap(idx, pte); + vaddr = __fix_to_virt(idx); + if (HYPERVISOR_update_va_mapping(vaddr, pte, UVMF_INVLPG)) + BUG(); #ifdef CONFIG_X86_VSYSCALL_EMULATION /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ - if (idx == VSYSCALL_PAGE) { - unsigned long vaddr = __fix_to_virt(idx); + if (idx == VSYSCALL_PAGE) set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); - } #endif } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index f387fc7e5250..af216feb63d9 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -306,10 +306,6 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn) BUG(); } - /* Update kernel mapping, but not for highmem. */ - if (pfn >= PFN_UP(__pa(high_memory - 1))) - return; - if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT), mfn_pte(mfn, PAGE_KERNEL), 0)) { WARN(1, "Failed to update kernel mapping for mfn=%ld pfn=%ld\n", @@ -429,13 +425,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk( } /* - * If the PFNs are currently mapped, the VA mapping also needs - * to be updated to be 1:1. + * If the PFNs are currently mapped, their VA mappings need to be + * zapped. */ for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) (void)HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), - mfn_pte(pfn, PAGE_KERNEL_IO), 0); + native_make_pte(0), 0); return remap_pfn; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index c1b2f764b29a..c3e1f9a7d43a 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -121,34 +121,10 @@ int xen_smp_intr_init(unsigned int cpu) void __init xen_smp_cpus_done(unsigned int max_cpus) { - int cpu, rc, count = 0; - if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); else calculate_max_logical_packages(); - - if (xen_have_vcpu_info_placement) - return; - - for_each_online_cpu(cpu) { - if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) - continue; - - rc = remove_cpu(cpu); - - if (rc == 0) { - /* - * Reset vcpu_info so this cpu cannot be onlined again. - */ - xen_vcpu_info_reset(cpu); - count++; - } else { - pr_warn("%s: failed to bring CPU %d down, error %d\n", - __func__, cpu, rc); - } - } - WARN(count, "%s: brought %d CPUs offline\n", __func__, count); } void xen_smp_send_reschedule(int cpu) @@ -268,20 +244,16 @@ void xen_send_IPI_allbutself(int vector) static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) { - irq_enter(); generic_smp_call_function_interrupt(); inc_irq_stat(irq_call_count); - irq_exit(); return IRQ_HANDLED; } static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id) { - irq_enter(); generic_smp_call_function_single_interrupt(); inc_irq_stat(irq_call_count); - irq_exit(); return IRQ_HANDLED; } diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 7ed56c6075b0..9e55bcbfcd33 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -458,10 +458,8 @@ static void xen_pv_stop_other_cpus(int wait) static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id) { - irq_enter(); irq_work_run(); inc_irq_stat(apic_irq_work_irqs); - irq_exit(); return IRQ_HANDLED; } diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 9e27b86a0c31..6a64496edefb 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,13 +45,13 @@ SYM_CODE_START(startup_xen) /* Clear .bss */ xor %eax,%eax - mov $__bss_start, %_ASM_DI - mov $__bss_stop, %_ASM_CX - sub %_ASM_DI, %_ASM_CX - shr $__ASM_SEL(2, 3), %_ASM_CX - rep __ASM_SIZE(stos) + mov $__bss_start, %rdi + mov $__bss_stop, %rcx + sub %rdi, %rcx + shr $3, %rcx + rep stosq - mov %_ASM_SI, xen_start_info + mov %rsi, xen_start_info mov initial_stack(%rip), %rsp /* Set up %gs. diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 8bc8b72a205d..fd0fec6e92f4 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -76,9 +76,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id); bool xen_vcpu_stolen(int vcpu); -extern int xen_have_vcpu_info_placement; - -int xen_vcpu_setup(int cpu); +void xen_vcpu_setup(int cpu); void xen_vcpu_info_reset(int cpu); void xen_setup_vcpu_info_placement(void); diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h index f9a671cbf933..5ee974bf8330 100644 --- a/arch/xtensa/include/asm/syscall.h +++ b/arch/xtensa/include/asm/syscall.h @@ -68,17 +68,6 @@ static inline void syscall_get_arguments(struct task_struct *task, args[i] = regs->areg[reg[i]]; } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS; - unsigned int i; - - for (i = 0; i < 6; ++i) - regs->areg[reg[i]] = args[i]; -} - asmlinkage long xtensa_rt_sigreturn(void); asmlinkage long xtensa_shmat(int, char __user *, int); asmlinkage long xtensa_fadvise64_64(int, int, diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 35a7d47f28cf..4b4dbeb2d612 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -527,7 +527,7 @@ void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) DEFINE_SPINLOCK(die_lock); -void die(const char * str, struct pt_regs * regs, long err) +void __noreturn die(const char * str, struct pt_regs * regs, long err) { static int die_counter; const char *pr = ""; diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 95a74890c7e9..fd6a70635962 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -238,7 +238,7 @@ bad_page_fault: void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) { - extern void die(const char*, struct pt_regs*, long); + extern void __noreturn die(const char*, struct pt_regs*, long); const struct exception_table_entry *entry; /* Are we prepared to handle this kernel fault? */ @@ -257,5 +257,4 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) "address %08lx\n pc = %08lx, ra = %08lx\n", address, regs->pc, regs->areg[0]); die("Oops", regs, sig); - do_exit(sig); } diff --git a/block/blk-core.c b/block/blk-core.c index b043de2baaac..9ee32f85d74e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -809,10 +809,8 @@ noinline_for_stack bool submit_bio_checks(struct bio *bio) if (unlikely(!current->io_context)) create_task_io_context(current, GFP_ATOMIC, q->node); - if (blk_throtl_bio(bio)) { - blkcg_bio_issue_init(bio); + if (blk_throtl_bio(bio)) return false; - } blk_cgroup_bio_start(bio); blkcg_bio_issue_init(bio); diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index c246c425d0d7..b925f3db3ab7 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -104,8 +104,8 @@ static struct kobj_type blk_ia_ranges_ktype = { }; /** - * disk_register_ia_ranges - register with sysfs a set of independent - * access ranges + * disk_register_independent_access_ranges - register with sysfs a set of + * independent access ranges * @disk: Target disk * @new_iars: New set of independent access ranges * diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 4be652fa38e7..ba21449439cc 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -370,9 +370,6 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, bool ret = false; enum hctx_type type; - if (bio_queue_enter(bio)) - return false; - if (e && e->type->ops.bio_merge) { ret = e->type->ops.bio_merge(q, bio, nr_segs); goto out_put; @@ -397,7 +394,6 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, spin_unlock(&ctx->lock); out_put: - blk_queue_exit(q); return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 629cf421417f..3ab34c4f20da 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2495,8 +2495,9 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) return BLK_MAX_REQUEST_COUNT; } -static bool blk_attempt_bio_merge(struct request_queue *q, struct bio *bio, - unsigned int nr_segs, bool *same_queue_rq) +static bool blk_mq_attempt_bio_merge(struct request_queue *q, + struct bio *bio, unsigned int nr_segs, + bool *same_queue_rq) { if (!blk_queue_nomerges(q) && bio_mergeable(bio)) { if (blk_attempt_plug_merge(q, bio, nr_segs, same_queue_rq)) @@ -2520,12 +2521,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, }; struct request *rq; - if (unlikely(bio_queue_enter(bio))) + if (blk_mq_attempt_bio_merge(q, bio, nsegs, same_queue_rq)) return NULL; - if (unlikely(!submit_bio_checks(bio))) - goto put_exit; - if (blk_attempt_bio_merge(q, bio, nsegs, same_queue_rq)) - goto put_exit; rq_qos_throttle(q, bio); @@ -2542,26 +2539,44 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); -put_exit: - blk_queue_exit(q); + return NULL; } +static inline bool blk_mq_can_use_cached_rq(struct request *rq, + struct bio *bio) +{ + if (blk_mq_get_hctx_type(bio->bi_opf) != rq->mq_hctx->type) + return false; + + if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + return false; + + return true; +} + static inline struct request *blk_mq_get_request(struct request_queue *q, struct blk_plug *plug, struct bio *bio, unsigned int nsegs, bool *same_queue_rq) { + struct request *rq; + bool checked = false; + if (plug) { - struct request *rq; rq = rq_list_peek(&plug->cached_rq); if (rq && rq->q == q) { if (unlikely(!submit_bio_checks(bio))) return NULL; - if (blk_attempt_bio_merge(q, bio, nsegs, same_queue_rq)) + if (blk_mq_attempt_bio_merge(q, bio, nsegs, + same_queue_rq)) return NULL; + checked = true; + if (!blk_mq_can_use_cached_rq(rq, bio)) + goto fallback; + rq->cmd_flags = bio->bi_opf; plug->cached_rq = rq_list_next(rq); INIT_LIST_HEAD(&rq->queuelist); rq_qos_throttle(q, bio); @@ -2569,7 +2584,15 @@ static inline struct request *blk_mq_get_request(struct request_queue *q, } } - return blk_mq_get_new_requests(q, plug, bio, nsegs, same_queue_rq); +fallback: + if (unlikely(bio_queue_enter(bio))) + return NULL; + if (!checked && !submit_bio_checks(bio)) + return NULL; + rq = blk_mq_get_new_requests(q, plug, bio, nsegs, same_queue_rq); + if (!rq) + blk_queue_exit(q); + return rq; } /** diff --git a/block/blk-mq.h b/block/blk-mq.h index cb0b5482ca5e..8acfa650f575 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -89,15 +89,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue * return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]]; } -/* - * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue - * @q: request queue - * @flags: request command flags - * @ctx: software queue cpu ctx - */ -static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, - unsigned int flags, - struct blk_mq_ctx *ctx) +static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags) { enum hctx_type type = HCTX_TYPE_DEFAULT; @@ -108,8 +100,20 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, type = HCTX_TYPE_POLL; else if ((flags & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; - - return ctx->hctxs[type]; + return type; +} + +/* + * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue + * @q: request queue + * @flags: request command flags + * @ctx: software queue cpu ctx + */ +static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, + unsigned int flags, + struct blk_mq_ctx *ctx) +{ + return ctx->hctxs[blk_mq_get_hctx_type(flags)]; } /* @@ -149,7 +153,7 @@ struct blk_mq_alloc_data { blk_mq_req_flags_t flags; unsigned int shallow_depth; unsigned int cmd_flags; - unsigned int rq_flags; + req_flags_t rq_flags; /* allocate multiple requests/tags in one go */ unsigned int nr_tags; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 1d0c76c18fc5..774ecc598bee 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -429,9 +429,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, op = REQ_OP_ZONE_RESET; /* Invalidate the page cache, including dirty pages. */ + filemap_invalidate_lock(bdev->bd_inode->i_mapping); ret = blkdev_truncate_zone_range(bdev, mode, &zrange); if (ret) - return ret; + goto fail; break; case BLKOPENZONE: op = REQ_OP_ZONE_OPEN; @@ -449,15 +450,9 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, GFP_KERNEL); - /* - * Invalidate the page cache again for zone reset: writes can only be - * direct for zoned devices so concurrent writes would not add any page - * to the page cache after/during reset. The page cache may be filled - * again due to concurrent reads though and dropping the pages for - * these is fine. - */ - if (!ret && cmd == BLKRESETZONE) - ret = blkdev_truncate_zone_range(bdev, mode, &zrange); +fail: + if (cmd == BLKRESETZONE) + filemap_invalidate_unlock(bdev->bd_inode->i_mapping); return ret; } diff --git a/block/genhd.c b/block/genhd.c index ca2fbab1d425..c5392cc24d37 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -394,8 +394,8 @@ static void disk_scan_partitions(struct gendisk *disk) * This function registers the partitioning information in @disk * with the kernel. */ -int device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups) { struct device *ddev = disk_to_dev(disk); @@ -544,7 +544,7 @@ out_disk_release_events: out_free_ext_minor: if (disk->major == BLOCK_EXT_MAJOR) blk_free_ext_minor(disk->first_minor); - return WARN_ON_ONCE(ret); /* keep until all callers handle errors */ + return ret; } EXPORT_SYMBOL(device_add_disk); diff --git a/block/ioctl.c b/block/ioctl.c index d6af0ac97e57..0a1d10ac2e1a 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -113,6 +113,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, uint64_t range[2]; uint64_t start, len; struct request_queue *q = bdev_get_queue(bdev); + struct inode *inode = bdev->bd_inode; int err; if (!(mode & FMODE_WRITE)) @@ -135,12 +136,17 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, if (start + len > bdev_nr_bytes(bdev)) return -EINVAL; + filemap_invalidate_lock(inode->i_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) - return err; + goto fail; - return blkdev_issue_discard(bdev, start >> 9, len >> 9, - GFP_KERNEL, flags); + err = blkdev_issue_discard(bdev, start >> 9, len >> 9, + GFP_KERNEL, flags); + +fail: + filemap_invalidate_unlock(inode->i_mapping); + return err; } static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, @@ -148,6 +154,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, { uint64_t range[2]; uint64_t start, end, len; + struct inode *inode = bdev->bd_inode; int err; if (!(mode & FMODE_WRITE)) @@ -170,12 +177,17 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, return -EINVAL; /* Invalidate the page cache, including dirty pages */ + filemap_invalidate_lock(inode->i_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) - return err; + goto fail; + + err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, + BLKDEV_ZERO_NOUNMAP); - return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, - BLKDEV_ZERO_NOUNMAP); +fail: + filemap_invalidate_unlock(inode->i_mapping); + return err; } static int put_ushort(unsigned short __user *argp, unsigned short val) diff --git a/crypto/algapi.c b/crypto/algapi.c index d379fd91fb7b..a366cb3e8aa1 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -284,6 +284,8 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg) if (larval) list_add(&larval->alg.cra_list, &crypto_alg_list); + else + alg->cra_flags |= CRYPTO_ALG_TESTED; crypto_stats_init(alg); diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 0028b6b51c87..19b33c028f35 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1400,4 +1400,30 @@ bool acpi_storage_d3(struct device *dev) } EXPORT_SYMBOL_GPL(acpi_storage_d3); +/** + * acpi_dev_state_d0 - Tell if the device is in D0 power state + * @dev: Physical device the ACPI power state of which to check + * + * On a system without ACPI, return true. On a system with ACPI, return true if + * the current ACPI power state of the device is D0, or false otherwise. + * + * Note that the power state of a device is not well-defined after it has been + * passed to acpi_device_set_power() and before that function returns, so it is + * not valid to ask for the ACPI power state of the device in that time frame. + * + * This function is intended to be used in a driver's probe or remove + * function. See Documentation/firmware-guide/acpi/low-power-probe.rst for + * more information. + */ +bool acpi_dev_state_d0(struct device *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(dev); + + if (!adev) + return true; + + return adev->power.state == ACPI_STATE_D0; +} +EXPORT_SYMBOL_GPL(acpi_dev_state_d0); + #endif /* CONFIG_PM */ diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index e629e891d1bb..a6366d3f0c78 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -133,7 +133,7 @@ static unsigned int ec_storm_threshold __read_mostly = 8; module_param(ec_storm_threshold, uint, 0644); MODULE_PARM_DESC(ec_storm_threshold, "Maxim false GPE numbers not considered as GPE storm"); -static bool ec_freeze_events __read_mostly = false; +static bool ec_freeze_events __read_mostly; module_param(ec_freeze_events, bool, 0644); MODULE_PARM_DESC(ec_freeze_events, "Disabling event handling during suspend/resume"); @@ -177,7 +177,7 @@ struct acpi_ec *first_ec; EXPORT_SYMBOL(first_ec); static struct acpi_ec *boot_ec; -static bool boot_ec_is_ecdt = false; +static bool boot_ec_is_ecdt; static struct workqueue_struct *ec_wq; static struct workqueue_struct *ec_query_wq; @@ -2152,6 +2152,13 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = { DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Yoga 3rd"), }, }, + { + .ident = "HP ZHAN 66 Pro", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"), + }, + }, { }, }; diff --git a/drivers/acpi/pmic/intel_pmic.c b/drivers/acpi/pmic/intel_pmic.c index a371f273f99d..9cde299eba88 100644 --- a/drivers/acpi/pmic/intel_pmic.c +++ b/drivers/acpi/pmic/intel_pmic.c @@ -211,31 +211,36 @@ static acpi_status intel_pmic_regs_handler(u32 function, void *handler_context, void *region_context) { struct intel_pmic_opregion *opregion = region_context; - int result = 0; + int result = -EINVAL; + + if (function == ACPI_WRITE) { + switch (address) { + case 0: + return AE_OK; + case 1: + opregion->ctx.addr |= (*value64 & 0xff) << 8; + return AE_OK; + case 2: + opregion->ctx.addr |= *value64 & 0xff; + return AE_OK; + case 3: + opregion->ctx.val = *value64 & 0xff; + return AE_OK; + case 4: + if (*value64) { + result = regmap_write(opregion->regmap, opregion->ctx.addr, + opregion->ctx.val); + } else { + result = regmap_read(opregion->regmap, opregion->ctx.addr, + &opregion->ctx.val); + } + opregion->ctx.addr = 0; + } + } - switch (address) { - case 0: - return AE_OK; - case 1: - opregion->ctx.addr |= (*value64 & 0xff) << 8; - return AE_OK; - case 2: - opregion->ctx.addr |= *value64 & 0xff; + if (function == ACPI_READ && address == 3) { + *value64 = opregion->ctx.val; return AE_OK; - case 3: - opregion->ctx.val = *value64 & 0xff; - return AE_OK; - case 4: - if (*value64) { - result = regmap_write(opregion->regmap, opregion->ctx.addr, - opregion->ctx.val); - } else { - result = regmap_read(opregion->regmap, opregion->ctx.addr, - &opregion->ctx.val); - if (result == 0) - *value64 = opregion->ctx.val; - } - memset(&opregion->ctx, 0x00, sizeof(opregion->ctx)); } if (result < 0) { diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 112256154880..5dcb02ededbc 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -757,13 +757,11 @@ int acpi_disable_wakeup_device_power(struct acpi_device *dev) mutex_lock(&acpi_device_lock); - if (dev->wakeup.prepare_count > 1) { - dev->wakeup.prepare_count--; + /* Do nothing if wakeup power has not been enabled for this device. */ + if (dev->wakeup.prepare_count <= 0) goto out; - } - /* Do nothing if wakeup power has not been enabled for this device. */ - if (!dev->wakeup.prepare_count) + if (--dev->wakeup.prepare_count > 0) goto out; err = acpi_device_sleep_wake(dev, 0, 0, 0); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dce2c291b982..a50f1967c73d 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1017,6 +1017,7 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state) static void acpi_bus_get_power_flags(struct acpi_device *device) { + unsigned long long dsc = ACPI_STATE_D0; u32 i; /* Presence of _PS0|_PR0 indicates 'power manageable' */ @@ -1038,6 +1039,9 @@ static void acpi_bus_get_power_flags(struct acpi_device *device) if (acpi_has_method(device->handle, "_DSW")) device->power.flags.dsw_present = 1; + acpi_evaluate_integer(device->handle, "_DSC", NULL, &dsc); + device->power.state_for_enumeration = dsc; + /* * Enumerate supported power management states */ diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 33474fd96991..068e393ea0c6 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -115,7 +115,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { */ { .callback = video_detect_force_vendor, - .ident = "X360", + /* X360 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, "X360"), @@ -124,7 +124,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_vendor, - .ident = "Asus UL30VT", + /* Asus UL30VT */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "UL30VT"), @@ -132,7 +132,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_vendor, - .ident = "Asus UL30A", + /* Asus UL30A */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"), @@ -140,7 +140,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_vendor, - .ident = "GIGABYTE GB-BXBT-2807", + /* GIGABYTE GB-BXBT-2807 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), DMI_MATCH(DMI_PRODUCT_NAME, "GB-BXBT-2807"), @@ -148,12 +148,20 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_vendor, - .ident = "Sony VPCEH3U1E", + /* Sony VPCEH3U1E */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), DMI_MATCH(DMI_PRODUCT_NAME, "VPCEH3U1E"), }, }, + { + .callback = video_detect_force_vendor, + /* Xiaomi Mi Pad 2 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Xiaomi Inc"), + DMI_MATCH(DMI_PRODUCT_NAME, "Mipad2"), + }, + }, /* * These models have a working acpi_video backlight control, and using @@ -164,7 +172,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { */ { .callback = video_detect_force_video, - .ident = "ThinkPad T420", + /* ThinkPad T420 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T420"), @@ -172,7 +180,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_video, - .ident = "ThinkPad T520", + /* ThinkPad T520 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T520"), @@ -180,7 +188,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_video, - .ident = "ThinkPad X201s", + /* ThinkPad X201s */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"), @@ -188,7 +196,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_video, - .ident = "ThinkPad X201T", + /* ThinkPad X201T */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), @@ -199,7 +207,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugs.freedesktop.org/show_bug.cgi?id=81515 */ .callback = video_detect_force_video, - .ident = "HP ENVY 15 Notebook", + /* HP ENVY 15 Notebook */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY 15 Notebook PC"), @@ -207,7 +215,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_video, - .ident = "SAMSUNG 870Z5E/880Z5E/680Z5E", + /* SAMSUNG 870Z5E/880Z5E/680Z5E */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, "870Z5E/880Z5E/680Z5E"), @@ -215,7 +223,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_video, - .ident = "SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V", + /* SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, @@ -225,7 +233,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1186097 */ .callback = video_detect_force_video, - .ident = "SAMSUNG 3570R/370R/470R/450R/510R/4450RV", + /* SAMSUNG 3570R/370R/470R/450R/510R/4450RV */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, @@ -235,7 +243,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1557060 */ .callback = video_detect_force_video, - .ident = "SAMSUNG 670Z5E", + /* SAMSUNG 670Z5E */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, "670Z5E"), @@ -244,7 +252,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1094948 */ .callback = video_detect_force_video, - .ident = "SAMSUNG 730U3E/740U3E", + /* SAMSUNG 730U3E/740U3E */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, "730U3E/740U3E"), @@ -253,7 +261,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugs.freedesktop.org/show_bug.cgi?id=87286 */ .callback = video_detect_force_video, - .ident = "SAMSUNG 900X3C/900X3D/900X3E/900X4C/900X4D", + /* SAMSUNG 900X3C/900X3D/900X3E/900X4C/900X4D */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, @@ -263,7 +271,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1272633 */ .callback = video_detect_force_video, - .ident = "Dell XPS14 L421X", + /* Dell XPS14 L421X */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "XPS L421X"), @@ -272,7 +280,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1163574 */ .callback = video_detect_force_video, - .ident = "Dell XPS15 L521X", + /* Dell XPS15 L521X */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "XPS L521X"), @@ -281,7 +289,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.kernel.org/show_bug.cgi?id=108971 */ .callback = video_detect_force_video, - .ident = "SAMSUNG 530U4E/540U4E", + /* SAMSUNG 530U4E/540U4E */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, "530U4E/540U4E"), @@ -290,7 +298,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { /* https://bugs.launchpad.net/bugs/1894667 */ { .callback = video_detect_force_video, - .ident = "HP 635 Notebook", + /* HP 635 Notebook */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), DMI_MATCH(DMI_PRODUCT_NAME, "HP 635 Notebook PC"), @@ -301,7 +309,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1201530 */ .callback = video_detect_force_native, - .ident = "Lenovo Ideapad S405", + /* Lenovo Ideapad S405 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "Lenovo IdeaPad S405"), @@ -310,7 +318,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1187004 */ .callback = video_detect_force_native, - .ident = "Lenovo Ideapad Z570", + /* Lenovo Ideapad Z570 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "102434U"), @@ -318,7 +326,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "Lenovo E41-25", + /* Lenovo E41-25 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "81FS"), @@ -326,7 +334,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "Lenovo E41-45", + /* Lenovo E41-45 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82BK"), @@ -335,7 +343,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1217249 */ .callback = video_detect_force_native, - .ident = "Apple MacBook Pro 12,1", + /* Apple MacBook Pro 12,1 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro12,1"), @@ -343,7 +351,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "Dell Vostro V131", + /* Dell Vostro V131 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V131"), @@ -352,7 +360,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.redhat.com/show_bug.cgi?id=1123661 */ .callback = video_detect_force_native, - .ident = "Dell XPS 17 L702X", + /* Dell XPS 17 L702X */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Dell System XPS L702X"), @@ -360,7 +368,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "Dell Precision 7510", + /* Dell Precision 7510 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"), @@ -368,7 +376,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "Acer Aspire 5738z", + /* Acer Aspire 5738z */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"), @@ -378,7 +386,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { { /* https://bugzilla.kernel.org/show_bug.cgi?id=207835 */ .callback = video_detect_force_native, - .ident = "Acer TravelMate 5735Z", + /* Acer TravelMate 5735Z */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 5735Z"), @@ -387,7 +395,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "ASUSTeK COMPUTER INC. GA401", + /* ASUSTeK COMPUTER INC. GA401 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "GA401"), @@ -395,7 +403,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "ASUSTeK COMPUTER INC. GA502", + /* ASUSTeK COMPUTER INC. GA502 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "GA502"), @@ -403,7 +411,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, - .ident = "ASUSTeK COMPUTER INC. GA503", + /* ASUSTeK COMPUTER INC. GA503 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "GA503"), @@ -416,7 +424,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { */ { .callback = video_detect_force_none, - .ident = "Dell OptiPlex 9020M", + /* Dell OptiPlex 9020M */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 9020M"), @@ -424,7 +432,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_none, - .ident = "MSI MS-7721", + /* MSI MS-7721 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MSI"), DMI_MATCH(DMI_PRODUCT_NAME, "MS-7721"), diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 28430c093a7f..8a6835bfd18a 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -131,7 +131,7 @@ const struct attribute_group *ahci_shost_groups[] = { }; EXPORT_SYMBOL_GPL(ahci_shost_groups); -struct attribute *ahci_sdev_attrs[] = { +static struct attribute *ahci_sdev_attrs[] = { &dev_attr_sw_activity.attr, &dev_attr_unload_heads.attr, &dev_attr_ncq_prio_supported.attr, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 3018ca84a3d8..8a0ccb190d76 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2052,8 +2052,19 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page) struct ata_port *ap = dev->link->ap; unsigned int err, i; + if (dev->horkage & ATA_HORKAGE_NO_ID_DEV_LOG) + return false; + if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE)) { - ata_dev_warn(dev, "ATA Identify Device Log not supported\n"); + /* + * IDENTIFY DEVICE data log is defined as mandatory starting + * with ACS-3 (ATA version 10). Warn about the missing log + * for drives which implement this ATA level or above. + */ + if (ata_id_major_version(dev->id) >= 10) + ata_dev_warn(dev, + "ATA Identify Device Log not supported\n"); + dev->horkage |= ATA_HORKAGE_NO_ID_DEV_LOG; return false; } diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index bf9c4b6c5c3d..1d4a6f1e88cd 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -93,6 +93,12 @@ static const unsigned long ata_eh_identify_timeouts[] = { ULONG_MAX, }; +static const unsigned long ata_eh_revalidate_timeouts[] = { + 15000, /* Some drives are slow to read log pages when waking-up */ + 15000, /* combined time till here is enough even for media access */ + ULONG_MAX, +}; + static const unsigned long ata_eh_flush_timeouts[] = { 15000, /* be generous with flush */ 15000, /* ditto */ @@ -129,6 +135,8 @@ static const struct ata_eh_cmd_timeout_ent ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { { .commands = CMDS(ATA_CMD_ID_ATA, ATA_CMD_ID_ATAPI), .timeouts = ata_eh_identify_timeouts, }, + { .commands = CMDS(ATA_CMD_READ_LOG_EXT, ATA_CMD_READ_LOG_DMA_EXT), + .timeouts = ata_eh_revalidate_timeouts, }, { .commands = CMDS(ATA_CMD_READ_NATIVE_MAX, ATA_CMD_READ_NATIVE_MAX_EXT), .timeouts = ata_eh_other_timeouts, }, { .commands = CMDS(ATA_CMD_SET_MAX, ATA_CMD_SET_MAX_EXT), diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c index 8440203e835e..b29d3f1d64b0 100644 --- a/drivers/ata/sata_highbank.c +++ b/drivers/ata/sata_highbank.c @@ -469,10 +469,8 @@ static int ahci_highbank_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "no irq\n"); + if (irq < 0) return irq; - } if (!irq) return -EINVAL; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index ac4dde8fdb8b..f4d0c555de29 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -710,6 +710,7 @@ static void dpm_noirq_resume_devices(pm_message_t state) dev = to_device(dpm_noirq_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_late_early_list); + mutex_unlock(&dpm_list_mtx); if (!is_async(dev)) { @@ -724,8 +725,9 @@ static void dpm_noirq_resume_devices(pm_message_t state) } } - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -849,6 +851,7 @@ void dpm_resume_early(pm_message_t state) dev = to_device(dpm_late_early_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_suspended_list); + mutex_unlock(&dpm_list_mtx); if (!is_async(dev)) { @@ -862,8 +865,10 @@ void dpm_resume_early(pm_message_t state) pm_dev_err(dev, state, " early", error); } } - mutex_lock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1026,7 +1031,12 @@ void dpm_resume(pm_message_t state) } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1104,14 +1114,16 @@ void dpm_complete(pm_message_t state) get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0); - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); @@ -1296,17 +1308,21 @@ static int dpm_noirq_suspend_devices(pm_message_t state) error = device_suspend_noirq(dev); mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, " noirq", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_noirq_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1463,6 +1479,7 @@ int dpm_suspend_late(pm_message_t state) int error = 0; trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); + wake_up_all_idle_cpus(); mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; @@ -1471,23 +1488,28 @@ int dpm_suspend_late(pm_message_t state) struct device *dev = to_device(dpm_suspended_list.prev); get_device(dev); + mutex_unlock(&dpm_list_mtx); error = device_suspend_late(dev); mutex_lock(&dpm_list_mtx); + if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &dpm_late_early_list); if (error) { pm_dev_err(dev, state, " late", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1747,21 +1769,27 @@ int dpm_suspend(pm_message_t state) struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); + mutex_unlock(&dpm_list_mtx); error = device_suspend(dev); mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, "", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_suspended_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1878,6 +1906,7 @@ int dpm_prepare(pm_message_t state) struct device *dev = to_device(dpm_list.next); get_device(dev); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); @@ -1885,21 +1914,23 @@ int dpm_prepare(pm_message_t state) trace_device_pm_callback_end(dev, error); mutex_lock(&dpm_list_mtx); - if (error) { - if (error == -EAGAIN) { - put_device(dev); - error = 0; - continue; - } + + if (!error) { + dev->power.is_prepared = true; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + } else if (error == -EAGAIN) { + error = 0; + } else { dev_info(dev, "not prepared for power transition: code %d\n", error); - put_device(dev); - break; } - dev->power.is_prepared = true; - if (!list_empty(&dev->power.entry)) - list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false); diff --git a/drivers/bus/brcmstb_gisb.c b/drivers/bus/brcmstb_gisb.c index 4c2f7d61cb9b..183d5cc37d42 100644 --- a/drivers/bus/brcmstb_gisb.c +++ b/drivers/bus/brcmstb_gisb.c @@ -485,7 +485,7 @@ static int __init brcmstb_gisb_arb_probe(struct platform_device *pdev) list_add_tail(&gdev->next, &brcmstb_gisb_arb_device_list); #ifdef CONFIG_MIPS - board_be_handler = brcmstb_bus_error_handler; + mips_set_be_handler(brcmstb_bus_error_handler); #endif if (list_is_singular(&brcmstb_gisb_arb_device_list)) { diff --git a/drivers/clk/actions/owl-factor.c b/drivers/clk/actions/owl-factor.c index f15e2621fa18..64f316cf7cfc 100644 --- a/drivers/clk/actions/owl-factor.c +++ b/drivers/clk/actions/owl-factor.c @@ -10,7 +10,6 @@ #include <linux/clk-provider.h> #include <linux/regmap.h> -#include <linux/slab.h> #include "owl-factor.h" diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index bc3be5f3eae1..24dab2312bc6 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -51,6 +51,8 @@ static DEFINE_SPINLOCK(aspeed_g6_clk_lock); static struct clk_hw_onecell_data *aspeed_g6_clk_data; static void __iomem *scu_g6_base; +/* AST2600 revision: A0, A1, A2, etc */ +static u8 soc_rev; /* * Clocks marked with CLK_IS_CRITICAL: @@ -191,9 +193,8 @@ static struct clk_hw *ast2600_calc_pll(const char *name, u32 val) static struct clk_hw *ast2600_calc_apll(const char *name, u32 val) { unsigned int mult, div; - u32 chip_id = readl(scu_g6_base + ASPEED_G6_SILICON_REV); - if (((chip_id & CHIP_REVISION_ID) >> 16) >= 2) { + if (soc_rev >= 2) { if (val & BIT(24)) { /* Pass through mode */ mult = div = 1; @@ -707,7 +708,7 @@ static const u32 ast2600_a1_axi_ahb200_tbl[] = { static void __init aspeed_g6_cc(struct regmap *map) { struct clk_hw *hw; - u32 val, div, divbits, chip_id, axi_div, ahb_div; + u32 val, div, divbits, axi_div, ahb_div; clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, 25000000); @@ -738,8 +739,7 @@ static void __init aspeed_g6_cc(struct regmap *map) axi_div = 2; divbits = (val >> 11) & 0x3; - regmap_read(map, ASPEED_G6_SILICON_REV, &chip_id); - if (chip_id & BIT(16)) { + if (soc_rev >= 1) { if (!divbits) { ahb_div = ast2600_a1_axi_ahb200_tbl[(val >> 8) & 0x3]; if (val & BIT(16)) @@ -784,6 +784,8 @@ static void __init aspeed_g6_cc_init(struct device_node *np) if (!scu_g6_base) return; + soc_rev = (readl(scu_g6_base + ASPEED_G6_SILICON_REV) & CHIP_REVISION_ID) >> 16; + aspeed_g6_clk_data = kzalloc(struct_size(aspeed_g6_clk_data, hws, ASPEED_G6_NUM_CLKS), GFP_KERNEL); if (!aspeed_g6_clk_data) diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c index c04ae0e7e4b4..b9c5f904f535 100644 --- a/drivers/clk/clk-composite.c +++ b/drivers/clk/clk-composite.c @@ -97,6 +97,7 @@ static int clk_composite_determine_rate(struct clk_hw *hw, return ret; req->rate = tmp_req.rate; + req->best_parent_hw = tmp_req.best_parent_hw; req->best_parent_rate = tmp_req.best_parent_rate; return 0; diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c index 57e4597cdf4c..93fa8c9e11be 100644 --- a/drivers/clk/clk-si5351.c +++ b/drivers/clk/clk-si5351.c @@ -1,15 +1,15 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * clk-si5351.c: Silicon Laboratories Si5351A/B/C I2C Clock Generator + * clk-si5351.c: Skyworks / Silicon Labs Si5351A/B/C I2C Clock Generator * * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> * Rabeeh Khoury <rabeeh@solid-run.com> * * References: * [1] "Si5351A/B/C Data Sheet" - * https://www.silabs.com/Support%20Documents/TechnicalDocs/Si5351.pdf - * [2] "Manually Generating an Si5351 Register Map" - * https://www.silabs.com/Support%20Documents/TechnicalDocs/AN619.pdf + * https://www.skyworksinc.com/-/media/Skyworks/SL/documents/public/data-sheets/Si5351-B.pdf + * [2] "AN619: Manually Generating an Si5351 Register Map" + * https://www.skyworksinc.com/-/media/Skyworks/SL/documents/public/application-notes/AN619.pdf */ #include <linux/module.h> diff --git a/drivers/clk/clk-si5351.h b/drivers/clk/clk-si5351.h index 73dc8effc519..e9e2bfdaaedf 100644 --- a/drivers/clk/clk-si5351.h +++ b/drivers/clk/clk-si5351.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * clk-si5351.h: Silicon Laboratories Si5351A/B/C I2C Clock Generator + * clk-si5351.h: Skyworks / Silicon Labs Si5351A/B/C I2C Clock Generator * * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> * Rabeeh Khoury <rabeeh@solid-run.com> diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c index c6d3b1ab3d55..e7be3e54b9be 100644 --- a/drivers/clk/clk-versaclock5.c +++ b/drivers/clk/clk-versaclock5.c @@ -905,7 +905,7 @@ output_error: static const struct of_device_id clk_vc5_of_match[]; -static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) +static int vc5_probe(struct i2c_client *client) { unsigned int oe, sd, src_mask = 0, src_val = 0; struct vc5_driver_data *vc5; @@ -1244,7 +1244,7 @@ static struct i2c_driver vc5_driver = { .pm = &vc5_pm_ops, .of_match_table = clk_vc5_of_match, }, - .probe = vc5_probe, + .probe_new = vc5_probe, .remove = vc5_remove, .id_table = vc5_id, }; diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index 819949973db1..7d220a01de1f 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -391,11 +391,11 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, #define imx8m_clk_hw_composite(name, parent_names, reg) \ _imx8m_clk_hw_composite(name, parent_names, reg, \ - IMX_COMPOSITE_CORE, IMX_COMPOSITE_CLK_FLAGS_DEFAULT) + 0, IMX_COMPOSITE_CLK_FLAGS_DEFAULT) #define imx8m_clk_hw_composite_critical(name, parent_names, reg) \ _imx8m_clk_hw_composite(name, parent_names, reg, \ - IMX_COMPOSITE_CORE, IMX_COMPOSITE_CLK_FLAGS_CRITICAL) + 0, IMX_COMPOSITE_CLK_FLAGS_CRITICAL) #define imx8m_clk_hw_composite_bus(name, parent_names, reg) \ _imx8m_clk_hw_composite(name, parent_names, reg, \ diff --git a/drivers/clk/ingenic/cgu.c b/drivers/clk/ingenic/cgu.c index 266c7595d330..af31633a8862 100644 --- a/drivers/clk/ingenic/cgu.c +++ b/drivers/clk/ingenic/cgu.c @@ -453,15 +453,15 @@ ingenic_clk_calc_div(struct clk_hw *hw, } /* Impose hardware constraints */ - div = min_t(unsigned, div, 1 << clk_info->div.bits); - div = max_t(unsigned, div, 1); + div = clamp_t(unsigned int, div, clk_info->div.div, + clk_info->div.div << clk_info->div.bits); /* * If the divider value itself must be divided before being written to * the divider register, we must ensure we don't have any bits set that * would be lost as a result of doing so. */ - div /= clk_info->div.div; + div = DIV_ROUND_UP(div, clk_info->div.div); div *= clk_info->div.div; return div; diff --git a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c index 0e2ac0a30aa0..4ab312eb26a5 100644 --- a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c @@ -10,8 +10,6 @@ #include <linux/clk-provider.h> #include <linux/platform_device.h> -#include <dt-bindings/clock/mt8195-clk.h> - static const struct mtk_gate_regs imp_iic_wrap_cg_regs = { .set_ofs = 0xe08, .clr_ofs = 0xe04, diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index 3c3a7ff04562..9b1674b28d45 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -2937,20 +2937,6 @@ static struct clk_branch gcc_smmu_aggre0_ahb_clk = { }, }; -static struct clk_branch gcc_aggre1_pnoc_ahb_clk = { - .halt_reg = 0x82014, - .clkr = { - .enable_reg = 0x82014, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_aggre1_pnoc_ahb_clk", - .parent_names = (const char *[]){ "periph_noc_clk_src" }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_aggre2_ufs_axi_clk = { .halt_reg = 0x83014, .clkr = { @@ -3474,7 +3460,6 @@ static struct clk_regmap *gcc_msm8996_clocks[] = { [GCC_AGGRE0_CNOC_AHB_CLK] = &gcc_aggre0_cnoc_ahb_clk.clkr, [GCC_SMMU_AGGRE0_AXI_CLK] = &gcc_smmu_aggre0_axi_clk.clkr, [GCC_SMMU_AGGRE0_AHB_CLK] = &gcc_smmu_aggre0_ahb_clk.clkr, - [GCC_AGGRE1_PNOC_AHB_CLK] = &gcc_aggre1_pnoc_ahb_clk.clkr, [GCC_AGGRE2_UFS_AXI_CLK] = &gcc_aggre2_ufs_axi_clk.clkr, [GCC_AGGRE2_USB3_AXI_CLK] = &gcc_aggre2_usb3_axi_clk.clkr, [GCC_QSPI_AHB_CLK] = &gcc_qspi_ahb_clk.clkr, diff --git a/drivers/clk/rockchip/Kconfig b/drivers/clk/rockchip/Kconfig index 2dfd6a383393..3067bdb6e119 100644 --- a/drivers/clk/rockchip/Kconfig +++ b/drivers/clk/rockchip/Kconfig @@ -80,14 +80,14 @@ config CLK_RK3368 Build the driver for RK3368 Clock Driver. config CLK_RK3399 - tristate "Rockchip RK3399 clock controller support" + bool "Rockchip RK3399 clock controller support" depends on ARM64 || COMPILE_TEST default y help Build the driver for RK3399 Clock Driver. config CLK_RK3568 - tristate "Rockchip RK3568 clock controller support" + bool "Rockchip RK3568 clock controller support" depends on ARM64 || COMPILE_TEST default y help diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 7924598747b6..306910a3a0d3 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -1630,7 +1630,6 @@ static const struct of_device_id clk_rk3399_match_table[] = { }, { } }; -MODULE_DEVICE_TABLE(of, clk_rk3399_match_table); static int __init clk_rk3399_probe(struct platform_device *pdev) { @@ -1656,7 +1655,4 @@ static struct platform_driver clk_rk3399_driver = { .suppress_bind_attrs = true, }, }; -module_platform_driver_probe(clk_rk3399_driver, clk_rk3399_probe); - -MODULE_DESCRIPTION("Rockchip RK3399 Clock Driver"); -MODULE_LICENSE("GPL"); +builtin_platform_driver_probe(clk_rk3399_driver, clk_rk3399_probe); diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c index 939e7079c334..69a9e8069a48 100644 --- a/drivers/clk/rockchip/clk-rk3568.c +++ b/drivers/clk/rockchip/clk-rk3568.c @@ -1693,7 +1693,6 @@ static const struct of_device_id clk_rk3568_match_table[] = { }, { } }; -MODULE_DEVICE_TABLE(of, clk_rk3568_match_table); static int __init clk_rk3568_probe(struct platform_device *pdev) { @@ -1719,7 +1718,4 @@ static struct platform_driver clk_rk3568_driver = { .suppress_bind_attrs = true, }, }; -module_platform_driver_probe(clk_rk3568_driver, clk_rk3568_probe); - -MODULE_DESCRIPTION("Rockchip RK3568 Clock Driver"); -MODULE_LICENSE("GPL"); +builtin_platform_driver_probe(clk_rk3568_driver, clk_rk3568_probe); diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c index 12380236d7ab..46c66fac48e6 100644 --- a/drivers/clk/uniphier/clk-uniphier-core.c +++ b/drivers/clk/uniphier/clk-uniphier-core.c @@ -132,6 +132,10 @@ static const struct of_device_id uniphier_clk_match[] = { .compatible = "socionext,uniphier-pxs3-clock", .data = uniphier_pxs3_sys_clk_data, }, + { + .compatible = "socionext,uniphier-nx1-clock", + .data = uniphier_nx1_sys_clk_data, + }, /* Media I/O clock, SD clock */ { .compatible = "socionext,uniphier-ld4-mio-clock", @@ -165,6 +169,10 @@ static const struct of_device_id uniphier_clk_match[] = { .compatible = "socionext,uniphier-pxs3-sd-clock", .data = uniphier_pro5_sd_clk_data, }, + { + .compatible = "socionext,uniphier-nx1-sd-clock", + .data = uniphier_pro5_sd_clk_data, + }, /* Peripheral clock */ { .compatible = "socionext,uniphier-ld4-peri-clock", @@ -198,6 +206,15 @@ static const struct of_device_id uniphier_clk_match[] = { .compatible = "socionext,uniphier-pxs3-peri-clock", .data = uniphier_pro4_peri_clk_data, }, + { + .compatible = "socionext,uniphier-nx1-peri-clock", + .data = uniphier_pro4_peri_clk_data, + }, + /* SoC-glue clock */ + { + .compatible = "socionext,uniphier-pro4-sg-clock", + .data = uniphier_pro4_sg_clk_data, + }, { /* sentinel */ } }; diff --git a/drivers/clk/uniphier/clk-uniphier-sys.c b/drivers/clk/uniphier/clk-uniphier-sys.c index 32b301724183..0180470b24db 100644 --- a/drivers/clk/uniphier/clk-uniphier-sys.c +++ b/drivers/clk/uniphier/clk-uniphier-sys.c @@ -20,6 +20,10 @@ UNIPHIER_CLK_FACTOR("sd-200m", -1, "spll", 1, 10), \ UNIPHIER_CLK_FACTOR("sd-133m", -1, "spll", 1, 15) +#define UNIPHIER_NX1_SYS_CLK_SD \ + UNIPHIER_CLK_FACTOR("sd-200m", -1, "spll", 1, 4), \ + UNIPHIER_CLK_FACTOR("sd-133m", -1, "spll", 1, 6) + #define UNIPHIER_LD4_SYS_CLK_NAND(idx) \ UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 32), \ UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x2104, 2) @@ -288,6 +292,8 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = { UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x210c, 7), UNIPHIER_CLK_GATE("sata1", 29, NULL, 0x210c, 8), UNIPHIER_CLK_GATE("sata-phy", 30, NULL, 0x210c, 21), + UNIPHIER_LD11_SYS_CLK_AIO(40), + UNIPHIER_LD11_SYS_CLK_EXIV(42), /* CPU gears */ UNIPHIER_CLK_DIV4("cpll", 2, 3, 4, 8), UNIPHIER_CLK_DIV4("spll", 2, 3, 4, 8), @@ -300,3 +306,44 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = { "spll/4", "spll/8", "s2pll/4", "s2pll/8"), { /* sentinel */ } }; + +const struct uniphier_clk_data uniphier_nx1_sys_clk_data[] = { + UNIPHIER_CLK_FACTOR("cpll", -1, "ref", 100, 1), /* ARM: 2500 MHz */ + UNIPHIER_CLK_FACTOR("spll", -1, "ref", 32, 1), /* 800 MHz */ + UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 6), + UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16), + UNIPHIER_NX1_SYS_CLK_SD, + UNIPHIER_CLK_GATE("emmc", 4, NULL, 0x2108, 8), + UNIPHIER_CLK_GATE("ether", 6, NULL, 0x210c, 0), + UNIPHIER_CLK_GATE("usb30-0", 12, NULL, 0x210c, 16), /* =GIO */ + UNIPHIER_CLK_GATE("usb30-1", 13, NULL, 0x210c, 20), /* =GIO1P */ + UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x210c, 24), + UNIPHIER_CLK_GATE("usb30-ssphy0", 17, NULL, 0x210c, 25), + UNIPHIER_CLK_GATE("usb30-ssphy1", 18, NULL, 0x210c, 26), + UNIPHIER_CLK_GATE("pcie", 24, NULL, 0x210c, 8), + UNIPHIER_CLK_GATE("voc", 52, NULL, 0x2110, 0), + UNIPHIER_CLK_GATE("hdmitx", 58, NULL, 0x2110, 8), + /* CPU gears */ + UNIPHIER_CLK_DIV5("cpll", 2, 4, 8, 16, 32), + UNIPHIER_CLK_CPUGEAR("cpu-ca53", 33, 0x8080, 0xf, 5, + "cpll/2", "cpll/4", "cpll/8", "cpll/16", + "cpll/32"), + { /* sentinel */ } +}; + +const struct uniphier_clk_data uniphier_pro4_sg_clk_data[] = { + UNIPHIER_CLK_DIV("gpll", 4), + { + .name = "sata-ref", + .type = UNIPHIER_CLK_TYPE_MUX, + .idx = 0, + .data.mux = { + .parent_names = { "gpll/4", "ref", }, + .num_parents = 2, + .reg = 0x1a28, + .masks = { 0x1, 0x1, }, + .vals = { 0x0, 0x1, }, + }, + }, + { /* sentinel */ } +}; diff --git a/drivers/clk/uniphier/clk-uniphier.h b/drivers/clk/uniphier/clk-uniphier.h index 9e30362e55e1..dea0c7829aee 100644 --- a/drivers/clk/uniphier/clk-uniphier.h +++ b/drivers/clk/uniphier/clk-uniphier.h @@ -119,6 +119,10 @@ struct uniphier_clk_data { UNIPHIER_CLK_DIV2(parent, div0, div1), \ UNIPHIER_CLK_DIV2(parent, div2, div3) +#define UNIPHIER_CLK_DIV5(parent, div0, div1, div2, div3, div4) \ + UNIPHIER_CLK_DIV4(parent, div0, div1, div2, div3), \ + UNIPHIER_CLK_DIV(parent, div4) + struct clk_hw *uniphier_clk_register_cpugear(struct device *dev, struct regmap *regmap, const char *name, @@ -146,9 +150,11 @@ extern const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_ld11_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_ld20_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[]; +extern const struct uniphier_clk_data uniphier_nx1_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_ld4_mio_clk_data[]; extern const struct uniphier_clk_data uniphier_pro5_sd_clk_data[]; extern const struct uniphier_clk_data uniphier_ld4_peri_clk_data[]; extern const struct uniphier_clk_data uniphier_pro4_peri_clk_data[]; +extern const struct uniphier_clk_data uniphier_pro4_sg_clk_data[]; #endif /* __CLK_UNIPHIER_H__ */ diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 349ddbaef796..815df3daae9d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1006,9 +1006,16 @@ static void intel_pstate_hwp_offline(struct cpudata *cpu) */ value &= ~GENMASK_ULL(31, 24); value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached); - WRITE_ONCE(cpu->hwp_req_cached, value); } + /* + * Clear the desired perf field in the cached HWP request value to + * prevent nonzero desired values from being leaked into the active + * mode. + */ + value &= ~HWP_DESIRED_PERF(~0L); + WRITE_ONCE(cpu->hwp_req_cached, value); + value &= ~GENMASK_ULL(31, 0); min_perf = HWP_LOWEST_PERF(READ_ONCE(cpu->hwp_cap_cached)); @@ -1620,6 +1627,9 @@ static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) { unsigned long flags; + if (!boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) + return; + /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); @@ -1642,6 +1652,7 @@ static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); + wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } } @@ -3003,6 +3014,27 @@ static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy) return intel_pstate_cpu_exit(policy); } +static int intel_cpufreq_suspend(struct cpufreq_policy *policy) +{ + intel_pstate_suspend(policy); + + if (hwp_active) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; + u64 value = READ_ONCE(cpu->hwp_req_cached); + + /* + * Clear the desired perf field in MSR_HWP_REQUEST in case + * intel_cpufreq_adjust_perf() is in use and the last value + * written by it may not be suitable. + */ + value &= ~HWP_DESIRED_PERF(~0L); + wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value); + WRITE_ONCE(cpu->hwp_req_cached, value); + } + + return 0; +} + static struct cpufreq_driver intel_cpufreq = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_cpufreq_verify_policy, @@ -3012,7 +3044,7 @@ static struct cpufreq_driver intel_cpufreq = { .exit = intel_cpufreq_cpu_exit, .offline = intel_cpufreq_cpu_offline, .online = intel_pstate_cpu_online, - .suspend = intel_pstate_suspend, + .suspend = intel_cpufreq_suspend, .resume = intel_pstate_resume, .update_limits = intel_pstate_update_limits, .name = "intel_cpufreq", diff --git a/drivers/dax/super.c b/drivers/dax/super.c index fc89e91beea7..b882cf8106ea 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -63,6 +63,24 @@ static int dax_host_hash(const char *host) return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; } +#ifdef CONFIG_BLOCK +#include <linux/blkdev.h> + +int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, + pgoff_t *pgoff) +{ + sector_t start_sect = bdev ? get_start_sect(bdev) : 0; + phys_addr_t phys_off = (start_sect + sector) * 512; + + if (pgoff) + *pgoff = PHYS_PFN(phys_off); + if (phys_off % PAGE_SIZE || size % PAGE_SIZE) + return -EINVAL; + return 0; +} +EXPORT_SYMBOL(bdev_dax_pgoff); + +#if IS_ENABLED(CONFIG_FS_DAX) /** * dax_get_by_host() - temporary lookup mechanism for filesystem-dax * @host: alternate name for the device registered by a dax driver @@ -94,24 +112,6 @@ static struct dax_device *dax_get_by_host(const char *host) return found; } -#ifdef CONFIG_BLOCK -#include <linux/blkdev.h> - -int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, - pgoff_t *pgoff) -{ - sector_t start_sect = bdev ? get_start_sect(bdev) : 0; - phys_addr_t phys_off = (start_sect + sector) * 512; - - if (pgoff) - *pgoff = PHYS_PFN(phys_off); - if (phys_off % PAGE_SIZE || size % PAGE_SIZE) - return -EINVAL; - return 0; -} -EXPORT_SYMBOL(bdev_dax_pgoff); - -#if IS_ENABLED(CONFIG_FS_DAX) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { if (!blk_queue_dax(bdev->bd_disk->queue)) @@ -231,70 +231,6 @@ enum dax_device_flags { DAXDEV_SYNC, }; -static ssize_t write_cache_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct dax_device *dax_dev = dax_get_by_host(dev_name(dev)); - ssize_t rc; - - WARN_ON_ONCE(!dax_dev); - if (!dax_dev) - return -ENXIO; - - rc = sprintf(buf, "%d\n", !!dax_write_cache_enabled(dax_dev)); - put_dax(dax_dev); - return rc; -} - -static ssize_t write_cache_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t len) -{ - bool write_cache; - int rc = strtobool(buf, &write_cache); - struct dax_device *dax_dev = dax_get_by_host(dev_name(dev)); - - WARN_ON_ONCE(!dax_dev); - if (!dax_dev) - return -ENXIO; - - if (rc) - len = rc; - else - dax_write_cache(dax_dev, write_cache); - - put_dax(dax_dev); - return len; -} -static DEVICE_ATTR_RW(write_cache); - -static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n) -{ - struct device *dev = container_of(kobj, typeof(*dev), kobj); - struct dax_device *dax_dev = dax_get_by_host(dev_name(dev)); - - WARN_ON_ONCE(!dax_dev); - if (!dax_dev) - return 0; - -#ifndef CONFIG_ARCH_HAS_PMEM_API - if (a == &dev_attr_write_cache.attr) - return 0; -#endif - return a->mode; -} - -static struct attribute *dax_attributes[] = { - &dev_attr_write_cache.attr, - NULL, -}; - -struct attribute_group dax_attribute_group = { - .name = "dax", - .attrs = dax_attributes, - .is_visible = dax_visible, -}; -EXPORT_SYMBOL_GPL(dax_attribute_group); - /** * dax_direct_access() - translate a device pgoff to an absolute pfn * @dax_dev: a dax_device instance representing the logical memory range diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 06333d430382..7906220d025c 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -1301,6 +1301,32 @@ err_out: } EXPORT_SYMBOL(devfreq_add_governor); +static void devm_devfreq_remove_governor(void *governor) +{ + WARN_ON(devfreq_remove_governor(governor)); +} + +/** + * devm_devfreq_add_governor() - Add devfreq governor + * @dev: device which adds devfreq governor + * @governor: the devfreq governor to be added + * + * This is a resource-managed variant of devfreq_add_governor(). + */ +int devm_devfreq_add_governor(struct device *dev, + struct devfreq_governor *governor) +{ + int err; + + err = devfreq_add_governor(governor); + if (err) + return err; + + return devm_add_action_or_reset(dev, devm_devfreq_remove_governor, + governor); +} +EXPORT_SYMBOL(devm_devfreq_add_governor); + /** * devfreq_remove_governor() - Remove devfreq feature from a device. * @governor: the devfreq governor to be removed diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h index 2d69a0ce6291..002a7d67e39d 100644 --- a/drivers/devfreq/governor.h +++ b/drivers/devfreq/governor.h @@ -84,6 +84,9 @@ void devfreq_update_interval(struct devfreq *devfreq, unsigned int *delay); int devfreq_add_governor(struct devfreq_governor *governor); int devfreq_remove_governor(struct devfreq_governor *governor); +int devm_devfreq_add_governor(struct device *dev, + struct devfreq_governor *governor); + int devfreq_update_status(struct devfreq *devfreq, unsigned long freq); int devfreq_update_target(struct devfreq *devfreq, unsigned long freq); diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index 10661eb2aed8..65ecf17a36f4 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -178,7 +178,6 @@ struct tegra_devfreq_soc_data { struct tegra_devfreq { struct devfreq *devfreq; - struct opp_table *opp_table; struct reset_control *reset; struct clk *clock; @@ -789,6 +788,39 @@ static struct devfreq_governor tegra_devfreq_governor = { .event_handler = tegra_governor_event_handler, }; +static void devm_tegra_devfreq_deinit_hw(void *data) +{ + struct tegra_devfreq *tegra = data; + + reset_control_reset(tegra->reset); + clk_disable_unprepare(tegra->clock); +} + +static int devm_tegra_devfreq_init_hw(struct device *dev, + struct tegra_devfreq *tegra) +{ + int err; + + err = clk_prepare_enable(tegra->clock); + if (err) { + dev_err(dev, "Failed to prepare and enable ACTMON clock\n"); + return err; + } + + err = devm_add_action_or_reset(dev, devm_tegra_devfreq_deinit_hw, + tegra); + if (err) + return err; + + err = reset_control_reset(tegra->reset); + if (err) { + dev_err(dev, "Failed to reset hardware: %d\n", err); + return err; + } + + return err; +} + static int tegra_devfreq_probe(struct platform_device *pdev) { u32 hw_version = BIT(tegra_sku_info.soc_speedo_id); @@ -842,38 +874,26 @@ static int tegra_devfreq_probe(struct platform_device *pdev) return err; } - tegra->opp_table = dev_pm_opp_set_supported_hw(&pdev->dev, - &hw_version, 1); - err = PTR_ERR_OR_ZERO(tegra->opp_table); + err = devm_pm_opp_set_supported_hw(&pdev->dev, &hw_version, 1); if (err) { dev_err(&pdev->dev, "Failed to set supported HW: %d\n", err); return err; } - err = dev_pm_opp_of_add_table_noclk(&pdev->dev, 0); + err = devm_pm_opp_of_add_table_noclk(&pdev->dev, 0); if (err) { dev_err(&pdev->dev, "Failed to add OPP table: %d\n", err); - goto put_hw; - } - - err = clk_prepare_enable(tegra->clock); - if (err) { - dev_err(&pdev->dev, - "Failed to prepare and enable ACTMON clock\n"); - goto remove_table; + return err; } - err = reset_control_reset(tegra->reset); - if (err) { - dev_err(&pdev->dev, "Failed to reset hardware: %d\n", err); - goto disable_clk; - } + err = devm_tegra_devfreq_init_hw(&pdev->dev, tegra); + if (err) + return err; rate = clk_round_rate(tegra->emc_clock, ULONG_MAX); - if (rate < 0) { + if (rate <= 0) { dev_err(&pdev->dev, "Failed to round clock rate: %ld\n", rate); - err = rate; - goto disable_clk; + return rate ?: -EINVAL; } tegra->max_freq = rate / KHZ; @@ -892,52 +912,18 @@ static int tegra_devfreq_probe(struct platform_device *pdev) INIT_DELAYED_WORK(&tegra->cpufreq_update_work, tegra_actmon_delayed_update); - err = devfreq_add_governor(&tegra_devfreq_governor); + err = devm_devfreq_add_governor(&pdev->dev, &tegra_devfreq_governor); if (err) { dev_err(&pdev->dev, "Failed to add governor: %d\n", err); - goto remove_opps; + return err; } tegra_devfreq_profile.initial_freq = clk_get_rate(tegra->emc_clock); - devfreq = devfreq_add_device(&pdev->dev, &tegra_devfreq_profile, - "tegra_actmon", NULL); - if (IS_ERR(devfreq)) { - err = PTR_ERR(devfreq); - goto remove_governor; - } - - return 0; - -remove_governor: - devfreq_remove_governor(&tegra_devfreq_governor); - -remove_opps: - dev_pm_opp_remove_all_dynamic(&pdev->dev); - - reset_control_reset(tegra->reset); -disable_clk: - clk_disable_unprepare(tegra->clock); -remove_table: - dev_pm_opp_of_remove_table(&pdev->dev); -put_hw: - dev_pm_opp_put_supported_hw(tegra->opp_table); - - return err; -} - -static int tegra_devfreq_remove(struct platform_device *pdev) -{ - struct tegra_devfreq *tegra = platform_get_drvdata(pdev); - - devfreq_remove_device(tegra->devfreq); - devfreq_remove_governor(&tegra_devfreq_governor); - - reset_control_reset(tegra->reset); - clk_disable_unprepare(tegra->clock); - - dev_pm_opp_of_remove_table(&pdev->dev); - dev_pm_opp_put_supported_hw(tegra->opp_table); + devfreq = devm_devfreq_add_device(&pdev->dev, &tegra_devfreq_profile, + "tegra_actmon", NULL); + if (IS_ERR(devfreq)) + return PTR_ERR(devfreq); return 0; } @@ -967,7 +953,6 @@ MODULE_DEVICE_TABLE(of, tegra_devfreq_of_match); static struct platform_driver tegra_devfreq_driver = { .probe = tegra_devfreq_probe, - .remove = tegra_devfreq_remove, .driver = { .name = "tegra-devfreq", .of_match_table = tegra_devfreq_of_match, diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 2ea59cb8edcd..6437b2e978fb 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -67,12 +67,9 @@ static void dma_buf_release(struct dentry *dentry) BUG_ON(dmabuf->vmapping_counter); /* - * Any fences that a dma-buf poll can wait on should be signaled - * before releasing dma-buf. This is the responsibility of each - * driver that uses the reservation objects. - * - * If you hit this BUG() it means someone dropped their ref to the - * dma-buf while still having pending operation to the buffer. + * If you hit this BUG() it could mean: + * * There's a file reference imbalance in dma_buf_poll / dma_buf_poll_cb or somewhere else + * * dmabuf->cb_in/out.active are non-0 despite no pending fence callback */ BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); @@ -200,6 +197,7 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; + struct dma_buf *dmabuf = container_of(dcb->poll, struct dma_buf, poll); unsigned long flags; spin_lock_irqsave(&dcb->poll->lock, flags); @@ -207,21 +205,18 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) dcb->active = 0; spin_unlock_irqrestore(&dcb->poll->lock, flags); dma_fence_put(fence); + /* Paired with get_file in dma_buf_poll */ + fput(dmabuf->file); } -static bool dma_buf_poll_shared(struct dma_resv *resv, +static bool dma_buf_poll_add_cb(struct dma_resv *resv, bool write, struct dma_buf_poll_cb_t *dcb) { - struct dma_resv_list *fobj = dma_resv_shared_list(resv); + struct dma_resv_iter cursor; struct dma_fence *fence; - int i, r; - - if (!fobj) - return false; + int r; - for (i = 0; i < fobj->shared_count; ++i) { - fence = rcu_dereference_protected(fobj->shared[i], - dma_resv_held(resv)); + dma_resv_for_each_fence(&cursor, resv, write, fence) { dma_fence_get(fence); r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); if (!r) @@ -232,24 +227,6 @@ static bool dma_buf_poll_shared(struct dma_resv *resv, return false; } -static bool dma_buf_poll_excl(struct dma_resv *resv, - struct dma_buf_poll_cb_t *dcb) -{ - struct dma_fence *fence = dma_resv_excl_fence(resv); - int r; - - if (!fence) - return false; - - dma_fence_get(fence); - r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); - if (!r) - return true; - dma_fence_put(fence); - - return false; -} - static __poll_t dma_buf_poll(struct file *file, poll_table *poll) { struct dma_buf *dmabuf; @@ -282,8 +259,10 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) spin_unlock_irq(&dmabuf->poll.lock); if (events & EPOLLOUT) { - if (!dma_buf_poll_shared(resv, dcb) && - !dma_buf_poll_excl(resv, dcb)) + /* Paired with fput in dma_buf_poll_cb */ + get_file(dmabuf->file); + + if (!dma_buf_poll_add_cb(resv, true, dcb)) /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); else @@ -303,7 +282,10 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) spin_unlock_irq(&dmabuf->poll.lock); if (events & EPOLLIN) { - if (!dma_buf_poll_excl(resv, dcb)) + /* Paired with fput in dma_buf_poll_cb */ + get_file(dmabuf->file); + + if (!dma_buf_poll_add_cb(resv, false, dcb)) /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); else @@ -1356,10 +1338,9 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) { struct dma_buf *buf_obj; struct dma_buf_attachment *attach_obj; - struct dma_resv *robj; - struct dma_resv_list *fobj; + struct dma_resv_iter cursor; struct dma_fence *fence; - int count = 0, attach_count, shared_count, i; + int count = 0, attach_count; size_t size = 0; int ret; @@ -1378,6 +1359,8 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) if (ret) goto error_unlock; + + spin_lock(&buf_obj->name_lock); seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n", buf_obj->size, buf_obj->file->f_flags, buf_obj->file->f_mode, @@ -1385,22 +1368,12 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) buf_obj->exp_name, file_inode(buf_obj->file)->i_ino, buf_obj->name ?: ""); + spin_unlock(&buf_obj->name_lock); - robj = buf_obj->resv; - fence = dma_resv_excl_fence(robj); - if (fence) - seq_printf(s, "\tExclusive fence: %s %s %ssignalled\n", - fence->ops->get_driver_name(fence), - fence->ops->get_timeline_name(fence), - dma_fence_is_signaled(fence) ? "" : "un"); - - fobj = rcu_dereference_protected(robj->fence, - dma_resv_held(robj)); - shared_count = fobj ? fobj->shared_count : 0; - for (i = 0; i < shared_count; i++) { - fence = rcu_dereference_protected(fobj->shared[i], - dma_resv_held(robj)); - seq_printf(s, "\tShared fence: %s %s %ssignalled\n", + dma_resv_for_each_fence(&cursor, buf_obj->resv, true, fence) { + seq_printf(s, "\t%s fence: %s %s %ssignalled\n", + dma_resv_iter_is_exclusive(&cursor) ? + "Exclusive" : "Shared", fence->ops->get_driver_name(fence), fence->ops->get_timeline_name(fence), dma_fence_is_signaled(fence) ? "" : "un"); diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index a480af9581bd..9eb2baa387d4 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -333,10 +333,14 @@ static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) { cursor->seq = read_seqcount_begin(&cursor->obj->seq); cursor->index = -1; - if (cursor->all_fences) + cursor->shared_count = 0; + if (cursor->all_fences) { cursor->fences = dma_resv_shared_list(cursor->obj); - else + if (cursor->fences) + cursor->shared_count = cursor->fences->shared_count; + } else { cursor->fences = NULL; + } cursor->is_restarted = true; } @@ -363,7 +367,7 @@ static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) continue; } else if (!cursor->fences || - cursor->index >= cursor->fences->shared_count) { + cursor->index >= cursor->shared_count) { cursor->fence = NULL; break; @@ -424,6 +428,57 @@ struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) EXPORT_SYMBOL(dma_resv_iter_next_unlocked); /** + * dma_resv_iter_first - first fence from a locked dma_resv object + * @cursor: cursor to record the current position + * + * Return the first fence in the dma_resv object while holding the + * &dma_resv.lock. + */ +struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor) +{ + struct dma_fence *fence; + + dma_resv_assert_held(cursor->obj); + + cursor->index = 0; + if (cursor->all_fences) + cursor->fences = dma_resv_shared_list(cursor->obj); + else + cursor->fences = NULL; + + fence = dma_resv_excl_fence(cursor->obj); + if (!fence) + fence = dma_resv_iter_next(cursor); + + cursor->is_restarted = true; + return fence; +} +EXPORT_SYMBOL_GPL(dma_resv_iter_first); + +/** + * dma_resv_iter_next - next fence from a locked dma_resv object + * @cursor: cursor to record the current position + * + * Return the next fences from the dma_resv object while holding the + * &dma_resv.lock. + */ +struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor) +{ + unsigned int idx; + + dma_resv_assert_held(cursor->obj); + + cursor->is_restarted = false; + if (!cursor->fences || cursor->index >= cursor->fences->shared_count) + return NULL; + + idx = cursor->index++; + return rcu_dereference_protected(cursor->fences->shared[idx], + dma_resv_held(cursor->obj)); +} +EXPORT_SYMBOL_GPL(dma_resv_iter_next); + +/** * dma_resv_copy_fences - Copy all fences from src to dst. * @dst: the destination reservation object * @src: the source reservation object @@ -448,10 +503,8 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) dma_resv_list_free(list); dma_fence_put(excl); - if (cursor.fences) { - unsigned int cnt = cursor.fences->shared_count; - - list = dma_resv_list_alloc(cnt); + if (cursor.shared_count) { + list = dma_resv_list_alloc(cursor.shared_count); if (!list) { dma_resv_iter_end(&cursor); return -ENOMEM; @@ -522,7 +575,7 @@ int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, if (fence_excl) dma_fence_put(*fence_excl); - count = cursor.fences ? cursor.fences->shared_count : 0; + count = cursor.shared_count; count += fence_excl ? 0 : 1; /* Eventually re-allocate the array */ diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 80c2c03cb014..6bcdb4e6a0d1 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -717,7 +717,7 @@ config XILINX_DMA config XILINX_ZYNQMP_DMA tristate "Xilinx ZynqMP DMA Engine" - depends on (ARCH_ZYNQ || MICROBLAZE || ARM64) + depends on ARCH_ZYNQ || MICROBLAZE || ARM64 || COMPILE_TEST select DMA_ENGINE help Enable support for Xilinx ZynqMP DMA controller. diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c index 5a2c7573b692..f5b885d69cd3 100644 --- a/drivers/dma/altera-msgdma.c +++ b/drivers/dma/altera-msgdma.c @@ -585,16 +585,14 @@ static void msgdma_chan_desc_cleanup(struct msgdma_device *mdev) struct msgdma_sw_desc *desc, *next; list_for_each_entry_safe(desc, next, &mdev->done_list, node) { - dma_async_tx_callback callback; - void *callback_param; + struct dmaengine_desc_callback cb; list_del(&desc->node); - callback = desc->async_tx.callback; - callback_param = desc->async_tx.callback_param; - if (callback) { + dmaengine_desc_get_callback(&desc->async_tx, &cb); + if (dmaengine_desc_callback_valid(&cb)) { spin_unlock(&mdev->lock); - callback(callback_param); + dmaengine_desc_callback_invoke(&cb, NULL); spin_lock(&mdev->lock); } diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index ab78e0f6afd7..275a76f188ae 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -155,7 +155,7 @@ #define AT_XDMAC_CC_WRIP (0x1 << 23) /* Write in Progress (read only) */ #define AT_XDMAC_CC_WRIP_DONE (0x0 << 23) #define AT_XDMAC_CC_WRIP_IN_PROGRESS (0x1 << 23) -#define AT_XDMAC_CC_PERID(i) (0x7f & (i) << 24) /* Channel Peripheral Identifier */ +#define AT_XDMAC_CC_PERID(i) ((0x7f & (i)) << 24) /* Channel Peripheral Identifier */ #define AT_XDMAC_CDS_MSP 0x2C /* Channel Data Stride Memory Set Pattern */ #define AT_XDMAC_CSUS 0x30 /* Channel Source Microblock Stride */ #define AT_XDMAC_CDUS 0x34 /* Channel Destination Microblock Stride */ @@ -1926,8 +1926,31 @@ static void at_xdmac_free_chan_resources(struct dma_chan *chan) return; } -#ifdef CONFIG_PM -static int atmel_xdmac_prepare(struct device *dev) +static void at_xdmac_axi_config(struct platform_device *pdev) +{ + struct at_xdmac *atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev); + bool dev_m2m = false; + u32 dma_requests; + + if (!atxdmac->layout->axi_config) + return; /* Not supported */ + + if (!of_property_read_u32(pdev->dev.of_node, "dma-requests", + &dma_requests)) { + dev_info(&pdev->dev, "controller in mem2mem mode.\n"); + dev_m2m = true; + } + + if (dev_m2m) { + at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_M2M); + at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_M2M); + } else { + at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_P2M); + at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_P2M); + } +} + +static int __maybe_unused atmel_xdmac_prepare(struct device *dev) { struct at_xdmac *atxdmac = dev_get_drvdata(dev); struct dma_chan *chan, *_chan; @@ -1941,12 +1964,8 @@ static int atmel_xdmac_prepare(struct device *dev) } return 0; } -#else -# define atmel_xdmac_prepare NULL -#endif -#ifdef CONFIG_PM_SLEEP -static int atmel_xdmac_suspend(struct device *dev) +static int __maybe_unused atmel_xdmac_suspend(struct device *dev) { struct at_xdmac *atxdmac = dev_get_drvdata(dev); struct dma_chan *chan, *_chan; @@ -1970,11 +1989,12 @@ static int atmel_xdmac_suspend(struct device *dev) return 0; } -static int atmel_xdmac_resume(struct device *dev) +static int __maybe_unused atmel_xdmac_resume(struct device *dev) { struct at_xdmac *atxdmac = dev_get_drvdata(dev); struct at_xdmac_chan *atchan; struct dma_chan *chan, *_chan; + struct platform_device *pdev = container_of(dev, struct platform_device, dev); int i; int ret; @@ -1982,6 +2002,8 @@ static int atmel_xdmac_resume(struct device *dev) if (ret) return ret; + at_xdmac_axi_config(pdev); + /* Clear pending interrupts. */ for (i = 0; i < atxdmac->dma.chancnt; i++) { atchan = &atxdmac->chan[i]; @@ -2005,31 +2027,6 @@ static int atmel_xdmac_resume(struct device *dev) } return 0; } -#endif /* CONFIG_PM_SLEEP */ - -static void at_xdmac_axi_config(struct platform_device *pdev) -{ - struct at_xdmac *atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev); - bool dev_m2m = false; - u32 dma_requests; - - if (!atxdmac->layout->axi_config) - return; /* Not supported */ - - if (!of_property_read_u32(pdev->dev.of_node, "dma-requests", - &dma_requests)) { - dev_info(&pdev->dev, "controller in mem2mem mode.\n"); - dev_m2m = true; - } - - if (dev_m2m) { - at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_M2M); - at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_M2M); - } else { - at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_P2M); - at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_P2M); - } -} static int at_xdmac_probe(struct platform_device *pdev) { @@ -2210,7 +2207,7 @@ static int at_xdmac_remove(struct platform_device *pdev) return 0; } -static const struct dev_pm_ops atmel_xdmac_dev_pm_ops = { +static const struct dev_pm_ops __maybe_unused atmel_xdmac_dev_pm_ops = { .prepare = atmel_xdmac_prepare, SET_LATE_SYSTEM_SLEEP_PM_OPS(atmel_xdmac_suspend, atmel_xdmac_resume) }; @@ -2234,7 +2231,7 @@ static struct platform_driver at_xdmac_driver = { .driver = { .name = "at_xdmac", .of_match_table = of_match_ptr(atmel_xdmac_dt_ids), - .pm = &atmel_xdmac_dev_pm_ops, + .pm = pm_ptr(&atmel_xdmac_dev_pm_ops), } }; diff --git a/drivers/dma/bestcomm/ata.c b/drivers/dma/bestcomm/ata.c index 2fd87f83cf90..e169f18da551 100644 --- a/drivers/dma/bestcomm/ata.c +++ b/drivers/dma/bestcomm/ata.c @@ -133,7 +133,7 @@ void bcom_ata_reset_bd(struct bcom_task *tsk) struct bcom_ata_var *var; /* Reset all BD */ - memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); + memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); tsk->index = 0; tsk->outdex = 0; diff --git a/drivers/dma/bestcomm/bestcomm.c b/drivers/dma/bestcomm/bestcomm.c index d91cbbe7a48f..8c42e5ca00a9 100644 --- a/drivers/dma/bestcomm/bestcomm.c +++ b/drivers/dma/bestcomm/bestcomm.c @@ -95,7 +95,7 @@ bcom_task_alloc(int bd_count, int bd_size, int priv_size) tsk->bd = bcom_sram_alloc(bd_count * bd_size, 4, &tsk->bd_pa); if (!tsk->bd) goto error; - memset(tsk->bd, 0x00, bd_count * bd_size); + memset_io(tsk->bd, 0x00, bd_count * bd_size); tsk->num_bd = bd_count; tsk->bd_size = bd_size; @@ -186,16 +186,16 @@ bcom_load_image(int task, u32 *task_image) inc = bcom_task_inc(task); /* Clear & copy */ - memset(var, 0x00, BCOM_VAR_SIZE); - memset(inc, 0x00, BCOM_INC_SIZE); + memset_io(var, 0x00, BCOM_VAR_SIZE); + memset_io(inc, 0x00, BCOM_INC_SIZE); desc_src = (u32 *)(hdr + 1); var_src = desc_src + hdr->desc_size; inc_src = var_src + hdr->var_size; - memcpy(desc, desc_src, hdr->desc_size * sizeof(u32)); - memcpy(var + hdr->first_var, var_src, hdr->var_size * sizeof(u32)); - memcpy(inc, inc_src, hdr->inc_size * sizeof(u32)); + memcpy_toio(desc, desc_src, hdr->desc_size * sizeof(u32)); + memcpy_toio(var + hdr->first_var, var_src, hdr->var_size * sizeof(u32)); + memcpy_toio(inc, inc_src, hdr->inc_size * sizeof(u32)); return 0; } @@ -302,13 +302,13 @@ static int bcom_engine_init(void) return -ENOMEM; } - memset(bcom_eng->tdt, 0x00, tdt_size); - memset(bcom_eng->ctx, 0x00, ctx_size); - memset(bcom_eng->var, 0x00, var_size); - memset(bcom_eng->fdt, 0x00, fdt_size); + memset_io(bcom_eng->tdt, 0x00, tdt_size); + memset_io(bcom_eng->ctx, 0x00, ctx_size); + memset_io(bcom_eng->var, 0x00, var_size); + memset_io(bcom_eng->fdt, 0x00, fdt_size); /* Copy the FDT for the EU#3 */ - memcpy(&bcom_eng->fdt[48], fdt_ops, sizeof(fdt_ops)); + memcpy_toio(&bcom_eng->fdt[48], fdt_ops, sizeof(fdt_ops)); /* Initialize Task base structure */ for (task=0; task<BCOM_MAX_TASKS; task++) diff --git a/drivers/dma/bestcomm/fec.c b/drivers/dma/bestcomm/fec.c index 7f1fb1c999e4..d203618ac11f 100644 --- a/drivers/dma/bestcomm/fec.c +++ b/drivers/dma/bestcomm/fec.c @@ -140,7 +140,7 @@ bcom_fec_rx_reset(struct bcom_task *tsk) tsk->index = 0; tsk->outdex = 0; - memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); + memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); /* Configure some stuff */ bcom_set_task_pragma(tsk->tasknum, BCOM_FEC_RX_BD_PRAGMA); @@ -241,7 +241,7 @@ bcom_fec_tx_reset(struct bcom_task *tsk) tsk->index = 0; tsk->outdex = 0; - memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); + memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); /* Configure some stuff */ bcom_set_task_pragma(tsk->tasknum, BCOM_FEC_TX_BD_PRAGMA); diff --git a/drivers/dma/bestcomm/gen_bd.c b/drivers/dma/bestcomm/gen_bd.c index 906ddba6a6f5..8a24a5cbc263 100644 --- a/drivers/dma/bestcomm/gen_bd.c +++ b/drivers/dma/bestcomm/gen_bd.c @@ -142,7 +142,7 @@ bcom_gen_bd_rx_reset(struct bcom_task *tsk) tsk->index = 0; tsk->outdex = 0; - memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); + memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); /* Configure some stuff */ bcom_set_task_pragma(tsk->tasknum, BCOM_GEN_RX_BD_PRAGMA); @@ -226,7 +226,7 @@ bcom_gen_bd_tx_reset(struct bcom_task *tsk) tsk->index = 0; tsk->outdex = 0; - memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); + memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size); /* Configure some stuff */ bcom_set_task_pragma(tsk->tasknum, BCOM_GEN_TX_BD_PRAGMA); diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c index ebee94dbd630..96701dedcac8 100644 --- a/drivers/dma/dma-jz4780.c +++ b/drivers/dma/dma-jz4780.c @@ -915,6 +915,7 @@ static int jz4780_dma_probe(struct platform_device *pdev) dd->dst_addr_widths = JZ_DMA_BUSWIDTHS; dd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); dd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + dd->max_sg_burst = JZ_DMA_MAX_DESC; /* * Enable DMA controller, mark all channels as not programmable. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index af3ee288bc11..d9f7c097cfd6 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -695,13 +695,12 @@ static struct dma_chan *find_candidate(struct dma_device *device, */ struct dma_chan *dma_get_slave_channel(struct dma_chan *chan) { - int err = -EBUSY; - /* lock against __dma_request_channel */ mutex_lock(&dma_list_mutex); if (chan->client_count == 0) { struct dma_device *device = chan->device; + int err; dma_cap_set(DMA_PRIVATE, device->cap_mask); device->privatecnt++; diff --git a/drivers/dma/dmaengine.h b/drivers/dma/dmaengine.h index 1bfbd64b1371..53f16d3f0029 100644 --- a/drivers/dma/dmaengine.h +++ b/drivers/dma/dmaengine.h @@ -176,7 +176,7 @@ dmaengine_desc_get_callback_invoke(struct dma_async_tx_descriptor *tx, static inline bool dmaengine_desc_callback_valid(struct dmaengine_desc_callback *cb) { - return (cb->callback) ? true : false; + return cb->callback || cb->callback_result; } struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index 35993ab92154..cd0d745eb071 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -79,6 +79,32 @@ axi_chan_iowrite64(struct axi_dma_chan *chan, u32 reg, u64 val) iowrite32(upper_32_bits(val), chan->chan_regs + reg + 4); } +static inline void axi_chan_config_write(struct axi_dma_chan *chan, + struct axi_dma_chan_config *config) +{ + u32 cfg_lo, cfg_hi; + + cfg_lo = (config->dst_multblk_type << CH_CFG_L_DST_MULTBLK_TYPE_POS | + config->src_multblk_type << CH_CFG_L_SRC_MULTBLK_TYPE_POS); + if (chan->chip->dw->hdata->reg_map_8_channels) { + cfg_hi = config->tt_fc << CH_CFG_H_TT_FC_POS | + config->hs_sel_src << CH_CFG_H_HS_SEL_SRC_POS | + config->hs_sel_dst << CH_CFG_H_HS_SEL_DST_POS | + config->src_per << CH_CFG_H_SRC_PER_POS | + config->dst_per << CH_CFG_H_DST_PER_POS | + config->prior << CH_CFG_H_PRIORITY_POS; + } else { + cfg_lo |= config->src_per << CH_CFG2_L_SRC_PER_POS | + config->dst_per << CH_CFG2_L_DST_PER_POS; + cfg_hi = config->tt_fc << CH_CFG2_H_TT_FC_POS | + config->hs_sel_src << CH_CFG2_H_HS_SEL_SRC_POS | + config->hs_sel_dst << CH_CFG2_H_HS_SEL_DST_POS | + config->prior << CH_CFG2_H_PRIORITY_POS; + } + axi_chan_iowrite32(chan, CH_CFG_L, cfg_lo); + axi_chan_iowrite32(chan, CH_CFG_H, cfg_hi); +} + static inline void axi_dma_disable(struct axi_dma_chip *chip) { u32 val; @@ -154,7 +180,10 @@ static inline void axi_chan_disable(struct axi_dma_chan *chan) val = axi_dma_ioread32(chan->chip, DMAC_CHEN); val &= ~(BIT(chan->id) << DMAC_CHAN_EN_SHIFT); - val |= BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT; + if (chan->chip->dw->hdata->reg_map_8_channels) + val |= BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT; + else + val |= BIT(chan->id) << DMAC_CHAN_EN2_WE_SHIFT; axi_dma_iowrite32(chan->chip, DMAC_CHEN, val); } @@ -163,8 +192,12 @@ static inline void axi_chan_enable(struct axi_dma_chan *chan) u32 val; val = axi_dma_ioread32(chan->chip, DMAC_CHEN); - val |= BIT(chan->id) << DMAC_CHAN_EN_SHIFT | - BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT; + if (chan->chip->dw->hdata->reg_map_8_channels) + val |= BIT(chan->id) << DMAC_CHAN_EN_SHIFT | + BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT; + else + val |= BIT(chan->id) << DMAC_CHAN_EN_SHIFT | + BIT(chan->id) << DMAC_CHAN_EN2_WE_SHIFT; axi_dma_iowrite32(chan->chip, DMAC_CHEN, val); } @@ -179,12 +212,16 @@ static inline bool axi_chan_is_hw_enable(struct axi_dma_chan *chan) static void axi_dma_hw_init(struct axi_dma_chip *chip) { + int ret; u32 i; for (i = 0; i < chip->dw->hdata->nr_channels; i++) { axi_chan_irq_disable(&chip->dw->chan[i], DWAXIDMAC_IRQ_ALL); axi_chan_disable(&chip->dw->chan[i]); } + ret = dma_set_mask_and_coherent(chip->dev, DMA_BIT_MASK(64)); + if (ret) + dev_warn(chip->dev, "Unable to set coherent mask\n"); } static u32 axi_chan_get_xfer_width(struct axi_dma_chan *chan, dma_addr_t src, @@ -336,7 +373,8 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan, struct axi_dma_desc *first) { u32 priority = chan->chip->dw->hdata->priority[chan->id]; - u32 reg, irq_mask; + struct axi_dma_chan_config config; + u32 irq_mask; u8 lms = 0; /* Select AXI0 master for LLI fetching */ if (unlikely(axi_chan_is_hw_enable(chan))) { @@ -348,36 +386,36 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan, axi_dma_enable(chan->chip); - reg = (DWAXIDMAC_MBLK_TYPE_LL << CH_CFG_L_DST_MULTBLK_TYPE_POS | - DWAXIDMAC_MBLK_TYPE_LL << CH_CFG_L_SRC_MULTBLK_TYPE_POS); - axi_chan_iowrite32(chan, CH_CFG_L, reg); - - reg = (DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC << CH_CFG_H_TT_FC_POS | - priority << CH_CFG_H_PRIORITY_POS | - DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_DST_POS | - DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_SRC_POS); + config.dst_multblk_type = DWAXIDMAC_MBLK_TYPE_LL; + config.src_multblk_type = DWAXIDMAC_MBLK_TYPE_LL; + config.tt_fc = DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC; + config.prior = priority; + config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW; + config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW; switch (chan->direction) { case DMA_MEM_TO_DEV: dw_axi_dma_set_byte_halfword(chan, true); - reg |= (chan->config.device_fc ? - DWAXIDMAC_TT_FC_MEM_TO_PER_DST : - DWAXIDMAC_TT_FC_MEM_TO_PER_DMAC) - << CH_CFG_H_TT_FC_POS; + config.tt_fc = chan->config.device_fc ? + DWAXIDMAC_TT_FC_MEM_TO_PER_DST : + DWAXIDMAC_TT_FC_MEM_TO_PER_DMAC; if (chan->chip->apb_regs) - reg |= (chan->id << CH_CFG_H_DST_PER_POS); + config.dst_per = chan->id; + else + config.dst_per = chan->hw_handshake_num; break; case DMA_DEV_TO_MEM: - reg |= (chan->config.device_fc ? - DWAXIDMAC_TT_FC_PER_TO_MEM_SRC : - DWAXIDMAC_TT_FC_PER_TO_MEM_DMAC) - << CH_CFG_H_TT_FC_POS; + config.tt_fc = chan->config.device_fc ? + DWAXIDMAC_TT_FC_PER_TO_MEM_SRC : + DWAXIDMAC_TT_FC_PER_TO_MEM_DMAC; if (chan->chip->apb_regs) - reg |= (chan->id << CH_CFG_H_SRC_PER_POS); + config.src_per = chan->id; + else + config.src_per = chan->hw_handshake_num; break; default: break; } - axi_chan_iowrite32(chan, CH_CFG_H, reg); + axi_chan_config_write(chan, &config); write_chan_llp(chan, first->hw_desc[0].llp | lms); @@ -1120,10 +1158,16 @@ static int dma_chan_pause(struct dma_chan *dchan) spin_lock_irqsave(&chan->vc.lock, flags); - val = axi_dma_ioread32(chan->chip, DMAC_CHEN); - val |= BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT | - BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT; - axi_dma_iowrite32(chan->chip, DMAC_CHEN, val); + if (chan->chip->dw->hdata->reg_map_8_channels) { + val = axi_dma_ioread32(chan->chip, DMAC_CHEN); + val |= BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT | + BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT; + axi_dma_iowrite32(chan->chip, DMAC_CHEN, val); + } else { + val = BIT(chan->id) << DMAC_CHAN_SUSP2_SHIFT | + BIT(chan->id) << DMAC_CHAN_SUSP2_WE_SHIFT; + axi_dma_iowrite32(chan->chip, DMAC_CHSUSPREG, val); + } do { if (axi_chan_irq_read(chan) & DWAXIDMAC_IRQ_SUSPENDED) @@ -1147,9 +1191,15 @@ static inline void axi_chan_resume(struct axi_dma_chan *chan) u32 val; val = axi_dma_ioread32(chan->chip, DMAC_CHEN); - val &= ~(BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT); - val |= (BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT); - axi_dma_iowrite32(chan->chip, DMAC_CHEN, val); + if (chan->chip->dw->hdata->reg_map_8_channels) { + val &= ~(BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT); + val |= (BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT); + axi_dma_iowrite32(chan->chip, DMAC_CHEN, val); + } else { + val &= ~(BIT(chan->id) << DMAC_CHAN_SUSP2_SHIFT); + val |= (BIT(chan->id) << DMAC_CHAN_SUSP2_WE_SHIFT); + axi_dma_iowrite32(chan->chip, DMAC_CHSUSPREG, val); + } chan->is_paused = false; } @@ -1241,6 +1291,8 @@ static int parse_device_properties(struct axi_dma_chip *chip) return -EINVAL; chip->dw->hdata->nr_channels = tmp; + if (tmp <= DMA_REG_MAP_CH_REF) + chip->dw->hdata->reg_map_8_channels = true; ret = device_property_read_u32(dev, "snps,dma-masters", &tmp); if (ret) diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h index 380005afde16..be69a0b76860 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h @@ -18,7 +18,7 @@ #include "../virt-dma.h" -#define DMAC_MAX_CHANNELS 8 +#define DMAC_MAX_CHANNELS 16 #define DMAC_MAX_MASTERS 2 #define DMAC_MAX_BLK_SIZE 0x200000 @@ -30,6 +30,8 @@ struct dw_axi_dma_hcfg { u32 priority[DMAC_MAX_CHANNELS]; /* maximum supported axi burst length */ u32 axi_rw_burst_len; + /* Register map for DMAX_NUM_CHANNELS <= 8 */ + bool reg_map_8_channels; bool restrict_axi_burst_len; }; @@ -103,6 +105,17 @@ struct axi_dma_desc { u32 period_len; }; +struct axi_dma_chan_config { + u8 dst_multblk_type; + u8 src_multblk_type; + u8 dst_per; + u8 src_per; + u8 tt_fc; + u8 prior; + u8 hs_sel_dst; + u8 hs_sel_src; +}; + static inline struct device *dchan2dev(struct dma_chan *dchan) { return &dchan->dev->device; @@ -139,6 +152,8 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan) #define DMAC_CHEN 0x018 /* R/W DMAC Channel Enable */ #define DMAC_CHEN_L 0x018 /* R/W DMAC Channel Enable 00-31 */ #define DMAC_CHEN_H 0x01C /* R/W DMAC Channel Enable 32-63 */ +#define DMAC_CHSUSPREG 0x020 /* R/W DMAC Channel Suspend */ +#define DMAC_CHABORTREG 0x028 /* R/W DMAC Channel Abort */ #define DMAC_INTSTATUS 0x030 /* R DMAC Interrupt Status */ #define DMAC_COMMON_INTCLEAR 0x038 /* W DMAC Interrupt Clear */ #define DMAC_COMMON_INTSTATUS_ENA 0x040 /* R DMAC Interrupt Status Enable */ @@ -187,6 +202,7 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan) #define DMA_APB_HS_SEL_BIT_SIZE 0x08 /* HW handshake bits per channel */ #define DMA_APB_HS_SEL_MASK 0xFF /* HW handshake select masks */ #define MAX_BLOCK_SIZE 0x1000 /* 1024 blocks * 4 bytes data width */ +#define DMA_REG_MAP_CH_REF 0x08 /* Channel count to choose register map */ /* DMAC_CFG */ #define DMAC_EN_POS 0 @@ -195,12 +211,20 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan) #define INT_EN_POS 1 #define INT_EN_MASK BIT(INT_EN_POS) +/* DMAC_CHEN */ #define DMAC_CHAN_EN_SHIFT 0 #define DMAC_CHAN_EN_WE_SHIFT 8 #define DMAC_CHAN_SUSP_SHIFT 16 #define DMAC_CHAN_SUSP_WE_SHIFT 24 +/* DMAC_CHEN2 */ +#define DMAC_CHAN_EN2_WE_SHIFT 16 + +/* DMAC_CHSUSP */ +#define DMAC_CHAN_SUSP2_SHIFT 0 +#define DMAC_CHAN_SUSP2_WE_SHIFT 16 + /* CH_CTL_H */ #define CH_CTL_H_ARLEN_EN BIT(6) #define CH_CTL_H_ARLEN_POS 7 @@ -289,6 +313,15 @@ enum { DWAXIDMAC_MBLK_TYPE_LL }; +/* CH_CFG2 */ +#define CH_CFG2_L_SRC_PER_POS 4 +#define CH_CFG2_L_DST_PER_POS 11 + +#define CH_CFG2_H_TT_FC_POS 0 +#define CH_CFG2_H_HS_SEL_SRC_POS 3 +#define CH_CFG2_H_HS_SEL_DST_POS 4 +#define CH_CFG2_H_PRIORITY_POS 20 + /** * DW AXI DMA channel interrupts * diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index 53289927dd0d..468d1097a1ec 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -249,7 +249,6 @@ static int dw_edma_device_terminate_all(struct dma_chan *dchan) { struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan); int err = 0; - LIST_HEAD(head); if (!chan->configured) { /* Do nothing */ diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index 44f6e09bdb53..198f6cd8ac1b 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -186,27 +186,18 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, pci_set_master(pdev); /* DMA configuration */ - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - pci_err(pdev, "consistent DMA mask 64 set failed\n"); - return err; - } + pci_err(pdev, "DMA mask 64 set failed\n"); + return err; } else { pci_err(pdev, "DMA mask 64 set failed\n"); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { pci_err(pdev, "DMA mask 32 set failed\n"); return err; } - - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (err) { - pci_err(pdev, "consistent DMA mask 32 set failed\n"); - return err; - } } /* Data structure allocation */ diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index 26a3f926da02..ad2d4d012cf7 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -32,11 +32,7 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) pci_set_master(pdev); pci_try_set_mwi(pdev); - ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (ret) - return ret; - - ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (ret) return ret; diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 930ae268c497..3ae05d1446a5 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -348,6 +348,7 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan, struct fsl_edma_engine *edma = fsl_chan->edma; struct edma_regs *regs = &fsl_chan->edma->regs; u32 ch = fsl_chan->vchan.chan.chan_id; + u16 csr = 0; /* * TCD parameters are stored in struct fsl_edma_hw_tcd in little @@ -373,6 +374,12 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan, edma_writel(edma, (s32)tcd->dlast_sga, ®s->tcd[ch].dlast_sga); + if (fsl_chan->is_sw) { + csr = le16_to_cpu(tcd->csr); + csr |= EDMA_TCD_CSR_START; + tcd->csr = cpu_to_le16(csr); + } + edma_writew(edma, (s16)tcd->csr, ®s->tcd[ch].csr); } @@ -587,6 +594,29 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg( } EXPORT_SYMBOL_GPL(fsl_edma_prep_slave_sg); +struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan, + dma_addr_t dma_dst, dma_addr_t dma_src, + size_t len, unsigned long flags) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + struct fsl_edma_desc *fsl_desc; + + fsl_desc = fsl_edma_alloc_desc(fsl_chan, 1); + if (!fsl_desc) + return NULL; + fsl_desc->iscyclic = false; + + fsl_chan->is_sw = true; + + /* To match with copy_align and max_seg_size so 1 tcd is enough */ + fsl_edma_fill_tcd(fsl_desc->tcd[0].vtcd, dma_src, dma_dst, + EDMA_TCD_ATTR_SSIZE_32BYTE | EDMA_TCD_ATTR_DSIZE_32BYTE, + 32, len, 0, 1, 1, 32, 0, true, true, false); + + return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags); +} +EXPORT_SYMBOL_GPL(fsl_edma_prep_memcpy); + void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan) { struct virt_dma_desc *vdesc; @@ -638,12 +668,14 @@ EXPORT_SYMBOL_GPL(fsl_edma_alloc_chan_resources); void fsl_edma_free_chan_resources(struct dma_chan *chan) { struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + struct fsl_edma_engine *edma = fsl_chan->edma; unsigned long flags; LIST_HEAD(head); spin_lock_irqsave(&fsl_chan->vchan.lock, flags); fsl_edma_disable_request(fsl_chan); - fsl_edma_chan_mux(fsl_chan, 0, false); + if (edma->drvdata->dmamuxs) + fsl_edma_chan_mux(fsl_chan, 0, false); fsl_chan->edesc = NULL; vchan_get_all_descriptors(&fsl_chan->vchan, &head); fsl_edma_unprep_slave_dma(fsl_chan); @@ -652,6 +684,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan) vchan_dma_desc_free_list(&fsl_chan->vchan, &head); dma_pool_destroy(fsl_chan->tcd_pool); fsl_chan->tcd_pool = NULL; + fsl_chan->is_sw = false; } EXPORT_SYMBOL_GPL(fsl_edma_free_chan_resources); diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index ec1169741de1..004ec4a6bc86 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -121,6 +121,7 @@ struct fsl_edma_chan { struct fsl_edma_desc *edesc; struct dma_slave_config cfg; u32 attr; + bool is_sw; struct dma_pool *tcd_pool; dma_addr_t dma_dev_addr; u32 dma_dev_size; @@ -240,6 +241,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction direction, unsigned long flags, void *context); +struct dma_async_tx_descriptor *fsl_edma_prep_memcpy( + struct dma_chan *chan, dma_addr_t dma_dst, dma_addr_t dma_src, + size_t len, unsigned long flags); void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan); void fsl_edma_issue_pending(struct dma_chan *chan); int fsl_edma_alloc_chan_resources(struct dma_chan *chan); diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c index 90bb72af306c..76cbf54aec58 100644 --- a/drivers/dma/fsl-edma.c +++ b/drivers/dma/fsl-edma.c @@ -17,6 +17,7 @@ #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_dma.h> +#include <linux/dma-mapping.h> #include "fsl-edma-common.h" @@ -372,6 +373,7 @@ static int fsl_edma_probe(struct platform_device *pdev) dma_cap_set(DMA_PRIVATE, fsl_edma->dma_dev.cap_mask); dma_cap_set(DMA_SLAVE, fsl_edma->dma_dev.cap_mask); dma_cap_set(DMA_CYCLIC, fsl_edma->dma_dev.cap_mask); + dma_cap_set(DMA_MEMCPY, fsl_edma->dma_dev.cap_mask); fsl_edma->dma_dev.dev = &pdev->dev; fsl_edma->dma_dev.device_alloc_chan_resources @@ -381,6 +383,7 @@ static int fsl_edma_probe(struct platform_device *pdev) fsl_edma->dma_dev.device_tx_status = fsl_edma_tx_status; fsl_edma->dma_dev.device_prep_slave_sg = fsl_edma_prep_slave_sg; fsl_edma->dma_dev.device_prep_dma_cyclic = fsl_edma_prep_dma_cyclic; + fsl_edma->dma_dev.device_prep_dma_memcpy = fsl_edma_prep_memcpy; fsl_edma->dma_dev.device_config = fsl_edma_slave_config; fsl_edma->dma_dev.device_pause = fsl_edma_pause; fsl_edma->dma_dev.device_resume = fsl_edma_resume; @@ -392,6 +395,10 @@ static int fsl_edma_probe(struct platform_device *pdev) fsl_edma->dma_dev.dst_addr_widths = FSL_EDMA_BUSWIDTHS; fsl_edma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + fsl_edma->dma_dev.copy_align = DMAENGINE_ALIGN_32_BYTES; + /* Per worst case 'nbytes = 1' take CITER as the max_seg_size */ + dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff); + platform_set_drvdata(pdev, fsl_edma); ret = dma_async_device_register(&fsl_edma->dma_dev); diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c index c855a0e4f9ff..97c87a7cba87 100644 --- a/drivers/dma/hisi_dma.c +++ b/drivers/dma/hisi_dma.c @@ -519,11 +519,7 @@ static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; } - ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); - if (ret) - return ret; - - ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (ret) return ret; diff --git a/drivers/dma/hsu/pci.c b/drivers/dma/hsu/pci.c index 9045a6f7f589..6a2df3dd78d0 100644 --- a/drivers/dma/hsu/pci.c +++ b/drivers/dma/hsu/pci.c @@ -65,11 +65,7 @@ static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); pci_try_set_mwi(pdev); - ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (ret) - return ret; - - ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (ret) return ret; diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 83a5ff2ecf2a..fab412349f7f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -135,8 +135,6 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) struct idxd_device *idxd = wq->idxd; struct device *dev = &idxd->pdev->dev; int rc, num_descs, i; - int align; - u64 tmp; if (wq->type != IDXD_WQT_KERNEL) return 0; @@ -148,21 +146,13 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) if (rc < 0) return rc; - align = idxd->data->align; - wq->compls_size = num_descs * idxd->data->compl_size + align; - wq->compls_raw = dma_alloc_coherent(dev, wq->compls_size, - &wq->compls_addr_raw, GFP_KERNEL); - if (!wq->compls_raw) { + wq->compls_size = num_descs * idxd->data->compl_size; + wq->compls = dma_alloc_coherent(dev, wq->compls_size, &wq->compls_addr, GFP_KERNEL); + if (!wq->compls) { rc = -ENOMEM; goto fail_alloc_compls; } - /* Adjust alignment */ - wq->compls_addr = (wq->compls_addr_raw + (align - 1)) & ~(align - 1); - tmp = (u64)wq->compls_raw; - tmp = (tmp + (align - 1)) & ~(align - 1); - wq->compls = (struct dsa_completion_record *)tmp; - rc = alloc_descs(wq, num_descs); if (rc < 0) goto fail_alloc_descs; @@ -191,8 +181,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) fail_sbitmap_init: free_descs(wq); fail_alloc_descs: - dma_free_coherent(dev, wq->compls_size, wq->compls_raw, - wq->compls_addr_raw); + dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); fail_alloc_compls: free_hw_descs(wq); return rc; @@ -207,8 +196,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq) free_hw_descs(wq); free_descs(wq); - dma_free_coherent(dev, wq->compls_size, wq->compls_raw, - wq->compls_addr_raw); + dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); sbitmap_queue_free(&wq->sbq); } @@ -427,7 +415,6 @@ void idxd_wq_quiesce(struct idxd_wq *wq) { percpu_ref_kill(&wq->wq_active); wait_for_completion(&wq->wq_dead); - percpu_ref_exit(&wq->wq_active); } /* Device control bits */ @@ -584,6 +571,8 @@ void idxd_device_reset(struct idxd_device *idxd) spin_lock(&idxd->dev_lock); idxd_device_clear_state(idxd); idxd->state = IDXD_DEV_DISABLED; + idxd_unmask_error_interrupts(idxd); + idxd_msix_perm_setup(idxd); spin_unlock(&idxd->dev_lock); } @@ -792,7 +781,7 @@ static int idxd_groups_config_write(struct idxd_device *idxd) struct device *dev = &idxd->pdev->dev; /* Setup bandwidth token limit */ - if (idxd->token_limit) { + if (idxd->hw.gen_cap.config_en && idxd->token_limit) { reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); reg.token_limit = idxd->token_limit; iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); @@ -1051,8 +1040,6 @@ static int idxd_wq_load_config(struct idxd_wq *wq) wq->size = wq->wqcfg->wq_size; wq->threshold = wq->wqcfg->wq_thresh; - if (wq->wqcfg->priv) - wq->type = IDXD_WQT_KERNEL; /* The driver does not support shared WQ mode in read-only config yet */ if (wq->wqcfg->mode == 0 || wq->wqcfg->pasid_en) diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c index e0f056c1d1f5..c39e9483206a 100644 --- a/drivers/dma/idxd/dma.c +++ b/drivers/dma/idxd/dma.c @@ -311,6 +311,7 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev) err_dma: idxd_wq_quiesce(wq); + percpu_ref_exit(&wq->wq_active); err_ref: idxd_wq_free_resources(wq); err_res_alloc: @@ -328,9 +329,9 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev) mutex_lock(&wq->wq_lock); idxd_wq_quiesce(wq); idxd_unregister_dma_channel(wq); - __drv_disable_wq(wq); idxd_wq_free_resources(wq); - wq->type = IDXD_WQT_NONE; + __drv_disable_wq(wq); + percpu_ref_exit(&wq->wq_active); mutex_unlock(&wq->wq_lock); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index bfcb03329f77..0cf8d3145870 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -187,9 +187,7 @@ struct idxd_wq { struct dsa_completion_record *compls; struct iax_completion_record *iax_compls; }; - void *compls_raw; dma_addr_t compls_addr; - dma_addr_t compls_addr_raw; int compls_size; struct idxd_desc **descs; struct sbitmap_queue sbq; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index eb09bc591c31..7bf03f371ce1 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -797,11 +797,19 @@ static void idxd_remove(struct pci_dev *pdev) int msixcnt = pci_msix_vec_count(pdev); int i; - dev_dbg(&pdev->dev, "%s called\n", __func__); + idxd_unregister_devices(idxd); + /* + * When ->release() is called for the idxd->conf_dev, it frees all the memory related + * to the idxd context. The driver still needs those bits in order to do the rest of + * the cleanup. However, we do need to unbound the idxd sub-driver. So take a ref + * on the device here to hold off the freeing while allowing the idxd sub-driver + * to unbind. + */ + get_device(idxd_confdev(idxd)); + device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); - idxd_unregister_devices(idxd); for (i = 0; i < msixcnt; i++) { irq_entry = &idxd->irq_entries[i]; @@ -815,7 +823,7 @@ static void idxd_remove(struct pci_dev *pdev) pci_disable_device(pdev); destroy_workqueue(idxd->wq); perfmon_pmu_remove(idxd); - device_unregister(idxd_confdev(idxd)); + put_device(idxd_confdev(idxd)); } static struct pci_driver idxd_pci_driver = { diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index ca88fa7a328e..17f2f8a31b63 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -63,6 +63,9 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) int i; bool err = false; + if (cause & IDXD_INTC_HALT_STATE) + goto halt; + if (cause & IDXD_INTC_ERR) { spin_lock(&idxd->dev_lock); for (i = 0; i < 4; i++) @@ -121,6 +124,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) if (!err) return 0; +halt: gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); if (gensts.state == IDXD_DEVICE_STATE_HALT) { idxd->state = IDXD_DEV_HALTED; @@ -134,6 +138,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) queue_work(idxd->wq, &idxd->work); } else { spin_lock(&idxd->dev_lock); + idxd->state = IDXD_DEV_HALTED; idxd_wqs_quiesce(idxd); idxd_wqs_unmap_portal(idxd); idxd_device_clear_state(idxd); @@ -221,8 +226,7 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry) list_for_each_entry_safe(desc, n, &irq_entry->work_list, list) { if (desc->completion->status) { - list_del(&desc->list); - list_add_tail(&desc->list, &flist); + list_move_tail(&desc->list, &flist); } } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index ffc7550a77ee..262c8220adbd 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -36,8 +36,7 @@ union gen_cap_reg { u64 max_batch_shift:4; u64 max_ims_mult:6; u64 config_en:1; - u64 max_descs_per_engine:8; - u64 rsvd3:24; + u64 rsvd3:32; }; u64 bits; } __packed; @@ -158,6 +157,7 @@ enum idxd_device_reset_type { #define IDXD_INTC_CMD 0x02 #define IDXD_INTC_OCCUPY 0x04 #define IDXD_INTC_PERFMON_OVFL 0x08 +#define IDXD_INTC_HALT_STATE 0x10 #define IDXD_CMD_OFFSET 0xa0 union idxd_command_reg { diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index cacc725ca545..75ec0754d4ad 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -741,9 +741,8 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size, unsigned long flags; buf_virt = dma_alloc_coherent(sdma->dev, size, &buf_phys, GFP_KERNEL); - if (!buf_virt) { + if (!buf_virt) return -ENOMEM; - } spin_lock_irqsave(&sdma->channel_0_lock, flags); @@ -1227,8 +1226,9 @@ static int sdma_config_channel(struct dma_chan *chan) if (sdmac->peripheral_type == IMX_DMATYPE_ASRC_SP || sdmac->peripheral_type == IMX_DMATYPE_ASRC) sdma_set_watermarklevel_for_p2p(sdmac); - } else + } else { __set_bit(sdmac->event_id0, sdmac->event_mask); + } /* Address */ sdmac->shp_addr = sdmac->per_address; @@ -1241,7 +1241,7 @@ static int sdma_config_channel(struct dma_chan *chan) } static int sdma_set_channel_priority(struct sdma_channel *sdmac, - unsigned int priority) + unsigned int priority) { struct sdma_engine *sdma = sdmac->sdma; int channel = sdmac->channel; @@ -1261,7 +1261,7 @@ static int sdma_request_channel0(struct sdma_engine *sdma) int ret = -EBUSY; sdma->bd0 = dma_alloc_coherent(sdma->dev, PAGE_SIZE, &sdma->bd0_phys, - GFP_NOWAIT); + GFP_NOWAIT); if (!sdma->bd0) { ret = -ENOMEM; goto out; @@ -1284,7 +1284,7 @@ static int sdma_alloc_bd(struct sdma_desc *desc) int ret = 0; desc->bd = dma_alloc_coherent(desc->sdmac->sdma->dev, bd_size, - &desc->bd_phys, GFP_NOWAIT); + &desc->bd_phys, GFP_NOWAIT); if (!desc->bd) { ret = -ENOMEM; goto out; @@ -1757,7 +1757,7 @@ static void sdma_issue_pending(struct dma_chan *chan) #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V4 46 static void sdma_add_scripts(struct sdma_engine *sdma, - const struct sdma_script_start_addrs *addr) + const struct sdma_script_start_addrs *addr) { s32 *addr_arr = (u32 *)addr; s32 *saddr_arr = (u32 *)sdma->script_addrs; @@ -1840,8 +1840,8 @@ static void sdma_load_firmware(const struct firmware *fw, void *context) clk_enable(sdma->clk_ahb); /* download the RAM image for SDMA */ sdma_load_script(sdma, ram_code, - header->ram_code_size, - addr->ram_code_start_addr); + header->ram_code_size, + addr->ram_code_start_addr); clk_disable(sdma->clk_ipg); clk_disable(sdma->clk_ahb); @@ -1850,8 +1850,8 @@ static void sdma_load_firmware(const struct firmware *fw, void *context) sdma->fw_loaded = true; dev_info(sdma->dev, "loaded firmware %d.%d\n", - header->version_major, - header->version_minor); + header->version_major, + header->version_minor); err_firmware: release_firmware(fw); @@ -1955,7 +1955,7 @@ static int sdma_init(struct sdma_engine *sdma) writel_relaxed(0, sdma->regs + SDMA_H_C0PTR); sdma->channel_control = dma_alloc_coherent(sdma->dev, - MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control) + + MAX_DMA_CHANNELS * sizeof(struct sdma_channel_control) + sizeof(struct sdma_context_data), &ccb_phys, GFP_KERNEL); @@ -1965,9 +1965,9 @@ static int sdma_init(struct sdma_engine *sdma) } sdma->context = (void *)sdma->channel_control + - MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control); + MAX_DMA_CHANNELS * sizeof(struct sdma_channel_control); sdma->context_phys = ccb_phys + - MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control); + MAX_DMA_CHANNELS * sizeof(struct sdma_channel_control); /* disable all channels */ for (i = 0; i < sdma->drvdata->num_events; i++) diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 191b59279007..373b8dac6c9b 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -1363,15 +1363,9 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!iomap) return -ENOMEM; - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (err) - return err; - - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) return err; diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c index a8cfb59f6efe..1b0a95892627 100644 --- a/drivers/dma/milbeaut-hdmac.c +++ b/drivers/dma/milbeaut-hdmac.c @@ -269,7 +269,7 @@ milbeaut_hdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (!md) return NULL; - md->sgl = kzalloc(sizeof(*sgl) * sg_len, GFP_NOWAIT); + md->sgl = kcalloc(sg_len, sizeof(*sgl), GFP_NOWAIT); if (!md->sgl) { kfree(md); return NULL; diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index 89f1814ff27a..a23563cd118b 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -1123,6 +1123,7 @@ static int mmp_pdma_probe(struct platform_device *op) mmp_pdma_dma_xlate, pdev); if (ret < 0) { dev_err(&op->dev, "of_dma_controller_register failed\n"); + dma_async_device_unregister(&pdev->device); return ret; } } diff --git a/drivers/dma/plx_dma.c b/drivers/dma/plx_dma.c index 166934544161..1ffcb5ca9788 100644 --- a/drivers/dma/plx_dma.c +++ b/drivers/dma/plx_dma.c @@ -563,15 +563,9 @@ static int plx_dma_probe(struct pci_dev *pdev, if (rc) return rc; - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(48)); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48)); if (rc) - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc) - return rc; - - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48)); - if (rc) - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (rc) return rc; diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index c8a77b428b52..87f6ca1541cf 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -388,6 +388,8 @@ struct bam_device { /* execution environment ID, from DT */ u32 ee; bool controlled_remotely; + bool powered_remotely; + u32 active_channels; const struct reg_offset_data *layout; @@ -416,6 +418,44 @@ static inline void __iomem *bam_addr(struct bam_device *bdev, u32 pipe, } /** + * bam_reset() - reset and initialize BAM registers + * @bdev: bam device + */ +static void bam_reset(struct bam_device *bdev) +{ + u32 val; + + /* s/w reset bam */ + /* after reset all pipes are disabled and idle */ + val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL)); + val |= BAM_SW_RST; + writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); + val &= ~BAM_SW_RST; + writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); + + /* make sure previous stores are visible before enabling BAM */ + wmb(); + + /* enable bam */ + val |= BAM_EN; + writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); + + /* set descriptor threshhold, start with 4 bytes */ + writel_relaxed(DEFAULT_CNT_THRSHLD, + bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); + + /* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */ + writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS)); + + /* enable irqs for errors */ + writel_relaxed(BAM_ERROR_EN | BAM_HRESP_ERR_EN, + bam_addr(bdev, 0, BAM_IRQ_EN)); + + /* unmask global bam interrupt */ + writel_relaxed(BAM_IRQ_MSK, bam_addr(bdev, 0, BAM_IRQ_SRCS_MSK_EE)); +} + +/** * bam_reset_channel - Reset individual BAM DMA channel * @bchan: bam channel * @@ -512,6 +552,9 @@ static int bam_alloc_chan(struct dma_chan *chan) return -ENOMEM; } + if (bdev->active_channels++ == 0 && bdev->powered_remotely) + bam_reset(bdev); + return 0; } @@ -565,6 +608,13 @@ static void bam_free_chan(struct dma_chan *chan) /* disable irq */ writel_relaxed(0, bam_addr(bdev, bchan->id, BAM_P_IRQ_EN)); + if (--bdev->active_channels == 0 && bdev->powered_remotely) { + /* s/w reset bam */ + val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL)); + val |= BAM_SW_RST; + writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); + } + err: pm_runtime_mark_last_busy(bdev->dev); pm_runtime_put_autosuspend(bdev->dev); @@ -1164,37 +1214,9 @@ static int bam_init(struct bam_device *bdev) bdev->num_channels = val & BAM_NUM_PIPES_MASK; } - if (bdev->controlled_remotely) - return 0; - - /* s/w reset bam */ - /* after reset all pipes are disabled and idle */ - val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL)); - val |= BAM_SW_RST; - writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); - val &= ~BAM_SW_RST; - writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); - - /* make sure previous stores are visible before enabling BAM */ - wmb(); - - /* enable bam */ - val |= BAM_EN; - writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); - - /* set descriptor threshhold, start with 4 bytes */ - writel_relaxed(DEFAULT_CNT_THRSHLD, - bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); - - /* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */ - writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS)); - - /* enable irqs for errors */ - writel_relaxed(BAM_ERROR_EN | BAM_HRESP_ERR_EN, - bam_addr(bdev, 0, BAM_IRQ_EN)); - - /* unmask global bam interrupt */ - writel_relaxed(BAM_IRQ_MSK, bam_addr(bdev, 0, BAM_IRQ_SRCS_MSK_EE)); + /* Reset BAM now if fully controlled locally */ + if (!bdev->controlled_remotely && !bdev->powered_remotely) + bam_reset(bdev); return 0; } @@ -1257,8 +1279,10 @@ static int bam_dma_probe(struct platform_device *pdev) bdev->controlled_remotely = of_property_read_bool(pdev->dev.of_node, "qcom,controlled-remotely"); + bdev->powered_remotely = of_property_read_bool(pdev->dev.of_node, + "qcom,powered-remotely"); - if (bdev->controlled_remotely) { + if (bdev->controlled_remotely || bdev->powered_remotely) { ret = of_property_read_u32(pdev->dev.of_node, "num-channels", &bdev->num_channels); if (ret) @@ -1270,7 +1294,7 @@ static int bam_dma_probe(struct platform_device *pdev) dev_err(bdev->dev, "num-ees unspecified in dt\n"); } - if (bdev->controlled_remotely) + if (bdev->controlled_remotely || bdev->powered_remotely) bdev->bamclk = devm_clk_get_optional(bdev->dev, "bam_clk"); else bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk"); diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c index 1e918e284fc0..a29c13cae716 100644 --- a/drivers/dma/sa11x0-dma.c +++ b/drivers/dma/sa11x0-dma.c @@ -1001,7 +1001,7 @@ static int sa11x0_dma_remove(struct platform_device *pdev) return 0; } -static int sa11x0_dma_suspend(struct device *dev) +static __maybe_unused int sa11x0_dma_suspend(struct device *dev) { struct sa11x0_dma_dev *d = dev_get_drvdata(dev); unsigned pch; @@ -1039,7 +1039,7 @@ static int sa11x0_dma_suspend(struct device *dev) return 0; } -static int sa11x0_dma_resume(struct device *dev) +static __maybe_unused int sa11x0_dma_resume(struct device *dev) { struct sa11x0_dma_dev *d = dev_get_drvdata(dev); unsigned pch; @@ -1072,12 +1072,7 @@ static int sa11x0_dma_resume(struct device *dev) } static const struct dev_pm_ops sa11x0_dma_pm_ops = { - .suspend_noirq = sa11x0_dma_suspend, - .resume_noirq = sa11x0_dma_resume, - .freeze_noirq = sa11x0_dma_suspend, - .thaw_noirq = sa11x0_dma_resume, - .poweroff_noirq = sa11x0_dma_suspend, - .restore_noirq = sa11x0_dma_resume, + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(sa11x0_dma_suspend, sa11x0_dma_resume) }; static struct platform_driver sa11x0_dma_driver = { diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 6885b3dcd7a9..5c7716fd6bc5 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1916,7 +1916,7 @@ static int rcar_dmac_probe(struct platform_device *pdev) ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); - return ret; + goto err_pm_disable; } ret = rcar_dmac_init(dmac); @@ -1924,7 +1924,7 @@ static int rcar_dmac_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to reset device\n"); - goto error; + goto err_pm_disable; } /* Initialize engine */ @@ -1958,14 +1958,14 @@ static int rcar_dmac_probe(struct platform_device *pdev) for_each_rcar_dmac_chan(i, dmac, chan) { ret = rcar_dmac_chan_probe(dmac, chan); if (ret < 0) - goto error; + goto err_pm_disable; } /* Register the DMAC as a DMA provider for DT. */ ret = of_dma_controller_register(pdev->dev.of_node, rcar_dmac_of_xlate, NULL); if (ret < 0) - goto error; + goto err_pm_disable; /* * Register the DMA engine device. @@ -1974,12 +1974,13 @@ static int rcar_dmac_probe(struct platform_device *pdev) */ ret = dma_async_device_register(engine); if (ret < 0) - goto error; + goto err_dma_free; return 0; -error: +err_dma_free: of_dma_controller_free(pdev->dev.of_node); +err_pm_disable: pm_runtime_disable(&pdev->dev); return ret; } diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index f9f30cbeccbe..ee2872e7d64c 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -18,6 +18,7 @@ #include <linux/of_dma.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -573,7 +574,7 @@ static void rz_dmac_issue_pending(struct dma_chan *chan) static u8 rz_dmac_ds_to_val_mapping(enum dma_slave_buswidth ds) { u8 i; - const enum dma_slave_buswidth ds_lut[] = { + static const enum dma_slave_buswidth ds_lut[] = { DMA_SLAVE_BUSWIDTH_1_BYTE, DMA_SLAVE_BUSWIDTH_2_BYTES, DMA_SLAVE_BUSWIDTH_4_BYTES, @@ -872,6 +873,13 @@ static int rz_dmac_probe(struct platform_device *pdev) /* Initialize the channels. */ INIT_LIST_HEAD(&dmac->engine.channels); + pm_runtime_enable(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) { + dev_err(&pdev->dev, "pm_runtime_resume_and_get failed\n"); + goto err_pm_disable; + } + for (i = 0; i < dmac->n_channels; i++) { ret = rz_dmac_chan_probe(dmac, &dmac->channels[i], i); if (ret < 0) @@ -925,6 +933,10 @@ err: channel->lmdesc.base_dma); } + pm_runtime_put(&pdev->dev); +err_pm_disable: + pm_runtime_disable(&pdev->dev); + return ret; } @@ -943,6 +955,8 @@ static int rz_dmac_remove(struct platform_device *pdev) } of_dma_controller_free(pdev->dev.of_node); dma_async_device_unregister(&dmac->engine); + pm_runtime_put(&pdev->dev); + pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 9063c727962e..83a37a6955a3 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -270,7 +270,6 @@ static enum dma_slave_buswidth stm32_dma_get_max_width(u32 buf_len, u32 threshold) { enum dma_slave_buswidth max_width; - u64 addr = buf_addr; if (threshold == STM32_DMA_FIFO_THRESHOLD_FULL) max_width = DMA_SLAVE_BUSWIDTH_4_BYTES; @@ -281,7 +280,7 @@ static enum dma_slave_buswidth stm32_dma_get_max_width(u32 buf_len, max_width > DMA_SLAVE_BUSWIDTH_1_BYTE) max_width = max_width >> 1; - if (do_div(addr, max_width)) + if (buf_addr & (max_width - 1)) max_width = DMA_SLAVE_BUSWIDTH_1_BYTE; return max_width; @@ -497,6 +496,7 @@ static int stm32_dma_terminate_all(struct dma_chan *c) spin_lock_irqsave(&chan->vchan.lock, flags); if (chan->desc) { + dma_cookie_complete(&chan->desc->vdesc.tx); vchan_terminate_vdesc(&chan->desc->vdesc); if (chan->busy) stm32_dma_stop(chan); @@ -753,8 +753,14 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan, if (src_bus_width < 0) return src_bus_width; - /* Set memory burst size */ - src_maxburst = STM32_DMA_MAX_BURST; + /* + * Set memory burst size - burst not possible if address is not aligned on + * the address boundary equal to the size of the transfer + */ + if (buf_addr & (buf_len - 1)) + src_maxburst = 1; + else + src_maxburst = STM32_DMA_MAX_BURST; src_best_burst = stm32_dma_get_best_burst(buf_len, src_maxburst, fifoth, @@ -803,8 +809,14 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan, if (dst_bus_width < 0) return dst_bus_width; - /* Set memory burst size */ - dst_maxburst = STM32_DMA_MAX_BURST; + /* + * Set memory burst size - burst not possible if address is not aligned on + * the address boundary equal to the size of the transfer + */ + if (buf_addr & (buf_len - 1)) + dst_maxburst = 1; + else + dst_maxburst = STM32_DMA_MAX_BURST; dst_best_burst = stm32_dma_get_best_burst(buf_len, dst_maxburst, fifoth, diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 18cbd1e43c2e..d30a4a28d3bf 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1566,7 +1566,8 @@ static int stm32_mdma_probe(struct platform_device *pdev) if (count < 0) count = 0; - dmadev = devm_kzalloc(&pdev->dev, sizeof(*dmadev) + sizeof(u32) * count, + dmadev = devm_kzalloc(&pdev->dev, + struct_size(dmadev, ahb_addr_masks, count), GFP_KERNEL); if (!dmadev) return -ENOMEM; diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index b1115a6d1935..ae39b52012b2 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -43,10 +43,8 @@ #define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs) (reqs << 4) #define ADMA_CH_FIFO_CTRL 0x2c -#define TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(val) (((val) & 0xf) << 8) -#define TEGRA210_ADMA_CH_FIFO_CTRL_RXSIZE(val) ((val) & 0xf) -#define TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(val) (((val) & 0x1f) << 8) -#define TEGRA186_ADMA_CH_FIFO_CTRL_RXSIZE(val) ((val) & 0x1f) +#define ADMA_CH_TX_FIFO_SIZE_SHIFT 8 +#define ADMA_CH_RX_FIFO_SIZE_SHIFT 0 #define ADMA_CH_LOWER_SRC_ADDR 0x34 #define ADMA_CH_LOWER_TRG_ADDR 0x3c @@ -61,29 +59,26 @@ #define TEGRA_ADMA_BURST_COMPLETE_TIME 20 -#define TEGRA210_FIFO_CTRL_DEFAULT (TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(3) | \ - TEGRA210_ADMA_CH_FIFO_CTRL_RXSIZE(3)) - -#define TEGRA186_FIFO_CTRL_DEFAULT (TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(3) | \ - TEGRA186_ADMA_CH_FIFO_CTRL_RXSIZE(3)) - #define ADMA_CH_REG_FIELD_VAL(val, mask, shift) (((val) & mask) << shift) struct tegra_adma; /* * struct tegra_adma_chip_data - Tegra chip specific data + * @adma_get_burst_config: Function callback used to set DMA burst size. * @global_reg_offset: Register offset of DMA global register. * @global_int_clear: Register offset of DMA global interrupt clear. * @ch_req_tx_shift: Register offset for AHUB transmit channel select. * @ch_req_rx_shift: Register offset for AHUB receive channel select. * @ch_base_offset: Register offset of DMA channel registers. - * @has_outstanding_reqs: If DMA channel can have outstanding requests. * @ch_fifo_ctrl: Default value for channel FIFO CTRL register. * @ch_req_mask: Mask for Tx or Rx channel select. * @ch_req_max: Maximum number of Tx or Rx channels available. * @ch_reg_size: Size of DMA channel register space. * @nr_channels: Number of DMA channels available. + * @ch_fifo_size_mask: Mask for FIFO size field. + * @sreq_index_offset: Slave channel index offset. + * @has_outstanding_reqs: If DMA channel can have outstanding requests. */ struct tegra_adma_chip_data { unsigned int (*adma_get_burst_config)(unsigned int burst_size); @@ -97,6 +92,8 @@ struct tegra_adma_chip_data { unsigned int ch_req_max; unsigned int ch_reg_size; unsigned int nr_channels; + unsigned int ch_fifo_size_mask; + unsigned int sreq_index_offset; bool has_outstanding_reqs; }; @@ -560,13 +557,14 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc, { struct tegra_adma_chan_regs *ch_regs = &desc->ch_regs; const struct tegra_adma_chip_data *cdata = tdc->tdma->cdata; - unsigned int burst_size, adma_dir; + unsigned int burst_size, adma_dir, fifo_size_shift; if (desc->num_periods > ADMA_CH_CONFIG_MAX_BUFS) return -EINVAL; switch (direction) { case DMA_MEM_TO_DEV: + fifo_size_shift = ADMA_CH_TX_FIFO_SIZE_SHIFT; adma_dir = ADMA_CH_CTRL_DIR_MEM2AHUB; burst_size = tdc->sconfig.dst_maxburst; ch_regs->config = ADMA_CH_CONFIG_SRC_BUF(desc->num_periods - 1); @@ -577,6 +575,7 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc, break; case DMA_DEV_TO_MEM: + fifo_size_shift = ADMA_CH_RX_FIFO_SIZE_SHIFT; adma_dir = ADMA_CH_CTRL_DIR_AHUB2MEM; burst_size = tdc->sconfig.src_maxburst; ch_regs->config = ADMA_CH_CONFIG_TRG_BUF(desc->num_periods - 1); @@ -598,7 +597,27 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc, ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1); if (cdata->has_outstanding_reqs) ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8); - ch_regs->fifo_ctrl = cdata->ch_fifo_ctrl; + + /* + * 'sreq_index' represents the current ADMAIF channel number and as per + * HW recommendation its FIFO size should match with the corresponding + * ADMA channel. + * + * ADMA FIFO size is set as per below (based on default ADMAIF channel + * FIFO sizes): + * fifo_size = 0x2 (sreq_index > sreq_index_offset) + * fifo_size = 0x3 (sreq_index <= sreq_index_offset) + * + */ + if (tdc->sreq_index > cdata->sreq_index_offset) + ch_regs->fifo_ctrl = + ADMA_CH_REG_FIELD_VAL(2, cdata->ch_fifo_size_mask, + fifo_size_shift); + else + ch_regs->fifo_ctrl = + ADMA_CH_REG_FIELD_VAL(3, cdata->ch_fifo_size_mask, + fifo_size_shift); + ch_regs->tc = desc->period_len & ADMA_CH_TC_COUNT_MASK; return tegra_adma_request_alloc(tdc, direction); @@ -782,12 +801,13 @@ static const struct tegra_adma_chip_data tegra210_chip_data = { .ch_req_tx_shift = 28, .ch_req_rx_shift = 24, .ch_base_offset = 0, - .has_outstanding_reqs = false, - .ch_fifo_ctrl = TEGRA210_FIFO_CTRL_DEFAULT, .ch_req_mask = 0xf, .ch_req_max = 10, .ch_reg_size = 0x80, .nr_channels = 22, + .ch_fifo_size_mask = 0xf, + .sreq_index_offset = 2, + .has_outstanding_reqs = false, }; static const struct tegra_adma_chip_data tegra186_chip_data = { @@ -797,12 +817,13 @@ static const struct tegra_adma_chip_data tegra186_chip_data = { .ch_req_tx_shift = 27, .ch_req_rx_shift = 22, .ch_base_offset = 0x10000, - .has_outstanding_reqs = true, - .ch_fifo_ctrl = TEGRA186_FIFO_CTRL_DEFAULT, .ch_req_mask = 0x1f, .ch_req_max = 20, .ch_reg_size = 0x100, .nr_channels = 32, + .ch_fifo_size_mask = 0x1f, + .sreq_index_offset = 4, + .has_outstanding_reqs = true, }; static const struct of_device_id tegra_adma_of_match[] = { @@ -867,7 +888,7 @@ static int tegra_adma_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) goto rpm_disable; @@ -940,7 +961,6 @@ static int tegra_adma_remove(struct platform_device *pdev) for (i = 0; i < tdma->nr_channels; ++i) irq_dispose_mapping(tdma->channels[i].irq); - pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); return 0; diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index a35858610780..041d8e32d630 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -1348,6 +1348,7 @@ static int bcdma_get_bchan(struct udma_chan *uc) { struct udma_dev *ud = uc->ud; enum udma_tp_level tpl; + int ret; if (uc->bchan) { dev_dbg(ud->dev, "chan%d: already have bchan%d allocated\n", @@ -1365,8 +1366,11 @@ static int bcdma_get_bchan(struct udma_chan *uc) tpl = ud->bchan_tpl.levels - 1; uc->bchan = __udma_reserve_bchan(ud, tpl, -1); - if (IS_ERR(uc->bchan)) - return PTR_ERR(uc->bchan); + if (IS_ERR(uc->bchan)) { + ret = PTR_ERR(uc->bchan); + uc->bchan = NULL; + return ret; + } uc->tchan = uc->bchan; @@ -1376,6 +1380,7 @@ static int bcdma_get_bchan(struct udma_chan *uc) static int udma_get_tchan(struct udma_chan *uc) { struct udma_dev *ud = uc->ud; + int ret; if (uc->tchan) { dev_dbg(ud->dev, "chan%d: already have tchan%d allocated\n", @@ -1390,8 +1395,11 @@ static int udma_get_tchan(struct udma_chan *uc) */ uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl, uc->config.mapped_channel_id); - if (IS_ERR(uc->tchan)) - return PTR_ERR(uc->tchan); + if (IS_ERR(uc->tchan)) { + ret = PTR_ERR(uc->tchan); + uc->tchan = NULL; + return ret; + } if (ud->tflow_cnt) { int tflow_id; @@ -1421,6 +1429,7 @@ static int udma_get_tchan(struct udma_chan *uc) static int udma_get_rchan(struct udma_chan *uc) { struct udma_dev *ud = uc->ud; + int ret; if (uc->rchan) { dev_dbg(ud->dev, "chan%d: already have rchan%d allocated\n", @@ -1435,8 +1444,13 @@ static int udma_get_rchan(struct udma_chan *uc) */ uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl, uc->config.mapped_channel_id); + if (IS_ERR(uc->rchan)) { + ret = PTR_ERR(uc->rchan); + uc->rchan = NULL; + return ret; + } - return PTR_ERR_OR_ZERO(uc->rchan); + return 0; } static int udma_get_chan_pair(struct udma_chan *uc) @@ -1490,6 +1504,7 @@ static int udma_get_chan_pair(struct udma_chan *uc) static int udma_get_rflow(struct udma_chan *uc, int flow_id) { struct udma_dev *ud = uc->ud; + int ret; if (!uc->rchan) { dev_err(ud->dev, "chan%d: does not have rchan??\n", uc->id); @@ -1503,8 +1518,13 @@ static int udma_get_rflow(struct udma_chan *uc, int flow_id) } uc->rflow = __udma_get_rflow(ud, flow_id); + if (IS_ERR(uc->rflow)) { + ret = PTR_ERR(uc->rflow); + uc->rflow = NULL; + return ret; + } - return PTR_ERR_OR_ZERO(uc->rflow); + return 0; } static void bcdma_put_bchan(struct udma_chan *uc) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index a4450bc95466..4677ce08ed40 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -792,7 +792,7 @@ static void xilinx_vdma_free_tx_segment(struct xilinx_dma_chan *chan, } /** - * xilinx_dma_tx_descriptor - Allocate transaction descriptor + * xilinx_dma_alloc_tx_descriptor - Allocate transaction descriptor * @chan: Driver specific DMA channel * * Return: The allocated descriptor on success and NULL on failure. @@ -998,14 +998,12 @@ static void xilinx_dma_chan_handle_cyclic(struct xilinx_dma_chan *chan, struct xilinx_dma_tx_descriptor *desc, unsigned long *flags) { - dma_async_tx_callback callback; - void *callback_param; + struct dmaengine_desc_callback cb; - callback = desc->async_tx.callback; - callback_param = desc->async_tx.callback_param; - if (callback) { + dmaengine_desc_get_callback(&desc->async_tx, &cb); + if (dmaengine_desc_callback_valid(&cb)) { spin_unlock_irqrestore(&chan->lock, *flags); - callback(callback_param); + dmaengine_desc_callback_invoke(&cb, NULL); spin_lock_irqsave(&chan->lock, *flags); } } @@ -2483,7 +2481,7 @@ static void xilinx_dma_synchronize(struct dma_chan *dchan) } /** - * xilinx_dma_channel_set_config - Configure VDMA channel + * xilinx_vdma_channel_set_config - Configure VDMA channel * Run-time configuration for Axi VDMA, supports: * . halt the channel * . configure interrupt coalescing and inter-packet delay threshold diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index b280a53e8570..ce5c66e6897d 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -271,9 +271,6 @@ struct xilinx_dpdma_device { /* ----------------------------------------------------------------------------- * DebugFS */ - -#ifdef CONFIG_DEBUG_FS - #define XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE 32 #define XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR "65535" @@ -299,7 +296,7 @@ struct xilinx_dpdma_debugfs_request { static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan) { - if (chan->id == dpdma_debugfs.chan_id) + if (IS_ENABLED(CONFIG_DEBUG_FS) && chan->id == dpdma_debugfs.chan_id) dpdma_debugfs.xilinx_dpdma_irq_done_count++; } @@ -462,16 +459,6 @@ static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev) dev_err(xdev->dev, "Failed to create debugfs testcase file\n"); } -#else -static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev) -{ -} - -static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan) -{ -} -#endif /* CONFIG_DEBUG_FS */ - /* ----------------------------------------------------------------------------- * I/O Accessors */ diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index 97f02f8eb03a..7aa63b652027 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -6,15 +6,12 @@ */ #include <linux/bitops.h> -#include <linux/dmapool.h> -#include <linux/dma/xilinx_dma.h> +#include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/module.h> -#include <linux/of_address.h> #include <linux/of_dma.h> -#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/slab.h> #include <linux/clk.h> @@ -603,22 +600,25 @@ static void zynqmp_dma_start_transfer(struct zynqmp_dma_chan *chan) static void zynqmp_dma_chan_desc_cleanup(struct zynqmp_dma_chan *chan) { struct zynqmp_dma_desc_sw *desc, *next; + unsigned long irqflags; + + spin_lock_irqsave(&chan->lock, irqflags); list_for_each_entry_safe(desc, next, &chan->done_list, node) { - dma_async_tx_callback callback; - void *callback_param; - - callback = desc->async_tx.callback; - callback_param = desc->async_tx.callback_param; - if (callback) { - spin_unlock(&chan->lock); - callback(callback_param); - spin_lock(&chan->lock); + struct dmaengine_desc_callback cb; + + dmaengine_desc_get_callback(&desc->async_tx, &cb); + if (dmaengine_desc_callback_valid(&cb)) { + spin_unlock_irqrestore(&chan->lock, irqflags); + dmaengine_desc_callback_invoke(&cb, NULL); + spin_lock_irqsave(&chan->lock, irqflags); } /* Run any dependencies, then free the descriptor */ zynqmp_dma_free_descriptor(chan, desc); } + + spin_unlock_irqrestore(&chan->lock, irqflags); } /** @@ -658,9 +658,13 @@ static void zynqmp_dma_issue_pending(struct dma_chan *dchan) */ static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan) { + unsigned long irqflags; + + spin_lock_irqsave(&chan->lock, irqflags); zynqmp_dma_free_desc_list(chan, &chan->active_list); zynqmp_dma_free_desc_list(chan, &chan->pending_list); zynqmp_dma_free_desc_list(chan, &chan->done_list); + spin_unlock_irqrestore(&chan->lock, irqflags); } /** @@ -670,11 +674,8 @@ static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan) static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan) { struct zynqmp_dma_chan *chan = to_chan(dchan); - unsigned long irqflags; - spin_lock_irqsave(&chan->lock, irqflags); zynqmp_dma_free_descriptors(chan); - spin_unlock_irqrestore(&chan->lock, irqflags); dma_free_coherent(chan->dev, (2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS), chan->desc_pool_v, chan->desc_pool_p); @@ -689,11 +690,16 @@ static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan) */ static void zynqmp_dma_reset(struct zynqmp_dma_chan *chan) { + unsigned long irqflags; + writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS); + spin_lock_irqsave(&chan->lock, irqflags); zynqmp_dma_complete_descriptor(chan); + spin_unlock_irqrestore(&chan->lock, irqflags); zynqmp_dma_chan_desc_cleanup(chan); zynqmp_dma_free_descriptors(chan); + zynqmp_dma_init(chan); } @@ -749,27 +755,27 @@ static void zynqmp_dma_do_tasklet(struct tasklet_struct *t) u32 count; unsigned long irqflags; - spin_lock_irqsave(&chan->lock, irqflags); - if (chan->err) { zynqmp_dma_reset(chan); chan->err = false; - goto unlock; + return; } + spin_lock_irqsave(&chan->lock, irqflags); count = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT); - while (count) { zynqmp_dma_complete_descriptor(chan); - zynqmp_dma_chan_desc_cleanup(chan); count--; } + spin_unlock_irqrestore(&chan->lock, irqflags); - if (chan->idle) - zynqmp_dma_start_transfer(chan); + zynqmp_dma_chan_desc_cleanup(chan); -unlock: - spin_unlock_irqrestore(&chan->lock, irqflags); + if (chan->idle) { + spin_lock_irqsave(&chan->lock, irqflags); + zynqmp_dma_start_transfer(chan); + spin_unlock_irqrestore(&chan->lock, irqflags); + } } /** @@ -781,12 +787,9 @@ unlock: static int zynqmp_dma_device_terminate_all(struct dma_chan *dchan) { struct zynqmp_dma_chan *chan = to_chan(dchan); - unsigned long irqflags; - spin_lock_irqsave(&chan->lock, irqflags); writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS); zynqmp_dma_free_descriptors(chan); - spin_unlock_irqrestore(&chan->lock, irqflags); return 0; } @@ -1061,16 +1064,14 @@ static int zynqmp_dma_probe(struct platform_device *pdev) p->dev = &pdev->dev; zdev->clk_main = devm_clk_get(&pdev->dev, "clk_main"); - if (IS_ERR(zdev->clk_main)) { - dev_err(&pdev->dev, "main clock not found.\n"); - return PTR_ERR(zdev->clk_main); - } + if (IS_ERR(zdev->clk_main)) + return dev_err_probe(&pdev->dev, PTR_ERR(zdev->clk_main), + "main clock not found.\n"); zdev->clk_apb = devm_clk_get(&pdev->dev, "clk_apb"); - if (IS_ERR(zdev->clk_apb)) { - dev_err(&pdev->dev, "apb clock not found.\n"); - return PTR_ERR(zdev->clk_apb); - } + if (IS_ERR(zdev->clk_apb)) + return dev_err_probe(&pdev->dev, PTR_ERR(zdev->clk_apb), + "apb clock not found.\n"); platform_set_drvdata(pdev, zdev); pm_runtime_set_autosuspend_delay(zdev->dev, ZDMA_PM_TIMEOUT); @@ -1085,7 +1086,7 @@ static int zynqmp_dma_probe(struct platform_device *pdev) ret = zynqmp_dma_chan_probe(zdev, pdev); if (ret) { - dev_err(&pdev->dev, "Probing channel failed\n"); + dev_err_probe(&pdev->dev, ret, "Probing channel failed\n"); goto err_disable_pm; } @@ -1097,7 +1098,7 @@ static int zynqmp_dma_probe(struct platform_device *pdev) ret = of_dma_controller_register(pdev->dev.of_node, of_zynqmp_dma_xlate, zdev); if (ret) { - dev_err(&pdev->dev, "Unable to register DMA to DT\n"); + dev_err_probe(&pdev->dev, ret, "Unable to register DMA to DT\n"); dma_async_device_unregister(&zdev->common); goto free_chan_resources; } @@ -1105,8 +1106,6 @@ static int zynqmp_dma_probe(struct platform_device *pdev) pm_runtime_mark_last_busy(zdev->dev); pm_runtime_put_sync_autosuspend(zdev->dev); - dev_info(&pdev->dev, "ZynqMP DMA driver Probe success\n"); - return 0; free_chan_resources: diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 2a7687911c09..29c0a616b317 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -520,7 +520,7 @@ static int svc_normal_to_secure_thread(void *data) * physical address of memory block reserved by secure monitor software at * secure world. * - * svc_normal_to_secure_shm_thread() calls do_exit() directly since it is a + * svc_normal_to_secure_shm_thread() terminates directly since it is a * standlone thread for which no one will call kthread_stop() or return when * 'kthread_should_stop()' is true. */ @@ -544,7 +544,7 @@ static int svc_normal_to_secure_shm_thread(void *data) } complete(&sh_mem->sync_complete); - do_exit(0); + return 0; } /** diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 2a926d0de423..0039df26854b 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -100,11 +100,25 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS This has the potential to use a lot of memory and print some very large kernel messages. If in doubt, say "N". +config DRM_DEBUG_MODESET_LOCK + bool "Enable backtrace history for lock contention" + depends on STACKTRACE_SUPPORT + depends on DEBUG_KERNEL + depends on EXPERT + select STACKDEPOT + default y if DEBUG_WW_MUTEX_SLOWPATH + help + Enable debug tracing of failures to gracefully handle drm modeset lock + contention. A history of each drm modeset lock path hitting -EDEADLK + will be saved until gracefully handled, and the backtrace will be + printed when attempting to lock a contended lock. + + If in doubt, say "N". + config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" - depends on DRM - depends on FB=y || FB=DRM - select DRM_KMS_HELPER + depends on DRM_KMS_HELPER + depends on FB=y || FB=DRM_KMS_HELPER select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 751557af09bb..a15a4787c7ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -297,7 +297,7 @@ void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd); void amdgpu_amdkfd_gpuvm_init_mem_limits(void); void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, struct amdgpu_vm *vm); -void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo); +void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo); void amdgpu_amdkfd_reserve_system_mem(uint64_t size); #else static inline @@ -312,7 +312,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, } static inline -void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo) +void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo) { } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 0e9cfe99ae9e..71acd577803e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -207,7 +207,7 @@ static void unreserve_mem_limit(struct amdgpu_device *adev, spin_unlock(&kfd_mem_limit.mem_limit_lock); } -void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo) +void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); u32 domain = bo->preferred_domains; @@ -219,6 +219,8 @@ void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo) } unreserve_mem_limit(adev, amdgpu_bo_size(bo), domain, sg); + + kfree(bo->kfd_bo); } @@ -734,14 +736,19 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem, } /* Add BO to VM internal data structures */ + ret = amdgpu_bo_reserve(bo[i], false); + if (ret) { + pr_debug("Unable to reserve BO during memory attach"); + goto unwind; + } attachment[i]->bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]); + amdgpu_bo_unreserve(bo[i]); if (unlikely(!attachment[i]->bo_va)) { ret = -ENOMEM; pr_err("Failed to add BO object to VM. ret == %d\n", ret); goto unwind; } - attachment[i]->va = va; attachment[i]->pte_flags = get_pte_flags(adev, mem); attachment[i]->adev = adev; @@ -757,7 +764,9 @@ unwind: if (!attachment[i]) continue; if (attachment[i]->bo_va) { + amdgpu_bo_reserve(bo[i], true); amdgpu_vm_bo_rmv(adev, attachment[i]->bo_va); + amdgpu_bo_unreserve(bo[i]); list_del(&attachment[i]->list); } if (bo[i]) @@ -1568,12 +1577,12 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va, mem->va + bo_size * (1 + mem->aql_queue)); - ret = unreserve_bo_and_vms(&ctx, false, false); - /* Remove from VM internal data structures */ list_for_each_entry_safe(entry, tmp, &mem->attachments, list) kfd_mem_detach(entry); + ret = unreserve_bo_and_vms(&ctx, false, false); + /* Free the sync object */ amdgpu_sync_free(&mem->sync); @@ -1600,9 +1609,13 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( drm_vma_node_revoke(&mem->bo->tbo.base.vma_node, drm_priv); if (mem->dmabuf) dma_buf_put(mem->dmabuf); - drm_gem_object_put(&mem->bo->tbo.base); mutex_destroy(&mem->lock); - kfree(mem); + + /* If this releases the last reference, it will end up calling + * amdgpu_amdkfd_release_notify and kfree the mem struct. That's why + * this needs to be the last call here. + */ + drm_gem_object_put(&mem->bo->tbo.base); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6e40cc1bc6dc..5625f7736e37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2398,10 +2398,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (!adev->gmc.xgmi.pending_reset) amdgpu_amdkfd_device_init(adev); - r = amdgpu_amdkfd_resume_iommu(adev); - if (r) - goto init_failed; - amdgpu_fru_get_product_info(adev); init_failed: @@ -3171,11 +3167,21 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type) { switch (asic_type) { #if defined(CONFIG_DRM_AMD_DC) -#if defined(CONFIG_DRM_AMD_DC_SI) case CHIP_TAHITI: case CHIP_PITCAIRN: case CHIP_VERDE: case CHIP_OLAND: + /* + * We have systems in the wild with these ASICs that require + * LVDS and VGA support which is not supported with DC. + * + * Fallback to the non-DC driver here by default so as not to + * cause regressions. + */ +#if defined(CONFIG_DRM_AMD_DC_SI) + return amdgpu_dc > 0; +#else + return false; #endif case CHIP_BONAIRE: case CHIP_KAVERI: @@ -4287,8 +4293,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; - amdgpu_amdkfd_pre_reset(adev); - /* Resume IP prior to SMC */ r = amdgpu_device_ip_reinit_early_sriov(adev); if (r) @@ -4850,6 +4854,9 @@ static void amdgpu_device_recheck_guilty_jobs( /* clear job's guilty and depend the folowing step to decide the real one */ drm_sched_reset_karma(s_job); + /* for the real bad job, it will be resubmitted twice, adding a dma_fence_get + * to make sure fence is balanced */ + dma_fence_get(s_job->s_fence->parent); drm_sched_resubmit_jobs_ext(&ring->sched, 1); ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout); @@ -4885,6 +4892,7 @@ retry: /* got the hw fence, signal finished fence */ atomic_dec(ring->sched.score); + dma_fence_put(s_job->s_fence->parent); dma_fence_get(&s_job->s_fence->finished); dma_fence_signal(&s_job->s_fence->finished); dma_fence_put(&s_job->s_fence->finished); @@ -5020,8 +5028,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, cancel_delayed_work_sync(&tmp_adev->delayed_init_work); - if (!amdgpu_sriov_vf(tmp_adev)) - amdgpu_amdkfd_pre_reset(tmp_adev); + amdgpu_amdkfd_pre_reset(tmp_adev); /* * Mark these ASICs to be reseted as untracked first diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index d7c8d9e3c203..ff70bc233489 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -867,7 +867,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(2, 0, 2): case IP_VERSION(2, 2, 0): amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); + if (!amdgpu_sriov_vf(adev)) + amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); break; case IP_VERSION(2, 0, 3): break; @@ -881,6 +882,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev) break; case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 16): + case IP_VERSION(3, 0, 64): case IP_VERSION(3, 1, 1): case IP_VERSION(3, 0, 2): amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index a573424a6e0b..a1e63ba4c54a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -60,9 +60,10 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf) goto unlock; } - ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, - TTM_BO_VM_NUM_PREFAULT, 1); - drm_dev_exit(idx); + ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, + TTM_BO_VM_NUM_PREFAULT); + + drm_dev_exit(idx); } else { ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index dfe667ea8b05..651c7abfde03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1423,6 +1423,8 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused) struct drm_amdgpu_info_firmware fw_info; struct drm_amdgpu_query_fw query_fw; struct atom_context *ctx = adev->mode_info.atom_context; + uint8_t smu_minor, smu_debug; + uint16_t smu_major; int ret, i; static const char *ta_fw_name[TA_FW_TYPE_MAX_INDEX] = { @@ -1568,8 +1570,11 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused) ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); if (ret) return ret; - seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n", - fw_info.feature, fw_info.ver); + smu_major = (fw_info.ver >> 16) & 0xffff; + smu_minor = (fw_info.ver >> 8) & 0xff; + smu_debug = (fw_info.ver >> 0) & 0xff; + seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x (%d.%d.%d)\n", + fw_info.feature, fw_info.ver, smu_major, smu_minor, smu_debug); /* SDMA */ query_fw.fw_type = AMDGPU_INFO_FW_SDMA; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index aeb92e5677ac..4fcfc2313b8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1274,7 +1274,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) abo = ttm_to_amdgpu_bo(bo); if (abo->kfd_bo) - amdgpu_amdkfd_unreserve_memory_limit(abo); + amdgpu_amdkfd_release_notify(abo); /* We only remove the fence if the resv has individualized. */ WARN_ON_ONCE(bo->type == ttm_bo_type_kernel diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 2658414c503d..4f7c70845785 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -134,6 +134,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) adev->vcn.indirect_sram = true; break; case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 64): if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0)) fw_name = FIRMWARE_SIENNA_CICHLID; else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 978ac927ac11..0fad2bf854ae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -806,9 +806,9 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++) pcs_clear_status(adev, xgmi23_pcs_err_status_reg_aldebaran[i]); - for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++) + for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++) pcs_clear_status(adev, - xgmi23_pcs_err_status_reg_aldebaran[i]); + xgmi3x16_pcs_err_status_reg_aldebaran[i]); for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++) pcs_clear_status(adev, walf_pcs_err_status_reg_aldebaran[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 90a834dc4008..e7dfeb466a0e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -8249,6 +8249,9 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { u32 reg, data; + + amdgpu_gfx_off_ctrl(adev, false); + /* not for *_SOC15 */ reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL); if (amdgpu_sriov_is_pp_one_vf(adev)) @@ -8263,6 +8266,8 @@ static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data); else WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data); + + amdgpu_gfx_off_ctrl(adev, true); } static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev, @@ -8316,11 +8321,8 @@ static void gfx_v10_cntl_power_gating(struct amdgpu_device *adev, bool enable) if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): - data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh; - WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data); - break; case IP_VERSION(10, 3, 3): - data = 0x1388 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh; + data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh; WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 37b4a3db6360..d17a6f399347 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3575,12 +3575,16 @@ static void gfx_v7_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { u32 data; + amdgpu_gfx_off_ctrl(adev, false); + data = RREG32(mmRLC_SPM_VMID); data &= ~RLC_SPM_VMID__RLC_SPM_VMID_MASK; data |= (vmid & RLC_SPM_VMID__RLC_SPM_VMID_MASK) << RLC_SPM_VMID__RLC_SPM_VMID__SHIFT; WREG32(mmRLC_SPM_VMID, data); + + amdgpu_gfx_off_ctrl(adev, true); } static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index e0302c23e9a7..5f112efda634 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -5624,6 +5624,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { u32 data; + amdgpu_gfx_off_ctrl(adev, false); + if (amdgpu_sriov_is_pp_one_vf(adev)) data = RREG32_NO_KIQ(mmRLC_SPM_VMID); else @@ -5636,6 +5638,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) WREG32_NO_KIQ(mmRLC_SPM_VMID, data); else WREG32(mmRLC_SPM_VMID, data); + + amdgpu_gfx_off_ctrl(adev, true); } static const struct amdgpu_rlc_funcs iceland_rlc_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 7f944bb11298..b4b80f27b894 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2462,7 +2462,9 @@ static int gfx_v9_0_sw_fini(void *handle) amdgpu_gfx_kiq_fini(adev); gfx_v9_0_mec_fini(adev); - amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj); + amdgpu_bo_free_kernel(&adev->gfx.rlc.clear_state_obj, + &adev->gfx.rlc.clear_state_gpu_addr, + (void **)&adev->gfx.rlc.cs_ptr); if (adev->flags & AMD_IS_APU) { amdgpu_bo_free_kernel(&adev->gfx.rlc.cp_table_obj, &adev->gfx.rlc.cp_table_gpu_addr, @@ -5102,6 +5104,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { u32 reg, data; + amdgpu_gfx_off_ctrl(adev, false); + reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL); if (amdgpu_sriov_is_pp_one_vf(adev)) data = RREG32_NO_KIQ(reg); @@ -5115,6 +5119,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data); else WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data); + + amdgpu_gfx_off_ctrl(adev, true); } static bool gfx_v9_0_check_rlcg_range(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index bda1542ef1dd..480e41847d7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -348,6 +348,10 @@ static void gfxhub_v1_0_gart_disable(struct amdgpu_device *adev) WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT0_CNTL, i * hub->ctx_distance, 0); + if (amdgpu_sriov_vf(adev)) + /* Avoid write to GMC registers */ + return; + /* Setup TLB control */ tmp = RREG32_SOC15(GC, 0, mmMC_VM_MX_L1_TLB_CNTL); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c index 497b86c376c6..90f0aefbdb39 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c @@ -54,15 +54,17 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev) seg_size = REG_GET_FIELD( RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE_ALDE), MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24; + max_region = + REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE, PF_MAX_REGION); } else { xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL); seg_size = REG_GET_FIELD( RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE), MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24; + max_region = + REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION); } - max_region = - REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION); switch (adev->asic_type) { @@ -89,9 +91,15 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev) if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes) return -EINVAL; - adev->gmc.xgmi.physical_node_id = - REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, - PF_LFB_REGION); + if (adev->asic_type == CHIP_ALDEBARAN) { + adev->gmc.xgmi.physical_node_id = + REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE, + PF_LFB_REGION); + } else { + adev->gmc.xgmi.physical_node_id = + REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, + PF_LFB_REGION); + } if (adev->gmc.xgmi.physical_node_id > max_physical_node_id) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index febc903adf58..59eafa31c626 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -182,6 +182,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, { switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 64): if (amdgpu_sriov_vf(adev)) { if (encode) *codecs = &sriov_sc_video_codecs_encode; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index d5d023a24269..2d558c2f417d 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -534,6 +534,19 @@ static int uvd_v6_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cancel_delayed_work_sync(&adev->uvd.idle_work); + + if (RREG32(mmUVD_STATUS) != 0) + uvd_v6_0_stop(adev); + + return 0; +} + +static int uvd_v6_0_suspend(void *handle) +{ + int r; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + /* * Proper cleanups before halting the HW engine: * - cancel the delayed idle work @@ -558,17 +571,6 @@ static int uvd_v6_0_hw_fini(void *handle) AMD_CG_STATE_GATE); } - if (RREG32(mmUVD_STATUS) != 0) - uvd_v6_0_stop(adev); - - return 0; -} - -static int uvd_v6_0_suspend(void *handle) -{ - int r; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = uvd_v6_0_hw_fini(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 0fffaf859c59..3b119db16003 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -406,7 +406,7 @@ static const struct kfd_device_info aldebaran_device_info = { static const struct kfd_device_info renoir_device_info = { .asic_family = CHIP_RENOIR, .asic_name = "renoir", - .gfx_target_version = 90002, + .gfx_target_version = 90012, .max_pasid_bits = 16, .max_no_of_hqd = 24, .doorbell_size = 8, 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 533b27b35fc9..003ba6a373ff 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1430,7 +1430,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, if (!dqm->sched_running) return 0; - if (dqm->is_hws_hang) + if (dqm->is_hws_hang || dqm->is_resetting) return -EIO; if (!dqm->active_runlist) return retval; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c index 2e86692def19..d1388896f9c1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c @@ -308,7 +308,7 @@ * 16MB are reserved for kernel use (CWSR trap handler and kernel IB * for now). */ -#define SVM_USER_BASE 0x1000000ull +#define SVM_USER_BASE (u64)(KFD_CWSR_TBA_TMA_SIZE + 2*PAGE_SIZE) #define SVM_CWSR_BASE (SVM_USER_BASE - KFD_CWSR_TBA_TMA_SIZE) #define SVM_IB_BASE (SVM_CWSR_BASE - PAGE_SIZE) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 6d8634e40b3b..9b9c2b9bf2ef 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -281,6 +281,19 @@ static unsigned long svm_migrate_successful_pages(struct migrate_vma *migrate) return cpages; } +static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate) +{ + unsigned long upages = 0; + unsigned long i; + + for (i = 0; i < migrate->npages; i++) { + if (migrate->src[i] & MIGRATE_PFN_VALID && + !(migrate->src[i] & MIGRATE_PFN_MIGRATE)) + upages++; + } + return upages; +} + static int svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, @@ -317,7 +330,6 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); svm_migrate_get_vram_page(prange, migrate->dst[i]); migrate->dst[i] = migrate_pfn(migrate->dst[i]); - migrate->dst[i] |= MIGRATE_PFN_LOCKED; src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, DMA_TO_DEVICE); r = dma_mapping_error(dev, src[i]); @@ -610,7 +622,6 @@ 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)); - migrate->dst[i] |= MIGRATE_PFN_LOCKED; j++; } @@ -634,10 +645,11 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end) { uint64_t npages = (end - start) >> PAGE_SHIFT; + unsigned long upages = npages; + unsigned long cpages = 0; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; struct migrate_vma migrate; - unsigned long cpages = 0; dma_addr_t *scratch; size_t size; void *buf; @@ -671,6 +683,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, if (!cpages) { pr_debug("failed collect migrate device pages [0x%lx 0x%lx]\n", prange->start, prange->last); + upages = svm_migrate_unsuccessful_pages(&migrate); goto out_free; } if (cpages != npages) @@ -683,8 +696,9 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, scratch, npages); migrate_vma_pages(&migrate); - pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n", - svm_migrate_successful_pages(&migrate), cpages, migrate.npages); + upages = svm_migrate_unsuccessful_pages(&migrate); + pr_debug("unsuccessful/cpages/npages 0x%lx/0x%lx/0x%lx\n", + upages, cpages, migrate.npages); svm_migrate_copy_done(adev, mfence); migrate_vma_finalize(&migrate); @@ -698,9 +712,9 @@ out: if (pdd) WRITE_ONCE(pdd->page_out, pdd->page_out + cpages); - return cpages; + return upages; } - return r; + return r ? r : upages; } /** @@ -720,7 +734,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm) unsigned long addr; unsigned long start; unsigned long end; - unsigned long cpages = 0; + unsigned long upages = 0; long r = 0; if (!prange->actual_loc) { @@ -756,12 +770,12 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm) pr_debug("failed %ld to migrate\n", r); break; } else { - cpages += r; + upages += r; } addr = next; } - if (cpages) { + if (!upages) { svm_range_vram_node_free(prange); prange->actual_loc = 0; } @@ -784,7 +798,7 @@ static int svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc, struct mm_struct *mm) { - int r; + int r, retries = 3; /* * TODO: for both devices with PCIe large bar or on same xgmi hive, skip @@ -793,9 +807,14 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc, pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc); - r = svm_migrate_vram_to_ram(prange, mm); - if (r) - return r; + do { + r = svm_migrate_vram_to_ram(prange, mm); + if (r) + return r; + } while (prange->actual_loc && --retries); + + if (prange->actual_loc) + return -EDEADLK; return svm_migrate_ram_to_vram(prange, best_loc, mm); } @@ -840,6 +859,11 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) pr_debug("failed find process at fault address 0x%lx\n", addr); return VM_FAULT_SIGBUS; } + if (READ_ONCE(p->svms.faulting_task) == current) { + pr_debug("skipping ram migration\n"); + kfd_unref_process(p); + return 0; + } addr >>= PAGE_SHIFT; pr_debug("CPU page fault svms 0x%p address 0x%lx\n", &p->svms, addr); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 4104b167e721..94e92c0812db 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -766,8 +766,10 @@ struct svm_range_list { struct list_head deferred_range_list; spinlock_t deferred_list_lock; atomic_t evicted_ranges; + bool drain_pagefaults; struct delayed_work restore_work; DECLARE_BITMAP(bitmap_supported, MAX_GPU_INSTANCE); + struct task_struct *faulting_task; }; /* Process data */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 457863861d6f..b993011cfa64 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1715,7 +1715,11 @@ int kfd_process_evict_queues(struct kfd_process *p) r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm, &pdd->qpd); - if (r) { + /* evict return -EIO if HWS is hang or asic is resetting, in this case + * we would like to set all the queues to be in evicted state to prevent + * them been add back since they actually not be saved right now. + */ + if (r && r != -EIO) { pr_err("Failed to evict process queues\n"); goto fail; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index b691c8495d66..16137c4247bb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1496,9 +1496,11 @@ static int svm_range_validate_and_map(struct mm_struct *mm, next = min(vma->vm_end, end); npages = (next - addr) >> PAGE_SHIFT; + WRITE_ONCE(p->svms.faulting_task, current); r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL, addr, npages, &hmm_range, readonly, true, owner); + WRITE_ONCE(p->svms.faulting_task, NULL); if (r) { pr_debug("failed %d to get svm range pages\n", r); goto unreserve_out; @@ -2000,20 +2002,28 @@ static void svm_range_deferred_list_work(struct work_struct *work) pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange, prange->start, prange->last, prange->work_item.op); - /* Make sure no stale retry fault coming after range is freed */ - if (prange->work_item.op == SVM_OP_UNMAP_RANGE) - svm_range_drain_retry_fault(prange->svms); - mm = prange->work_item.mm; +retry: mmap_write_lock(mm); mutex_lock(&svms->lock); - /* Remove from deferred_list must be inside mmap write lock, + /* Checking for the need to drain retry faults must be in + * mmap write lock to serialize with munmap notifiers. + * + * Remove from deferred_list must be inside mmap write lock, * otherwise, svm_range_list_lock_and_flush_work may hold mmap * write lock, and continue because deferred_list is empty, then * deferred_list handle is blocked by mmap write lock. */ spin_lock(&svms->deferred_list_lock); + if (unlikely(svms->drain_pagefaults)) { + svms->drain_pagefaults = false; + spin_unlock(&svms->deferred_list_lock); + mutex_unlock(&svms->lock); + mmap_write_unlock(mm); + svm_range_drain_retry_fault(svms); + goto retry; + } list_del_init(&prange->deferred_list); spin_unlock(&svms->deferred_list_lock); @@ -2046,6 +2056,12 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange, struct mm_struct *mm, enum svm_work_list_ops op) { spin_lock(&svms->deferred_list_lock); + /* Make sure pending page faults are drained in the deferred worker + * before the range is freed to avoid straggler interrupts on + * unmapped memory causing "phantom faults". + */ + if (op == SVM_OP_UNMAP_RANGE) + svms->drain_pagefaults = true; /* if prange is on the deferred list */ if (!list_empty(&prange->deferred_list)) { pr_debug("update exist prange 0x%p work op %d\n", prange, op); @@ -2261,7 +2277,7 @@ svm_range_from_addr(struct svm_range_list *svms, unsigned long addr, * migration if actual loc is not best location, then update GPU page table * mapping to the best location. * - * If vm fault gpu is range preferred loc, the best_loc is preferred loc. + * If the preferred loc is accessible by faulting GPU, use preferred loc. * If vm fault gpu idx is on range ACCESSIBLE bitmap, best_loc is vm fault gpu * If vm fault gpu idx is on range ACCESSIBLE_IN_PLACE bitmap, then * if range actual loc is cpu, best_loc is cpu @@ -2278,7 +2294,7 @@ svm_range_best_restore_location(struct svm_range *prange, struct amdgpu_device *adev, int32_t *gpuidx) { - struct amdgpu_device *bo_adev; + struct amdgpu_device *bo_adev, *preferred_adev; struct kfd_process *p; uint32_t gpuid; int r; @@ -2291,8 +2307,16 @@ svm_range_best_restore_location(struct svm_range *prange, return -1; } - if (prange->preferred_loc == gpuid) + if (prange->preferred_loc == gpuid || + prange->preferred_loc == KFD_IOCTL_SVM_LOCATION_SYSMEM) { return prange->preferred_loc; + } else if (prange->preferred_loc != KFD_IOCTL_SVM_LOCATION_UNDEFINED) { + preferred_adev = svm_range_get_adev_by_id(prange, + prange->preferred_loc); + if (amdgpu_xgmi_same_hive(adev, preferred_adev)) + return prange->preferred_loc; + /* fall through */ + } if (test_bit(*gpuidx, prange->bitmap_access)) return gpuid; @@ -2313,7 +2337,8 @@ svm_range_best_restore_location(struct svm_range *prange, static int svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, - unsigned long *start, unsigned long *last) + unsigned long *start, unsigned long *last, + bool *is_heap_stack) { struct vm_area_struct *vma; struct interval_tree_node *node; @@ -2324,6 +2349,12 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, pr_debug("VMA does not exist in address [0x%llx]\n", addr); return -EFAULT; } + + *is_heap_stack = (vma->vm_start <= vma->vm_mm->brk && + vma->vm_end >= vma->vm_mm->start_brk) || + (vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack); + start_limit = max(vma->vm_start >> PAGE_SHIFT, (unsigned long)ALIGN_DOWN(addr, 2UL << 8)); end_limit = min(vma->vm_end >> PAGE_SHIFT, @@ -2353,9 +2384,9 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, *start = start_limit; *last = end_limit - 1; - pr_debug("vma start: 0x%lx start: 0x%lx vma end: 0x%lx last: 0x%lx\n", - vma->vm_start >> PAGE_SHIFT, *start, - vma->vm_end >> PAGE_SHIFT, *last); + pr_debug("vma [0x%lx 0x%lx] range [0x%lx 0x%lx] is_heap_stack %d\n", + vma->vm_start >> PAGE_SHIFT, vma->vm_end >> PAGE_SHIFT, + *start, *last, *is_heap_stack); return 0; } @@ -2420,11 +2451,13 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev, struct svm_range *prange = NULL; unsigned long start, last; uint32_t gpuid, gpuidx; + bool is_heap_stack; uint64_t bo_s = 0; uint64_t bo_l = 0; int r; - if (svm_range_get_range_boundaries(p, addr, &start, &last)) + if (svm_range_get_range_boundaries(p, addr, &start, &last, + &is_heap_stack)) return NULL; r = svm_range_check_vm(p, start, last, &bo_s, &bo_l); @@ -2451,6 +2484,9 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev, return NULL; } + if (is_heap_stack) + prange->preferred_loc = KFD_IOCTL_SVM_LOCATION_SYSMEM; + svm_range_add_to_svms(prange); svm_range_add_notifier_locked(mm, prange); @@ -3076,6 +3112,8 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) struct svm_range *prange = list_first_entry(&svm_bo->range_list, struct svm_range, svm_bo_list); + int retries = 3; + list_del_init(&prange->svm_bo_list); spin_unlock(&svm_bo->list_lock); @@ -3083,7 +3121,11 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) prange->start, prange->last); mutex_lock(&prange->migrate_mutex); - svm_migrate_vram_to_ram(prange, svm_bo->eviction_fence->mm); + do { + svm_migrate_vram_to_ram(prange, + svm_bo->eviction_fence->mm); + } while (prange->actual_loc && --retries); + WARN(prange->actual_loc, "Migration failed during eviction"); mutex_lock(&prange->lock); prange->svm_bo = NULL; 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 43e983e42c0f..c911b30de658 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -217,6 +217,7 @@ static const struct drm_format_info * amd_get_format_info(const struct drm_mode_fb_cmd2 *cmd); static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector); +static void handle_hpd_rx_irq(void *param); static bool is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state, @@ -619,7 +620,7 @@ static void dm_dcn_vertical_interrupt0_high_irq(void *interrupt_params) amdgpu_dm_crtc_handle_crc_window_irq(&acrtc->base); } -#endif +#endif /* CONFIG_DRM_AMD_SECURE_DISPLAY */ /** * dmub_aux_setconfig_reply_callback - Callback for AUX or SET_CONFIG command. @@ -669,10 +670,7 @@ void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *not return; } - drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); - link_index = notify->link_index; - link = adev->dm.dc->links[link_index]; drm_connector_list_iter_begin(dev, &iter); @@ -685,10 +683,13 @@ void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *not } } drm_connector_list_iter_end(&iter); - drm_modeset_unlock(&dev->mode_config.connection_mutex); - if (hpd_aconnector) - handle_hpd_irq_helper(hpd_aconnector); + if (hpd_aconnector) { + if (notify->type == DMUB_NOTIFICATION_HPD) + handle_hpd_irq_helper(hpd_aconnector); + else if (notify->type == DMUB_NOTIFICATION_HPD_IRQ) + handle_hpd_rx_irq(hpd_aconnector); + } } /** @@ -764,6 +765,10 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params) DRM_ERROR("DM: notify type %d invalid!", notify.type); continue; } + if (!dm->dmub_callback[notify.type]) { + DRM_DEBUG_DRIVER("DMUB notification skipped, no handler: type=%d\n", notify.type); + continue; + } if (dm->dmub_thread_offload[notify.type] == true) { dmub_hpd_wrk = kzalloc(sizeof(*dmub_hpd_wrk), GFP_ATOMIC); if (!dmub_hpd_wrk) { @@ -813,7 +818,7 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params) if (count > DMUB_TRACE_MAX_READ) DRM_DEBUG_DRIVER("Warning : count > DMUB_TRACE_MAX_READ"); } -#endif +#endif /* CONFIG_DRM_AMD_DC_DCN */ static int dm_set_clockgating_state(void *handle, enum amd_clockgating_state state) @@ -1410,7 +1415,15 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) switch (adev->ip_versions[DCE_HWIP][0]) { case IP_VERSION(2, 1, 0): init_data.flags.gpu_vm_support = true; - init_data.flags.disable_dmcu = true; + switch (adev->dm.dmcub_fw_version) { + case 0: /* development */ + case 0x1: /* linux-firmware.git hash 6d9f399 */ + case 0x01000000: /* linux-firmware.git hash 9a0b0f4 */ + init_data.flags.disable_dmcu = false; + break; + default: + init_data.flags.disable_dmcu = true; + } break; case IP_VERSION(1, 0, 0): case IP_VERSION(1, 0, 1): @@ -1556,7 +1569,11 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) DRM_ERROR("amdgpu: fail to register dmub hpd callback"); goto error; } -#endif + if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) { + DRM_ERROR("amdgpu: fail to register dmub hpd callback"); + goto error; + } +#endif /* CONFIG_DRM_AMD_DC_DCN */ } if (amdgpu_dm_initialize_drm_device(adev)) { @@ -4565,7 +4582,8 @@ static void get_min_max_dc_plane_scaling(struct drm_device *dev, } -static int fill_dc_scaling_info(const struct drm_plane_state *state, +static int fill_dc_scaling_info(struct amdgpu_device *adev, + const struct drm_plane_state *state, struct dc_scaling_info *scaling_info) { int scale_w, scale_h, min_downscale, max_upscale; @@ -4579,7 +4597,8 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state, /* * For reasons we don't (yet) fully understand a non-zero * src_y coordinate into an NV12 buffer can cause a - * system hang. To avoid hangs (and maybe be overly cautious) + * system hang on DCN1x. + * To avoid hangs (and maybe be overly cautious) * let's reject both non-zero src_x and src_y. * * We currently know of only one use-case to reproduce a @@ -4587,10 +4606,10 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state, * is to gesture the YouTube Android app into full screen * on ChromeOS. */ - if (state->fb && - state->fb->format->format == DRM_FORMAT_NV12 && - (scaling_info->src_rect.x != 0 || - scaling_info->src_rect.y != 0)) + if (((adev->ip_versions[DCE_HWIP][0] == IP_VERSION(1, 0, 0)) || + (adev->ip_versions[DCE_HWIP][0] == IP_VERSION(1, 0, 1))) && + (state->fb && state->fb->format->format == DRM_FORMAT_NV12 && + (scaling_info->src_rect.x != 0 || scaling_info->src_rect.y != 0))) return -EINVAL; scaling_info->src_rect.width = state->src_w >> 16; @@ -5496,7 +5515,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, int ret; bool force_disable_dcc = false; - ret = fill_dc_scaling_info(plane_state, &scaling_info); + ret = fill_dc_scaling_info(adev, plane_state, &scaling_info); if (ret) return ret; @@ -6070,7 +6089,7 @@ static void apply_dsc_policy_for_stream(struct amdgpu_dm_connector *aconnector, if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_bits_per_pixel) stream->timing.dsc_cfg.bits_per_pixel = aconnector->dsc_settings.dsc_bits_per_pixel; } -#endif +#endif /* CONFIG_DRM_AMD_DC_DCN */ /** * DOC: FreeSync Video @@ -7241,8 +7260,8 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, struct drm_connector_state *new_con_state; struct amdgpu_dm_connector *aconnector; struct dm_connector_state *dm_conn_state; - int i, j, clock; - int vcpi, pbn_div, pbn = 0; + int i, j; + int vcpi, pbn_div, pbn, slot_num = 0; for_each_new_connector_in_state(state, connector, new_con_state, i) { @@ -7270,17 +7289,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, if (!stream) continue; - if (stream->timing.flags.DSC != 1) { - drm_dp_mst_atomic_enable_dsc(state, - aconnector->port, - dm_conn_state->pbn, - 0, - false); - continue; - } - pbn_div = dm_mst_get_pbn_divider(stream->link); - clock = stream->timing.pix_clk_100hz / 10; /* pbn is calculated by compute_mst_dsc_configs_for_state*/ for (j = 0; j < dc_state->stream_count; j++) { if (vars[j].aconnector == aconnector) { @@ -7289,6 +7298,23 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, } } + if (j == dc_state->stream_count) + continue; + + slot_num = DIV_ROUND_UP(pbn, pbn_div); + + if (stream->timing.flags.DSC != 1) { + dm_conn_state->pbn = pbn; + dm_conn_state->vcpi_slots = slot_num; + + drm_dp_mst_atomic_enable_dsc(state, + aconnector->port, + dm_conn_state->pbn, + 0, + false); + continue; + } + vcpi = drm_dp_mst_atomic_enable_dsc(state, aconnector->port, pbn, pbn_div, @@ -7552,7 +7578,7 @@ static int dm_plane_atomic_check(struct drm_plane *plane, if (ret) return ret; - ret = fill_dc_scaling_info(new_plane_state, &scaling_info); + ret = fill_dc_scaling_info(adev, new_plane_state, &scaling_info); if (ret) return ret; @@ -9000,7 +9026,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix; } - fill_dc_scaling_info(new_plane_state, + fill_dc_scaling_info(dm->adev, new_plane_state, &bundle->scaling_infos[planes_count]); bundle->surface_updates[planes_count].scaling_info = @@ -10787,7 +10813,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, ret = drm_atomic_add_affected_connectors(state, crtc); if (ret) - return ret; + goto fail; ret = drm_atomic_add_affected_planes(state, crtc); if (ret) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 3655663e079b..9d43ecb1f692 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -78,12 +78,10 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size, wr_buf_ptr = wr_buf; - r = copy_from_user(wr_buf_ptr, buf, wr_buf_size); - - /* r is bytes not be copied */ - if (r >= wr_buf_size) { - DRM_DEBUG_DRIVER("user data not be read\n"); - return -EINVAL; + /* r is bytes not be copied */ + if (copy_from_user(wr_buf_ptr, buf, wr_buf_size)) { + DRM_DEBUG_DRIVER("user data could not be read successfully\n"); + return -EFAULT; } /* check number of parameters. isspace could not differ space and \n */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 874a49b605c7..32a5ce09a62a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -534,13 +534,14 @@ static int kbps_to_peak_pbn(int kbps) static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params, struct dsc_mst_fairness_vars *vars, - int count) + int count, + int k) { int i; for (i = 0; i < count; i++) { memset(¶ms[i].timing->dsc_cfg, 0, sizeof(params[i].timing->dsc_cfg)); - if (vars[i].dsc_enabled && dc_dsc_compute_config( + if (vars[i + k].dsc_enabled && dc_dsc_compute_config( params[i].sink->ctx->dc->res_pool->dscs[0], ¶ms[i].sink->dsc_caps.dsc_dec_caps, params[i].sink->ctx->dc->debug.dsc_min_slice_height_override, @@ -553,7 +554,7 @@ static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *p if (params[i].bpp_overwrite) params[i].timing->dsc_cfg.bits_per_pixel = params[i].bpp_overwrite; else - params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16; + params[i].timing->dsc_cfg.bits_per_pixel = vars[i + k].bpp_x16; if (params[i].num_slices_h) params[i].timing->dsc_cfg.num_slices_h = params[i].num_slices_h; @@ -586,7 +587,8 @@ static void increase_dsc_bpp(struct drm_atomic_state *state, struct dc_link *dc_link, struct dsc_mst_fairness_params *params, struct dsc_mst_fairness_vars *vars, - int count) + int count, + int k) { int i; bool bpp_increased[MAX_PIPES]; @@ -601,8 +603,9 @@ static void increase_dsc_bpp(struct drm_atomic_state *state, pbn_per_timeslot = dm_mst_get_pbn_divider(dc_link); for (i = 0; i < count; i++) { - if (vars[i].dsc_enabled) { - initial_slack[i] = kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i].pbn; + if (vars[i + k].dsc_enabled) { + initial_slack[i] = + kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn; bpp_increased[i] = false; remaining_to_increase += 1; } else { @@ -629,7 +632,7 @@ static void increase_dsc_bpp(struct drm_atomic_state *state, link_timeslots_used = 0; for (i = 0; i < count; i++) - link_timeslots_used += DIV_ROUND_UP(vars[i].pbn, pbn_per_timeslot); + link_timeslots_used += DIV_ROUND_UP(vars[i + k].pbn, pbn_per_timeslot); fair_pbn_alloc = (63 - link_timeslots_used) / remaining_to_increase * pbn_per_timeslot; @@ -682,7 +685,8 @@ static void try_disable_dsc(struct drm_atomic_state *state, struct dc_link *dc_link, struct dsc_mst_fairness_params *params, struct dsc_mst_fairness_vars *vars, - int count) + int count, + int k) { int i; bool tried[MAX_PIPES]; @@ -692,8 +696,8 @@ static void try_disable_dsc(struct drm_atomic_state *state, int remaining_to_try = 0; for (i = 0; i < count; i++) { - if (vars[i].dsc_enabled - && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16 + if (vars[i + k].dsc_enabled + && vars[i + k].bpp_x16 == params[i].bw_range.max_target_bpp_x16 && params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) { kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps; tried[i] = false; @@ -748,9 +752,10 @@ static void try_disable_dsc(struct drm_atomic_state *state, static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, struct dc_state *dc_state, struct dc_link *dc_link, - struct dsc_mst_fairness_vars *vars) + struct dsc_mst_fairness_vars *vars, + int *link_vars_start_index) { - int i; + int i, k; struct dc_stream_state *stream; struct dsc_mst_fairness_params params[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; @@ -768,11 +773,17 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (stream->link != dc_link) continue; + aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; + if (!aconnector) + continue; + + if (!aconnector->port) + continue; + stream->timing.flags.DSC = 0; params[count].timing = &stream->timing; params[count].sink = stream->sink; - aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; params[count].aconnector = aconnector; params[count].port = aconnector->port; params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable; @@ -794,44 +805,55 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, count++; } + + if (count == 0) { + ASSERT(0); + return true; + } + + /* k is start index of vars for current phy link used by mst hub */ + k = *link_vars_start_index; + /* set vars start index for next mst hub phy link */ + *link_vars_start_index += count; + /* Try no compression */ for (i = 0; i < count; i++) { - vars[i].aconnector = params[i].aconnector; - vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); - vars[i].dsc_enabled = false; - vars[i].bpp_x16 = 0; + vars[i + k].aconnector = params[i].aconnector; + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i + k].dsc_enabled = false; + vars[i + k].bpp_x16 = 0; if (drm_dp_atomic_find_vcpi_slots(state, params[i].port->mgr, params[i].port, - vars[i].pbn, + vars[i + k].pbn, dm_mst_get_pbn_divider(dc_link)) < 0) return false; } if (!drm_dp_mst_atomic_check(state) && !debugfs_overwrite) { - set_dsc_configs_from_fairness_vars(params, vars, count); + set_dsc_configs_from_fairness_vars(params, vars, count, k); return true; } /* Try max compression */ for (i = 0; i < count; i++) { if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { - vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); - vars[i].dsc_enabled = true; - vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16; + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); + vars[i + k].dsc_enabled = true; + vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; if (drm_dp_atomic_find_vcpi_slots(state, params[i].port->mgr, params[i].port, - vars[i].pbn, + vars[i + k].pbn, dm_mst_get_pbn_divider(dc_link)) < 0) return false; } else { - vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); - vars[i].dsc_enabled = false; - vars[i].bpp_x16 = 0; + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i + k].dsc_enabled = false; + vars[i + k].bpp_x16 = 0; if (drm_dp_atomic_find_vcpi_slots(state, params[i].port->mgr, params[i].port, - vars[i].pbn, + vars[i + k].pbn, dm_mst_get_pbn_divider(dc_link)) < 0) return false; } @@ -840,15 +862,76 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, return false; /* Optimize degree of compression */ - increase_dsc_bpp(state, dc_link, params, vars, count); + increase_dsc_bpp(state, dc_link, params, vars, count, k); - try_disable_dsc(state, dc_link, params, vars, count); + try_disable_dsc(state, dc_link, params, vars, count, k); - set_dsc_configs_from_fairness_vars(params, vars, count); + set_dsc_configs_from_fairness_vars(params, vars, count, k); return true; } +static bool is_dsc_need_re_compute( + struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dc_link *dc_link) +{ + int i; + bool is_dsc_need_re_compute = false; + + /* only check phy used by mst branch */ + if (dc_link->type != dc_connection_mst_branch) + return false; + + /* check if there is mode change in new request */ + for (i = 0; i < dc_state->stream_count; i++) { + struct amdgpu_dm_connector *aconnector; + struct dc_stream_state *stream; + struct drm_crtc_state *new_crtc_state; + struct drm_connector_state *new_conn_state; + + stream = dc_state->streams[i]; + + if (!stream) + continue; + + /* check if stream using the same link for mst */ + if (stream->link != dc_link) + continue; + + aconnector = (struct amdgpu_dm_connector *) stream->dm_stream_context; + if (!aconnector) + continue; + + new_conn_state = drm_atomic_get_new_connector_state(state, &aconnector->base); + + if (!new_conn_state) + continue; + + if (IS_ERR(new_conn_state)) + continue; + + if (!new_conn_state->crtc) + continue; + + new_crtc_state = drm_atomic_get_new_crtc_state(state, new_conn_state->crtc); + + if (!new_crtc_state) + continue; + + if (IS_ERR(new_crtc_state)) + continue; + + if (new_crtc_state->enable && new_crtc_state->active) { + if (new_crtc_state->mode_changed || new_crtc_state->active_changed || + new_crtc_state->connectors_changed) + is_dsc_need_re_compute = true; + } + } + + return is_dsc_need_re_compute; +} + bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, struct dc_state *dc_state, struct dsc_mst_fairness_vars *vars) @@ -857,6 +940,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, struct dc_stream_state *stream; bool computed_streams[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; + int link_vars_start_index = 0; for (i = 0; i < dc_state->stream_count; i++) computed_streams[i] = false; @@ -881,8 +965,12 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK) return false; + if (!is_dsc_need_re_compute(state, dc_state, stream->link)) + continue; + mutex_lock(&aconnector->mst_mgr.lock); - if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars)) { + if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, + vars, &link_vars_start_index)) { mutex_unlock(&aconnector->mst_mgr.lock); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 12e5470fa567..0ded4decee05 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1085,6 +1085,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) struct dc_stream_state *old_stream = dc->current_state->res_ctx.pipe_ctx[i].stream; bool should_disable = true; + bool pipe_split_change = + context->res_ctx.pipe_ctx[i].top_pipe != dc->current_state->res_ctx.pipe_ctx[i].top_pipe; for (j = 0; j < context->stream_count; j++) { if (old_stream == context->streams[j]) { @@ -1092,6 +1094,9 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) break; } } + if (!should_disable && pipe_split_change) + should_disable = true; + if (should_disable && old_stream) { dc_rem_all_planes_for_stream(dc, old_stream, dangling_context); disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context); @@ -1887,6 +1892,7 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context) return false; } +#ifdef CONFIG_DRM_AMD_DC_DCN /* Perform updates here which need to be deferred until next vupdate * * i.e. blnd lut, 3dlut, and shaper lut bypass regs are double buffered @@ -1896,7 +1902,6 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context) */ static void process_deferred_updates(struct dc *dc) { -#ifdef CONFIG_DRM_AMD_DC_DCN int i = 0; if (dc->debug.enable_mem_low_power.bits.cm) { @@ -1905,8 +1910,8 @@ static void process_deferred_updates(struct dc *dc) if (dc->res_pool->dpps[i]->funcs->dpp_deferred_update) dc->res_pool->dpps[i]->funcs->dpp_deferred_update(dc->res_pool->dpps[i]); } -#endif } +#endif /* CONFIG_DRM_AMD_DC_DCN */ void dc_post_update_surfaces_to_stream(struct dc *dc) { @@ -1933,7 +1938,9 @@ void dc_post_update_surfaces_to_stream(struct dc *dc) dc->hwss.disable_plane(dc, &context->res_ctx.pipe_ctx[i]); } +#ifdef CONFIG_DRM_AMD_DC_DCN process_deferred_updates(dc); +#endif dc->hwss.optimize_bandwidth(dc, context); @@ -3603,7 +3610,8 @@ bool dc_enable_dmub_notifications(struct dc *dc) #if defined(CONFIG_DRM_AMD_DC_DCN) /* YELLOW_CARP B0 USB4 DPIA needs dmub notifications for interrupts */ if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP && - dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) + dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 && + !dc->debug.dpia_debug.bits.disable_dpia) return true; #endif /* dmub aux needs dmub notifications to be enabled */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 2796bdd17de1..60544788e911 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -4279,6 +4279,8 @@ void core_link_enable_stream( */ if (status != DC_FAIL_DP_LINK_TRAINING || pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + if (false == stream->link->link_status.link_active) + disable_link(stream->link, pipe_ctx->stream->signal); BREAK_TO_DEBUGGER(); return; } @@ -4768,7 +4770,7 @@ uint32_t dc_bandwidth_in_kbps_from_timing( timing->dsc_cfg.bits_per_pixel, timing->dsc_cfg.num_slices_h, timing->dsc_cfg.is_dp); -#endif +#endif /* CONFIG_DRM_AMD_DC_DCN */ switch (timing->display_color_depth) { case COLOR_DEPTH_666: diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index cc25ba0ec7db..cb7bf9148904 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5329,6 +5329,14 @@ bool dc_link_dp_set_test_pattern( return false; if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) { +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (test_pattern == DP_TEST_PATTERN_SQUARE_PULSE) + core_link_write_dpcd(link, + DP_LINK_SQUARE_PATTERN, + p_custom_pattern, + 1); + +#endif /* tell receiver that we are sending qualification * pattern DP 1.2 or later - DP receiver's link quality * pattern is set using DPCD LINK_QUAL_LANEx_SET diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c index 72b0f8594b4a..25e48a8cbb78 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c @@ -236,6 +236,23 @@ static struct link_encoder *get_link_enc_used_by_link( return link_enc; } +/* Clear all link encoder assignments. */ +static void clear_enc_assignments(struct dc_state *state) +{ + int i; + enum engine_id eng_id; + struct dc_stream_state *stream; + + for (i = 0; i < MAX_PIPES; i++) { + state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].valid = false; + eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].eng_id; + stream = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].stream; + if (eng_id != ENGINE_ID_UNKNOWN) + state->res_ctx.link_enc_cfg_ctx.link_enc_avail[eng_id - ENGINE_ID_DIGA] = eng_id; + if (stream) + stream->link_enc = NULL; + } +} void link_enc_cfg_init( struct dc *dc, @@ -250,6 +267,8 @@ void link_enc_cfg_init( state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i] = ENGINE_ID_UNKNOWN; } + clear_enc_assignments(state); + state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_STEADY; } @@ -265,6 +284,9 @@ void link_enc_cfg_link_encs_assign( ASSERT(state->stream_count == stream_count); + if (stream_count == 0) + clear_enc_assignments(state); + /* Release DIG link encoder resources before running assignment algorithm. */ for (i = 0; i < stream_count; i++) dc->res_pool->funcs->link_enc_unassign(state, streams[i]); diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index a5339796902a..3aac3f4a2852 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.159" +#define DC_VER "3.2.160" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -675,6 +675,7 @@ struct dc_debug_options { #endif union mem_low_power_enable_options enable_mem_low_power; union root_clock_optimization_options root_clock_optimization; + bool hpo_optimization; bool force_vblank_alignment; /* Enable dmub aux for legacy ddc */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index bc87ea0adf94..e68e9a86a4d9 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -898,6 +898,9 @@ struct dpcd_usb4_dp_tunneling_info { #ifndef DP_DFP_CAPABILITY_EXTENSION_SUPPORT #define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0A3 #endif +#ifndef DP_LINK_SQUARE_PATTERN +#define DP_LINK_SQUARE_PATTERN 0x10F +#endif #ifndef DP_DSC_CONFIGURATION #define DP_DSC_CONFIGURATION 0x161 #endif diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h index 989f5b6907e2..a3fee929cd12 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h @@ -671,6 +671,7 @@ struct dce_hwseq_registers { uint32_t MC_VM_FB_LOCATION_BASE; uint32_t MC_VM_FB_LOCATION_TOP; uint32_t MC_VM_FB_OFFSET; + uint32_t HPO_TOP_HW_CONTROL; }; /* set field name */ #define HWS_SF(blk_name, reg_name, field_name, post_fix)\ @@ -1152,7 +1153,8 @@ struct dce_hwseq_registers { type DOMAIN_PGFSM_PWR_STATUS;\ type HPO_HDMISTREAMCLK_G_GATE_DIS;\ type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;\ - type I2C_LIGHT_SLEEP_FORCE; + type I2C_LIGHT_SLEEP_FORCE;\ + type HPO_IO_EN; struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index af3e68d3e747..24e47df526f6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1244,6 +1244,12 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) #endif if (dc_is_dp_signal(pipe_ctx->stream->signal)) dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISCONNECT_DIG_FE_BE); + +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (dc->hwseq->funcs.setup_hpo_hw_control && is_dp_128b_132b_signal(pipe_ctx)) + dc->hwseq->funcs.setup_hpo_hw_control(dc->hwseq, false); +#endif + } void dce110_unblank_stream(struct pipe_ctx *pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index a25732d07222..0b788d794fb3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -231,7 +231,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx) if (!s->blank_en) DTN_INFO("[%2d]: %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh" - "% 8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh" + " %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh" " %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh %8xh\n", pool->hubps[i]->inst, dlg_regs->refcyc_h_blank_end, dlg_regs->dlg_vblank_end, dlg_regs->min_dst_y_next_start, dlg_regs->refcyc_per_htotal, dlg_regs->refcyc_x_after_scaler, dlg_regs->dst_y_after_scaler, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index cfee456c6c9a..4f88376a118f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2397,6 +2397,9 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) * BY this, it is logic clean to separate stream and link */ if (is_dp_128b_132b_signal(pipe_ctx)) { + if (pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control) + pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control( + pipe_ctx->stream->ctx->dc->hwseq, true); setup_dp_hpo_stream(pipe_ctx, true); pipe_ctx->stream_res.hpo_dp_stream_enc->funcs->enable_stream( pipe_ctx->stream_res.hpo_dp_stream_enc); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c index a82319f4d081..95149734378b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c @@ -1381,13 +1381,11 @@ int mpcc3_release_rmu(struct mpc *mpc, int mpcc_id) } -static void mpc3_mpc_init(struct mpc *mpc) +static void mpc3_set_mpc_mem_lp_mode(struct mpc *mpc) { struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc); int mpcc_id; - mpc1_mpc_init(mpc); - if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) { if (mpc30->mpc_mask->MPC_RMU0_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPC_RMU1_MEM_LOW_PWR_MODE) { REG_UPDATE(MPC_RMU_MEM_PWR_CTRL, MPC_RMU0_MEM_LOW_PWR_MODE, 3); @@ -1405,7 +1403,7 @@ const struct mpc_funcs dcn30_mpc_funcs = { .read_mpcc_state = mpc1_read_mpcc_state, .insert_plane = mpc1_insert_plane, .remove_mpcc = mpc1_remove_mpcc, - .mpc_init = mpc3_mpc_init, + .mpc_init = mpc1_mpc_init, .mpc_init_single_inst = mpc1_mpc_init_single_inst, .update_blending = mpc2_update_blending, .cursor_lock = mpc1_cursor_lock, @@ -1432,6 +1430,7 @@ const struct mpc_funcs dcn30_mpc_funcs = { .power_on_mpc_mem_pwr = mpc3_power_on_ogam_lut, .get_mpc_out_mux = mpc1_get_mpc_out_mux, .set_bg_color = mpc1_set_bg_color, + .set_mpc_mem_lp_mode = mpc3_set_mpc_mem_lp_mode, }; void dcn30_mpc_construct(struct dcn30_mpc *mpc30, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index e50c695e3c96..79a66e0c4303 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -2128,10 +2128,10 @@ static noinline void dcn30_calculate_wm_and_dlg_fp( int pipe_cnt, int vlevel) { + int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb; int i, pipe_idx; - double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; - bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != - dm_dram_clock_change_unsupported; + double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][maxMpcComb]; + bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] != dm_dram_clock_change_unsupported; if (context->bw_ctx.dml.soc.min_dcfclk > dcfclk) dcfclk = context->bw_ctx.dml.soc.min_dcfclk; @@ -2207,6 +2207,7 @@ static noinline void dcn30_calculate_wm_and_dlg_fp( context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us; context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us; } + context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index d24ad7754d71..5dd1ce9ddb53 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -66,6 +66,45 @@ #define FN(reg_name, field_name) \ hws->shifts->field_name, hws->masks->field_name +static void enable_memory_low_power(struct dc *dc) +{ + struct dce_hwseq *hws = dc->hwseq; + int i; + + if (dc->debug.enable_mem_low_power.bits.dmcu) { + // Force ERAM to shutdown if DMCU is not enabled + if (dc->debug.disable_dmcu || dc->config.disable_dmcu) { + REG_UPDATE(DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, 3); + } + } + + // Set default OPTC memory power states + if (dc->debug.enable_mem_low_power.bits.optc) { + // Shutdown when unassigned and light sleep in VBLANK + REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1); + } + + if (dc->debug.enable_mem_low_power.bits.vga) { + // Power down VGA memory + REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1); + } + + if (dc->debug.enable_mem_low_power.bits.mpc) + dc->res_pool->mpc->funcs->set_mpc_mem_lp_mode(dc->res_pool->mpc); + + + if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) { + // Power down VPGs + for (i = 0; i < dc->res_pool->stream_enc_count; i++) + dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg); +#if defined(CONFIG_DRM_AMD_DC_DCN) + for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++) + dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg); +#endif + } + +} + void dcn31_init_hw(struct dc *dc) { struct abm **abms = dc->res_pool->multiple_abms; @@ -108,35 +147,7 @@ void dcn31_init_hw(struct dc *dc) if (res_pool->dccg->funcs->dccg_init) res_pool->dccg->funcs->dccg_init(res_pool->dccg); - if (dc->debug.enable_mem_low_power.bits.dmcu) { - // Force ERAM to shutdown if DMCU is not enabled - if (dc->debug.disable_dmcu || dc->config.disable_dmcu) { - REG_UPDATE(DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, 3); - } - } - - // Set default OPTC memory power states - if (dc->debug.enable_mem_low_power.bits.optc) { - // Shutdown when unassigned and light sleep in VBLANK - REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1); - } - - if (dc->debug.enable_mem_low_power.bits.vga) { - // Power down VGA memory - REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1); - } - -#if defined(CONFIG_DRM_AMD_DC_DCN) - if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) { - // Power down VPGs - for (i = 0; i < dc->res_pool->stream_enc_count; i++) - dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg); -#if defined(CONFIG_DRM_AMD_DC_DP2_0) - for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++) - dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg); -#endif - } -#endif + enable_memory_low_power(dc); if (dc->ctx->dc_bios->fw_info_valid) { res_pool->ref_clocks.xtalin_clock_inKhz = @@ -264,6 +275,9 @@ void dcn31_init_hw(struct dc *dc) if (dc->debug.enable_mem_low_power.bits.i2c) REG_UPDATE(DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, 1); + if (hws->funcs.setup_hpo_hw_control) + hws->funcs.setup_hpo_hw_control(hws, false); + if (!dc->debug.disable_clock_gate) { /* enable all DCN clock gating */ REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0); @@ -597,3 +611,9 @@ void dcn31_reset_hw_ctx_wrap( /* New dc_state in the process of being applied to hardware. */ dc->current_state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_TRANSIENT; } + +void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable) +{ + if (hws->ctx->dc->debug.hpo_optimization) + REG_UPDATE(HPO_TOP_HW_CONTROL, HPO_IO_EN, !!enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h index 7ae45dd202d9..edfc01d6ad73 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h @@ -54,5 +54,6 @@ void dcn31_reset_hw_ctx_wrap( bool dcn31_is_abm_supported(struct dc *dc, struct dc_state *context, struct dc_stream_state *stream); void dcn31_init_pipes(struct dc *dc, struct dc_state *context); +void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable); #endif /* __DC_HWSS_DCN31_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index c6a737781ad1..05335a8c3c2d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -137,6 +137,7 @@ static const struct hwseq_private_funcs dcn31_private_funcs = { .dccg_init = dcn20_dccg_init, .set_blend_lut = dcn30_set_blend_lut, .set_shaper_3dlut = dcn20_set_shaper_3dlut, + .setup_hpo_hw_control = dcn31_setup_hpo_hw_control, }; void dcn31_hw_sequencer_construct(struct dc *dc) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 87b2c2428842..18896294ae12 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -860,7 +860,8 @@ static const struct dccg_mask dccg_mask = { SR(D6VGA_CONTROL), \ SR(DC_IP_REQUEST_CNTL), \ SR(AZALIA_AUDIO_DTO), \ - SR(AZALIA_CONTROLLER_CLOCK_GATING) + SR(AZALIA_CONTROLLER_CLOCK_GATING), \ + SR(HPO_TOP_HW_CONTROL) static const struct dce_hwseq_registers hwseq_reg = { HWSEQ_DCN31_REG_LIST() @@ -898,7 +899,8 @@ static const struct dce_hwseq_registers hwseq_reg = { HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_UNASSIGNED_PWR_MODE, mask_sh), \ HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_VBLANK_PWR_MODE, mask_sh), \ HWS_SF(, MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, mask_sh), \ - HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh) + HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh), \ + HWS_SF(, HPO_TOP_HW_CONTROL, HPO_IO_EN, mask_sh) static const struct dce_hwseq_shift hwseq_shift = { HWSEQ_DCN31_MASK_SH_LIST(__SHIFT) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index e3d9f1decdfc..f47d82da115c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -3576,16 +3576,9 @@ static double TruncToValidBPP( MinDSCBPP = 8; MaxDSCBPP = 3 * DSCInputBitPerComponent - 1.0 / 16; } else { - if (Output == dm_hdmi) { - NonDSCBPP0 = 24; - NonDSCBPP1 = 24; - NonDSCBPP2 = 24; - } - else { - NonDSCBPP0 = 16; - NonDSCBPP1 = 20; - NonDSCBPP2 = 24; - } + NonDSCBPP0 = 16; + NonDSCBPP1 = 20; + NonDSCBPP2 = 24; if (Format == dm_n422) { MinDSCBPP = 7; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index d58925cff420..7e937bdcea00 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -3892,15 +3892,11 @@ static double TruncToValidBPP( MinDSCBPP = 8; MaxDSCBPP = 3 * DSCInputBitPerComponent - 1.0 / 16; } else { - if (Output == dm_hdmi) { - NonDSCBPP0 = 24; - NonDSCBPP1 = 24; - NonDSCBPP2 = 24; - } else { - NonDSCBPP0 = 16; - NonDSCBPP1 = 20; - NonDSCBPP2 = 24; - } + + NonDSCBPP0 = 16; + NonDSCBPP1 = 20; + NonDSCBPP2 = 24; + if (Format == dm_n422) { MinDSCBPP = 7; MaxDSCBPP = 2 * DSCInputBitPerComponent - 1.0 / 16.0; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h index 04d6ec3f021f..f5fd2a067323 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h @@ -367,6 +367,7 @@ struct mpc_funcs { void (*set_bg_color)(struct mpc *mpc, struct tg_color *bg_color, int mpcc_id); + void (*set_mpc_mem_lp_mode)(struct mpc *mpc); }; #endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h index f324285394be..c2008258c50a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h @@ -143,6 +143,7 @@ struct hwseq_private_funcs { const struct dc_plane_state *plane_state); void (*PLAT_58856_wa)(struct dc_state *context, struct pipe_ctx *pipe_ctx); + void (*setup_hpo_hw_control)(const struct dce_hwseq *hws, bool enable); }; struct dce_hwseq { diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index 717c0e572d2f..cd204eef073b 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -238,6 +238,7 @@ struct dmub_srv_hw_params { bool load_inst_const; bool skip_panel_power_sequence; bool disable_z10; + bool power_optimization; bool dpia_supported; bool disable_dpia; }; diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 0293c58f0701..c29a67ccef17 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -46,10 +46,10 @@ /* Firmware versioning. */ #ifdef DMUB_EXPOSE_VERSION -#define DMUB_FW_VERSION_GIT_HASH 0x9525efb5 +#define DMUB_FW_VERSION_GIT_HASH 0x1d82d23e #define DMUB_FW_VERSION_MAJOR 0 #define DMUB_FW_VERSION_MINOR 0 -#define DMUB_FW_VERSION_REVISION 90 +#define DMUB_FW_VERSION_REVISION 91 #define DMUB_FW_VERSION_TEST 0 #define DMUB_FW_VERSION_VBIOS 0 #define DMUB_FW_VERSION_HOTFIX 0 diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index 10ebf20eaa41..fa0569174aec 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -340,6 +340,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu boot_options.bits.z10_disable = params->disable_z10; boot_options.bits.dpia_supported = params->dpia_supported; boot_options.bits.enable_dpia = params->disable_dpia ? 0 : 1; + boot_options.bits.power_optimization = params->power_optimization; boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 49fe4155c374..41472ed99253 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2094,6 +2094,10 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ } else if (DEVICE_ATTR_IS(pp_dpm_dclk)) { if (!(asic_type == CHIP_VANGOGH || asic_type == CHIP_SIENNA_CICHLID)) *states = ATTR_STATE_UNSUPPORTED; + } else if (DEVICE_ATTR_IS(pp_power_profile_mode)) { + if (!adev->powerplay.pp_funcs->get_power_profile_mode || + amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP) + *states = ATTR_STATE_UNSUPPORTED; } switch (asic_type) { diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h index 1d3447991d0c..fc9198846e70 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h @@ -51,7 +51,7 @@ #define PPSMC_MSG_PowerUpVcn 0x07 ///< Power up VCN; VCN is power gated by default #define PPSMC_MSG_SetHardMinVcn 0x08 ///< For wireless display #define PPSMC_MSG_SetSoftMinGfxclk 0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz -#define PPSMC_MSG_ActiveProcessNotify 0x0A ///< Set active work load type +#define PPSMC_MSG_ActiveProcessNotify 0x0A ///< Deprecated (Not to be used) #define PPSMC_MSG_ForcePowerDownGfx 0x0B ///< Force power down GFX, i.e. enter GFXOFF #define PPSMC_MSG_PrepareMp1ForUnload 0x0C ///< Prepare PMFW for GFX driver unload #define PPSMC_MSG_SetDriverDramAddrHigh 0x0D ///< Set high 32 bits of DRAM address for Driver table transfer @@ -63,7 +63,7 @@ #define PPSMC_MSG_SetHardMinSocclkByFreq 0x13 ///< Set hard min for SOC CLK #define PPSMC_MSG_SetSoftMinFclk 0x14 ///< Set hard min for FCLK #define PPSMC_MSG_SetSoftMinVcn 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK) -#define PPSMC_MSG_SPARE0 0x16 ///< Spared +#define PPSMC_MSG_SPARE 0x16 ///< Spare #define PPSMC_MSG_GetGfxclkFrequency 0x17 ///< Get GFX clock frequency #define PPSMC_MSG_GetFclkFrequency 0x18 ///< Get FCLK frequency #define PPSMC_MSG_AllowGfxOff 0x19 ///< Inform PMFW of allowing GFXOFF entry diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 321215003643..8d796ed3b7d1 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -875,34 +875,30 @@ pp_dpm_get_vce_clock_state(void *handle, unsigned idx) static int pp_get_power_profile_mode(void *handle, char *buf) { struct pp_hwmgr *hwmgr = handle; + int ret; - if (!hwmgr || !hwmgr->pm_en || !buf) + if (!hwmgr || !hwmgr->pm_en || !hwmgr->hwmgr_func->get_power_profile_mode) + return -EOPNOTSUPP; + if (!buf) return -EINVAL; - if (hwmgr->hwmgr_func->get_power_profile_mode == NULL) { - pr_info_ratelimited("%s was not implemented.\n", __func__); - return snprintf(buf, PAGE_SIZE, "\n"); - } - - return hwmgr->hwmgr_func->get_power_profile_mode(hwmgr, buf); + mutex_lock(&hwmgr->smu_lock); + ret = hwmgr->hwmgr_func->get_power_profile_mode(hwmgr, buf); + mutex_unlock(&hwmgr->smu_lock); + return ret; } static int pp_set_power_profile_mode(void *handle, long *input, uint32_t size) { struct pp_hwmgr *hwmgr = handle; - int ret = -EINVAL; + int ret = -EOPNOTSUPP; - if (!hwmgr || !hwmgr->pm_en) - return ret; - - if (hwmgr->hwmgr_func->set_power_profile_mode == NULL) { - pr_info_ratelimited("%s was not implemented.\n", __func__); + if (!hwmgr || !hwmgr->pm_en || !hwmgr->hwmgr_func->set_power_profile_mode) return ret; - } if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) { pr_debug("power profile setting is for manual dpm mode only.\n"); - return ret; + return -EINVAL; } mutex_lock(&hwmgr->smu_lock); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 1de3ae77e03e..258c573acc97 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1024,6 +1024,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, uint32_t min_freq, max_freq = 0; uint32_t ret = 0; + phm_get_sysfs_buf(&buf, &size); + switch (type) { case PP_SCLK: smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now); @@ -1065,7 +1067,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, if (ret) return ret; - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", (data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", @@ -1081,7 +1083,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, if (ret) return ret; - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n", min_freq, max_freq); } @@ -1456,6 +1458,8 @@ static int smu10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf) if (!buf) return -EINVAL; + phm_get_sysfs_buf(&buf, &size); + size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0], title[1], title[2], title[3], title[4], title[5]); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index e7803ce8f67a..aceebf584225 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -4914,6 +4914,8 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, int size = 0; uint32_t i, now, clock, pcie_speed; + phm_get_sysfs_buf(&buf, &size); + switch (type) { case PP_SCLK: smum_send_msg_to_smc(hwmgr, PPSMC_MSG_API_GetSclkFrequency, &clock); @@ -4963,7 +4965,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_SCLK: if (hwmgr->od_enabled) { - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); for (i = 0; i < odn_sclk_table->num_of_pl; i++) size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n", i, odn_sclk_table->entries[i].clock/100, @@ -4972,7 +4974,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_MCLK: if (hwmgr->od_enabled) { - size = sysfs_emit(buf, "%s:\n", "OD_MCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); for (i = 0; i < odn_mclk_table->num_of_pl; i++) size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n", i, odn_mclk_table->entries[i].clock/100, @@ -4981,7 +4983,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_RANGE: if (hwmgr->od_enabled) { - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n", data->golden_dpm_table.sclk_table.dpm_levels[0].value/100, hwmgr->platform_descriptor.overdriveLimit.engineClock/100); @@ -5518,6 +5520,8 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf) if (!buf) return -EINVAL; + phm_get_sysfs_buf(&buf, &size); + size += sysfs_emit_at(buf, size, "%s %16s %16s %16s %16s %16s %16s %16s\n", title[0], title[1], title[2], title[3], title[4], title[5], title[6], title[7]); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index b94a77e4e714..8e28a8eecefc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -1550,6 +1550,8 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr, uint32_t i, now; int size = 0; + phm_get_sysfs_buf(&buf, &size); + switch (type) { case PP_SCLK: now = PHM_GET_FIELD(cgs_read_ind_register(hwmgr->device, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h index ad33983a8064..2a75da1e9f03 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h @@ -109,6 +109,19 @@ int phm_irq_process(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +/* + * Helper function to make sysfs_emit_at() happy. Align buf to + * the current page boundary and record the offset. + */ +static inline void phm_get_sysfs_buf(char **buf, int *offset) +{ + if (!*buf || !offset) + return; + + *offset = offset_in_page(*buf); + *buf -= *offset; +} + int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr); void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index c152a61ddd2c..c981fc2882f0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -4548,6 +4548,8 @@ static int vega10_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) int ret = 0; int size = 0; + phm_get_sysfs_buf(&buf, &size); + ret = vega10_get_enabled_smc_features(hwmgr, &features_enabled); PP_ASSERT_WITH_CODE(!ret, "[EnableAllSmuFeatures] Failed to get enabled smc features!", @@ -4637,6 +4639,8 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, int i, now, size = 0, count = 0; + phm_get_sysfs_buf(&buf, &size); + switch (type) { case PP_SCLK: if (data->registry_data.sclk_dpm_key_disabled) @@ -4717,7 +4721,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, case OD_SCLK: if (hwmgr->od_enabled) { - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk; for (i = 0; i < podn_vdd_dep->count; i++) size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n", @@ -4727,7 +4731,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_MCLK: if (hwmgr->od_enabled) { - size = sysfs_emit(buf, "%s:\n", "OD_MCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk; for (i = 0; i < podn_vdd_dep->count; i++) size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n", @@ -4737,7 +4741,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_RANGE: if (hwmgr->od_enabled) { - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n", data->golden_dpm_table.gfx_table.dpm_levels[0].value/100, hwmgr->platform_descriptor.overdriveLimit.engineClock/100); @@ -5112,6 +5116,8 @@ static int vega10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf) if (!buf) return -EINVAL; + phm_get_sysfs_buf(&buf, &size); + size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0], title[1], title[2], title[3], title[4], title[5]); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 8558718e15a8..f7e783e1c888 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -2141,6 +2141,8 @@ static int vega12_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) int ret = 0; int size = 0; + phm_get_sysfs_buf(&buf, &size); + ret = vega12_get_enabled_smc_features(hwmgr, &features_enabled); PP_ASSERT_WITH_CODE(!ret, "[EnableAllSmuFeatures] Failed to get enabled smc features!", @@ -2244,6 +2246,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr, int i, now, size = 0; struct pp_clock_levels_with_latency clocks; + phm_get_sysfs_buf(&buf, &size); + switch (type) { case PP_SCLK: PP_ASSERT_WITH_CODE( diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 0cf39c1244b1..03e63be4ee27 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -3238,6 +3238,8 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) int ret = 0; int size = 0; + phm_get_sysfs_buf(&buf, &size); + ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); PP_ASSERT_WITH_CODE(!ret, "[EnableAllSmuFeatures] Failed to get enabled smc features!", @@ -3364,6 +3366,8 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, int ret = 0; uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width; + phm_get_sysfs_buf(&buf, &size); + switch (type) { case PP_SCLK: ret = vega20_get_current_clk_freq(hwmgr, PPCLK_GFXCLK, &now); @@ -3479,7 +3483,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, case OD_SCLK: if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id && od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) { - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", od_table->GfxclkFmin); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", @@ -3489,7 +3493,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, case OD_MCLK: if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) { - size = sysfs_emit(buf, "%s:\n", "OD_MCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", od_table->UclkFmax); } @@ -3503,7 +3507,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id && od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id && od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) { - size = sysfs_emit(buf, "%s:\n", "OD_VDDC_CURVE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_VDDC_CURVE"); size += sysfs_emit_at(buf, size, "0: %10uMhz %10dmV\n", od_table->GfxclkFreq1, od_table->GfxclkVolt1 / VOLTAGE_SCALE); @@ -3518,7 +3522,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_RANGE: - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id && od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) { @@ -4003,6 +4007,8 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf) if (!buf) return -EINVAL; + phm_get_sysfs_buf(&buf, &size); + size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n", title[0], title[1], title[2], title[3], title[4], title[5], title[6], title[7], title[8], title[9], title[10]); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index b06c59dcc1b4..01168b8955bf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1468,7 +1468,7 @@ static int smu_disable_dpms(struct smu_context *smu) dev_err(adev->dev, "Failed to disable smu features.\n"); } - if (adev->ip_versions[MP1_HWIP][0] >= IP_VERSION(11, 0, 0) && + if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0) && adev->gfx.rlc.funcs->stop) adev->gfx.rlc.funcs->stop(adev); @@ -2534,13 +2534,15 @@ static int smu_get_power_profile_mode(void *handle, char *buf) struct smu_context *smu = handle; int ret = 0; - if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) + if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled || + !smu->ppt_funcs->get_power_profile_mode) return -EOPNOTSUPP; + if (!buf) + return -EINVAL; mutex_lock(&smu->mutex); - if (smu->ppt_funcs->get_power_profile_mode) - ret = smu->ppt_funcs->get_power_profile_mode(smu, buf); + ret = smu->ppt_funcs->get_power_profile_mode(smu, buf); mutex_unlock(&smu->mutex); @@ -2554,7 +2556,8 @@ static int smu_set_power_profile_mode(void *handle, struct smu_context *smu = handle; int ret = 0; - if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) + if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled || + !smu->ppt_funcs->set_power_profile_mode) return -EOPNOTSUPP; mutex_lock(&smu->mutex); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index a403657151ba..8215bbf5ed7c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -64,7 +64,6 @@ static struct cmn2asic_msg_mapping yellow_carp_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(PowerDownVcn, PPSMC_MSG_PowerDownVcn, 1), MSG_MAP(PowerUpVcn, PPSMC_MSG_PowerUpVcn, 1), MSG_MAP(SetHardMinVcn, PPSMC_MSG_SetHardMinVcn, 1), - MSG_MAP(ActiveProcessNotify, PPSMC_MSG_ActiveProcessNotify, 1), MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 1), MSG_MAP(SetDriverDramAddrHigh, PPSMC_MSG_SetDriverDramAddrHigh, 1), MSG_MAP(SetDriverDramAddrLow, PPSMC_MSG_SetDriverDramAddrLow, 1), @@ -135,14 +134,6 @@ static struct cmn2asic_mapping yellow_carp_table_map[SMU_TABLE_COUNT] = { TAB_MAP_VALID(CUSTOM_DPM), TAB_MAP_VALID(DPMCLOCKS), }; - -static struct cmn2asic_mapping yellow_carp_workload_map[PP_SMC_POWER_PROFILE_COUNT] = { - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_FULLSCREEN3D, WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), -}; static int yellow_carp_init_smc_tables(struct smu_context *smu) { @@ -543,81 +534,6 @@ static int yellow_carp_set_watermarks_table(struct smu_context *smu, return 0; } -static int yellow_carp_get_power_profile_mode(struct smu_context *smu, - char *buf) -{ - static const char *profile_name[] = { - "BOOTUP_DEFAULT", - "3D_FULL_SCREEN", - "POWER_SAVING", - "VIDEO", - "VR", - "COMPUTE", - "CUSTOM"}; - uint32_t i, size = 0; - int16_t workload_type = 0; - - if (!buf) - return -EINVAL; - - for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) { - /* - * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT. - * Not all profile modes are supported on yellow carp. - */ - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - i); - - if (workload_type < 0) - continue; - - size += sysfs_emit_at(buf, size, "%2d %14s%s\n", - i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " "); - } - - return size; -} - -static int yellow_carp_set_power_profile_mode(struct smu_context *smu, - long *input, uint32_t size) -{ - int workload_type, ret; - uint32_t profile_mode = input[size]; - - if (profile_mode > PP_SMC_POWER_PROFILE_CUSTOM) { - dev_err(smu->adev->dev, "Invalid power profile mode %d\n", profile_mode); - return -EINVAL; - } - - if (profile_mode == PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT || - profile_mode == PP_SMC_POWER_PROFILE_POWERSAVING) - return 0; - - /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - profile_mode); - if (workload_type < 0) { - dev_dbg(smu->adev->dev, "Unsupported power profile mode %d on YELLOWCARP\n", - profile_mode); - return -EINVAL; - } - - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify, - 1 << workload_type, - NULL); - if (ret) { - dev_err_once(smu->adev->dev, "Fail to set workload type %d\n", - workload_type); - return ret; - } - - smu->power_profile_mode = profile_mode; - - return 0; -} - static ssize_t yellow_carp_get_gpu_metrics(struct smu_context *smu, void **table) { @@ -1238,8 +1154,6 @@ static const struct pptable_funcs yellow_carp_ppt_funcs = { .read_sensor = yellow_carp_read_sensor, .is_dpm_running = yellow_carp_is_dpm_running, .set_watermarks_table = yellow_carp_set_watermarks_table, - .get_power_profile_mode = yellow_carp_get_power_profile_mode, - .set_power_profile_mode = yellow_carp_set_power_profile_mode, .get_gpu_metrics = yellow_carp_get_gpu_metrics, .get_enabled_mask = smu_cmn_get_enabled_32_bits_mask, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, @@ -1261,6 +1175,5 @@ void yellow_carp_set_ppt_funcs(struct smu_context *smu) smu->message_map = yellow_carp_message_map; smu->feature_map = yellow_carp_feature_mask_map; smu->table_map = yellow_carp_table_map; - smu->workload_map = yellow_carp_workload_map; smu->is_apu = true; } diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c index 3cac16db970f..010657ea7af7 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c @@ -167,9 +167,10 @@ static void lt9611uxc_hpd_work(struct work_struct *work) struct lt9611uxc *lt9611uxc = container_of(work, struct lt9611uxc, work); bool connected; - if (lt9611uxc->connector.dev) - drm_kms_helper_hotplug_event(lt9611uxc->connector.dev); - else { + if (lt9611uxc->connector.dev) { + if (lt9611uxc->connector.dev->mode_config.funcs) + drm_kms_helper_hotplug_event(lt9611uxc->connector.dev); + } else { mutex_lock(<9611uxc->ocm_lock); connected = lt9611uxc->hdmi_connected; @@ -339,6 +340,8 @@ static int lt9611uxc_connector_init(struct drm_bridge *bridge, struct lt9611uxc return -ENODEV; } + lt9611uxc->connector.polled = DRM_CONNECTOR_POLL_HPD; + drm_connector_helper_add(<9611uxc->connector, <9611uxc_bridge_connector_helper_funcs); ret = drm_connector_init(bridge->dev, <9611uxc->connector, diff --git a/drivers/gpu/drm/bridge/lvds-codec.c b/drivers/gpu/drm/bridge/lvds-codec.c index dcf579a4cf83..ad460b96c0a3 100644 --- a/drivers/gpu/drm/bridge/lvds-codec.c +++ b/drivers/gpu/drm/bridge/lvds-codec.c @@ -12,6 +12,7 @@ #include <linux/platform_device.h> #include <linux/regulator/consumer.h> +#include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_panel.h> @@ -22,6 +23,7 @@ struct lvds_codec { struct regulator *vcc; struct gpio_desc *powerdown_gpio; u32 connector_type; + unsigned int bus_format; }; static inline struct lvds_codec *to_lvds_codec(struct drm_bridge *bridge) @@ -74,12 +76,50 @@ static const struct drm_bridge_funcs funcs = { .disable = lvds_codec_disable, }; +#define MAX_INPUT_SEL_FORMATS 1 +static u32 * +lvds_codec_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + struct lvds_codec *lvds_codec = to_lvds_codec(bridge); + u32 *input_fmts; + + *num_input_fmts = 0; + + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + input_fmts[0] = lvds_codec->bus_format; + *num_input_fmts = MAX_INPUT_SEL_FORMATS; + + return input_fmts; +} + +static const struct drm_bridge_funcs funcs_decoder = { + .attach = lvds_codec_attach, + .enable = lvds_codec_enable, + .disable = lvds_codec_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_get_input_bus_fmts = lvds_codec_atomic_get_input_bus_fmts, +}; + static int lvds_codec_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *panel_node; + struct device_node *bus_node; struct drm_panel *panel; struct lvds_codec *lvds_codec; + const char *mapping; + int ret; lvds_codec = devm_kzalloc(dev, sizeof(*lvds_codec), GFP_KERNEL); if (!lvds_codec) @@ -119,13 +159,47 @@ static int lvds_codec_probe(struct platform_device *pdev) if (IS_ERR(lvds_codec->panel_bridge)) return PTR_ERR(lvds_codec->panel_bridge); + lvds_codec->bridge.funcs = &funcs; + + /* + * Decoder input LVDS format is a property of the decoder chip or even + * its strapping. Handle data-mapping the same way lvds-panel does. In + * case data-mapping is not present, do nothing, since there are still + * legacy bindings which do not specify this property. + */ + if (lvds_codec->connector_type != DRM_MODE_CONNECTOR_LVDS) { + bus_node = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + if (!bus_node) { + dev_dbg(dev, "bus DT node not found\n"); + return -ENXIO; + } + + ret = of_property_read_string(bus_node, "data-mapping", + &mapping); + of_node_put(bus_node); + if (ret < 0) { + dev_warn(dev, "missing 'data-mapping' DT property\n"); + } else { + if (!strcmp(mapping, "jeida-18")) { + lvds_codec->bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG; + } else if (!strcmp(mapping, "jeida-24")) { + lvds_codec->bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA; + } else if (!strcmp(mapping, "vesa-24")) { + lvds_codec->bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG; + } else { + dev_err(dev, "invalid 'data-mapping' DT property\n"); + return -EINVAL; + } + lvds_codec->bridge.funcs = &funcs_decoder; + } + } + /* * The panel_bridge bridge is attached to the panel's of_node, * but we need a bridge attached to our of_node for our user * to look up. */ lvds_codec->bridge.of_node = dev->of_node; - lvds_codec->bridge.funcs = &funcs; drm_bridge_add(&lvds_codec->bridge); platform_set_drvdata(pdev, lvds_codec); diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index ed8ac5059cd2..a7389a0facfb 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -939,6 +939,40 @@ static void nwl_dsi_bridge_detach(struct drm_bridge *bridge) drm_of_panel_bridge_remove(dsi->dev->of_node, 1, 0); } +static u32 *nwl_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + u32 *input_fmts, input_fmt; + + *num_input_fmts = 0; + + switch (output_fmt) { + /* If MEDIA_BUS_FMT_FIXED is tested, return default bus format */ + case MEDIA_BUS_FMT_FIXED: + input_fmt = MEDIA_BUS_FMT_RGB888_1X24; + break; + case MEDIA_BUS_FMT_RGB888_1X24: + case MEDIA_BUS_FMT_RGB666_1X18: + case MEDIA_BUS_FMT_RGB565_1X16: + input_fmt = output_fmt; + break; + default: + return NULL; + } + + input_fmts = kcalloc(1, sizeof(*input_fmts), GFP_KERNEL); + if (!input_fmts) + return NULL; + input_fmts[0] = input_fmt; + *num_input_fmts = 1; + + return input_fmts; +} + static const struct drm_bridge_funcs nwl_dsi_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, @@ -946,6 +980,7 @@ static const struct drm_bridge_funcs nwl_dsi_bridge_funcs = { .atomic_check = nwl_dsi_bridge_atomic_check, .atomic_enable = nwl_dsi_bridge_atomic_enable, .atomic_disable = nwl_dsi_bridge_atomic_disable, + .atomic_get_input_bus_fmts = nwl_bridge_atomic_get_input_bus_fmts, .mode_set = nwl_dsi_bridge_mode_set, .mode_valid = nwl_dsi_bridge_mode_valid, .attach = nwl_dsi_bridge_attach, diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index a32f70bc68ea..ba1160ec6d6e 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -288,6 +288,19 @@ err_dsi_attach: return ret; } +static void sn65dsi83_detach(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + if (!ctx->dsi) + return; + + mipi_dsi_detach(ctx->dsi); + mipi_dsi_device_unregister(ctx->dsi); + drm_bridge_remove(&ctx->bridge); + ctx->dsi = NULL; +} + static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, struct drm_bridge_state *old_bridge_state) { @@ -583,6 +596,7 @@ sn65dsi83_atomic_get_input_bus_fmts(struct drm_bridge *bridge, static const struct drm_bridge_funcs sn65dsi83_funcs = { .attach = sn65dsi83_attach, + .detach = sn65dsi83_detach, .atomic_pre_enable = sn65dsi83_atomic_pre_enable, .atomic_enable = sn65dsi83_atomic_enable, .atomic_disable = sn65dsi83_atomic_disable, @@ -697,9 +711,6 @@ static int sn65dsi83_remove(struct i2c_client *client) { struct sn65dsi83 *ctx = i2c_get_clientdata(client); - mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_bridge_remove(&ctx->bridge); of_node_put(ctx->host_node); return 0; diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 3bc782b630b9..52e20c68813b 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -625,6 +625,8 @@ int drm_connector_register_all(struct drm_device *dev) * * In contrast to the other drm_get_*_name functions this one here returns a * const pointer and hence is threadsafe. + * + * Returns: connector status string */ const char *drm_get_connector_status_name(enum drm_connector_status status) { @@ -707,7 +709,7 @@ __drm_connector_put_safe(struct drm_connector *conn) * drm_connector_list_iter_next - return next connector * @iter: connector_list iterator * - * Returns the next connector for @iter, or NULL when the list walk has + * Returns: the next connector for @iter, or NULL when the list walk has * completed. */ struct drm_connector * @@ -780,6 +782,8 @@ static const struct drm_prop_enum_list drm_subpixel_enum_list[] = { * * Note you could abuse this and return something out of bounds, but that * would be a caller error. No unscrubbed user data should make it here. + * + * Returns: string describing an enumerated subpixel property */ const char *drm_get_subpixel_order_name(enum subpixel_order order) { @@ -809,6 +813,9 @@ static const struct drm_prop_enum_list drm_link_status_enum_list[] = { * Store the supported bus formats in display info structure. * See MEDIA_BUS_FMT_* definitions in include/uapi/linux/media-bus-format.h for * a full list of available formats. + * + * Returns: + * 0 on success or a negative error code on failure. */ int drm_display_info_set_bus_formats(struct drm_display_info *info, const u32 *formats, @@ -1326,6 +1333,8 @@ int drm_connector_create_standard_properties(struct drm_device *dev) * @dev: DRM device * * Called by a driver the first time a DVI-I connector is made. + * + * Returns: %0 */ int drm_mode_create_dvi_i_properties(struct drm_device *dev) { @@ -1397,6 +1406,8 @@ EXPORT_SYMBOL(drm_connector_attach_dp_subconnector_property); * Game: * Content type is game * + * The meaning of each content type is defined in CTA-861-G table 15. + * * Drivers can set up this property by calling * drm_connector_attach_content_type_property(). Decoding to * infoframe values is done through drm_hdmi_avi_infoframe_content_type(). @@ -1407,6 +1418,8 @@ EXPORT_SYMBOL(drm_connector_attach_dp_subconnector_property); * @connector: connector to attach content type property on. * * Called by a driver the first time a HDMI connector is made. + * + * Returns: %0 */ int drm_connector_attach_content_type_property(struct drm_connector *connector) { @@ -1487,6 +1500,9 @@ EXPORT_SYMBOL(drm_connector_attach_tv_margin_properties); * creates the TV margin properties for a given device. No need to call this * function for an SDTV connector, it's already called from * drm_mode_create_tv_properties(). + * + * Returns: + * 0 on success or a negative error code on failure. */ int drm_mode_create_tv_margin_properties(struct drm_device *dev) { @@ -1527,6 +1543,9 @@ EXPORT_SYMBOL(drm_mode_create_tv_margin_properties); * the TV specific connector properties for a given device. Caller is * responsible for allocating a list of format names and passing them to * this routine. + * + * Returns: + * 0 on success or a negative error code on failure. */ int drm_mode_create_tv_properties(struct drm_device *dev, unsigned int num_modes, @@ -1622,6 +1641,8 @@ EXPORT_SYMBOL(drm_mode_create_tv_properties); * Atomic drivers should use drm_connector_attach_scaling_mode_property() * instead to correctly assign &drm_connector_state.scaling_mode * in the atomic state. + * + * Returns: %0 */ int drm_mode_create_scaling_mode_property(struct drm_device *dev) { @@ -1939,6 +1960,9 @@ EXPORT_SYMBOL(drm_mode_create_content_type_property); * @dev: DRM device * * Create the suggested x/y offset property for connectors. + * + * Returns: + * 0 on success or a negative error code on failure. */ int drm_mode_create_suggested_offset_properties(struct drm_device *dev) { @@ -2312,8 +2336,8 @@ int drm_connector_set_panel_orientation( EXPORT_SYMBOL(drm_connector_set_panel_orientation); /** - * drm_connector_set_panel_orientation_with_quirk - - * set the connector's panel_orientation after checking for quirks + * drm_connector_set_panel_orientation_with_quirk - set the + * connector's panel_orientation after checking for quirks * @connector: connector for which to init the panel-orientation property. * @panel_orientation: drm_panel_orientation value to set * @width: width in pixels of the panel, used for panel quirk detection @@ -2597,7 +2621,7 @@ struct drm_connector *drm_connector_find_by_fwnode(struct fwnode_handle *fwnode) /** * drm_connector_oob_hotplug_event - Report out-of-band hotplug event to connector - * @connector: connector to report the event on + * @connector_fwnode: fwnode_handle to report the event on * * On some hardware a hotplug event notification may come from outside the display * driver / device. An example of this is some USB Type-C setups where the hardware diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 09c820045859..4dcdec6487bb 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1340,31 +1340,15 @@ int drm_gem_fence_array_add_implicit(struct xarray *fence_array, struct drm_gem_object *obj, bool write) { - int ret; - struct dma_fence **fences; - unsigned int i, fence_count; - - if (!write) { - struct dma_fence *fence = - dma_resv_get_excl_unlocked(obj->resv); - - return drm_gem_fence_array_add(fence_array, fence); - } + struct dma_resv_iter cursor; + struct dma_fence *fence; + int ret = 0; - ret = dma_resv_get_fences(obj->resv, NULL, - &fence_count, &fences); - if (ret || !fence_count) - return ret; - - for (i = 0; i < fence_count; i++) { - ret = drm_gem_fence_array_add(fence_array, fences[i]); + dma_resv_for_each_fence(&cursor, obj->resv, write, fence) { + ret = drm_gem_fence_array_add(fence_array, fence); if (ret) break; } - - for (; i < fence_count; i++) - dma_fence_put(fences[i]); - kfree(fences); return ret; } EXPORT_SYMBOL(drm_gem_fence_array_add_implicit); diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index bf8a6e823a15..c97323365675 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -25,6 +25,7 @@ #include <drm/drm_crtc.h> #include <drm/drm_device.h> #include <drm/drm_modeset_lock.h> +#include <drm/drm_print.h> /** * DOC: kms locking @@ -77,6 +78,45 @@ static DEFINE_WW_CLASS(crtc_ww_class); +#if IS_ENABLED(CONFIG_DRM_DEBUG_MODESET_LOCK) +static noinline depot_stack_handle_t __drm_stack_depot_save(void) +{ + unsigned long entries[8]; + unsigned int n; + + n = stack_trace_save(entries, ARRAY_SIZE(entries), 1); + + return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN); +} + +static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) +{ + struct drm_printer p = drm_debug_printer("drm_modeset_lock"); + unsigned long *entries; + unsigned int nr_entries; + char *buf; + + buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN); + if (!buf) + return; + + nr_entries = stack_depot_fetch(stack_depot, &entries); + stack_trace_snprint(buf, PAGE_SIZE, entries, nr_entries, 2); + + drm_printf(&p, "attempting to lock a contended lock without backoff:\n%s", buf); + + kfree(buf); +} +#else /* CONFIG_DRM_DEBUG_MODESET_LOCK */ +static depot_stack_handle_t __drm_stack_depot_save(void) +{ + return 0; +} +static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) +{ +} +#endif /* CONFIG_DRM_DEBUG_MODESET_LOCK */ + /** * drm_modeset_lock_all - take all modeset locks * @dev: DRM device @@ -225,7 +265,9 @@ EXPORT_SYMBOL(drm_modeset_acquire_fini); */ void drm_modeset_drop_locks(struct drm_modeset_acquire_ctx *ctx) { - WARN_ON(ctx->contended); + if (WARN_ON(ctx->contended)) + __drm_stack_depot_print(ctx->stack_depot); + while (!list_empty(&ctx->locked)) { struct drm_modeset_lock *lock; @@ -243,7 +285,8 @@ static inline int modeset_lock(struct drm_modeset_lock *lock, { int ret; - WARN_ON(ctx->contended); + if (WARN_ON(ctx->contended)) + __drm_stack_depot_print(ctx->stack_depot); if (ctx->trylock_only) { lockdep_assert_held(&ctx->ww_ctx); @@ -274,6 +317,7 @@ static inline int modeset_lock(struct drm_modeset_lock *lock, ret = 0; } else if (ret == -EDEADLK) { ctx->contended = lock; + ctx->stack_depot = __drm_stack_depot_save(); } return ret; @@ -296,6 +340,7 @@ int drm_modeset_backoff(struct drm_modeset_acquire_ctx *ctx) struct drm_modeset_lock *contended = ctx->contended; ctx->contended = NULL; + ctx->stack_depot = 0; if (WARN_ON(!contended)) return 0; diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c index 5b2d0ca03705..838b32b70bce 100644 --- a/drivers/gpu/drm/drm_plane_helper.c +++ b/drivers/gpu/drm/drm_plane_helper.c @@ -123,7 +123,6 @@ static int drm_plane_helper_check_update(struct drm_plane *plane, .crtc_w = drm_rect_width(dst), .crtc_h = drm_rect_height(dst), .rotation = rotation, - .visible = *visible, }; struct drm_crtc_state crtc_state = { .crtc = crtc, diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index d8ba95744410..c773d3dfb1ab 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -722,11 +722,13 @@ int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) if (obj->funcs && obj->funcs->mmap) { vma->vm_ops = obj->funcs->vm_ops; + drm_gem_object_get(obj); ret = obj->funcs->mmap(obj, vma); - if (ret) + if (ret) { + drm_gem_object_put(obj); return ret; + } vma->vm_private_data = obj; - drm_gem_object_get(obj); return 0; } diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index 88c427f3c346..f5b4dd5b4275 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -584,6 +584,7 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv, else intel_encoder->enable = g4x_enable_hdmi; } + intel_encoder->shutdown = intel_hdmi_encoder_shutdown; intel_encoder->type = INTEL_OUTPUT_HDMI; intel_encoder->power_domain = intel_port_to_power_domain(port); diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index b99907c656bb..2b1423a43437 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1707,6 +1707,39 @@ static void sanitize_aux_ch(struct intel_bios_encoder_data *devdata, child->aux_channel = 0; } +static u8 dvo_port_type(u8 dvo_port) +{ + switch (dvo_port) { + case DVO_PORT_HDMIA: + case DVO_PORT_HDMIB: + case DVO_PORT_HDMIC: + case DVO_PORT_HDMID: + case DVO_PORT_HDMIE: + case DVO_PORT_HDMIF: + case DVO_PORT_HDMIG: + case DVO_PORT_HDMIH: + case DVO_PORT_HDMII: + return DVO_PORT_HDMIA; + case DVO_PORT_DPA: + case DVO_PORT_DPB: + case DVO_PORT_DPC: + case DVO_PORT_DPD: + case DVO_PORT_DPE: + case DVO_PORT_DPF: + case DVO_PORT_DPG: + case DVO_PORT_DPH: + case DVO_PORT_DPI: + return DVO_PORT_DPA; + case DVO_PORT_MIPIA: + case DVO_PORT_MIPIB: + case DVO_PORT_MIPIC: + case DVO_PORT_MIPID: + return DVO_PORT_MIPIA; + default: + return dvo_port; + } +} + static enum port __dvo_port_to_port(int n_ports, int n_dvo, const int port_mapping[][3], u8 dvo_port) { @@ -1930,50 +1963,6 @@ static int _intel_bios_max_tmds_clock(const struct intel_bios_encoder_data *devd } } -static enum port get_edp_port(struct drm_i915_private *i915) -{ - const struct intel_bios_encoder_data *devdata; - enum port port; - - for_each_port(port) { - devdata = i915->vbt.ports[port]; - - if (devdata && intel_bios_encoder_supports_edp(devdata)) - return port; - } - - return PORT_NONE; -} - -/* - * FIXME: The power sequencer and backlight code currently do not support more - * than one set registers, at least not on anything other than VLV/CHV. It will - * clobber the registers. As a temporary workaround, gracefully prevent more - * than one eDP from being registered. - */ -static void sanitize_dual_edp(struct intel_bios_encoder_data *devdata, - enum port port) -{ - struct drm_i915_private *i915 = devdata->i915; - struct child_device_config *child = &devdata->child; - enum port p; - - /* CHV might not clobber PPS registers. */ - if (IS_CHERRYVIEW(i915)) - return; - - p = get_edp_port(i915); - if (p == PORT_NONE) - return; - - drm_dbg_kms(&i915->drm, "both ports %c and %c configured as eDP, " - "disabling port %c eDP\n", port_name(p), port_name(port), - port_name(port)); - - child->device_type &= ~DEVICE_TYPE_DISPLAYPORT_OUTPUT; - child->device_type &= ~DEVICE_TYPE_INTERNAL_CONNECTOR; -} - static bool is_port_valid(struct drm_i915_private *i915, enum port port) { /* @@ -2031,9 +2020,6 @@ static void parse_ddi_port(struct drm_i915_private *i915, supports_typec_usb, supports_tbt, devdata->dsc != NULL); - if (is_edp) - sanitize_dual_edp(devdata, port); - if (is_dvi) sanitize_ddc_pin(devdata, port); @@ -2670,35 +2656,17 @@ bool intel_bios_is_port_edp(struct drm_i915_private *i915, enum port port) return false; } -static bool child_dev_is_dp_dual_mode(const struct child_device_config *child, - enum port port) +static bool child_dev_is_dp_dual_mode(const struct child_device_config *child) { - static const struct { - u16 dp, hdmi; - } port_mapping[] = { - /* - * Buggy VBTs may declare DP ports as having - * HDMI type dvo_port :( So let's check both. - */ - [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, }, - [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, }, - [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, }, - [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, }, - [PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, }, - }; - - if (port == PORT_A || port >= ARRAY_SIZE(port_mapping)) - return false; - if ((child->device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) != (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS)) return false; - if (child->dvo_port == port_mapping[port].dp) + if (dvo_port_type(child->dvo_port) == DVO_PORT_DPA) return true; /* Only accept a HDMI dvo_port as DP++ if it has an AUX channel */ - if (child->dvo_port == port_mapping[port].hdmi && + if (dvo_port_type(child->dvo_port) == DVO_PORT_HDMIA && child->aux_channel != 0) return true; @@ -2708,10 +2676,36 @@ static bool child_dev_is_dp_dual_mode(const struct child_device_config *child, bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *i915, enum port port) { + static const struct { + u16 dp, hdmi; + } port_mapping[] = { + /* + * Buggy VBTs may declare DP ports as having + * HDMI type dvo_port :( So let's check both. + */ + [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, }, + [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, }, + [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, }, + [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, }, + [PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, }, + }; const struct intel_bios_encoder_data *devdata; + if (HAS_DDI(i915)) { + const struct intel_bios_encoder_data *devdata; + + devdata = intel_bios_encoder_data_lookup(i915, port); + + return devdata && child_dev_is_dp_dual_mode(&devdata->child); + } + + if (port == PORT_A || port >= ARRAY_SIZE(port_mapping)) + return false; + list_for_each_entry(devdata, &i915->vbt.display_devices, node) { - if (child_dev_is_dp_dual_mode(&devdata->child, port)) + if ((devdata->child.dvo_port == port_mapping[port].dp || + devdata->child.dvo_port == port_mapping[port].hdmi) && + child_dev_is_dp_dual_mode(&devdata->child)) return true; } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 9e466d829019..868dd43a7542 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2885,7 +2885,7 @@ u32 intel_read_rawclk(struct drm_i915_private *dev_priv) return freq; } -static struct intel_cdclk_funcs tgl_cdclk_funcs = { +static const struct intel_cdclk_funcs tgl_cdclk_funcs = { .get_cdclk = bxt_get_cdclk, .set_cdclk = bxt_set_cdclk, .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, @@ -2893,7 +2893,7 @@ static struct intel_cdclk_funcs tgl_cdclk_funcs = { .calc_voltage_level = tgl_calc_voltage_level, }; -static struct intel_cdclk_funcs ehl_cdclk_funcs = { +static const struct intel_cdclk_funcs ehl_cdclk_funcs = { .get_cdclk = bxt_get_cdclk, .set_cdclk = bxt_set_cdclk, .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, @@ -2901,7 +2901,7 @@ static struct intel_cdclk_funcs ehl_cdclk_funcs = { .calc_voltage_level = ehl_calc_voltage_level, }; -static struct intel_cdclk_funcs icl_cdclk_funcs = { +static const struct intel_cdclk_funcs icl_cdclk_funcs = { .get_cdclk = bxt_get_cdclk, .set_cdclk = bxt_set_cdclk, .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, @@ -2909,7 +2909,7 @@ static struct intel_cdclk_funcs icl_cdclk_funcs = { .calc_voltage_level = icl_calc_voltage_level, }; -static struct intel_cdclk_funcs bxt_cdclk_funcs = { +static const struct intel_cdclk_funcs bxt_cdclk_funcs = { .get_cdclk = bxt_get_cdclk, .set_cdclk = bxt_set_cdclk, .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, @@ -2917,54 +2917,54 @@ static struct intel_cdclk_funcs bxt_cdclk_funcs = { .calc_voltage_level = bxt_calc_voltage_level, }; -static struct intel_cdclk_funcs skl_cdclk_funcs = { +static const struct intel_cdclk_funcs skl_cdclk_funcs = { .get_cdclk = skl_get_cdclk, .set_cdclk = skl_set_cdclk, .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, .modeset_calc_cdclk = skl_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs bdw_cdclk_funcs = { +static const struct intel_cdclk_funcs bdw_cdclk_funcs = { .get_cdclk = bdw_get_cdclk, .set_cdclk = bdw_set_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = bdw_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs chv_cdclk_funcs = { +static const struct intel_cdclk_funcs chv_cdclk_funcs = { .get_cdclk = vlv_get_cdclk, .set_cdclk = chv_set_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = vlv_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs vlv_cdclk_funcs = { +static const struct intel_cdclk_funcs vlv_cdclk_funcs = { .get_cdclk = vlv_get_cdclk, .set_cdclk = vlv_set_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = vlv_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs hsw_cdclk_funcs = { +static const struct intel_cdclk_funcs hsw_cdclk_funcs = { .get_cdclk = hsw_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; /* SNB, IVB, 965G, 945G */ -static struct intel_cdclk_funcs fixed_400mhz_cdclk_funcs = { +static const struct intel_cdclk_funcs fixed_400mhz_cdclk_funcs = { .get_cdclk = fixed_400mhz_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs ilk_cdclk_funcs = { +static const struct intel_cdclk_funcs ilk_cdclk_funcs = { .get_cdclk = fixed_450mhz_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs gm45_cdclk_funcs = { +static const struct intel_cdclk_funcs gm45_cdclk_funcs = { .get_cdclk = gm45_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, @@ -2972,7 +2972,7 @@ static struct intel_cdclk_funcs gm45_cdclk_funcs = { /* G45 uses G33 */ -static struct intel_cdclk_funcs i965gm_cdclk_funcs = { +static const struct intel_cdclk_funcs i965gm_cdclk_funcs = { .get_cdclk = i965gm_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, @@ -2980,19 +2980,19 @@ static struct intel_cdclk_funcs i965gm_cdclk_funcs = { /* i965G uses fixed 400 */ -static struct intel_cdclk_funcs pnv_cdclk_funcs = { +static const struct intel_cdclk_funcs pnv_cdclk_funcs = { .get_cdclk = pnv_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs g33_cdclk_funcs = { +static const struct intel_cdclk_funcs g33_cdclk_funcs = { .get_cdclk = g33_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs i945gm_cdclk_funcs = { +static const struct intel_cdclk_funcs i945gm_cdclk_funcs = { .get_cdclk = i945gm_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, @@ -3000,37 +3000,37 @@ static struct intel_cdclk_funcs i945gm_cdclk_funcs = { /* i945G uses fixed 400 */ -static struct intel_cdclk_funcs i915gm_cdclk_funcs = { +static const struct intel_cdclk_funcs i915gm_cdclk_funcs = { .get_cdclk = i915gm_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs i915g_cdclk_funcs = { +static const struct intel_cdclk_funcs i915g_cdclk_funcs = { .get_cdclk = fixed_333mhz_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs i865g_cdclk_funcs = { +static const struct intel_cdclk_funcs i865g_cdclk_funcs = { .get_cdclk = fixed_266mhz_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs i85x_cdclk_funcs = { +static const struct intel_cdclk_funcs i85x_cdclk_funcs = { .get_cdclk = i85x_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs i845g_cdclk_funcs = { +static const struct intel_cdclk_funcs i845g_cdclk_funcs = { .get_cdclk = fixed_200mhz_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, }; -static struct intel_cdclk_funcs i830_cdclk_funcs = { +static const struct intel_cdclk_funcs i830_cdclk_funcs = { .get_cdclk = fixed_133mhz_get_cdclk, .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, .modeset_calc_cdclk = fixed_modeset_calc_cdclk, diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 1dcfe31e6c6f..cfb567df71b3 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -4361,6 +4361,7 @@ static void intel_ddi_encoder_shutdown(struct intel_encoder *encoder) enum phy phy = intel_port_to_phy(i915, encoder->port); intel_dp_encoder_shutdown(encoder); + intel_hdmi_encoder_shutdown(encoder); if (!intel_phy_is_tc(i915, phy)) return; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index ff598b6cd953..ec403e46a328 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -848,9 +848,16 @@ unsigned int intel_remapped_info_size(const struct intel_remapped_info *rem_info int i; for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { + unsigned int plane_size; + + plane_size = rem_info->plane[i].dst_stride * rem_info->plane[i].height; + if (plane_size == 0) + continue; + if (rem_info->plane_alignment) size = ALIGN(size, rem_info->plane_alignment); - size += rem_info->plane[i].dst_stride * rem_info->plane[i].height; + + size += plane_size; } return size; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 23de500d56b5..be883469d2fc 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -120,6 +120,12 @@ bool intel_dp_is_uhbr(const struct intel_crtc_state *crtc_state) return crtc_state->port_clock >= 1000000; } +static void intel_dp_set_default_sink_rates(struct intel_dp *intel_dp) +{ + intel_dp->sink_rates[0] = 162000; + intel_dp->num_sink_rates = 1; +} + /* update sink rates from dpcd */ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) { @@ -281,7 +287,7 @@ intel_dp_max_data_rate(int max_link_rate, int max_lanes) */ int max_link_rate_kbps = max_link_rate * 10; - max_link_rate_kbps = DIV_ROUND_CLOSEST_ULL(max_link_rate_kbps * 9671, 10000); + max_link_rate_kbps = DIV_ROUND_CLOSEST_ULL(mul_u32_u32(max_link_rate_kbps, 9671), 10000); max_link_rate = max_link_rate_kbps / 8; } @@ -1858,6 +1864,12 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp, intel_dp->lane_count = lane_count; } +static void intel_dp_reset_max_link_params(struct intel_dp *intel_dp) +{ + intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp); + intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp); +} + /* Enable backlight PWM and backlight PP control. */ void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) @@ -2017,8 +2029,7 @@ void intel_dp_sync_state(struct intel_encoder *encoder, if (intel_dp->dpcd[DP_DPCD_REV] == 0) intel_dp_get_dpcd(intel_dp); - intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp); - intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp); + intel_dp_reset_max_link_params(intel_dp); } bool intel_dp_initial_fastset_check(struct intel_encoder *encoder, @@ -2556,6 +2567,9 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) */ intel_psr_init_dpcd(intel_dp); + /* Clear the default sink rates */ + intel_dp->num_sink_rates = 0; + /* Read the eDP 1.4+ supported link rates. */ if (intel_dp->edp_dpcd[0] >= DP_EDP_14) { __le16 sink_rates[DP_MAX_SUPPORTED_RATES]; @@ -2591,6 +2605,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) intel_dp_set_sink_rates(intel_dp); intel_dp_set_common_rates(intel_dp); + intel_dp_reset_max_link_params(intel_dp); /* Read the eDP DSC DPCD registers */ if (DISPLAY_VER(dev_priv) >= 10) @@ -4332,12 +4347,7 @@ intel_dp_detect(struct drm_connector *connector, * supports link training fallback params. */ if (intel_dp->reset_link_params || intel_dp->is_mst) { - /* Initial max link lane count */ - intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp); - - /* Initial max link rate */ - intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp); - + intel_dp_reset_max_link_params(intel_dp); intel_dp->reset_link_params = false; } @@ -5003,6 +5013,9 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, } intel_dp_set_source_rates(intel_dp); + intel_dp_set_default_sink_rates(intel_dp); + intel_dp_set_common_rates(intel_dp); + intel_dp_reset_max_link_params(intel_dp); if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) intel_dp->pps.active_pipe = vlv_active_pipe(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index fa1f375e696b..cb511b2b7069 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -378,8 +378,8 @@ static void intel_fb_plane_dims(const struct intel_framebuffer *fb, int color_pl intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, &fb->base, main_plane); intel_fb_plane_get_subsampling(&hsub, &vsub, &fb->base, color_plane); - *w = main_width / main_hsub / hsub; - *h = main_height / main_vsub / vsub; + *w = DIV_ROUND_UP(main_width, main_hsub * hsub); + *h = DIV_ROUND_UP(main_height, main_vsub * vsub); } static u32 intel_adjust_tile_offset(int *x, int *y, diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index d2e61f6c6e08..371736bdc01f 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1246,12 +1246,13 @@ static void hsw_set_infoframes(struct intel_encoder *encoder, void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable) { struct drm_i915_private *dev_priv = intel_hdmi_to_i915(hdmi); - struct i2c_adapter *adapter = - intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus); + struct i2c_adapter *adapter; if (hdmi->dp_dual_mode.type < DRM_DP_DUAL_MODE_TYPE2_DVI) return; + adapter = intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus); + drm_dbg_kms(&dev_priv->drm, "%s DP dual mode adaptor TMDS output\n", enable ? "Enabling" : "Disabling"); @@ -2258,6 +2259,17 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, return 0; } +void intel_hdmi_encoder_shutdown(struct intel_encoder *encoder) +{ + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + + /* + * Give a hand to buggy BIOSen which forget to turn + * the TMDS output buffers back on after a reboot. + */ + intel_dp_dual_mode_set_tmds_output(intel_hdmi, true); +} + static void intel_hdmi_unset_edid(struct drm_connector *connector) { diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h index b43a180d007e..2bf440eb400a 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.h +++ b/drivers/gpu/drm/i915/display/intel_hdmi.h @@ -28,6 +28,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port, int intel_hdmi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state); +void intel_hdmi_encoder_shutdown(struct intel_encoder *encoder); bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder, struct drm_connector *connector, bool high_tmds_clock_ratio, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index eae09d323049..e8a58c997170 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -9,6 +9,8 @@ #include <linux/dma-resv.h> #include <linux/module.h> +#include <asm/smp.h> + #include "i915_drv.h" #include "i915_gem_object.h" #include "i915_scatterlist.h" diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index f17383e76eb7..57c97554393b 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -1396,6 +1396,9 @@ remap_pages(struct drm_i915_gem_object *obj, { unsigned int row; + if (!width || !height) + return sg; + if (alignment_pad) { st->nents++; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index d7710debcd47..38b47e73e35d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -2373,6 +2373,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) unsigned long flags; bool disabled; + lockdep_assert_held(&guc->submission_state.lock); GEM_BUG_ON(!intel_gt_pm_is_awake(gt)); GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id)); GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id)); @@ -2388,7 +2389,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) } spin_unlock_irqrestore(&ce->guc_state.lock, flags); if (unlikely(disabled)) { - release_guc_id(guc, ce); + __release_guc_id(guc, ce); __guc_context_destroy(ce); return; } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 2c3cd6e635b5..820a1f38b271 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1537,38 +1537,14 @@ i915_request_await_object(struct i915_request *to, struct drm_i915_gem_object *obj, bool write) { - struct dma_fence *excl; + struct dma_resv_iter cursor; + struct dma_fence *fence; int ret = 0; - if (write) { - struct dma_fence **shared; - unsigned int count, i; - - ret = dma_resv_get_fences(obj->base.resv, &excl, &count, - &shared); + dma_resv_for_each_fence(&cursor, obj->base.resv, write, fence) { + ret = i915_request_await_dma_fence(to, fence); if (ret) - return ret; - - for (i = 0; i < count; i++) { - ret = i915_request_await_dma_fence(to, shared[i]); - if (ret) - break; - - dma_fence_put(shared[i]); - } - - for (; i < count; i++) - dma_fence_put(shared[i]); - kfree(shared); - } else { - excl = dma_resv_get_excl_unlocked(obj->base.resv); - } - - if (excl) { - if (ret == 0) - ret = i915_request_await_dma_fence(to, excl); - - dma_fence_put(excl); + break; } return ret; diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 9558e9e1b431..cb685fe2039b 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -81,7 +81,6 @@ static void imx_drm_atomic_commit_tail(struct drm_atomic_state *state) struct drm_plane_state *old_plane_state, *new_plane_state; bool plane_disabling = false; int i; - bool fence_cookie = dma_fence_begin_signalling(); drm_atomic_helper_commit_modeset_disables(dev, state); @@ -112,7 +111,6 @@ static void imx_drm_atomic_commit_tail(struct drm_atomic_state *state) } drm_atomic_helper_commit_hw_done(state); - dma_fence_end_signalling(fence_cookie); } static const struct drm_mode_config_helper_funcs imx_drm_mode_config_helpers = { diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index 89dd618d78f3..0655582ae8ed 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -88,7 +88,7 @@ static void mxsfb_set_formats(struct mxsfb_drm_private *mxsfb, ctrl |= CTRL_BUS_WIDTH_24; break; default: - dev_err(drm->dev, "Unknown media bus format %d\n", bus_format); + dev_err(drm->dev, "Unknown media bus format 0x%x\n", bus_format); break; } @@ -362,6 +362,12 @@ static void mxsfb_crtc_atomic_enable(struct drm_crtc *crtc, drm_atomic_get_new_bridge_state(state, mxsfb->bridge); bus_format = bridge_state->input_bus_cfg.format; + if (bus_format == MEDIA_BUS_FMT_FIXED) { + dev_warn_once(drm->dev, + "Bridge does not provide bus format, assuming MEDIA_BUS_FMT_RGB888_1X24.\n" + "Please fix bridge driver by handling atomic_get_input_bus_fmts.\n"); + bus_format = MEDIA_BUS_FMT_RGB888_1X24; + } } /* If there is no bridge, use bus format from connector */ diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 12b107acb6ee..fa73fe57f97b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1249,7 +1249,6 @@ nouveau_ttm_tt_populate(struct ttm_device *bdev, { struct ttm_tt *ttm_dma = (void *)ttm; struct nouveau_drm *drm; - struct device *dev; bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (ttm_tt_is_populated(ttm)) @@ -1262,7 +1261,6 @@ nouveau_ttm_tt_populate(struct ttm_device *bdev, } drm = nouveau_bdev(bdev); - dev = drm->dev->dev; return ttm_pool_alloc(&drm->ttm.bdev.pool, ttm, ctx); } @@ -1272,7 +1270,6 @@ nouveau_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) { struct nouveau_drm *drm; - struct device *dev; bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (slave) @@ -1281,7 +1278,6 @@ nouveau_ttm_tt_unpopulate(struct ttm_device *bdev, nouveau_ttm_tt_unbind(bdev, ttm); drm = nouveau_bdev(bdev); - dev = drm->dev->dev; return ttm_pool_free(&drm->ttm.bdev.pool, ttm); } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 92987daa5e17..3828aafd3ac4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -166,7 +166,7 @@ static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, goto error_dma_unmap; mutex_unlock(&svmm->mutex); - args->dst[0] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + args->dst[0] = migrate_pfn(page_to_pfn(dpage)); return 0; error_dma_unmap: @@ -602,7 +602,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, ((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT); if (src & MIGRATE_PFN_WRITE) *pfn |= NVIF_VMM_PFNMAP_V0_W; - return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + return migrate_pfn(page_to_pfn(dpage)); out_dma_unmap: dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 6109cd9e3399..e7efd9ede8e4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -562,6 +562,7 @@ nouveau_drm_device_init(struct drm_device *dev) nvkm_dbgopt(nouveau_debug, "DRM"); INIT_LIST_HEAD(&drm->clients); + mutex_init(&drm->clients_lock); spin_lock_init(&drm->tile.lock); /* workaround an odd issue on nvc1 by disabling the device's @@ -632,6 +633,7 @@ fail_alloc: static void nouveau_drm_device_fini(struct drm_device *dev) { + struct nouveau_cli *cli, *temp_cli; struct nouveau_drm *drm = nouveau_drm(dev); if (nouveau_pmops_runtime()) { @@ -656,9 +658,28 @@ nouveau_drm_device_fini(struct drm_device *dev) nouveau_ttm_fini(drm); nouveau_vga_fini(drm); + /* + * There may be existing clients from as-yet unclosed files. For now, + * clean them up here rather than deferring until the file is closed, + * but this likely not correct if we want to support hot-unplugging + * properly. + */ + mutex_lock(&drm->clients_lock); + list_for_each_entry_safe(cli, temp_cli, &drm->clients, head) { + list_del(&cli->head); + mutex_lock(&cli->mutex); + if (cli->abi16) + nouveau_abi16_fini(cli->abi16); + mutex_unlock(&cli->mutex); + nouveau_cli_fini(cli); + kfree(cli); + } + mutex_unlock(&drm->clients_lock); + nouveau_cli_fini(&drm->client); nouveau_cli_fini(&drm->master); nvif_parent_dtor(&drm->parent); + mutex_destroy(&drm->clients_lock); kfree(drm); } @@ -796,7 +817,7 @@ nouveau_drm_device_remove(struct drm_device *dev) struct nvkm_client *client; struct nvkm_device *device; - drm_dev_unregister(dev); + drm_dev_unplug(dev); client = nvxx_client(&drm->client.base); device = nvkm_device_find(client->device); @@ -1090,9 +1111,9 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) fpriv->driver_priv = cli; - mutex_lock(&drm->client.mutex); + mutex_lock(&drm->clients_lock); list_add(&cli->head, &drm->clients); - mutex_unlock(&drm->client.mutex); + mutex_unlock(&drm->clients_lock); done: if (ret && cli) { @@ -1110,6 +1131,16 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv) { struct nouveau_cli *cli = nouveau_cli(fpriv); struct nouveau_drm *drm = nouveau_drm(dev); + int dev_index; + + /* + * The device is gone, and as it currently stands all clients are + * cleaned up in the removal codepath. In the future this may change + * so that we can support hot-unplugging, but for now we immediately + * return to avoid a double-free situation. + */ + if (!drm_dev_enter(dev, &dev_index)) + return; pm_runtime_get_sync(dev->dev); @@ -1118,14 +1149,15 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv) nouveau_abi16_fini(cli->abi16); mutex_unlock(&cli->mutex); - mutex_lock(&drm->client.mutex); + mutex_lock(&drm->clients_lock); list_del(&cli->head); - mutex_unlock(&drm->client.mutex); + mutex_unlock(&drm->clients_lock); nouveau_cli_fini(cli); kfree(cli); pm_runtime_mark_last_busy(dev->dev); pm_runtime_put_autosuspend(dev->dev); + drm_dev_exit(dev_index); } static const struct drm_ioctl_desc diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index ba65f136cf48..b2a970aa9bf4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -139,6 +139,11 @@ struct nouveau_drm { struct list_head clients; + /** + * @clients_lock: Protects access to the @clients list of &struct nouveau_cli. + */ + struct mutex clients_lock; + u8 old_pm_cap; struct { diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 8c2ecc282723..9416bee92141 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -56,7 +56,7 @@ static vm_fault_t nouveau_ttm_fault(struct vm_fault *vmf) nouveau_bo_del_io_reserve_lru(bo); prot = vm_get_page_prot(vma->vm_flags); - ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1); + ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT); nouveau_bo_add_io_reserve_lru(bo); if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) return ret; @@ -337,7 +337,7 @@ nouveau_gem_set_domain(struct drm_gem_object *gem, uint32_t read_domains, struct ttm_buffer_object *bo = &nvbo->bo; uint32_t domains = valid_domains & nvbo->valid_domains & (write_domains ? write_domains : read_domains); - uint32_t pref_domains = 0;; + uint32_t pref_domains = 0; if (!domains) return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 1a896a24288a..266809e511e2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -162,10 +162,14 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, */ mm = get_task_mm(current); + if (!mm) { + return -EINVAL; + } mmap_read_lock(mm); if (!cli->svm.svmm) { mmap_read_unlock(mm); + mmput(mm); return -EINVAL; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c index 704df0f2d1f1..09a112af2f89 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c @@ -78,6 +78,6 @@ int gt215_ce_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_engine **pengine) { - return nvkm_falcon_new_(>215_ce, device, type, inst, + return nvkm_falcon_new_(>215_ce, device, type, -1, (device->chipset != 0xaf), 0x104000, pengine); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index ca75c5f6ecaf..b51d690f375f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -3147,8 +3147,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, WARN_ON(device->chip->ptr.inst & ~((1 << ARRAY_SIZE(device->ptr)) - 1)); \ for (j = 0; device->chip->ptr.inst && j < ARRAY_SIZE(device->ptr); j++) { \ if ((device->chip->ptr.inst & BIT(j)) && (subdev_mask & BIT_ULL(type))) { \ - int inst = (device->chip->ptr.inst == 1) ? -1 : (j); \ - ret = device->chip->ptr.ctor(device, (type), inst, &device->ptr[j]); \ + ret = device->chip->ptr.ctor(device, (type), (j), &device->ptr[j]); \ subdev = nvkm_device_subdev(device, (type), (j)); \ if (ret) { \ nvkm_subdev_del(&subdev); \ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c index c39e797dc7c9..cf5dcfda7b25 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c @@ -21,7 +21,6 @@ */ #include "priv.h" -#include "priv.h" #include <core/firmware.h> static void * diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c index d6a1f8d04c09..186b4e63e559 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c @@ -299,7 +299,7 @@ nvkm_uvmm_mthd_page(struct nvkm_uvmm *uvmm, void *argv, u32 argc) page = uvmm->vmm->func->page; for (nr = 0; page[nr].shift; nr++); - if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) { + if (!(nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) { if ((index = args->v0.index) >= nr) return -EINVAL; type = page[index].type; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c index b5e733783b5b..17899fc95b2d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c @@ -488,7 +488,7 @@ gp100_vmm_fault_cancel(struct nvkm_vmm *vmm, void *argv, u32 argc) struct gp100_vmm_fault_cancel_v0 v0; } *args = argv; int ret = -ENOSYS; - u32 inst, aper; + u32 aper; if ((ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) return ret; @@ -502,7 +502,7 @@ gp100_vmm_fault_cancel(struct nvkm_vmm *vmm, void *argv, u32 argc) args->v0.inst |= 0x80000000; if (!WARN_ON(nvkm_gr_ctxsw_pause(device))) { - if ((inst = nvkm_gr_ctxsw_inst(device)) == args->v0.inst) { + if (nvkm_gr_ctxsw_inst(device) == args->v0.inst) { gf100_vmm_invalidate(vmm, 0x0000001b /* CANCEL_TARGETED. */ | (args->v0.hub << 20) | diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index 2cb8eba76af8..cfc8d644cedf 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -520,6 +520,16 @@ config DRM_PANEL_SHARP_LS043T1LE01 Say Y here if you want to enable support for Sharp LS043T1LE01 qHD (540x960) DSI panel as found on the Qualcomm APQ8074 Dragonboard +config DRM_PANEL_SHARP_LS060T1SX01 + tristate "Sharp LS060T1SX01 FullHD video mode panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + help + Say Y here if you want to enable support for Sharp LS060T1SX01 6.0" + FullHD (1080x1920) DSI panel as found in Dragonboard Display Adapter + Bundle. + config DRM_PANEL_SITRONIX_ST7701 tristate "Sitronix ST7701 panel driver" depends on OF diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index 6e30640b9099..bca4cc1f2715 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_DRM_PANEL_SEIKO_43WVF1G) += panel-seiko-43wvf1g.o obj-$(CONFIG_DRM_PANEL_SHARP_LQ101R1SX01) += panel-sharp-lq101r1sx01.o obj-$(CONFIG_DRM_PANEL_SHARP_LS037V7DW01) += panel-sharp-ls037v7dw01.o obj-$(CONFIG_DRM_PANEL_SHARP_LS043T1LE01) += panel-sharp-ls043t1le01.o +obj-$(CONFIG_DRM_PANEL_SHARP_LS060T1SX01) += panel-sharp-ls060t1sx01.o obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7701) += panel-sitronix-st7701.o obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7703) += panel-sitronix-st7703.o obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7789V) += panel-sitronix-st7789v.o diff --git a/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c b/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c index 30f28ad4df6b..31daae1da9c9 100644 --- a/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c +++ b/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c @@ -8,6 +8,7 @@ #include <linux/backlight.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> +#include <linux/media-bus-format.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/regulator/consumer.h> @@ -220,6 +221,10 @@ static const struct drm_display_mode default_mode_ys = { .height_mm = 130, }; +static const u32 mantix_bus_formats[] = { + MEDIA_BUS_FMT_RGB888_1X24, +}; + static int mantix_get_modes(struct drm_panel *panel, struct drm_connector *connector) { @@ -241,6 +246,10 @@ static int mantix_get_modes(struct drm_panel *panel, connector->display_info.height_mm = mode->height_mm; drm_mode_probed_add(connector, mode); + drm_display_info_set_bus_formats(&connector->display_info, + mantix_bus_formats, + ARRAY_SIZE(mantix_bus_formats)); + return 1; } diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c index e0b1a7e354f3..e0f773678168 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c @@ -116,7 +116,8 @@ static int s6e63m0_dsi_probe(struct mipi_dsi_device *dsi) static int s6e63m0_dsi_remove(struct mipi_dsi_device *dsi) { mipi_dsi_detach(dsi); - return s6e63m0_remove(&dsi->dev); + s6e63m0_remove(&dsi->dev); + return 0; } static const struct of_device_id s6e63m0_dsi_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c index 3669cc3719ce..c178d962b0d5 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c @@ -64,7 +64,8 @@ static int s6e63m0_spi_probe(struct spi_device *spi) static int s6e63m0_spi_remove(struct spi_device *spi) { - return s6e63m0_remove(&spi->dev); + s6e63m0_remove(&spi->dev); + return 0; } static const struct of_device_id s6e63m0_spi_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c index 35d72ac663d6..b34fa4d5de07 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c @@ -749,13 +749,11 @@ int s6e63m0_probe(struct device *dev, void *trsp, } EXPORT_SYMBOL_GPL(s6e63m0_probe); -int s6e63m0_remove(struct device *dev) +void s6e63m0_remove(struct device *dev) { struct s6e63m0 *ctx = dev_get_drvdata(dev); drm_panel_remove(&ctx->panel); - - return 0; } EXPORT_SYMBOL_GPL(s6e63m0_remove); diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h index 306605ed1117..c926eca1c817 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h @@ -35,6 +35,6 @@ int s6e63m0_probe(struct device *dev, void *trsp, const u8 *data, size_t len), bool dsi_mode); -int s6e63m0_remove(struct device *dev); +void s6e63m0_remove(struct device *dev); #endif /* _PANEL_SAMSUNG_S6E63M0_H */ diff --git a/drivers/gpu/drm/panel/panel-sharp-ls060t1sx01.c b/drivers/gpu/drm/panel/panel-sharp-ls060t1sx01.c new file mode 100644 index 000000000000..e12570561629 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-sharp-ls060t1sx01.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2021 Linaro Ltd. + * Generated with linux-mdss-dsi-panel-driver-generator from vendor device tree: + * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved. + */ + +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/regulator/consumer.h> + +#include <video/mipi_display.h> + +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> + +struct sharp_ls060 { + struct drm_panel panel; + struct mipi_dsi_device *dsi; + struct regulator *vddi_supply; + struct regulator *vddh_supply; + struct regulator *avdd_supply; + struct regulator *avee_supply; + struct gpio_desc *reset_gpio; + bool prepared; +}; + +static inline struct sharp_ls060 *to_sharp_ls060(struct drm_panel *panel) +{ + return container_of(panel, struct sharp_ls060, panel); +} + +#define dsi_dcs_write_seq(dsi, seq...) ({ \ + static const u8 d[] = { seq }; \ + \ + mipi_dsi_dcs_write_buffer(dsi, d, ARRAY_SIZE(d)); \ + }) + +static void sharp_ls060_reset(struct sharp_ls060 *ctx) +{ + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + usleep_range(10000, 11000); +} + +static int sharp_ls060_on(struct sharp_ls060 *ctx) +{ + struct mipi_dsi_device *dsi = ctx->dsi; + struct device *dev = &dsi->dev; + int ret; + + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + + ret = dsi_dcs_write_seq(dsi, 0xbb, 0x13); + if (ret < 0) { + dev_err(dev, "Failed to send command: %d\n", ret); + return ret; + } + + ret = dsi_dcs_write_seq(dsi, MIPI_DCS_WRITE_MEMORY_START); + if (ret < 0) { + dev_err(dev, "Failed to send command: %d\n", ret); + return ret; + } + + ret = mipi_dsi_dcs_exit_sleep_mode(dsi); + if (ret < 0) { + dev_err(dev, "Failed to exit sleep mode: %d\n", ret); + return ret; + } + msleep(120); + + ret = mipi_dsi_dcs_set_display_on(dsi); + if (ret < 0) { + dev_err(dev, "Failed to set display on: %d\n", ret); + return ret; + } + msleep(50); + + return 0; +} + +static int sharp_ls060_off(struct sharp_ls060 *ctx) +{ + struct mipi_dsi_device *dsi = ctx->dsi; + struct device *dev = &dsi->dev; + int ret; + + dsi->mode_flags &= ~MIPI_DSI_MODE_LPM; + + ret = mipi_dsi_dcs_set_display_off(dsi); + if (ret < 0) { + dev_err(dev, "Failed to set display off: %d\n", ret); + return ret; + } + usleep_range(2000, 3000); + + ret = mipi_dsi_dcs_enter_sleep_mode(dsi); + if (ret < 0) { + dev_err(dev, "Failed to enter sleep mode: %d\n", ret); + return ret; + } + msleep(121); + + return 0; +} + +static int sharp_ls060_prepare(struct drm_panel *panel) +{ + struct sharp_ls060 *ctx = to_sharp_ls060(panel); + struct device *dev = &ctx->dsi->dev; + int ret; + + if (ctx->prepared) + return 0; + + ret = regulator_enable(ctx->vddi_supply); + if (ret < 0) + return ret; + + ret = regulator_enable(ctx->avdd_supply); + if (ret < 0) + goto err_avdd; + + usleep_range(1000, 2000); + + ret = regulator_enable(ctx->avee_supply); + if (ret < 0) + goto err_avee; + + usleep_range(10000, 11000); + + ret = regulator_enable(ctx->vddh_supply); + if (ret < 0) + goto err_vddh; + + usleep_range(10000, 11000); + + sharp_ls060_reset(ctx); + + ret = sharp_ls060_on(ctx); + if (ret < 0) { + dev_err(dev, "Failed to initialize panel: %d\n", ret); + goto err_on; + } + + ctx->prepared = true; + + return 0; + +err_on: + regulator_disable(ctx->vddh_supply); + + usleep_range(10000, 11000); + +err_vddh: + regulator_disable(ctx->avee_supply); + +err_avee: + regulator_disable(ctx->avdd_supply); + + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + +err_avdd: + regulator_disable(ctx->vddi_supply); + + return ret; +} + +static int sharp_ls060_unprepare(struct drm_panel *panel) +{ + struct sharp_ls060 *ctx = to_sharp_ls060(panel); + struct device *dev = &ctx->dsi->dev; + int ret; + + if (!ctx->prepared) + return 0; + + ret = sharp_ls060_off(ctx); + if (ret < 0) + dev_err(dev, "Failed to un-initialize panel: %d\n", ret); + + regulator_disable(ctx->vddh_supply); + + usleep_range(10000, 11000); + + regulator_disable(ctx->avee_supply); + regulator_disable(ctx->avdd_supply); + + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + + regulator_disable(ctx->vddi_supply); + + ctx->prepared = false; + return 0; +} + +static const struct drm_display_mode sharp_ls060_mode = { + .clock = (1080 + 96 + 16 + 64) * (1920 + 4 + 1 + 16) * 60 / 1000, + .hdisplay = 1080, + .hsync_start = 1080 + 96, + .hsync_end = 1080 + 96 + 16, + .htotal = 1080 + 96 + 16 + 64, + .vdisplay = 1920, + .vsync_start = 1920 + 4, + .vsync_end = 1920 + 4 + 1, + .vtotal = 1920 + 4 + 1 + 16, + .width_mm = 75, + .height_mm = 132, +}; + +static int sharp_ls060_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct drm_display_mode *mode; + + mode = drm_mode_duplicate(connector->dev, &sharp_ls060_mode); + if (!mode) + return -ENOMEM; + + drm_mode_set_name(mode); + + mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; + connector->display_info.width_mm = mode->width_mm; + connector->display_info.height_mm = mode->height_mm; + drm_mode_probed_add(connector, mode); + + return 1; +} + +static const struct drm_panel_funcs sharp_ls060_panel_funcs = { + .prepare = sharp_ls060_prepare, + .unprepare = sharp_ls060_unprepare, + .get_modes = sharp_ls060_get_modes, +}; + +static int sharp_ls060_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + struct sharp_ls060 *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->vddi_supply = devm_regulator_get(dev, "vddi"); + if (IS_ERR(ctx->vddi_supply)) + return PTR_ERR(ctx->vddi_supply); + + ctx->vddh_supply = devm_regulator_get(dev, "vddh"); + if (IS_ERR(ctx->vddh_supply)) + return PTR_ERR(ctx->vddh_supply); + + ctx->avdd_supply = devm_regulator_get(dev, "avdd"); + if (IS_ERR(ctx->avdd_supply)) + return PTR_ERR(ctx->avdd_supply); + + ctx->avee_supply = devm_regulator_get(dev, "avee"); + if (IS_ERR(ctx->avee_supply)) + return PTR_ERR(ctx->avee_supply); + + ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(ctx->reset_gpio)) + return dev_err_probe(dev, PTR_ERR(ctx->reset_gpio), + "Failed to get reset-gpios\n"); + + ctx->dsi = dsi; + mipi_dsi_set_drvdata(dsi, ctx); + + dsi->lanes = 4; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | + MIPI_DSI_MODE_NO_EOT_PACKET | + MIPI_DSI_CLOCK_NON_CONTINUOUS; + + drm_panel_init(&ctx->panel, dev, &sharp_ls060_panel_funcs, + DRM_MODE_CONNECTOR_DSI); + + ret = drm_panel_of_backlight(&ctx->panel); + if (ret) + return dev_err_probe(dev, ret, "Failed to get backlight\n"); + + drm_panel_add(&ctx->panel); + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "Failed to attach to DSI host: %d\n", ret); + drm_panel_remove(&ctx->panel); + return ret; + } + + return 0; +} + +static int sharp_ls060_remove(struct mipi_dsi_device *dsi) +{ + struct sharp_ls060 *ctx = mipi_dsi_get_drvdata(dsi); + int ret; + + ret = mipi_dsi_detach(dsi); + if (ret < 0) + dev_err(&dsi->dev, "Failed to detach from DSI host: %d\n", ret); + + drm_panel_remove(&ctx->panel); + + return 0; +} + +static const struct of_device_id sharp_ls060t1sx01_of_match[] = { + { .compatible = "sharp,ls060t1sx01" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, sharp_ls060t1sx01_of_match); + +static struct mipi_dsi_driver sharp_ls060_driver = { + .probe = sharp_ls060_probe, + .remove = sharp_ls060_remove, + .driver = { + .name = "panel-sharp-ls060t1sx01", + .of_match_table = sharp_ls060t1sx01_of_match, + }, +}; +module_mipi_dsi_driver(sharp_ls060_driver); + +MODULE_AUTHOR("Dmitry Baryshkov <dmitry.baryshkov@linaro.org>"); +MODULE_DESCRIPTION("DRM driver for Sharp LS060T1SX01 1080p video mode dsi panel"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 7f3e1b84b5f5..eb475a3a774b 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2370,6 +2370,38 @@ static const struct panel_desc logictechno_lt170410_2whc = { .connector_type = DRM_MODE_CONNECTOR_LVDS, }; +static const struct drm_display_mode logictechno_lttd800480070_l2rt_mode = { + .clock = 33000, + .hdisplay = 800, + .hsync_start = 800 + 112, + .hsync_end = 800 + 112 + 3, + .htotal = 800 + 112 + 3 + 85, + .vdisplay = 480, + .vsync_start = 480 + 38, + .vsync_end = 480 + 38 + 3, + .vtotal = 480 + 38 + 3 + 29, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, +}; + +static const struct panel_desc logictechno_lttd800480070_l2rt = { + .modes = &logictechno_lttd800480070_l2rt_mode, + .num_modes = 1, + .bpc = 8, + .size = { + .width = 154, + .height = 86, + }, + .delay = { + .prepare = 45, + .enable = 100, + .disable = 100, + .unprepare = 45 + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .bus_flags = DRM_BUS_FLAG_PIXDATA_SAMPLE_NEGEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, +}; + static const struct drm_display_mode logictechno_lttd800480070_l6wh_rt_mode = { .clock = 33000, .hdisplay = 800, @@ -3751,6 +3783,9 @@ static const struct of_device_id platform_of_match[] = { .compatible = "logictechno,lt170410-2whc", .data = &logictechno_lt170410_2whc, }, { + .compatible = "logictechno,lttd800480070-l2rt", + .data = &logictechno_lttd800480070_l2rt, + }, { .compatible = "logictechno,lttd800480070-l6wh-rt", .data = &logictechno_lttd800480070_l6wh_rt, }, { diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7703.c b/drivers/gpu/drm/panel/panel-sitronix-st7703.c index a2c303e5732c..73f69c929a75 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7703.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7703.c @@ -453,6 +453,10 @@ disable_vcc: return ret; } +static const u32 mantix_bus_formats[] = { + MEDIA_BUS_FMT_RGB888_1X24, +}; + static int st7703_get_modes(struct drm_panel *panel, struct drm_connector *connector) { @@ -474,6 +478,10 @@ static int st7703_get_modes(struct drm_panel *panel, connector->display_info.height_mm = mode->height_mm; drm_mode_probed_add(connector, mode); + drm_display_info_set_bus_formats(&connector->display_info, + mantix_bus_formats, + ARRAY_SIZE(mantix_bus_formats)); + return 1; } diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 458f92a70887..a36a4f2c76b0 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -61,7 +61,7 @@ static vm_fault_t radeon_gem_fault(struct vm_fault *vmf) goto unlock_resv; ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, - TTM_BO_VM_NUM_PREFAULT, 1); + TTM_BO_VM_NUM_PREFAULT); if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) goto unlock_mclk; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 042c16b5d54a..5bc5f775abe1 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -699,30 +699,16 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, struct drm_gem_object *obj, bool write) { + struct dma_resv_iter cursor; + struct dma_fence *fence; int ret; - struct dma_fence **fences; - unsigned int i, fence_count; - - if (!write) { - struct dma_fence *fence = dma_resv_get_excl_unlocked(obj->resv); - - return drm_sched_job_add_dependency(job, fence); - } - - ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences); - if (ret || !fence_count) - return ret; - for (i = 0; i < fence_count; i++) { - ret = drm_sched_job_add_dependency(job, fences[i]); + dma_resv_for_each_fence(&cursor, obj->resv, write, fence) { + ret = drm_sched_job_add_dependency(job, fence); if (ret) - break; + return ret; } - - for (; i < fence_count; i++) - dma_fence_put(fences[i]); - kfree(fences); - return ret; + return 0; } EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index d62b2013c367..739f11c0109c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -269,23 +269,15 @@ static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo) static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) { struct dma_resv *resv = &bo->base._resv; - struct dma_resv_list *fobj; + struct dma_resv_iter cursor; struct dma_fence *fence; - int i; - - rcu_read_lock(); - fobj = dma_resv_shared_list(resv); - fence = dma_resv_excl_fence(resv); - if (fence && !fence->ops->signaled) - dma_fence_enable_sw_signaling(fence); - - for (i = 0; fobj && i < fobj->shared_count; ++i) { - fence = rcu_dereference(fobj->shared[i]); + dma_resv_iter_begin(&cursor, resv, true); + dma_resv_for_each_fence_unlocked(&cursor, fence) { if (!fence->ops->signaled) dma_fence_enable_sw_signaling(fence); } - rcu_read_unlock(); + dma_resv_iter_end(&cursor); } /** @@ -627,7 +619,8 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, *busy = !ret; } - if (ret && place && !bo->bdev->funcs->eviction_valuable(bo, place)) { + if (ret && place && (bo->resource->mem_type != place->mem_type || + !bo->bdev->funcs->eviction_valuable(bo, place))) { ret = false; if (*locked) { dma_resv_unlock(bo->base.resv); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 33680c94127c..08ba083a80d2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -173,89 +173,6 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_vm_reserve); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/** - * ttm_bo_vm_insert_huge - Insert a pfn for PUD or PMD faults - * @vmf: Fault data - * @bo: The buffer object - * @page_offset: Page offset from bo start - * @fault_page_size: The size of the fault in pages. - * @pgprot: The page protections. - * Does additional checking whether it's possible to insert a PUD or PMD - * pfn and performs the insertion. - * - * Return: VM_FAULT_NOPAGE on successful insertion, VM_FAULT_FALLBACK if - * a huge fault was not possible, or on insertion error. - */ -static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, - struct ttm_buffer_object *bo, - pgoff_t page_offset, - pgoff_t fault_page_size, - pgprot_t pgprot) -{ - pgoff_t i; - vm_fault_t ret; - unsigned long pfn; - pfn_t pfnt; - struct ttm_tt *ttm = bo->ttm; - bool write = vmf->flags & FAULT_FLAG_WRITE; - - /* Fault should not cross bo boundary. */ - page_offset &= ~(fault_page_size - 1); - if (page_offset + fault_page_size > bo->resource->num_pages) - goto out_fallback; - - if (bo->resource->bus.is_iomem) - pfn = ttm_bo_io_mem_pfn(bo, page_offset); - else - pfn = page_to_pfn(ttm->pages[page_offset]); - - /* pfn must be fault_page_size aligned. */ - if ((pfn & (fault_page_size - 1)) != 0) - goto out_fallback; - - /* Check that memory is contiguous. */ - if (!bo->resource->bus.is_iomem) { - for (i = 1; i < fault_page_size; ++i) { - if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i) - goto out_fallback; - } - } else if (bo->bdev->funcs->io_mem_pfn) { - for (i = 1; i < fault_page_size; ++i) { - if (ttm_bo_io_mem_pfn(bo, page_offset + i) != pfn + i) - goto out_fallback; - } - } - - pfnt = __pfn_to_pfn_t(pfn, PFN_DEV); - if (fault_page_size == (HPAGE_PMD_SIZE >> PAGE_SHIFT)) - ret = vmf_insert_pfn_pmd_prot(vmf, pfnt, pgprot, write); -#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD - else if (fault_page_size == (HPAGE_PUD_SIZE >> PAGE_SHIFT)) - ret = vmf_insert_pfn_pud_prot(vmf, pfnt, pgprot, write); -#endif - else - WARN_ON_ONCE(ret = VM_FAULT_FALLBACK); - - if (ret != VM_FAULT_NOPAGE) - goto out_fallback; - - return VM_FAULT_NOPAGE; -out_fallback: - count_vm_event(THP_FAULT_FALLBACK); - return VM_FAULT_FALLBACK; -} -#else -static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, - struct ttm_buffer_object *bo, - pgoff_t page_offset, - pgoff_t fault_page_size, - pgprot_t pgprot) -{ - return VM_FAULT_FALLBACK; -} -#endif - /** * ttm_bo_vm_fault_reserved - TTM fault helper * @vmf: The struct vm_fault given as argument to the fault callback @@ -263,7 +180,6 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, * @num_prefault: Maximum number of prefault pages. The caller may want to * specify this based on madvice settings and the size of the GPU object * backed by the memory. - * @fault_page_size: The size of the fault in pages. * * This function inserts one or more page table entries pointing to the * memory backing the buffer object, and then returns a return code @@ -277,8 +193,7 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, */ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, pgprot_t prot, - pgoff_t num_prefault, - pgoff_t fault_page_size) + pgoff_t num_prefault) { struct vm_area_struct *vma = vmf->vma; struct ttm_buffer_object *bo = vma->vm_private_data; @@ -329,11 +244,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, prot = pgprot_decrypted(prot); } - /* We don't prefault on huge faults. Yet. */ - if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1) - return ttm_bo_vm_insert_huge(vmf, bo, page_offset, - fault_page_size, prot); - /* * Speculatively prefault a number of pages. Only error on * first page. @@ -429,7 +339,7 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) prot = vma->vm_page_prot; if (drm_dev_enter(ddev, &idx)) { - ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1); + ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT); drm_dev_exit(idx); } else { ret = ttm_bo_vm_dummy_page(vmf, prot); diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index 3750fd216131..930574ad2bca 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -30,7 +30,7 @@ static int udl_get_edid_block(void *data, u8 *buf, unsigned int block, int bval = (i + block * EDID_LENGTH) << 8; ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), 0x02, (0x80 | (0x02 << 5)), bval, - 0xA1, read_buff, 2, HZ); + 0xA1, read_buff, 2, 1000); if (ret < 1) { DRM_ERROR("Read EDID byte %d failed err %x\n", i, ret); kfree(read_buff); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 6a000d77c568..e47ae40a865a 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -487,8 +487,8 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, for (i = 0; i < se->in_sync_count; i++) { struct drm_v3d_sem in; - ret = copy_from_user(&in, handle++, sizeof(in)); - if (ret) { + if (copy_from_user(&in, handle++, sizeof(in))) { + ret = -EFAULT; DRM_DEBUG("Failed to copy wait dep handle.\n"); goto fail_deps; } @@ -609,8 +609,8 @@ v3d_get_multisync_post_deps(struct drm_file *file_priv, for (i = 0; i < count; i++) { struct drm_v3d_sem out; - ret = copy_from_user(&out, post_deps++, sizeof(out)); - if (ret) { + if (copy_from_user(&out, post_deps++, sizeof(out))) { + ret = -EFAULT; DRM_DEBUG("Failed to copy post dep handles\n"); goto fail; } @@ -646,9 +646,8 @@ v3d_get_multisync_submit_deps(struct drm_file *file_priv, struct v3d_submit_ext *se = data; int ret; - ret = copy_from_user(&multisync, ext, sizeof(multisync)); - if (ret) - return ret; + if (copy_from_user(&multisync, ext, sizeof(multisync))) + return -EFAULT; if (multisync.pad) return -EINVAL; diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index a6caebd4a0dd..5b00310ac4cd 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -308,8 +308,10 @@ virtio_gpu_user_framebuffer_create(struct drm_device *dev, return ERR_PTR(-EINVAL); virtio_gpu_fb = kzalloc(sizeof(*virtio_gpu_fb), GFP_KERNEL); - if (virtio_gpu_fb == NULL) + if (virtio_gpu_fb == NULL) { + drm_gem_object_put(obj); return ERR_PTR(-ENOMEM); + } ret = virtio_gpu_framebuffer_init(dev, virtio_gpu_fb, mode_cmd, obj); if (ret) { diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 749db18dcfa2..d86e1ad4a972 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -163,10 +163,11 @@ static __poll_t virtio_gpu_poll(struct file *filp, struct drm_file *drm_file = filp->private_data; struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv; struct drm_device *dev = drm_file->minor->dev; + struct virtio_gpu_device *vgdev = dev->dev_private; struct drm_pending_event *e = NULL; __poll_t mask = 0; - if (!vfpriv->ring_idx_mask) + if (!vgdev->has_virgl_3d || !vfpriv || !vfpriv->ring_idx_mask) return drm_poll(filp, wait); poll_wait(filp, &drm_file->event_wait, wait); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index a833751099b5..858aff99a3fe 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1550,10 +1550,6 @@ void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, pgoff_t start, pgoff_t end); vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf); vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, - enum page_entry_size pe_size); -#endif /* Transparent hugepage support - vmwgfx_thp.c */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index e5a9a5cbd01a..922317d1acc8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -477,7 +477,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) else prot = vm_get_page_prot(vma->vm_flags); - ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault, 1); + ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault); if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) return ret; @@ -486,73 +486,3 @@ out_unlock: return ret; } - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, - enum page_entry_size pe_size) -{ - struct vm_area_struct *vma = vmf->vma; - struct ttm_buffer_object *bo = (struct ttm_buffer_object *) - vma->vm_private_data; - struct vmw_buffer_object *vbo = - container_of(bo, struct vmw_buffer_object, base); - pgprot_t prot; - vm_fault_t ret; - pgoff_t fault_page_size; - bool write = vmf->flags & FAULT_FLAG_WRITE; - - switch (pe_size) { - case PE_SIZE_PMD: - fault_page_size = HPAGE_PMD_SIZE >> PAGE_SHIFT; - break; -#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD - case PE_SIZE_PUD: - fault_page_size = HPAGE_PUD_SIZE >> PAGE_SHIFT; - break; -#endif - default: - WARN_ON_ONCE(1); - return VM_FAULT_FALLBACK; - } - - /* Always do write dirty-tracking and COW on PTE level. */ - if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping(vma->vm_flags))) - return VM_FAULT_FALLBACK; - - ret = ttm_bo_vm_reserve(bo, vmf); - if (ret) - return ret; - - if (vbo->dirty) { - pgoff_t allowed_prefault; - unsigned long page_offset; - - page_offset = vmf->pgoff - - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->resource->num_pages || - vmw_resources_clean(vbo, page_offset, - page_offset + PAGE_SIZE, - &allowed_prefault)) { - ret = VM_FAULT_SIGBUS; - goto out_unlock; - } - - /* - * Write protect, so we get a new fault on write, and can - * split. - */ - prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED); - } else { - prot = vm_get_page_prot(vma->vm_flags); - } - - ret = ttm_bo_vm_fault_reserved(vmf, prot, 1, fault_page_size); - if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) - return ret; - -out_unlock: - dma_resv_unlock(bo->base.resv); - - return ret; -} -#endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index e6b1f98ec99f..0a4c340252ec 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -61,9 +61,6 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma) .fault = vmw_bo_vm_fault, .open = ttm_bo_vm_open, .close = ttm_bo_vm_close, -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - .huge_fault = vmw_bo_vm_huge_fault, -#endif }; struct drm_file *file_priv = filp->private_data; struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev); diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 80631f93ad2f..92c1cc07ed46 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -522,6 +522,16 @@ struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, } EXPORT_SYMBOL_GPL(i2c_acpi_new_device); +bool i2c_acpi_waive_d0_probe(struct device *dev) +{ + struct i2c_driver *driver = to_i2c_driver(dev->driver); + struct acpi_device *adev = ACPI_COMPANION(dev); + + return driver->flags & I2C_DRV_ACPI_WAIVE_D0_PROBE && + adev && adev->power.state_for_enumeration >= adev->power.state; +} +EXPORT_SYMBOL_GPL(i2c_acpi_waive_d0_probe); + #ifdef CONFIG_ACPI_I2C_OPREGION static int acpi_gsb_i2c_read_bytes(struct i2c_client *client, u8 cmd, u8 *data, u8 data_len) diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 54964fbe3f03..f193f9058584 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -551,7 +551,8 @@ static int i2c_device_probe(struct device *dev) if (status < 0) goto err_clear_wakeup_irq; - status = dev_pm_domain_attach(&client->dev, true); + status = dev_pm_domain_attach(&client->dev, + !i2c_acpi_waive_d0_probe(dev)); if (status) goto err_clear_wakeup_irq; @@ -590,7 +591,7 @@ static int i2c_device_probe(struct device *dev) err_release_driver_resources: devres_release_group(&client->dev, client->devres_group_id); err_detach_pm_domain: - dev_pm_domain_detach(&client->dev, true); + dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev)); err_clear_wakeup_irq: dev_pm_clear_wake_irq(&client->dev); device_init_wakeup(&client->dev, false); @@ -621,7 +622,7 @@ static void i2c_device_remove(struct device *dev) devres_release_group(&client->dev, client->devres_group_id); - dev_pm_domain_detach(&client->dev, true); + dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev)); if (!pm_runtime_status_suspended(&client->dev) && adap->bus_regulator) regulator_disable(adap->bus_regulator); diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index 28bde13003b7..b2725c6adc7f 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -831,8 +831,7 @@ EXPORT_SYMBOL_GPL(cros_ec_sensors_core_write); static int __maybe_unused cros_ec_sensors_resume(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct iio_dev *indio_dev = platform_get_drvdata(pdev); + struct iio_dev *indio_dev = dev_get_drvdata(dev); struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); int ret = 0; diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c index 882c3c8ba399..3088c5b829f0 100644 --- a/drivers/input/joystick/analog.c +++ b/drivers/input/joystick/analog.c @@ -19,6 +19,7 @@ #include <linux/input.h> #include <linux/gameport.h> #include <linux/jiffies.h> +#include <linux/seq_buf.h> #include <linux/timex.h> #include <linux/timekeeping.h> @@ -338,23 +339,24 @@ static void analog_calibrate_timer(struct analog_port *port) static void analog_name(struct analog *analog) { - snprintf(analog->name, sizeof(analog->name), "Analog %d-axis %d-button", + struct seq_buf s; + + seq_buf_init(&s, analog->name, sizeof(analog->name)); + seq_buf_printf(&s, "Analog %d-axis %d-button", hweight8(analog->mask & ANALOG_AXES_STD), hweight8(analog->mask & ANALOG_BTNS_STD) + !!(analog->mask & ANALOG_BTNS_CHF) * 2 + hweight16(analog->mask & ANALOG_BTNS_GAMEPAD) + !!(analog->mask & ANALOG_HBTN_CHF) * 4); if (analog->mask & ANALOG_HATS_ALL) - snprintf(analog->name, sizeof(analog->name), "%s %d-hat", - analog->name, hweight16(analog->mask & ANALOG_HATS_ALL)); + seq_buf_printf(&s, " %d-hat", + hweight16(analog->mask & ANALOG_HATS_ALL)); if (analog->mask & ANALOG_HAT_FCS) - strlcat(analog->name, " FCS", sizeof(analog->name)); + seq_buf_printf(&s, " FCS"); if (analog->mask & ANALOG_ANY_CHF) - strlcat(analog->name, (analog->mask & ANALOG_SAITEK) ? " Saitek" : " CHF", - sizeof(analog->name)); + seq_buf_printf(&s, (analog->mask & ANALOG_SAITEK) ? " Saitek" : " CHF"); - strlcat(analog->name, (analog->mask & ANALOG_GAMEPAD) ? " gamepad": " joystick", - sizeof(analog->name)); + seq_buf_printf(&s, (analog->mask & ANALOG_GAMEPAD) ? " gamepad" : " joystick"); } /* diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c index 6c554c11a7ac..ea58805c480f 100644 --- a/drivers/input/joystick/iforce/iforce-usb.c +++ b/drivers/input/joystick/iforce/iforce-usb.c @@ -92,7 +92,7 @@ static int iforce_usb_get_id(struct iforce *iforce, u8 id, id, USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_INTERFACE, - 0, 0, buf, IFORCE_MAX_LENGTH, HZ); + 0, 0, buf, IFORCE_MAX_LENGTH, 1000); if (status < 0) { dev_err(&iforce_usb->intf->dev, "usb_submit_urb failed: %d\n", status); diff --git a/drivers/input/joystick/tmdc.c b/drivers/input/joystick/tmdc.c index f89e9aa6d328..7416de84b955 100644 --- a/drivers/input/joystick/tmdc.c +++ b/drivers/input/joystick/tmdc.c @@ -83,7 +83,7 @@ static const struct tmdc_model { const signed char *axes; const short *buttons; } tmdc_models[] = { - { 1, "ThrustMaster Millenium 3D Inceptor", 6, 2, { 4, 2 }, { 4, 6 }, tmdc_abs, tmdc_btn_joy }, + { 1, "ThrustMaster Millennium 3D Inceptor", 6, 2, { 4, 2 }, { 4, 6 }, tmdc_abs, tmdc_btn_joy }, { 3, "ThrustMaster Rage 3D Gamepad", 2, 0, { 8, 2 }, { 0, 0 }, tmdc_abs, tmdc_btn_pad }, { 4, "ThrustMaster Attack Throttle", 5, 2, { 4, 6 }, { 4, 2 }, tmdc_abs_at, tmdc_btn_at }, { 8, "ThrustMaster FragMaster", 4, 0, { 8, 2 }, { 0, 0 }, tmdc_abs_fm, tmdc_btn_fm }, diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index e75650e98c9e..0c607da9ee10 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -788,4 +788,14 @@ config KEYBOARD_MTK_PMIC To compile this driver as a module, choose M here: the module will be called pmic-keys. +config KEYBOARD_CYPRESS_SF + tristate "Cypress StreetFighter touchkey support" + depends on I2C + help + Say Y here if you want to enable support for Cypress StreetFighter + touchkeys. + + To compile this driver as a module, choose M here: the + module will be called cypress-sf. + endif diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index 1d689fdd5c00..e3c8648f834e 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_KEYBOARD_BCM) += bcm-keypad.o obj-$(CONFIG_KEYBOARD_CAP11XX) += cap11xx.o obj-$(CONFIG_KEYBOARD_CLPS711X) += clps711x-keypad.o obj-$(CONFIG_KEYBOARD_CROS_EC) += cros_ec_keyb.o +obj-$(CONFIG_KEYBOARD_CYPRESS_SF) += cypress-sf.o obj-$(CONFIG_KEYBOARD_DAVINCI) += davinci_keyscan.o obj-$(CONFIG_KEYBOARD_DLINK_DIR685) += dlink-dir685-touchkeys.o obj-$(CONFIG_KEYBOARD_EP93XX) += ep93xx_keypad.o diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c index 688e2bef682e..7c85343cd32f 100644 --- a/drivers/input/keyboard/cap11xx.c +++ b/drivers/input/keyboard/cap11xx.c @@ -91,18 +91,21 @@ struct cap11xx_hw_model { u8 product_id; unsigned int num_channels; unsigned int num_leds; + bool no_gain; }; enum { CAP1106, CAP1126, CAP1188, + CAP1206, }; static const struct cap11xx_hw_model cap11xx_devices[] = { - [CAP1106] = { .product_id = 0x55, .num_channels = 6, .num_leds = 0 }, - [CAP1126] = { .product_id = 0x53, .num_channels = 6, .num_leds = 2 }, - [CAP1188] = { .product_id = 0x50, .num_channels = 8, .num_leds = 8 }, + [CAP1106] = { .product_id = 0x55, .num_channels = 6, .num_leds = 0, .no_gain = false }, + [CAP1126] = { .product_id = 0x53, .num_channels = 6, .num_leds = 2, .no_gain = false }, + [CAP1188] = { .product_id = 0x50, .num_channels = 8, .num_leds = 8, .no_gain = false }, + [CAP1206] = { .product_id = 0x67, .num_channels = 6, .num_leds = 0, .no_gain = true }, }; static const struct reg_default cap11xx_reg_defaults[] = { @@ -378,17 +381,24 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client, node = dev->of_node; if (!of_property_read_u32(node, "microchip,sensor-gain", &gain32)) { - if (is_power_of_2(gain32) && gain32 <= 8) + if (cap->no_gain) + dev_warn(dev, + "This version doesn't support sensor gain\n"); + else if (is_power_of_2(gain32) && gain32 <= 8) gain = ilog2(gain32); else dev_err(dev, "Invalid sensor-gain value %d\n", gain32); } - if (of_property_read_bool(node, "microchip,irq-active-high")) { - error = regmap_update_bits(priv->regmap, CAP11XX_REG_CONFIG2, - CAP11XX_REG_CONFIG2_ALT_POL, 0); - if (error) - return error; + if (id->driver_data != CAP1206) { + if (of_property_read_bool(node, "microchip,irq-active-high")) { + error = regmap_update_bits(priv->regmap, + CAP11XX_REG_CONFIG2, + CAP11XX_REG_CONFIG2_ALT_POL, + 0); + if (error) + return error; + } } /* Provide some useful defaults */ @@ -398,11 +408,14 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client, of_property_read_u32_array(node, "linux,keycodes", priv->keycodes, cap->num_channels); - error = regmap_update_bits(priv->regmap, CAP11XX_REG_MAIN_CONTROL, - CAP11XX_REG_MAIN_CONTROL_GAIN_MASK, - gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT); - if (error) - return error; + if (!cap->no_gain) { + error = regmap_update_bits(priv->regmap, + CAP11XX_REG_MAIN_CONTROL, + CAP11XX_REG_MAIN_CONTROL_GAIN_MASK, + gain << CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT); + if (error) + return error; + } /* Disable autorepeat. The Linux input system has its own handling. */ error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0); @@ -470,6 +483,7 @@ static const struct of_device_id cap11xx_dt_ids[] = { { .compatible = "microchip,cap1106", }, { .compatible = "microchip,cap1126", }, { .compatible = "microchip,cap1188", }, + { .compatible = "microchip,cap1206", }, {} }; MODULE_DEVICE_TABLE(of, cap11xx_dt_ids); @@ -478,6 +492,7 @@ static const struct i2c_device_id cap11xx_i2c_ids[] = { { "cap1106", CAP1106 }, { "cap1126", CAP1126 }, { "cap1188", CAP1188 }, + { "cap1206", CAP1206 }, {} }; MODULE_DEVICE_TABLE(i2c, cap11xx_i2c_ids); diff --git a/drivers/input/keyboard/cypress-sf.c b/drivers/input/keyboard/cypress-sf.c new file mode 100644 index 000000000000..c28996028e80 --- /dev/null +++ b/drivers/input/keyboard/cypress-sf.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Cypress StreetFighter Touchkey Driver + * + * Copyright (c) 2021 Yassine Oudjana <y.oudjana@protonmail.com> + */ + +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/device.h> +#include <linux/i2c.h> +#include <linux/input.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/pm.h> +#include <linux/regulator/consumer.h> + +#define CYPRESS_SF_DEV_NAME "cypress-sf" + +#define CYPRESS_SF_REG_BUTTON_STATUS 0x4a + +struct cypress_sf_data { + struct i2c_client *client; + struct input_dev *input_dev; + struct regulator_bulk_data regulators[2]; + u32 *keycodes; + unsigned long keystates; + int num_keys; +}; + +static irqreturn_t cypress_sf_irq_handler(int irq, void *devid) +{ + struct cypress_sf_data *touchkey = devid; + unsigned long keystates, changed; + bool new_state; + int val, key; + + val = i2c_smbus_read_byte_data(touchkey->client, + CYPRESS_SF_REG_BUTTON_STATUS); + if (val < 0) { + dev_err(&touchkey->client->dev, + "Failed to read button status: %d", val); + return IRQ_NONE; + } + keystates = val; + + bitmap_xor(&changed, &keystates, &touchkey->keystates, + touchkey->num_keys); + + for_each_set_bit(key, &changed, touchkey->num_keys) { + new_state = keystates & BIT(key); + dev_dbg(&touchkey->client->dev, + "Key %d changed to %d", key, new_state); + input_report_key(touchkey->input_dev, + touchkey->keycodes[key], new_state); + } + + input_sync(touchkey->input_dev); + touchkey->keystates = keystates; + + return IRQ_HANDLED; +} + +static int cypress_sf_probe(struct i2c_client *client) +{ + struct cypress_sf_data *touchkey; + int key, error; + + touchkey = devm_kzalloc(&client->dev, sizeof(*touchkey), GFP_KERNEL); + if (!touchkey) + return -ENOMEM; + + touchkey->client = client; + i2c_set_clientdata(client, touchkey); + + touchkey->regulators[0].supply = "vdd"; + touchkey->regulators[1].supply = "avdd"; + + error = devm_regulator_bulk_get(&client->dev, + ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); + if (error) { + dev_err(&client->dev, "Failed to get regulators: %d\n", error); + return error; + } + + touchkey->num_keys = device_property_read_u32_array(&client->dev, + "linux,keycodes", + NULL, 0); + if (touchkey->num_keys < 0) { + /* Default key count */ + touchkey->num_keys = 2; + } + + touchkey->keycodes = devm_kcalloc(&client->dev, + touchkey->num_keys, + sizeof(*touchkey->keycodes), + GFP_KERNEL); + if (!touchkey->keycodes) + return -ENOMEM; + + error = device_property_read_u32_array(&client->dev, "linux,keycodes", + touchkey->keycodes, + touchkey->num_keys); + + if (error) { + dev_warn(&client->dev, + "Failed to read keycodes: %d, using defaults\n", + error); + + /* Default keycodes */ + touchkey->keycodes[0] = KEY_BACK; + touchkey->keycodes[1] = KEY_MENU; + } + + error = regulator_bulk_enable(ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); + if (error) { + dev_err(&client->dev, + "Failed to enable regulators: %d\n", error); + return error; + } + + touchkey->input_dev = devm_input_allocate_device(&client->dev); + if (!touchkey->input_dev) { + dev_err(&client->dev, "Failed to allocate input device\n"); + return -ENOMEM; + } + + touchkey->input_dev->name = CYPRESS_SF_DEV_NAME; + touchkey->input_dev->id.bustype = BUS_I2C; + + for (key = 0; key < touchkey->num_keys; ++key) + input_set_capability(touchkey->input_dev, + EV_KEY, touchkey->keycodes[key]); + + error = input_register_device(touchkey->input_dev); + if (error) { + dev_err(&client->dev, + "Failed to register input device: %d\n", error); + return error; + } + + error = devm_request_threaded_irq(&client->dev, client->irq, + NULL, cypress_sf_irq_handler, + IRQF_ONESHOT, + CYPRESS_SF_DEV_NAME, touchkey); + if (error) { + dev_err(&client->dev, + "Failed to register threaded irq: %d", error); + return error; + } + + return 0; +}; + +static int __maybe_unused cypress_sf_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct cypress_sf_data *touchkey = i2c_get_clientdata(client); + int error; + + disable_irq(client->irq); + + error = regulator_bulk_disable(ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); + if (error) { + dev_err(dev, "Failed to disable regulators: %d", error); + enable_irq(client->irq); + return error; + } + + return 0; +} + +static int __maybe_unused cypress_sf_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct cypress_sf_data *touchkey = i2c_get_clientdata(client); + int error; + + error = regulator_bulk_enable(ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); + if (error) { + dev_err(dev, "Failed to enable regulators: %d", error); + return error; + } + + enable_irq(client->irq); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(cypress_sf_pm_ops, + cypress_sf_suspend, cypress_sf_resume); + +static struct i2c_device_id cypress_sf_id_table[] = { + { CYPRESS_SF_DEV_NAME, 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, cypress_sf_id_table); + +#ifdef CONFIG_OF +static const struct of_device_id cypress_sf_of_match[] = { + { .compatible = "cypress,sf3155", }, + { }, +}; +MODULE_DEVICE_TABLE(of, cypress_sf_of_match); +#endif + +static struct i2c_driver cypress_sf_driver = { + .driver = { + .name = CYPRESS_SF_DEV_NAME, + .pm = &cypress_sf_pm_ops, + .of_match_table = of_match_ptr(cypress_sf_of_match), + }, + .id_table = cypress_sf_id_table, + .probe_new = cypress_sf_probe, +}; +module_i2c_driver(cypress_sf_driver); + +MODULE_AUTHOR("Yassine Oudjana <y.oudjana@protonmail.com>"); +MODULE_DESCRIPTION("Cypress StreetFighter Touchkey Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/input/keyboard/ep93xx_keypad.c b/drivers/input/keyboard/ep93xx_keypad.c index e0e931e796fa..272a4f1c6e81 100644 --- a/drivers/input/keyboard/ep93xx_keypad.c +++ b/drivers/input/keyboard/ep93xx_keypad.c @@ -17,6 +17,7 @@ * flag. */ +#include <linux/bits.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/interrupt.h> @@ -26,6 +27,7 @@ #include <linux/slab.h> #include <linux/soc/cirrus/ep93xx.h> #include <linux/platform_data/keypad-ep93xx.h> +#include <linux/pm_wakeirq.h> /* * Keypad Interface Register offsets @@ -35,28 +37,28 @@ #define KEY_REG 0x08 /* Key Value Capture register */ /* Key Scan Initialization Register bit defines */ -#define KEY_INIT_DBNC_MASK (0x00ff0000) -#define KEY_INIT_DBNC_SHIFT (16) -#define KEY_INIT_DIS3KY (1<<15) -#define KEY_INIT_DIAG (1<<14) -#define KEY_INIT_BACK (1<<13) -#define KEY_INIT_T2 (1<<12) -#define KEY_INIT_PRSCL_MASK (0x000003ff) -#define KEY_INIT_PRSCL_SHIFT (0) +#define KEY_INIT_DBNC_MASK GENMASK(23, 16) +#define KEY_INIT_DBNC_SHIFT 16 +#define KEY_INIT_DIS3KY BIT(15) +#define KEY_INIT_DIAG BIT(14) +#define KEY_INIT_BACK BIT(13) +#define KEY_INIT_T2 BIT(12) +#define KEY_INIT_PRSCL_MASK GENMASK(9, 0) +#define KEY_INIT_PRSCL_SHIFT 0 /* Key Scan Diagnostic Register bit defines */ -#define KEY_DIAG_MASK (0x0000003f) -#define KEY_DIAG_SHIFT (0) +#define KEY_DIAG_MASK GENMASK(5, 0) +#define KEY_DIAG_SHIFT 0 /* Key Value Capture Register bit defines */ -#define KEY_REG_K (1<<15) -#define KEY_REG_INT (1<<14) -#define KEY_REG_2KEYS (1<<13) -#define KEY_REG_1KEY (1<<12) -#define KEY_REG_KEY2_MASK (0x00000fc0) -#define KEY_REG_KEY2_SHIFT (6) -#define KEY_REG_KEY1_MASK (0x0000003f) -#define KEY_REG_KEY1_SHIFT (0) +#define KEY_REG_K BIT(15) +#define KEY_REG_INT BIT(14) +#define KEY_REG_2KEYS BIT(13) +#define KEY_REG_1KEY BIT(12) +#define KEY_REG_KEY2_MASK GENMASK(11, 6) +#define KEY_REG_KEY2_SHIFT 6 +#define KEY_REG_KEY1_MASK GENMASK(5, 0) +#define KEY_REG_KEY1_SHIFT 0 #define EP93XX_MATRIX_SIZE (EP93XX_MATRIX_ROWS * EP93XX_MATRIX_COLS) @@ -175,8 +177,7 @@ static void ep93xx_keypad_close(struct input_dev *pdev) } -#ifdef CONFIG_PM_SLEEP -static int ep93xx_keypad_suspend(struct device *dev) +static int __maybe_unused ep93xx_keypad_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct ep93xx_keypad *keypad = platform_get_drvdata(pdev); @@ -191,21 +192,15 @@ static int ep93xx_keypad_suspend(struct device *dev) mutex_unlock(&input_dev->mutex); - if (device_may_wakeup(&pdev->dev)) - enable_irq_wake(keypad->irq); - return 0; } -static int ep93xx_keypad_resume(struct device *dev) +static int __maybe_unused ep93xx_keypad_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct ep93xx_keypad *keypad = platform_get_drvdata(pdev); struct input_dev *input_dev = keypad->input_dev; - if (device_may_wakeup(&pdev->dev)) - disable_irq_wake(keypad->irq); - mutex_lock(&input_dev->mutex); if (input_device_enabled(input_dev)) { @@ -220,11 +215,17 @@ static int ep93xx_keypad_resume(struct device *dev) return 0; } -#endif static SIMPLE_DEV_PM_OPS(ep93xx_keypad_pm_ops, ep93xx_keypad_suspend, ep93xx_keypad_resume); +static void ep93xx_keypad_release_gpio_action(void *_pdev) +{ + struct platform_device *pdev = _pdev; + + ep93xx_keypad_release_gpio(pdev); +} + static int ep93xx_keypad_probe(struct platform_device *pdev) { struct ep93xx_keypad *keypad; @@ -233,61 +234,46 @@ static int ep93xx_keypad_probe(struct platform_device *pdev) struct resource *res; int err; - keypad = kzalloc(sizeof(struct ep93xx_keypad), GFP_KERNEL); + keypad = devm_kzalloc(&pdev->dev, sizeof(*keypad), GFP_KERNEL); if (!keypad) return -ENOMEM; keypad->pdata = dev_get_platdata(&pdev->dev); - if (!keypad->pdata) { - err = -EINVAL; - goto failed_free; - } + if (!keypad->pdata) + return -EINVAL; keymap_data = keypad->pdata->keymap_data; - if (!keymap_data) { - err = -EINVAL; - goto failed_free; - } + if (!keymap_data) + return -EINVAL; keypad->irq = platform_get_irq(pdev, 0); - if (keypad->irq < 0) { - err = keypad->irq; - goto failed_free; - } + if (keypad->irq < 0) + return keypad->irq; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - err = -ENXIO; - goto failed_free; - } + if (!res) + return -ENXIO; - res = request_mem_region(res->start, resource_size(res), pdev->name); - if (!res) { - err = -EBUSY; - goto failed_free; - } - - keypad->mmio_base = ioremap(res->start, resource_size(res)); - if (keypad->mmio_base == NULL) { - err = -ENXIO; - goto failed_free_mem; - } + keypad->mmio_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(keypad->mmio_base)) + return PTR_ERR(keypad->mmio_base); err = ep93xx_keypad_acquire_gpio(pdev); if (err) - goto failed_free_io; + return err; - keypad->clk = clk_get(&pdev->dev, NULL); - if (IS_ERR(keypad->clk)) { - err = PTR_ERR(keypad->clk); - goto failed_free_gpio; - } + err = devm_add_action_or_reset(&pdev->dev, + ep93xx_keypad_release_gpio_action, pdev); + if (err) + return err; - input_dev = input_allocate_device(); - if (!input_dev) { - err = -ENOMEM; - goto failed_put_clk; - } + keypad->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(keypad->clk)) + return PTR_ERR(keypad->clk); + + input_dev = devm_input_allocate_device(&pdev->dev); + if (!input_dev) + return -ENOMEM; keypad->input_dev = input_dev; @@ -295,70 +281,40 @@ static int ep93xx_keypad_probe(struct platform_device *pdev) input_dev->id.bustype = BUS_HOST; input_dev->open = ep93xx_keypad_open; input_dev->close = ep93xx_keypad_close; - input_dev->dev.parent = &pdev->dev; err = matrix_keypad_build_keymap(keymap_data, NULL, EP93XX_MATRIX_ROWS, EP93XX_MATRIX_COLS, keypad->keycodes, input_dev); if (err) - goto failed_free_dev; + return err; if (keypad->pdata->flags & EP93XX_KEYPAD_AUTOREPEAT) __set_bit(EV_REP, input_dev->evbit); input_set_drvdata(input_dev, keypad); - err = request_irq(keypad->irq, ep93xx_keypad_irq_handler, - 0, pdev->name, keypad); + err = devm_request_irq(&pdev->dev, keypad->irq, + ep93xx_keypad_irq_handler, + 0, pdev->name, keypad); if (err) - goto failed_free_dev; + return err; err = input_register_device(input_dev); if (err) - goto failed_free_irq; + return err; platform_set_drvdata(pdev, keypad); + device_init_wakeup(&pdev->dev, 1); + err = dev_pm_set_wake_irq(&pdev->dev, keypad->irq); + if (err) + dev_warn(&pdev->dev, "failed to set up wakeup irq: %d\n", err); return 0; - -failed_free_irq: - free_irq(keypad->irq, keypad); -failed_free_dev: - input_free_device(input_dev); -failed_put_clk: - clk_put(keypad->clk); -failed_free_gpio: - ep93xx_keypad_release_gpio(pdev); -failed_free_io: - iounmap(keypad->mmio_base); -failed_free_mem: - release_mem_region(res->start, resource_size(res)); -failed_free: - kfree(keypad); - return err; } static int ep93xx_keypad_remove(struct platform_device *pdev) { - struct ep93xx_keypad *keypad = platform_get_drvdata(pdev); - struct resource *res; - - free_irq(keypad->irq, keypad); - - if (keypad->enabled) - clk_disable(keypad->clk); - clk_put(keypad->clk); - - input_unregister_device(keypad->input_dev); - - ep93xx_keypad_release_gpio(pdev); - - iounmap(keypad->mmio_base); - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - - kfree(keypad); + dev_pm_clear_wake_irq(&pdev->dev); return 0; } diff --git a/drivers/input/keyboard/mpr121_touchkey.c b/drivers/input/keyboard/mpr121_touchkey.c index 40d6e5087cde..230ab3d50b9e 100644 --- a/drivers/input/keyboard/mpr121_touchkey.c +++ b/drivers/input/keyboard/mpr121_touchkey.c @@ -107,9 +107,9 @@ static struct regulator *mpr121_vdd_supply_init(struct device *dev) return ERR_PTR(err); } - err = devm_add_action(dev, mpr121_vdd_supply_disable, vdd_supply); + err = devm_add_action_or_reset(dev, mpr121_vdd_supply_disable, + vdd_supply); if (err) { - regulator_disable(vdd_supply); dev_err(dev, "failed to add disable regulator action: %d\n", err); return ERR_PTR(err); diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c index dbe836c7ff47..eb3a687796e7 100644 --- a/drivers/input/keyboard/omap-keypad.c +++ b/drivers/input/keyboard/omap-keypad.c @@ -190,8 +190,7 @@ static int omap_kp_probe(struct platform_device *pdev) row_shift = get_count_order(pdata->cols); keycodemax = pdata->rows << row_shift; - omap_kp = kzalloc(sizeof(struct omap_kp) + - keycodemax * sizeof(unsigned short), GFP_KERNEL); + omap_kp = kzalloc(struct_size(omap_kp, keymap, keycodemax), GFP_KERNEL); input_dev = input_allocate_device(); if (!omap_kp || !input_dev) { kfree(omap_kp); diff --git a/drivers/input/keyboard/tm2-touchkey.c b/drivers/input/keyboard/tm2-touchkey.c index 6218b1c682ef..632cd6c1c8d4 100644 --- a/drivers/input/keyboard/tm2-touchkey.c +++ b/drivers/input/keyboard/tm2-touchkey.c @@ -156,6 +156,8 @@ static irqreturn_t tm2_touchkey_irq_handler(int irq, void *devid) goto out; } + input_event(touchkey->input_dev, EV_MSC, MSC_SCAN, index); + if (data & TM2_TOUCHKEY_BIT_PRESS_EV) { for (i = 0; i < touchkey->num_keycodes; i++) input_report_key(touchkey->input_dev, @@ -250,6 +252,11 @@ static int tm2_touchkey_probe(struct i2c_client *client, touchkey->input_dev->name = TM2_TOUCHKEY_DEV_NAME; touchkey->input_dev->id.bustype = BUS_I2C; + touchkey->input_dev->keycode = touchkey->keycodes; + touchkey->input_dev->keycodemax = touchkey->num_keycodes; + touchkey->input_dev->keycodesize = sizeof(touchkey->keycodes[0]); + + input_set_capability(touchkey->input_dev, EV_MSC, MSC_SCAN); for (i = 0; i < touchkey->num_keycodes; i++) input_set_capability(touchkey->input_dev, EV_KEY, touchkey->keycodes[i]); diff --git a/drivers/input/misc/adxl34x-i2c.c b/drivers/input/misc/adxl34x-i2c.c index e64368a63346..a3b5f88d2bd1 100644 --- a/drivers/input/misc/adxl34x-i2c.c +++ b/drivers/input/misc/adxl34x-i2c.c @@ -103,7 +103,9 @@ static int adxl34x_i2c_remove(struct i2c_client *client) { struct adxl34x *ac = i2c_get_clientdata(client); - return adxl34x_remove(ac); + adxl34x_remove(ac); + + return 0; } static int __maybe_unused adxl34x_i2c_suspend(struct device *dev) diff --git a/drivers/input/misc/adxl34x-spi.c b/drivers/input/misc/adxl34x-spi.c index df6afa455e46..6e51c9bc619f 100644 --- a/drivers/input/misc/adxl34x-spi.c +++ b/drivers/input/misc/adxl34x-spi.c @@ -91,7 +91,9 @@ static int adxl34x_spi_remove(struct spi_device *spi) { struct adxl34x *ac = spi_get_drvdata(spi); - return adxl34x_remove(ac); + adxl34x_remove(ac); + + return 0; } static int __maybe_unused adxl34x_spi_suspend(struct device *dev) diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c index 4cc4e8ff42b3..a4af314392a9 100644 --- a/drivers/input/misc/adxl34x.c +++ b/drivers/input/misc/adxl34x.c @@ -237,7 +237,7 @@ static const struct adxl34x_platform_data adxl34x_default_init = { static void adxl34x_get_triple(struct adxl34x *ac, struct axis_triple *axis) { - short buf[3]; + __le16 buf[3]; ac->bops->read_block(ac->dev, DATAX0, DATAZ1 - DATAX0 + 1, buf); @@ -896,15 +896,13 @@ struct adxl34x *adxl34x_probe(struct device *dev, int irq, } EXPORT_SYMBOL_GPL(adxl34x_probe); -int adxl34x_remove(struct adxl34x *ac) +void adxl34x_remove(struct adxl34x *ac) { sysfs_remove_group(&ac->dev->kobj, &adxl34x_attr_group); free_irq(ac->irq, ac); input_unregister_device(ac->input); dev_dbg(ac->dev, "unregistered accelerometer\n"); kfree(ac); - - return 0; } EXPORT_SYMBOL_GPL(adxl34x_remove); diff --git a/drivers/input/misc/adxl34x.h b/drivers/input/misc/adxl34x.h index 83a0eeccf613..febf85270fff 100644 --- a/drivers/input/misc/adxl34x.h +++ b/drivers/input/misc/adxl34x.h @@ -25,6 +25,6 @@ void adxl34x_resume(struct adxl34x *ac); struct adxl34x *adxl34x_probe(struct device *dev, int irq, bool fifo_delay_default, const struct adxl34x_bus_ops *bops); -int adxl34x_remove(struct adxl34x *ac); +void adxl34x_remove(struct adxl34x *ac); #endif diff --git a/drivers/input/misc/ariel-pwrbutton.c b/drivers/input/misc/ariel-pwrbutton.c index 17bbaac8b80c..cdc80715b5fd 100644 --- a/drivers/input/misc/ariel-pwrbutton.c +++ b/drivers/input/misc/ariel-pwrbutton.c @@ -149,12 +149,19 @@ static const struct of_device_id ariel_pwrbutton_of_match[] = { }; MODULE_DEVICE_TABLE(of, ariel_pwrbutton_of_match); +static const struct spi_device_id ariel_pwrbutton_spi_ids[] = { + { .name = "wyse-ariel-ec-input" }, + { } +}; +MODULE_DEVICE_TABLE(spi, ariel_pwrbutton_spi_ids); + static struct spi_driver ariel_pwrbutton_driver = { .driver = { .name = "dell-wyse-ariel-ec-input", .of_match_table = ariel_pwrbutton_of_match, }, .probe = ariel_pwrbutton_probe, + .id_table = ariel_pwrbutton_spi_ids, }; module_spi_driver(ariel_pwrbutton_driver); diff --git a/drivers/input/misc/cpcap-pwrbutton.c b/drivers/input/misc/cpcap-pwrbutton.c index 0abef63217e2..879790bbf9fe 100644 --- a/drivers/input/misc/cpcap-pwrbutton.c +++ b/drivers/input/misc/cpcap-pwrbutton.c @@ -54,9 +54,13 @@ static irqreturn_t powerbutton_irq(int irq, void *_button) static int cpcap_power_button_probe(struct platform_device *pdev) { struct cpcap_power_button *button; - int irq = platform_get_irq(pdev, 0); + int irq; int err; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + button = devm_kmalloc(&pdev->dev, sizeof(*button), GFP_KERNEL); if (!button) return -ENOMEM; @@ -73,7 +77,6 @@ static int cpcap_power_button_probe(struct platform_device *pdev) button->idev->name = "cpcap-pwrbutton"; button->idev->phys = "cpcap-pwrbutton/input0"; - button->idev->dev.parent = button->dev; input_set_capability(button->idev, EV_KEY, KEY_POWER); err = devm_request_threaded_irq(&pdev->dev, irq, NULL, diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c index 0d09ffeafeea..4369d3c04d38 100644 --- a/drivers/input/misc/max77693-haptic.c +++ b/drivers/input/misc/max77693-haptic.c @@ -424,5 +424,4 @@ module_platform_driver(max77693_haptic_driver); MODULE_AUTHOR("Jaewon Kim <jaewon02.kim@samsung.com>"); MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>"); MODULE_DESCRIPTION("MAXIM 77693/77843 Haptic driver"); -MODULE_ALIAS("platform:max77693-haptic"); MODULE_LICENSE("GPL"); diff --git a/drivers/input/misc/max8925_onkey.c b/drivers/input/misc/max8925_onkey.c index ffab4a490c75..4770cb55631a 100644 --- a/drivers/input/misc/max8925_onkey.c +++ b/drivers/input/misc/max8925_onkey.c @@ -1,4 +1,4 @@ -/** +/* * MAX8925 ONKEY driver * * Copyright (C) 2009 Marvell International Ltd. diff --git a/drivers/input/misc/palmas-pwrbutton.c b/drivers/input/misc/palmas-pwrbutton.c index 1e1baed63929..f9b05cf09ff5 100644 --- a/drivers/input/misc/palmas-pwrbutton.c +++ b/drivers/input/misc/palmas-pwrbutton.c @@ -210,6 +210,11 @@ static int palmas_pwron_probe(struct platform_device *pdev) INIT_DELAYED_WORK(&pwron->input_work, palmas_power_button_work); pwron->irq = platform_get_irq(pdev, 0); + if (pwron->irq < 0) { + error = pwron->irq; + goto err_free_input; + } + error = request_threaded_irq(pwron->irq, NULL, pwron_irq, IRQF_TRIGGER_HIGH | IRQF_TRIGGER_LOW | diff --git a/drivers/input/misc/pm8941-pwrkey.c b/drivers/input/misc/pm8941-pwrkey.c index 33609603245d..89af52498c96 100644 --- a/drivers/input/misc/pm8941-pwrkey.c +++ b/drivers/input/misc/pm8941-pwrkey.c @@ -29,6 +29,7 @@ #define PON_PS_HOLD_RST_CTL2 0x5b #define PON_PS_HOLD_ENABLE BIT(7) #define PON_PS_HOLD_TYPE_MASK 0x0f +#define PON_PS_HOLD_TYPE_WARM_RESET 1 #define PON_PS_HOLD_TYPE_SHUTDOWN 4 #define PON_PS_HOLD_TYPE_HARD_RESET 7 @@ -99,7 +100,10 @@ static int pm8941_reboot_notify(struct notifier_block *nb, break; case SYS_RESTART: default: - reset_type = PON_PS_HOLD_TYPE_HARD_RESET; + if (reboot_mode == REBOOT_WARM) + reset_type = PON_PS_HOLD_TYPE_WARM_RESET; + else + reset_type = PON_PS_HOLD_TYPE_HARD_RESET; break; } diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 2d0bc029619f..956d9cd34796 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -517,6 +517,19 @@ static void elantech_report_trackpoint(struct psmouse *psmouse, case 0x16008020U: case 0x26800010U: case 0x36808000U: + + /* + * This firmware misreport coordinates for trackpoint + * occasionally. Discard packets outside of [-127, 127] range + * to prevent cursor jumps. + */ + if (packet[4] == 0x80 || packet[5] == 0x80 || + packet[1] >> 7 == packet[4] >> 7 || + packet[2] >> 7 == packet[5] >> 7) { + elantech_debug("discarding packet [%6ph]\n", packet); + break; + + } x = packet[4] - (int)((packet[1]^0x80) << 1); y = (int)((packet[2]^0x80) << 1) - packet[5]; diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c index 24f31a5c0e04..50a0134b6901 100644 --- a/drivers/input/rmi4/rmi_bus.c +++ b/drivers/input/rmi4/rmi_bus.c @@ -90,6 +90,7 @@ int rmi_register_transport_device(struct rmi_transport_dev *xport) rmi_dev->dev.bus = &rmi_bus_type; rmi_dev->dev.type = &rmi_device_type; + rmi_dev->dev.parent = xport->dev; xport->rmi_dev = rmi_dev; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index a5a003553646..aedd05541044 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -273,6 +273,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, }, { + /* Fujitsu Lifebook T725 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), + }, + }, + { /* Fujitsu Lifebook U745 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), @@ -841,6 +848,13 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { }, }, { + /* Fujitsu Lifebook T725 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), + }, + }, + { /* Fujitsu U574 laptop */ /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ .matches = { diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index d4e74738c5a8..2f6adfb7b938 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -425,6 +425,7 @@ config TOUCHSCREEN_HYCON_HY46XX config TOUCHSCREEN_ILI210X tristate "Ilitek ILI210X based touchscreen" depends on I2C + select CRC_CCITT help Say Y here if you have a ILI210X based touchscreen controller. This driver supports models ILI2102, diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 7d34100f7f22..39a8127cf6a5 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -6,6 +6,7 @@ # Each configuration option enables a list of files. wm97xx-ts-y := wm97xx-core.o +goodix_ts-y := goodix.o goodix_fwupload.o obj-$(CONFIG_TOUCHSCREEN_88PM860X) += 88pm860x-ts.o obj-$(CONFIG_TOUCHSCREEN_AD7877) += ad7877.o @@ -44,7 +45,7 @@ obj-$(CONFIG_TOUCHSCREEN_EGALAX) += egalax_ts.o obj-$(CONFIG_TOUCHSCREEN_EGALAX_SERIAL) += egalax_ts_serial.o obj-$(CONFIG_TOUCHSCREEN_EXC3000) += exc3000.o obj-$(CONFIG_TOUCHSCREEN_FUJITSU) += fujitsu_ts.o -obj-$(CONFIG_TOUCHSCREEN_GOODIX) += goodix.o +obj-$(CONFIG_TOUCHSCREEN_GOODIX) += goodix_ts.o obj-$(CONFIG_TOUCHSCREEN_HIDEEP) += hideep.o obj-$(CONFIG_TOUCHSCREEN_ILI210X) += ili210x.o obj-$(CONFIG_TOUCHSCREEN_ILITEK) += ilitek_ts_i2c.o diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index f113a27aeb1e..a25a77dd9a32 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -101,10 +101,6 @@ struct ads7846 { struct spi_device *spi; struct regulator *reg; -#if IS_ENABLED(CONFIG_HWMON) - struct device *hwmon; -#endif - u16 model; u16 vref_mv; u16 vref_delay_usecs; @@ -142,13 +138,18 @@ struct ads7846 { int (*filter)(void *data, int data_idx, int *val); void *filter_data; - void (*filter_cleanup)(void *data); int (*get_pendown_state)(void); int gpio_pendown; void (*wait_for_sync)(void); }; +enum ads7846_filter { + ADS7846_FILTER_OK, + ADS7846_FILTER_REPEAT, + ADS7846_FILTER_IGNORE, +}; + /* leave chip selected when we're done, for quicker re-select? */ #if 0 #define CS_CHANGE(xfer) ((xfer).cs_change = 1) @@ -549,6 +550,8 @@ __ATTRIBUTE_GROUPS(ads7846_attr); static int ads784x_hwmon_register(struct spi_device *spi, struct ads7846 *ts) { + struct device *hwmon; + /* hwmon sensors need a reference voltage */ switch (ts->model) { case 7846: @@ -569,17 +572,11 @@ static int ads784x_hwmon_register(struct spi_device *spi, struct ads7846 *ts) break; } - ts->hwmon = hwmon_device_register_with_groups(&spi->dev, spi->modalias, - ts, ads7846_attr_groups); + hwmon = devm_hwmon_device_register_with_groups(&spi->dev, + spi->modalias, ts, + ads7846_attr_groups); - return PTR_ERR_OR_ZERO(ts->hwmon); -} - -static void ads784x_hwmon_unregister(struct spi_device *spi, - struct ads7846 *ts) -{ - if (ts->hwmon) - hwmon_device_unregister(ts->hwmon); + return PTR_ERR_OR_ZERO(hwmon); } #else @@ -588,11 +585,6 @@ static inline int ads784x_hwmon_register(struct spi_device *spi, { return 0; } - -static inline void ads784x_hwmon_unregister(struct spi_device *spi, - struct ads7846 *ts) -{ -} #endif static ssize_t ads7846_pen_down_show(struct device *dev, @@ -1014,8 +1006,8 @@ static int ads7846_setup_pendown(struct spi_device *spi, ts->get_pendown_state = pdata->get_pendown_state; } else if (gpio_is_valid(pdata->gpio_pendown)) { - err = gpio_request_one(pdata->gpio_pendown, GPIOF_IN, - "ads7846_pendown"); + err = devm_gpio_request_one(&spi->dev, pdata->gpio_pendown, + GPIOF_IN, "ads7846_pendown"); if (err) { dev_err(&spi->dev, "failed to request/setup pendown GPIO%d: %d\n", @@ -1212,24 +1204,30 @@ static const struct ads7846_platform_data *ads7846_probe_dt(struct device *dev) } #endif +static void ads7846_regulator_disable(void *regulator) +{ + regulator_disable(regulator); +} + static int ads7846_probe(struct spi_device *spi) { const struct ads7846_platform_data *pdata; struct ads7846 *ts; + struct device *dev = &spi->dev; struct ads7846_packet *packet; struct input_dev *input_dev; unsigned long irq_flags; int err; if (!spi->irq) { - dev_dbg(&spi->dev, "no IRQ?\n"); + dev_dbg(dev, "no IRQ?\n"); return -EINVAL; } /* don't exceed max specified sample rate */ if (spi->max_speed_hz > (125000 * SAMPLE_BITS)) { - dev_err(&spi->dev, "f(sample) %d KHz?\n", - (spi->max_speed_hz/SAMPLE_BITS)/1000); + dev_err(dev, "f(sample) %d KHz?\n", + (spi->max_speed_hz/SAMPLE_BITS)/1000); return -EINVAL; } @@ -1245,13 +1243,17 @@ static int ads7846_probe(struct spi_device *spi) if (err < 0) return err; - ts = kzalloc(sizeof(struct ads7846), GFP_KERNEL); - packet = kzalloc(sizeof(struct ads7846_packet), GFP_KERNEL); - input_dev = input_allocate_device(); - if (!ts || !packet || !input_dev) { - err = -ENOMEM; - goto err_free_mem; - } + ts = devm_kzalloc(dev, sizeof(struct ads7846), GFP_KERNEL); + if (!ts) + return -ENOMEM; + + packet = devm_kzalloc(dev, sizeof(struct ads7846_packet), GFP_KERNEL); + if (!packet) + return -ENOMEM; + + input_dev = devm_input_allocate_device(dev); + if (!input_dev) + return -ENOMEM; spi_set_drvdata(spi, ts); @@ -1262,13 +1264,11 @@ static int ads7846_probe(struct spi_device *spi) mutex_init(&ts->lock); init_waitqueue_head(&ts->wait); - pdata = dev_get_platdata(&spi->dev); + pdata = dev_get_platdata(dev); if (!pdata) { - pdata = ads7846_probe_dt(&spi->dev); - if (IS_ERR(pdata)) { - err = PTR_ERR(pdata); - goto err_free_mem; - } + pdata = ads7846_probe_dt(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); } ts->model = pdata->model ? : 7846; @@ -1276,15 +1276,7 @@ static int ads7846_probe(struct spi_device *spi) ts->x_plate_ohms = pdata->x_plate_ohms ? : 400; ts->vref_mv = pdata->vref_mv; - if (pdata->filter != NULL) { - if (pdata->filter_init != NULL) { - err = pdata->filter_init(pdata, &ts->filter_data); - if (err < 0) - goto err_free_mem; - } - ts->filter = pdata->filter; - ts->filter_cleanup = pdata->filter_cleanup; - } else if (pdata->debounce_max) { + if (pdata->debounce_max) { ts->debounce_max = pdata->debounce_max; if (ts->debounce_max < 2) ts->debounce_max = 2; @@ -1298,7 +1290,7 @@ static int ads7846_probe(struct spi_device *spi) err = ads7846_setup_pendown(spi, ts, pdata); if (err) - goto err_cleanup_filter; + return err; if (pdata->penirq_recheck_delay_usecs) ts->penirq_recheck_delay_usecs = @@ -1306,15 +1298,16 @@ static int ads7846_probe(struct spi_device *spi) ts->wait_for_sync = pdata->wait_for_sync ? : null_wait_for_sync; - snprintf(ts->phys, sizeof(ts->phys), "%s/input0", dev_name(&spi->dev)); + snprintf(ts->phys, sizeof(ts->phys), "%s/input0", dev_name(dev)); snprintf(ts->name, sizeof(ts->name), "ADS%d Touchscreen", ts->model); input_dev->name = ts->name; input_dev->phys = ts->phys; - input_dev->dev.parent = &spi->dev; - input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); - input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); + input_dev->id.bustype = BUS_SPI; + input_dev->id.product = pdata->model; + + input_set_capability(input_dev, EV_KEY, BTN_TOUCH); input_set_abs_params(input_dev, ABS_X, pdata->x_min ? : 0, pdata->x_max ? : MAX_12BIT, @@ -1345,125 +1338,84 @@ static int ads7846_probe(struct spi_device *spi) ads7846_setup_spi_msg(ts, pdata); - ts->reg = regulator_get(&spi->dev, "vcc"); + ts->reg = devm_regulator_get(dev, "vcc"); if (IS_ERR(ts->reg)) { err = PTR_ERR(ts->reg); - dev_err(&spi->dev, "unable to get regulator: %d\n", err); - goto err_free_gpio; + dev_err(dev, "unable to get regulator: %d\n", err); + return err; } err = regulator_enable(ts->reg); if (err) { - dev_err(&spi->dev, "unable to enable regulator: %d\n", err); - goto err_put_regulator; + dev_err(dev, "unable to enable regulator: %d\n", err); + return err; } + err = devm_add_action_or_reset(dev, ads7846_regulator_disable, ts->reg); + if (err) + return err; + irq_flags = pdata->irq_flags ? : IRQF_TRIGGER_FALLING; irq_flags |= IRQF_ONESHOT; - err = request_threaded_irq(spi->irq, ads7846_hard_irq, ads7846_irq, - irq_flags, spi->dev.driver->name, ts); - if (err && !pdata->irq_flags) { - dev_info(&spi->dev, + err = devm_request_threaded_irq(dev, spi->irq, + ads7846_hard_irq, ads7846_irq, + irq_flags, dev->driver->name, ts); + if (err && err != -EPROBE_DEFER && !pdata->irq_flags) { + dev_info(dev, "trying pin change workaround on irq %d\n", spi->irq); irq_flags |= IRQF_TRIGGER_RISING; - err = request_threaded_irq(spi->irq, - ads7846_hard_irq, ads7846_irq, - irq_flags, spi->dev.driver->name, ts); + err = devm_request_threaded_irq(dev, spi->irq, + ads7846_hard_irq, ads7846_irq, + irq_flags, dev->driver->name, + ts); } if (err) { - dev_dbg(&spi->dev, "irq %d busy?\n", spi->irq); - goto err_disable_regulator; + dev_dbg(dev, "irq %d busy?\n", spi->irq); + return err; } err = ads784x_hwmon_register(spi, ts); if (err) - goto err_free_irq; + return err; - dev_info(&spi->dev, "touchscreen, irq %d\n", spi->irq); + dev_info(dev, "touchscreen, irq %d\n", spi->irq); /* * Take a first sample, leaving nPENIRQ active and vREF off; avoid * the touchscreen, in case it's not connected. */ if (ts->model == 7845) - ads7845_read12_ser(&spi->dev, PWRDOWN); + ads7845_read12_ser(dev, PWRDOWN); else - (void) ads7846_read12_ser(&spi->dev, READ_12BIT_SER(vaux)); + (void) ads7846_read12_ser(dev, READ_12BIT_SER(vaux)); - err = sysfs_create_group(&spi->dev.kobj, &ads784x_attr_group); + err = devm_device_add_group(dev, &ads784x_attr_group); if (err) - goto err_remove_hwmon; + return err; err = input_register_device(input_dev); if (err) - goto err_remove_attr_group; + return err; - device_init_wakeup(&spi->dev, pdata->wakeup); + device_init_wakeup(dev, pdata->wakeup); /* * If device does not carry platform data we must have allocated it * when parsing DT data. */ - if (!dev_get_platdata(&spi->dev)) - devm_kfree(&spi->dev, (void *)pdata); + if (!dev_get_platdata(dev)) + devm_kfree(dev, (void *)pdata); return 0; - - err_remove_attr_group: - sysfs_remove_group(&spi->dev.kobj, &ads784x_attr_group); - err_remove_hwmon: - ads784x_hwmon_unregister(spi, ts); - err_free_irq: - free_irq(spi->irq, ts); - err_disable_regulator: - regulator_disable(ts->reg); - err_put_regulator: - regulator_put(ts->reg); - err_free_gpio: - if (!ts->get_pendown_state) - gpio_free(ts->gpio_pendown); - err_cleanup_filter: - if (ts->filter_cleanup) - ts->filter_cleanup(ts->filter_data); - err_free_mem: - input_free_device(input_dev); - kfree(packet); - kfree(ts); - return err; } static int ads7846_remove(struct spi_device *spi) { struct ads7846 *ts = spi_get_drvdata(spi); - sysfs_remove_group(&spi->dev.kobj, &ads784x_attr_group); - - ads7846_disable(ts); - free_irq(ts->spi->irq, ts); - - input_unregister_device(ts->input); - - ads784x_hwmon_unregister(spi, ts); - - regulator_put(ts->reg); - - if (!ts->get_pendown_state) { - /* - * If we are not using specialized pendown method we must - * have been relying on gpio we set up ourselves. - */ - gpio_free(ts->gpio_pendown); - } - - if (ts->filter_cleanup) - ts->filter_cleanup(ts->filter_data); - - kfree(ts->packet); - kfree(ts); - - dev_dbg(&spi->dev, "unregistered touchscreen\n"); + ads7846_stop(ts); return 0; } diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 68f542bb809f..7e13a66a8a95 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -1439,11 +1439,11 @@ static int elants_i2c_probe(struct i2c_client *client) if (error) return error; - error = devm_add_action(&client->dev, elants_i2c_power_off, ts); + error = devm_add_action_or_reset(&client->dev, + elants_i2c_power_off, ts); if (error) { dev_err(&client->dev, "failed to install power off action: %d\n", error); - elants_i2c_power_off(ts); return error; } diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 4f53d3c57e69..b5cc91788195 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -14,20 +14,15 @@ #include <linux/kernel.h> #include <linux/dmi.h> #include <linux/firmware.h> -#include <linux/gpio/consumer.h> -#include <linux/i2c.h> -#include <linux/input.h> -#include <linux/input/mt.h> -#include <linux/input/touchscreen.h> #include <linux/module.h> #include <linux/delay.h> #include <linux/irq.h> #include <linux/interrupt.h> -#include <linux/regulator/consumer.h> #include <linux/slab.h> #include <linux/acpi.h> #include <linux/of.h> #include <asm/unaligned.h> +#include "goodix.h" #define GOODIX_GPIO_INT_NAME "irq" #define GOODIX_GPIO_RST_NAME "reset" @@ -38,22 +33,11 @@ #define GOODIX_CONTACT_SIZE 8 #define GOODIX_MAX_CONTACT_SIZE 9 #define GOODIX_MAX_CONTACTS 10 -#define GOODIX_MAX_KEYS 7 #define GOODIX_CONFIG_MIN_LENGTH 186 #define GOODIX_CONFIG_911_LENGTH 186 #define GOODIX_CONFIG_967_LENGTH 228 #define GOODIX_CONFIG_GT9X_LENGTH 240 -#define GOODIX_CONFIG_MAX_LENGTH 240 - -/* Register defines */ -#define GOODIX_REG_COMMAND 0x8040 -#define GOODIX_CMD_SCREEN_OFF 0x05 - -#define GOODIX_READ_COOR_ADDR 0x814E -#define GOODIX_GT1X_REG_CONFIG_DATA 0x8050 -#define GOODIX_GT9X_REG_CONFIG_DATA 0x8047 -#define GOODIX_REG_ID 0x8140 #define GOODIX_BUFFER_STATUS_READY BIT(7) #define GOODIX_HAVE_KEY BIT(4) @@ -68,55 +52,11 @@ #define ACPI_GPIO_SUPPORT #endif -struct goodix_ts_data; - -enum goodix_irq_pin_access_method { - IRQ_PIN_ACCESS_NONE, - IRQ_PIN_ACCESS_GPIO, - IRQ_PIN_ACCESS_ACPI_GPIO, - IRQ_PIN_ACCESS_ACPI_METHOD, -}; - -struct goodix_chip_data { - u16 config_addr; - int config_len; - int (*check_config)(struct goodix_ts_data *ts, const u8 *cfg, int len); - void (*calc_config_checksum)(struct goodix_ts_data *ts); -}; - struct goodix_chip_id { const char *id; const struct goodix_chip_data *data; }; -#define GOODIX_ID_MAX_LEN 4 - -struct goodix_ts_data { - struct i2c_client *client; - struct input_dev *input_dev; - const struct goodix_chip_data *chip; - struct touchscreen_properties prop; - unsigned int max_touch_num; - unsigned int int_trigger_type; - struct regulator *avdd28; - struct regulator *vddio; - struct gpio_desc *gpiod_int; - struct gpio_desc *gpiod_rst; - int gpio_count; - int gpio_int_idx; - char id[GOODIX_ID_MAX_LEN + 1]; - u16 version; - const char *cfg_name; - bool reset_controller_at_probe; - bool load_cfg_from_disk; - struct completion firmware_loading_complete; - unsigned long irq_flags; - enum goodix_irq_pin_access_method irq_pin_access_method; - unsigned int contact_size; - u8 config[GOODIX_CONFIG_MAX_LENGTH]; - unsigned short keymap[GOODIX_MAX_KEYS]; -}; - static int goodix_check_cfg_8(struct goodix_ts_data *ts, const u8 *cfg, int len); static int goodix_check_cfg_16(struct goodix_ts_data *ts, @@ -215,8 +155,7 @@ static const struct dmi_system_id inverted_x_screen[] = { * @buf: raw write data buffer. * @len: length of the buffer to write */ -static int goodix_i2c_read(struct i2c_client *client, - u16 reg, u8 *buf, int len) +int goodix_i2c_read(struct i2c_client *client, u16 reg, u8 *buf, int len) { struct i2c_msg msgs[2]; __be16 wbuf = cpu_to_be16(reg); @@ -233,7 +172,13 @@ static int goodix_i2c_read(struct i2c_client *client, msgs[1].buf = buf; ret = i2c_transfer(client->adapter, msgs, 2); - return ret < 0 ? ret : (ret != ARRAY_SIZE(msgs) ? -EIO : 0); + if (ret >= 0) + ret = (ret == ARRAY_SIZE(msgs) ? 0 : -EIO); + + if (ret) + dev_err(&client->dev, "Error reading %d bytes from 0x%04x: %d\n", + len, reg, ret); + return ret; } /** @@ -244,8 +189,7 @@ static int goodix_i2c_read(struct i2c_client *client, * @buf: raw data buffer to write. * @len: length of the buffer to write */ -static int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf, - unsigned len) +int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf, int len) { u8 *addr_buf; struct i2c_msg msg; @@ -265,11 +209,18 @@ static int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf, msg.len = len + 2; ret = i2c_transfer(client->adapter, &msg, 1); + if (ret >= 0) + ret = (ret == 1 ? 0 : -EIO); + kfree(addr_buf); - return ret < 0 ? ret : (ret != 1 ? -EIO : 0); + + if (ret) + dev_err(&client->dev, "Error writing %d bytes to 0x%04x: %d\n", + len, reg, ret); + return ret; } -static int goodix_i2c_write_u8(struct i2c_client *client, u16 reg, u8 value) +int goodix_i2c_write_u8(struct i2c_client *client, u16 reg, u8 value) { return goodix_i2c_write(client, reg, &value, sizeof(value)); } @@ -308,11 +259,8 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) do { error = goodix_i2c_read(ts->client, addr, data, header_contact_keycode_size); - if (error) { - dev_err(&ts->client->dev, "I2C transfer error: %d\n", - error); + if (error) return error; - } if (data[0] & GOODIX_BUFFER_STATUS_READY) { touch_num = data[0] & 0x0f; @@ -333,6 +281,11 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) return touch_num; } + if (data[0] == 0 && ts->firmware_name) { + if (goodix_handle_fw_request(ts)) + return 0; + } + usleep_range(1000, 2000); /* Poll every 1 - 2 ms */ } while (time_before(jiffies, max_timeout)); @@ -435,9 +388,7 @@ static irqreturn_t goodix_ts_irq_handler(int irq, void *dev_id) struct goodix_ts_data *ts = dev_id; goodix_process_events(ts); - - if (goodix_i2c_write_u8(ts->client, GOODIX_READ_COOR_ADDR, 0) < 0) - dev_err(&ts->client->dev, "I2C write end_cmd error\n"); + goodix_i2c_write_u8(ts->client, GOODIX_READ_COOR_ADDR, 0); return IRQ_HANDLED; } @@ -553,7 +504,7 @@ static int goodix_check_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len) * @cfg: config firmware to write to device * @len: config data length */ -static int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len) +int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len) { int error; @@ -562,11 +513,9 @@ static int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len) return error; error = goodix_i2c_write(ts->client, ts->chip->config_addr, cfg, len); - if (error) { - dev_err(&ts->client->dev, "Failed to write config data: %d", - error); + if (error) return error; - } + dev_dbg(&ts->client->dev, "Config sent successfully."); /* Let the firmware reconfigure itself, so sleep for 10ms */ @@ -651,62 +600,82 @@ static int goodix_irq_direction_input(struct goodix_ts_data *ts) return -EINVAL; /* Never reached */ } -static int goodix_int_sync(struct goodix_ts_data *ts) +int goodix_int_sync(struct goodix_ts_data *ts) { int error; error = goodix_irq_direction_output(ts, 0); if (error) - return error; + goto error; msleep(50); /* T5: 50ms */ error = goodix_irq_direction_input(ts); if (error) - return error; + goto error; return 0; + +error: + dev_err(&ts->client->dev, "Controller irq sync failed.\n"); + return error; } /** - * goodix_reset - Reset device during power on + * goodix_reset_no_int_sync - Reset device, leaving interrupt line in output mode * * @ts: goodix_ts_data pointer */ -static int goodix_reset(struct goodix_ts_data *ts) +int goodix_reset_no_int_sync(struct goodix_ts_data *ts) { int error; /* begin select I2C slave addr */ error = gpiod_direction_output(ts->gpiod_rst, 0); if (error) - return error; + goto error; msleep(20); /* T2: > 10ms */ /* HIGH: 0x28/0x29, LOW: 0xBA/0xBB */ error = goodix_irq_direction_output(ts, ts->client->addr == 0x14); if (error) - return error; + goto error; usleep_range(100, 2000); /* T3: > 100us */ error = gpiod_direction_output(ts->gpiod_rst, 1); if (error) - return error; + goto error; usleep_range(6000, 10000); /* T4: > 5ms */ /* end select I2C slave addr */ error = gpiod_direction_input(ts->gpiod_rst); if (error) - return error; + goto error; - error = goodix_int_sync(ts); + return 0; + +error: + dev_err(&ts->client->dev, "Controller reset failed.\n"); + return error; +} + +/** + * goodix_reset - Reset device during power on + * + * @ts: goodix_ts_data pointer + */ +static int goodix_reset(struct goodix_ts_data *ts) +{ + int error; + + error = goodix_reset_no_int_sync(ts); if (error) return error; - return 0; + return goodix_int_sync(ts); } #ifdef ACPI_GPIO_SUPPORT @@ -931,14 +900,19 @@ static void goodix_read_config(struct goodix_ts_data *ts) int x_max, y_max; int error; - error = goodix_i2c_read(ts->client, ts->chip->config_addr, - ts->config, ts->chip->config_len); - if (error) { - dev_warn(&ts->client->dev, "Error reading config: %d\n", - error); - ts->int_trigger_type = GOODIX_INT_TRIGGER; - ts->max_touch_num = GOODIX_MAX_CONTACTS; - return; + /* + * On controllers where we need to upload the firmware + * (controllers without flash) ts->config already has the config + * at this point and the controller itself does not have it yet! + */ + if (!ts->firmware_name) { + error = goodix_i2c_read(ts->client, ts->chip->config_addr, + ts->config, ts->chip->config_len); + if (error) { + ts->int_trigger_type = GOODIX_INT_TRIGGER; + ts->max_touch_num = GOODIX_MAX_CONTACTS; + return; + } } ts->int_trigger_type = ts->config[TRIGGER_LOC] & 0x03; @@ -966,10 +940,8 @@ static int goodix_read_version(struct goodix_ts_data *ts) char id_str[GOODIX_ID_MAX_LEN + 1]; error = goodix_i2c_read(ts->client, GOODIX_REG_ID, buf, sizeof(buf)); - if (error) { - dev_err(&ts->client->dev, "read version failed: %d\n", error); + if (error) return error; - } memcpy(id_str, buf, GOODIX_ID_MAX_LEN); id_str[GOODIX_ID_MAX_LEN] = 0; @@ -995,13 +967,10 @@ static int goodix_i2c_test(struct i2c_client *client) u8 test; while (retry++ < 2) { - error = goodix_i2c_read(client, GOODIX_REG_ID, - &test, 1); + error = goodix_i2c_read(client, GOODIX_REG_ID, &test, 1); if (!error) return 0; - dev_err(&client->dev, "i2c test failed attempt %d: %d\n", - retry, error); msleep(20); } @@ -1130,7 +1099,16 @@ static void goodix_config_cb(const struct firmware *cfg, void *ctx) struct goodix_ts_data *ts = ctx; int error; - if (cfg) { + if (ts->firmware_name) { + if (!cfg) + goto err_release_cfg; + + error = goodix_check_cfg(ts, cfg->data, cfg->size); + if (error) + goto err_release_cfg; + + memcpy(ts->config, cfg->data, cfg->size); + } else if (cfg) { /* send device configuration to the firmware */ error = goodix_send_cfg(ts, cfg->data, cfg->size); if (error) @@ -1156,6 +1134,7 @@ static int goodix_ts_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct goodix_ts_data *ts; + const char *cfg_name; int error; dev_dbg(&client->dev, "I2C Address: 0x%02x\n", client->addr); @@ -1205,10 +1184,8 @@ reset: if (ts->reset_controller_at_probe) { /* reset the controller */ error = goodix_reset(ts); - if (error) { - dev_err(&client->dev, "Controller reset failed.\n"); + if (error) return error; - } } error = goodix_i2c_test(client); @@ -1223,20 +1200,27 @@ reset: return error; } + error = goodix_firmware_check(ts); + if (error) + return error; + error = goodix_read_version(ts); - if (error) { - dev_err(&client->dev, "Read version failed.\n"); + if (error) return error; - } ts->chip = goodix_get_chip_data(ts->id); if (ts->load_cfg_from_disk) { /* update device config */ - ts->cfg_name = devm_kasprintf(&client->dev, GFP_KERNEL, - "goodix_%s_cfg.bin", ts->id); - if (!ts->cfg_name) - return -ENOMEM; + error = device_property_read_string(&client->dev, + "goodix,config-name", + &cfg_name); + if (!error) + snprintf(ts->cfg_name, sizeof(ts->cfg_name), + "goodix/%s", cfg_name); + else + snprintf(ts->cfg_name, sizeof(ts->cfg_name), + "goodix_%s_cfg.bin", ts->id); error = request_firmware_nowait(THIS_MODULE, true, ts->cfg_name, &client->dev, GFP_KERNEL, ts, @@ -1286,6 +1270,9 @@ static int __maybe_unused goodix_suspend(struct device *dev) /* Free IRQ as IRQ pin is used as output in the suspend sequence */ goodix_free_irq(ts); + /* Save reference (calibration) info if necessary */ + goodix_save_bak_ref(ts); + /* Output LOW on the INT pin for 5 ms */ error = goodix_irq_direction_output(ts, 0); if (error) { @@ -1298,7 +1285,6 @@ static int __maybe_unused goodix_suspend(struct device *dev) error = goodix_i2c_write_u8(ts->client, GOODIX_REG_COMMAND, GOODIX_CMD_SCREEN_OFF); if (error) { - dev_err(&ts->client->dev, "Screen off command failed\n"); goodix_irq_direction_input(ts); goodix_request_irq(ts); return -EAGAIN; @@ -1341,19 +1327,14 @@ static int __maybe_unused goodix_resume(struct device *dev) error = goodix_i2c_read(ts->client, ts->chip->config_addr, &config_ver, 1); - if (error) - dev_warn(dev, "Error reading config version: %d, resetting controller\n", - error); - else if (config_ver != ts->config[0]) + if (!error && config_ver != ts->config[0]) dev_info(dev, "Config version mismatch %d != %d, resetting controller\n", config_ver, ts->config[0]); if (error != 0 || config_ver != ts->config[0]) { error = goodix_reset(ts); - if (error) { - dev_err(dev, "Controller reset failed.\n"); + if (error) return error; - } error = goodix_send_cfg(ts, ts->config, ts->chip->config_len); if (error) diff --git a/drivers/input/touchscreen/goodix.h b/drivers/input/touchscreen/goodix.h new file mode 100644 index 000000000000..62138f930d1a --- /dev/null +++ b/drivers/input/touchscreen/goodix.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __GOODIX_H__ +#define __GOODIX_H__ + +#include <linux/gpio/consumer.h> +#include <linux/i2c.h> +#include <linux/input.h> +#include <linux/input/mt.h> +#include <linux/input/touchscreen.h> +#include <linux/regulator/consumer.h> + +/* Register defines */ +#define GOODIX_REG_MISCTL_DSP_CTL 0x4010 +#define GOODIX_REG_MISCTL_SRAM_BANK 0x4048 +#define GOODIX_REG_MISCTL_MEM_CD_EN 0x4049 +#define GOODIX_REG_MISCTL_CACHE_EN 0x404B +#define GOODIX_REG_MISCTL_TMR0_EN 0x40B0 +#define GOODIX_REG_MISCTL_SWRST 0x4180 +#define GOODIX_REG_MISCTL_CPU_SWRST_PULSE 0x4184 +#define GOODIX_REG_MISCTL_BOOTCTL 0x4190 +#define GOODIX_REG_MISCTL_BOOT_OPT 0x4218 +#define GOODIX_REG_MISCTL_BOOT_CTL 0x5094 + +#define GOODIX_REG_FW_SIG 0x8000 +#define GOODIX_FW_SIG_LEN 10 + +#define GOODIX_REG_MAIN_CLK 0x8020 +#define GOODIX_MAIN_CLK_LEN 6 + +#define GOODIX_REG_COMMAND 0x8040 +#define GOODIX_CMD_SCREEN_OFF 0x05 + +#define GOODIX_REG_SW_WDT 0x8041 + +#define GOODIX_REG_REQUEST 0x8043 +#define GOODIX_RQST_RESPONDED 0x00 +#define GOODIX_RQST_CONFIG 0x01 +#define GOODIX_RQST_BAK_REF 0x02 +#define GOODIX_RQST_RESET 0x03 +#define GOODIX_RQST_MAIN_CLOCK 0x04 +/* + * Unknown request which gets send by the controller aprox. + * every 34 seconds once it is up and running. + */ +#define GOODIX_RQST_UNKNOWN 0x06 +#define GOODIX_RQST_IDLE 0xFF + +#define GOODIX_REG_STATUS 0x8044 + +#define GOODIX_GT1X_REG_CONFIG_DATA 0x8050 +#define GOODIX_GT9X_REG_CONFIG_DATA 0x8047 +#define GOODIX_REG_ID 0x8140 +#define GOODIX_READ_COOR_ADDR 0x814E +#define GOODIX_REG_BAK_REF 0x99D0 + +#define GOODIX_ID_MAX_LEN 4 +#define GOODIX_CONFIG_MAX_LENGTH 240 +#define GOODIX_MAX_KEYS 7 + +enum goodix_irq_pin_access_method { + IRQ_PIN_ACCESS_NONE, + IRQ_PIN_ACCESS_GPIO, + IRQ_PIN_ACCESS_ACPI_GPIO, + IRQ_PIN_ACCESS_ACPI_METHOD, +}; + +struct goodix_ts_data; + +struct goodix_chip_data { + u16 config_addr; + int config_len; + int (*check_config)(struct goodix_ts_data *ts, const u8 *cfg, int len); + void (*calc_config_checksum)(struct goodix_ts_data *ts); +}; + +struct goodix_ts_data { + struct i2c_client *client; + struct input_dev *input_dev; + const struct goodix_chip_data *chip; + const char *firmware_name; + struct touchscreen_properties prop; + unsigned int max_touch_num; + unsigned int int_trigger_type; + struct regulator *avdd28; + struct regulator *vddio; + struct gpio_desc *gpiod_int; + struct gpio_desc *gpiod_rst; + int gpio_count; + int gpio_int_idx; + char id[GOODIX_ID_MAX_LEN + 1]; + char cfg_name[64]; + u16 version; + bool reset_controller_at_probe; + bool load_cfg_from_disk; + struct completion firmware_loading_complete; + unsigned long irq_flags; + enum goodix_irq_pin_access_method irq_pin_access_method; + unsigned int contact_size; + u8 config[GOODIX_CONFIG_MAX_LENGTH]; + unsigned short keymap[GOODIX_MAX_KEYS]; + u8 main_clk[GOODIX_MAIN_CLK_LEN]; + int bak_ref_len; + u8 *bak_ref; +}; + +int goodix_i2c_read(struct i2c_client *client, u16 reg, u8 *buf, int len); +int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf, int len); +int goodix_i2c_write_u8(struct i2c_client *client, u16 reg, u8 value); +int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len); +int goodix_int_sync(struct goodix_ts_data *ts); +int goodix_reset_no_int_sync(struct goodix_ts_data *ts); + +int goodix_firmware_check(struct goodix_ts_data *ts); +bool goodix_handle_fw_request(struct goodix_ts_data *ts); +void goodix_save_bak_ref(struct goodix_ts_data *ts); + +#endif diff --git a/drivers/input/touchscreen/goodix_fwupload.c b/drivers/input/touchscreen/goodix_fwupload.c new file mode 100644 index 000000000000..c1e7a2413078 --- /dev/null +++ b/drivers/input/touchscreen/goodix_fwupload.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Goodix Touchscreen firmware upload support + * + * Copyright (c) 2021 Hans de Goede <hdegoede@redhat.com> + * + * This is a rewrite of gt9xx_update.c from the Allwinner H3 BSP which is: + * Copyright (c) 2010 - 2012 Goodix Technology. + * Author: andrew@goodix.com + */ + +#include <linux/device.h> +#include <linux/firmware.h> +#include <linux/i2c.h> +#include "goodix.h" + +#define GOODIX_FW_HEADER_LENGTH sizeof(struct goodix_fw_header) +#define GOODIX_FW_SECTION_LENGTH 0x2000 +#define GOODIX_FW_DSP_LENGTH 0x1000 +#define GOODIX_FW_UPLOAD_ADDRESS 0xc000 + +#define GOODIX_CFG_LOC_HAVE_KEY 7 +#define GOODIX_CFG_LOC_DRVA_NUM 27 +#define GOODIX_CFG_LOC_DRVB_NUM 28 +#define GOODIX_CFG_LOC_SENS_NUM 29 + +struct goodix_fw_header { + u8 hw_info[4]; + u8 pid[8]; + u8 vid[2]; +} __packed; + +static u16 goodix_firmware_checksum(const u8 *data, int size) +{ + u16 checksum = 0; + int i; + + for (i = 0; i < size; i += 2) + checksum += (data[i] << 8) + data[i + 1]; + + return checksum; +} + +static int goodix_firmware_verify(struct device *dev, const struct firmware *fw) +{ + const struct goodix_fw_header *fw_header; + size_t expected_size; + const u8 *data; + u16 checksum; + char buf[9]; + + expected_size = GOODIX_FW_HEADER_LENGTH + 4 * GOODIX_FW_SECTION_LENGTH + + GOODIX_FW_DSP_LENGTH; + if (fw->size != expected_size) { + dev_err(dev, "Firmware has wrong size, expected %zu got %zu\n", + expected_size, fw->size); + return -EINVAL; + } + + data = fw->data + GOODIX_FW_HEADER_LENGTH; + checksum = goodix_firmware_checksum(data, 4 * GOODIX_FW_SECTION_LENGTH); + if (checksum) { + dev_err(dev, "Main firmware checksum error\n"); + return -EINVAL; + } + + data += 4 * GOODIX_FW_SECTION_LENGTH; + checksum = goodix_firmware_checksum(data, GOODIX_FW_DSP_LENGTH); + if (checksum) { + dev_err(dev, "DSP firmware checksum error\n"); + return -EINVAL; + } + + fw_header = (const struct goodix_fw_header *)fw->data; + dev_info(dev, "Firmware hardware info %02x%02x%02x%02x\n", + fw_header->hw_info[0], fw_header->hw_info[1], + fw_header->hw_info[2], fw_header->hw_info[3]); + /* pid is a 8 byte buffer containing a string, weird I know */ + memcpy(buf, fw_header->pid, 8); + buf[8] = 0; + dev_info(dev, "Firmware PID: %s VID: %02x%02x\n", buf, + fw_header->vid[0], fw_header->vid[1]); + return 0; +} + +static int goodix_enter_upload_mode(struct i2c_client *client) +{ + int tries, error; + u8 val; + + tries = 200; + do { + error = goodix_i2c_write_u8(client, + GOODIX_REG_MISCTL_SWRST, 0x0c); + if (error) + return error; + + error = goodix_i2c_read(client, + GOODIX_REG_MISCTL_SWRST, &val, 1); + if (error) + return error; + + if (val == 0x0c) + break; + } while (--tries); + + if (!tries) { + dev_err(&client->dev, "Error could not hold ss51 & dsp\n"); + return -EIO; + } + + /* DSP_CK and DSP_ALU_CK PowerOn */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_DSP_CTL, 0x00); + if (error) + return error; + + /* Disable watchdog */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_TMR0_EN, 0x00); + if (error) + return error; + + /* Clear cache enable */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_CACHE_EN, 0x00); + if (error) + return error; + + /* Set boot from SRAM */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_BOOTCTL, 0x02); + if (error) + return error; + + /* Software reboot */ + error = goodix_i2c_write_u8(client, + GOODIX_REG_MISCTL_CPU_SWRST_PULSE, 0x01); + if (error) + return error; + + /* Clear control flag */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_BOOTCTL, 0x00); + if (error) + return error; + + /* Set scramble */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_BOOT_OPT, 0x00); + if (error) + return error; + + /* Enable accessing code */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_MEM_CD_EN, 0x01); + if (error) + return error; + + return 0; +} + +static int goodix_start_firmware(struct i2c_client *client) +{ + int error; + u8 val; + + /* Init software watchdog */ + error = goodix_i2c_write_u8(client, GOODIX_REG_SW_WDT, 0xaa); + if (error) + return error; + + /* Release SS51 & DSP */ + error = goodix_i2c_write_u8(client, GOODIX_REG_MISCTL_SWRST, 0x00); + if (error) + return error; + + error = goodix_i2c_read(client, GOODIX_REG_SW_WDT, &val, 1); + if (error) + return error; + + /* The value we've written to SW_WDT should have been cleared now */ + if (val == 0xaa) { + dev_err(&client->dev, "Error SW_WDT reg not cleared on fw startup\n"); + return -EIO; + } + + /* Re-init software watchdog */ + error = goodix_i2c_write_u8(client, GOODIX_REG_SW_WDT, 0xaa); + if (error) + return error; + + return 0; +} + +static int goodix_firmware_upload(struct goodix_ts_data *ts) +{ + const struct firmware *fw; + char fw_name[64]; + const u8 *data; + int error; + + snprintf(fw_name, sizeof(fw_name), "goodix/%s", ts->firmware_name); + + error = request_firmware(&fw, fw_name, &ts->client->dev); + if (error) { + dev_err(&ts->client->dev, "Firmware request error %d\n", error); + return error; + } + + error = goodix_firmware_verify(&ts->client->dev, fw); + if (error) + goto release; + + error = goodix_reset_no_int_sync(ts); + if (error) + return error; + + error = goodix_enter_upload_mode(ts->client); + if (error) + goto release; + + /* Select SRAM bank 0 and upload section 1 & 2 */ + error = goodix_i2c_write_u8(ts->client, + GOODIX_REG_MISCTL_SRAM_BANK, 0x00); + if (error) + goto release; + + data = fw->data + GOODIX_FW_HEADER_LENGTH; + error = goodix_i2c_write(ts->client, GOODIX_FW_UPLOAD_ADDRESS, + data, 2 * GOODIX_FW_SECTION_LENGTH); + if (error) + goto release; + + /* Select SRAM bank 1 and upload section 3 & 4 */ + error = goodix_i2c_write_u8(ts->client, + GOODIX_REG_MISCTL_SRAM_BANK, 0x01); + if (error) + goto release; + + data += 2 * GOODIX_FW_SECTION_LENGTH; + error = goodix_i2c_write(ts->client, GOODIX_FW_UPLOAD_ADDRESS, + data, 2 * GOODIX_FW_SECTION_LENGTH); + if (error) + goto release; + + /* Select SRAM bank 2 and upload the DSP firmware */ + error = goodix_i2c_write_u8(ts->client, + GOODIX_REG_MISCTL_SRAM_BANK, 0x02); + if (error) + goto release; + + data += 2 * GOODIX_FW_SECTION_LENGTH; + error = goodix_i2c_write(ts->client, GOODIX_FW_UPLOAD_ADDRESS, + data, GOODIX_FW_DSP_LENGTH); + if (error) + goto release; + + error = goodix_start_firmware(ts->client); + if (error) + goto release; + + error = goodix_int_sync(ts); +release: + release_firmware(fw); + return error; +} + +static int goodix_prepare_bak_ref(struct goodix_ts_data *ts) +{ + u8 have_key, driver_num, sensor_num; + + if (ts->bak_ref) + return 0; /* Already done */ + + have_key = (ts->config[GOODIX_CFG_LOC_HAVE_KEY] & 0x01); + + driver_num = (ts->config[GOODIX_CFG_LOC_DRVA_NUM] & 0x1f) + + (ts->config[GOODIX_CFG_LOC_DRVB_NUM] & 0x1f); + if (have_key) + driver_num--; + + sensor_num = (ts->config[GOODIX_CFG_LOC_SENS_NUM] & 0x0f) + + ((ts->config[GOODIX_CFG_LOC_SENS_NUM] >> 4) & 0x0f); + + dev_dbg(&ts->client->dev, "Drv %d Sen %d Key %d\n", + driver_num, sensor_num, have_key); + + ts->bak_ref_len = (driver_num * (sensor_num - 2) + 2) * 2; + + ts->bak_ref = devm_kzalloc(&ts->client->dev, + ts->bak_ref_len, GFP_KERNEL); + if (!ts->bak_ref) + return -ENOMEM; + + /* + * The bak_ref array contains the backup of an array of (self/auto) + * calibration related values which the Android version of the driver + * stores on the filesystem so that it can be restored after reboot. + * The mainline kernel never writes directly to the filesystem like + * this, we always start will all the values which give a correction + * factor in approx. the -20 - +20 range (in 2s complement) set to 0. + * + * Note the touchscreen works fine without restoring the reference + * values after a reboot / power-cycle. + * + * The last 2 bytes are a 16 bits unsigned checksum which is expected + * to make the addition al all 16 bit unsigned values in the array add + * up to 1 (rather then the usual 0), so we must set the last byte to 1. + */ + ts->bak_ref[ts->bak_ref_len - 1] = 1; + + return 0; +} + +static int goodix_send_main_clock(struct goodix_ts_data *ts) +{ + u32 main_clk = 54; /* Default main clock */ + u8 checksum = 0; + int i; + + device_property_read_u32(&ts->client->dev, + "goodix,main-clk", &main_clk); + + for (i = 0; i < (GOODIX_MAIN_CLK_LEN - 1); i++) { + ts->main_clk[i] = main_clk; + checksum += main_clk; + } + + /* The value of all bytes combines must be 0 */ + ts->main_clk[GOODIX_MAIN_CLK_LEN - 1] = 256 - checksum; + + return goodix_i2c_write(ts->client, GOODIX_REG_MAIN_CLK, + ts->main_clk, GOODIX_MAIN_CLK_LEN); +} + +int goodix_firmware_check(struct goodix_ts_data *ts) +{ + device_property_read_string(&ts->client->dev, + "firmware-name", &ts->firmware_name); + if (!ts->firmware_name) + return 0; + + if (ts->irq_pin_access_method == IRQ_PIN_ACCESS_NONE) { + dev_err(&ts->client->dev, "Error no IRQ-pin access method, cannot upload fw.\n"); + return -EINVAL; + } + + dev_info(&ts->client->dev, "Touchscreen controller needs fw-upload\n"); + ts->load_cfg_from_disk = true; + + return goodix_firmware_upload(ts); +} + +bool goodix_handle_fw_request(struct goodix_ts_data *ts) +{ + int error; + u8 val; + + error = goodix_i2c_read(ts->client, GOODIX_REG_REQUEST, &val, 1); + if (error) + return false; + + switch (val) { + case GOODIX_RQST_RESPONDED: + /* + * If we read back our own last ack the IRQ was not for + * a request. + */ + return false; + case GOODIX_RQST_CONFIG: + error = goodix_send_cfg(ts, ts->config, ts->chip->config_len); + if (error) + return false; + + break; + case GOODIX_RQST_BAK_REF: + error = goodix_prepare_bak_ref(ts); + if (error) + return false; + + error = goodix_i2c_write(ts->client, GOODIX_REG_BAK_REF, + ts->bak_ref, ts->bak_ref_len); + if (error) + return false; + + break; + case GOODIX_RQST_RESET: + error = goodix_firmware_upload(ts); + if (error) + return false; + + break; + case GOODIX_RQST_MAIN_CLOCK: + error = goodix_send_main_clock(ts); + if (error) + return false; + + break; + case GOODIX_RQST_UNKNOWN: + case GOODIX_RQST_IDLE: + break; + default: + dev_err_ratelimited(&ts->client->dev, "Unknown Request: 0x%02x\n", val); + } + + /* Ack the request */ + goodix_i2c_write_u8(ts->client, + GOODIX_REG_REQUEST, GOODIX_RQST_RESPONDED); + return true; +} + +void goodix_save_bak_ref(struct goodix_ts_data *ts) +{ + int error; + u8 val; + + if (!ts->firmware_name) + return; + + error = goodix_i2c_read(ts->client, GOODIX_REG_STATUS, &val, 1); + if (error) + return; + + if (!(val & 0x80)) + return; + + error = goodix_i2c_read(ts->client, GOODIX_REG_BAK_REF, + ts->bak_ref, ts->bak_ref_len); + if (error) { + memset(ts->bak_ref, 0, ts->bak_ref_len); + ts->bak_ref[ts->bak_ref_len - 1] = 1; + } +} diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index 30576a5f2f04..2bd407d86bae 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/crc-ccitt.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> #include <linux/i2c.h> +#include <linux/ihex.h> #include <linux/input.h> #include <linux/input/mt.h> #include <linux/input/touchscreen.h> @@ -12,7 +14,7 @@ #include <linux/slab.h> #include <asm/unaligned.h> -#define ILI2XXX_POLL_PERIOD 20 +#define ILI2XXX_POLL_PERIOD 15 #define ILI210X_DATA_SIZE 64 #define ILI211X_DATA_SIZE 43 @@ -22,8 +24,23 @@ /* Touchscreen commands */ #define REG_TOUCHDATA 0x10 #define REG_PANEL_INFO 0x20 +#define REG_FIRMWARE_VERSION 0x40 +#define REG_PROTOCOL_VERSION 0x42 +#define REG_KERNEL_VERSION 0x61 +#define REG_IC_BUSY 0x80 +#define REG_IC_BUSY_NOT_BUSY 0x50 +#define REG_GET_MODE 0xc0 +#define REG_GET_MODE_AP 0x5a +#define REG_GET_MODE_BL 0x55 +#define REG_SET_MODE_AP 0xc1 +#define REG_SET_MODE_BL 0xc2 +#define REG_WRITE_DATA 0xc3 +#define REG_WRITE_ENABLE 0xc4 +#define REG_READ_DATA_CRC 0xc7 #define REG_CALIBRATE 0xcc +#define ILI251X_FW_FILENAME "ilitek/ili251x.bin" + struct ili2xxx_chip { int (*read_reg)(struct i2c_client *client, u8 reg, void *buf, size_t len); @@ -35,6 +52,7 @@ struct ili2xxx_chip { unsigned int max_touches; unsigned int resolution; bool has_calibrate_reg; + bool has_firmware_proto; bool has_pressure_reg; }; @@ -44,6 +62,10 @@ struct ili210x { struct gpio_desc *reset_gpio; struct touchscreen_properties prop; const struct ili2xxx_chip *chip; + u8 version_firmware[8]; + u8 version_kernel[5]; + u8 version_proto[2]; + u8 ic_mode[2]; bool stop; }; @@ -202,15 +224,17 @@ static const struct ili2xxx_chip ili212x_chip = { .has_calibrate_reg = true, }; -static int ili251x_read_reg(struct i2c_client *client, - u8 reg, void *buf, size_t len) +static int ili251x_read_reg_common(struct i2c_client *client, + u8 reg, void *buf, size_t len, + unsigned int delay) { int error; int ret; ret = i2c_master_send(client, ®, 1); if (ret == 1) { - usleep_range(5000, 5500); + if (delay) + usleep_range(delay, delay + 500); ret = i2c_master_recv(client, buf, len); if (ret == len) @@ -222,12 +246,18 @@ static int ili251x_read_reg(struct i2c_client *client, return ret; } +static int ili251x_read_reg(struct i2c_client *client, + u8 reg, void *buf, size_t len) +{ + return ili251x_read_reg_common(client, reg, buf, len, 5000); +} + static int ili251x_read_touch_data(struct i2c_client *client, u8 *data) { int error; - error = ili251x_read_reg(client, REG_TOUCHDATA, - data, ILI251X_DATA_SIZE1); + error = ili251x_read_reg_common(client, REG_TOUCHDATA, + data, ILI251X_DATA_SIZE1, 0); if (!error && data[0] == 2) { error = i2c_master_recv(client, data + ILI251X_DATA_SIZE1, ILI251X_DATA_SIZE2); @@ -268,6 +298,7 @@ static const struct ili2xxx_chip ili251x_chip = { .continue_polling = ili251x_check_continue_polling, .max_touches = 10, .has_calibrate_reg = true, + .has_firmware_proto = true, .has_pressure_reg = true, }; @@ -303,10 +334,13 @@ static irqreturn_t ili210x_irq(int irq, void *irq_data) const struct ili2xxx_chip *chip = priv->chip; u8 touchdata[ILI210X_DATA_SIZE] = { 0 }; bool keep_polling; + ktime_t time_next; + s64 time_delta; bool touch; int error; do { + time_next = ktime_add_ms(ktime_get(), ILI2XXX_POLL_PERIOD); error = chip->get_touch_data(client, touchdata); if (error) { dev_err(&client->dev, @@ -316,13 +350,201 @@ static irqreturn_t ili210x_irq(int irq, void *irq_data) touch = ili210x_report_events(priv, touchdata); keep_polling = chip->continue_polling(touchdata, touch); - if (keep_polling) - msleep(ILI2XXX_POLL_PERIOD); + if (keep_polling) { + time_delta = ktime_us_delta(time_next, ktime_get()); + if (time_delta > 0) + usleep_range(time_delta, time_delta + 1000); + } } while (!priv->stop && keep_polling); return IRQ_HANDLED; } +static int ili251x_firmware_update_resolution(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + u16 resx, resy; + u8 rs[10]; + int error; + + /* The firmware update blob might have changed the resolution. */ + error = priv->chip->read_reg(client, REG_PANEL_INFO, &rs, sizeof(rs)); + if (error) + return error; + + resx = le16_to_cpup((__le16 *)rs); + resy = le16_to_cpup((__le16 *)(rs + 2)); + + /* The value reported by the firmware is invalid. */ + if (!resx || resx == 0xffff || !resy || resy == 0xffff) + return -EINVAL; + + input_abs_set_max(priv->input, ABS_X, resx - 1); + input_abs_set_max(priv->input, ABS_Y, resy - 1); + input_abs_set_max(priv->input, ABS_MT_POSITION_X, resx - 1); + input_abs_set_max(priv->input, ABS_MT_POSITION_Y, resy - 1); + + return 0; +} + +static ssize_t ili251x_firmware_update_firmware_version(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + int error; + u8 fw[8]; + + /* Get firmware version */ + error = priv->chip->read_reg(client, REG_FIRMWARE_VERSION, + &fw, sizeof(fw)); + if (!error) + memcpy(priv->version_firmware, fw, sizeof(fw)); + + return error; +} + +static ssize_t ili251x_firmware_update_kernel_version(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + int error; + u8 kv[5]; + + /* Get kernel version */ + error = priv->chip->read_reg(client, REG_KERNEL_VERSION, + &kv, sizeof(kv)); + if (!error) + memcpy(priv->version_kernel, kv, sizeof(kv)); + + return error; +} + +static ssize_t ili251x_firmware_update_protocol_version(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + int error; + u8 pv[2]; + + /* Get protocol version */ + error = priv->chip->read_reg(client, REG_PROTOCOL_VERSION, + &pv, sizeof(pv)); + if (!error) + memcpy(priv->version_proto, pv, sizeof(pv)); + + return error; +} + +static ssize_t ili251x_firmware_update_ic_mode(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + int error; + u8 md[2]; + + /* Get chip boot mode */ + error = priv->chip->read_reg(client, REG_GET_MODE, &md, sizeof(md)); + if (!error) + memcpy(priv->ic_mode, md, sizeof(md)); + + return error; +} + +static int ili251x_firmware_update_cached_state(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + int error; + + if (!priv->chip->has_firmware_proto) + return 0; + + /* Wait for firmware to boot and stabilize itself. */ + msleep(200); + + /* Firmware does report valid information. */ + error = ili251x_firmware_update_resolution(dev); + if (error) + return error; + + error = ili251x_firmware_update_firmware_version(dev); + if (error) + return error; + + error = ili251x_firmware_update_kernel_version(dev); + if (error) + return error; + + error = ili251x_firmware_update_protocol_version(dev); + if (error) + return error; + + error = ili251x_firmware_update_ic_mode(dev); + if (error) + return error; + + return 0; +} + +static ssize_t ili251x_firmware_version_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + u8 *fw = priv->version_firmware; + + return sysfs_emit(buf, "%02x%02x.%02x%02x.%02x%02x.%02x%02x\n", + fw[0], fw[1], fw[2], fw[3], + fw[4], fw[5], fw[6], fw[7]); +} +static DEVICE_ATTR(firmware_version, 0444, ili251x_firmware_version_show, NULL); + +static ssize_t ili251x_kernel_version_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + u8 *kv = priv->version_kernel; + + return sysfs_emit(buf, "%02x.%02x.%02x.%02x.%02x\n", + kv[0], kv[1], kv[2], kv[3], kv[4]); +} +static DEVICE_ATTR(kernel_version, 0444, ili251x_kernel_version_show, NULL); + +static ssize_t ili251x_protocol_version_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + u8 *pv = priv->version_proto; + + return sysfs_emit(buf, "%02x.%02x\n", pv[0], pv[1]); +} +static DEVICE_ATTR(protocol_version, 0444, ili251x_protocol_version_show, NULL); + +static ssize_t ili251x_mode_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + u8 *md = priv->ic_mode; + char *mode = "AP"; + + if (md[0] == REG_GET_MODE_AP) /* Application Mode */ + mode = "AP"; + else if (md[0] == REG_GET_MODE_BL) /* BootLoader Mode */ + mode = "BL"; + else /* Unknown Mode */ + mode = "??"; + + return sysfs_emit(buf, "%02x.%02x:%s\n", md[0], md[1], mode); +} +static DEVICE_ATTR(mode, 0444, ili251x_mode_show, NULL); + static ssize_t ili210x_calibrate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -349,24 +571,333 @@ static ssize_t ili210x_calibrate(struct device *dev, } static DEVICE_ATTR(calibrate, S_IWUSR, NULL, ili210x_calibrate); +static int ili251x_firmware_to_buffer(const struct firmware *fw, + u8 **buf, u16 *ac_end, u16 *df_end) +{ + const struct ihex_binrec *rec; + u32 fw_addr, fw_last_addr = 0; + u16 fw_len; + u8 *fw_buf; + int error; + + /* + * The firmware ihex blob can never be bigger than 64 kiB, so make this + * simple -- allocate a 64 kiB buffer, iterate over the ihex blob records + * once, copy them all into this buffer at the right locations, and then + * do all operations on this linear buffer. + */ + fw_buf = kzalloc(SZ_64K, GFP_KERNEL); + if (!fw_buf) + return -ENOMEM; + + rec = (const struct ihex_binrec *)fw->data; + while (rec) { + fw_addr = be32_to_cpu(rec->addr); + fw_len = be16_to_cpu(rec->len); + + /* The last 32 Byte firmware block can be 0xffe0 */ + if (fw_addr + fw_len > SZ_64K || fw_addr > SZ_64K - 32) { + error = -EFBIG; + goto err_big; + } + + /* Find the last address before DF start address, that is AC end */ + if (fw_addr == 0xf000) + *ac_end = fw_last_addr; + fw_last_addr = fw_addr + fw_len; + + memcpy(fw_buf + fw_addr, rec->data, fw_len); + rec = ihex_next_binrec(rec); + } + + /* DF end address is the last address in the firmware blob */ + *df_end = fw_addr + fw_len; + *buf = fw_buf; + return 0; + +err_big: + kfree(fw_buf); + return error; +} + +/* Switch mode between Application and BootLoader */ +static int ili251x_switch_ic_mode(struct i2c_client *client, u8 cmd_mode) +{ + struct ili210x *priv = i2c_get_clientdata(client); + u8 cmd_wren[3] = { REG_WRITE_ENABLE, 0x5a, 0xa5 }; + u8 md[2]; + int error; + + error = priv->chip->read_reg(client, REG_GET_MODE, md, sizeof(md)); + if (error) + return error; + /* Mode already set */ + if ((cmd_mode == REG_SET_MODE_AP && md[0] == REG_GET_MODE_AP) || + (cmd_mode == REG_SET_MODE_BL && md[0] == REG_GET_MODE_BL)) + return 0; + + /* Unlock writes */ + error = i2c_master_send(client, cmd_wren, sizeof(cmd_wren)); + if (error != sizeof(cmd_wren)) + return -EINVAL; + + mdelay(20); + + /* Select mode (BootLoader or Application) */ + error = i2c_master_send(client, &cmd_mode, 1); + if (error != 1) + return -EINVAL; + + mdelay(200); /* Reboot into bootloader takes a lot of time ... */ + + /* Read back mode */ + error = priv->chip->read_reg(client, REG_GET_MODE, md, sizeof(md)); + if (error) + return error; + /* Check if mode is correct now. */ + if ((cmd_mode == REG_SET_MODE_AP && md[0] == REG_GET_MODE_AP) || + (cmd_mode == REG_SET_MODE_BL && md[0] == REG_GET_MODE_BL)) + return 0; + + return -EINVAL; +} + +static int ili251x_firmware_busy(struct i2c_client *client) +{ + struct ili210x *priv = i2c_get_clientdata(client); + int error, i = 0; + u8 data; + + do { + /* The read_reg already contains suitable delay */ + error = priv->chip->read_reg(client, REG_IC_BUSY, &data, 1); + if (error) + return error; + if (i++ == 100000) + return -ETIMEDOUT; + } while (data != REG_IC_BUSY_NOT_BUSY); + + return 0; +} + +static int ili251x_firmware_write_to_ic(struct device *dev, u8 *fwbuf, + u16 start, u16 end, u8 dataflash) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + u8 cmd_crc = REG_READ_DATA_CRC; + u8 crcrb[4] = { 0 }; + u8 fw_data[33]; + u16 fw_addr; + int error; + + /* + * The DF (dataflash) needs 2 bytes offset for unknown reasons, + * the AC (application) has 2 bytes CRC16-CCITT at the end. + */ + u16 crc = crc_ccitt(0, fwbuf + start + (dataflash ? 2 : 0), + end - start - 2); + + /* Unlock write to either AC (application) or DF (dataflash) area */ + u8 cmd_wr[10] = { + REG_WRITE_ENABLE, 0x5a, 0xa5, dataflash, + (end >> 16) & 0xff, (end >> 8) & 0xff, end & 0xff, + (crc >> 16) & 0xff, (crc >> 8) & 0xff, crc & 0xff + }; + + error = i2c_master_send(client, cmd_wr, sizeof(cmd_wr)); + if (error != sizeof(cmd_wr)) + return -EINVAL; + + error = ili251x_firmware_busy(client); + if (error) + return error; + + for (fw_addr = start; fw_addr < end; fw_addr += 32) { + fw_data[0] = REG_WRITE_DATA; + memcpy(&(fw_data[1]), fwbuf + fw_addr, 32); + error = i2c_master_send(client, fw_data, 33); + if (error != sizeof(fw_data)) + return error; + error = ili251x_firmware_busy(client); + if (error) + return error; + } + + error = i2c_master_send(client, &cmd_crc, 1); + if (error != 1) + return -EINVAL; + + error = ili251x_firmware_busy(client); + if (error) + return error; + + error = priv->chip->read_reg(client, REG_READ_DATA_CRC, + &crcrb, sizeof(crcrb)); + if (error) + return error; + + /* Check CRC readback */ + if ((crcrb[0] != (crc & 0xff)) || crcrb[1] != ((crc >> 8) & 0xff)) + return -EINVAL; + + return 0; +} + +static int ili251x_firmware_reset(struct i2c_client *client) +{ + u8 cmd_reset[2] = { 0xf2, 0x01 }; + int error; + + error = i2c_master_send(client, cmd_reset, sizeof(cmd_reset)); + if (error != sizeof(cmd_reset)) + return -EINVAL; + + return ili251x_firmware_busy(client); +} + +static void ili251x_hardware_reset(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); + + /* Reset the controller */ + gpiod_set_value_cansleep(priv->reset_gpio, 1); + usleep_range(10000, 15000); + gpiod_set_value_cansleep(priv->reset_gpio, 0); + msleep(300); +} + +static ssize_t ili210x_firmware_update_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct i2c_client *client = to_i2c_client(dev); + const char *fwname = ILI251X_FW_FILENAME; + const struct firmware *fw; + u16 ac_end, df_end; + u8 *fwbuf; + int error; + int i; + + error = request_ihex_firmware(&fw, fwname, dev); + if (error) { + dev_err(dev, "Failed to request firmware %s, error=%d\n", + fwname, error); + return error; + } + + error = ili251x_firmware_to_buffer(fw, &fwbuf, &ac_end, &df_end); + release_firmware(fw); + if (error) + return error; + + /* + * Disable touchscreen IRQ, so that we would not get spurious touch + * interrupt during firmware update, and so that the IRQ handler won't + * trigger and interfere with the firmware update. There is no bit in + * the touch controller to disable the IRQs during update, so we have + * to do it this way here. + */ + disable_irq(client->irq); + + dev_dbg(dev, "Firmware update started, firmware=%s\n", fwname); + + ili251x_hardware_reset(dev); + + error = ili251x_firmware_reset(client); + if (error) + goto exit; + + /* This may not succeed on first try, so re-try a few times. */ + for (i = 0; i < 5; i++) { + error = ili251x_switch_ic_mode(client, REG_SET_MODE_BL); + if (!error) + break; + } + + if (error) + goto exit; + + dev_dbg(dev, "IC is now in BootLoader mode\n"); + + msleep(200); /* The bootloader seems to need some time too. */ + + error = ili251x_firmware_write_to_ic(dev, fwbuf, 0xf000, df_end, 1); + if (error) { + dev_err(dev, "DF firmware update failed, error=%d\n", error); + goto exit; + } + + dev_dbg(dev, "DataFlash firmware written\n"); + + error = ili251x_firmware_write_to_ic(dev, fwbuf, 0x2000, ac_end, 0); + if (error) { + dev_err(dev, "AC firmware update failed, error=%d\n", error); + goto exit; + } + + dev_dbg(dev, "Application firmware written\n"); + + /* This may not succeed on first try, so re-try a few times. */ + for (i = 0; i < 5; i++) { + error = ili251x_switch_ic_mode(client, REG_SET_MODE_AP); + if (!error) + break; + } + + if (error) + goto exit; + + dev_dbg(dev, "IC is now in Application mode\n"); + + error = ili251x_firmware_update_cached_state(dev); + if (error) + goto exit; + + error = count; + +exit: + ili251x_hardware_reset(dev); + dev_dbg(dev, "Firmware update ended, error=%i\n", error); + enable_irq(client->irq); + kfree(fwbuf); + return error; +} + +static DEVICE_ATTR(firmware_update, 0200, NULL, ili210x_firmware_update_store); + static struct attribute *ili210x_attributes[] = { &dev_attr_calibrate.attr, + &dev_attr_firmware_update.attr, + &dev_attr_firmware_version.attr, + &dev_attr_kernel_version.attr, + &dev_attr_protocol_version.attr, + &dev_attr_mode.attr, NULL, }; -static umode_t ili210x_calibrate_visible(struct kobject *kobj, +static umode_t ili210x_attributes_visible(struct kobject *kobj, struct attribute *attr, int index) { struct device *dev = kobj_to_dev(kobj); struct i2c_client *client = to_i2c_client(dev); struct ili210x *priv = i2c_get_clientdata(client); - return priv->chip->has_calibrate_reg ? attr->mode : 0; + /* Calibrate is present on all ILI2xxx which have calibrate register */ + if (attr == &dev_attr_calibrate.attr) + return priv->chip->has_calibrate_reg ? attr->mode : 0; + + /* Firmware/Kernel/Protocol/BootMode is implememted only for ILI251x */ + if (!priv->chip->has_firmware_proto) + return 0; + + return attr->mode; } static const struct attribute_group ili210x_attr_group = { .attrs = ili210x_attributes, - .is_visible = ili210x_calibrate_visible, + .is_visible = ili210x_attributes_visible, }; static void ili210x_power_down(void *data) @@ -449,6 +980,12 @@ static int ili210x_i2c_probe(struct i2c_client *client, input_set_abs_params(input, ABS_MT_POSITION_Y, 0, max_xy, 0, 0); if (priv->chip->has_pressure_reg) input_set_abs_params(input, ABS_MT_PRESSURE, 0, 0xa, 0, 0); + error = ili251x_firmware_update_cached_state(dev); + if (error) { + dev_err(dev, "Unable to cache firmware information, err: %d\n", + error); + return error; + } touchscreen_parse_properties(input, true, &priv->prop); error = input_mt_init_slots(input, priv->chip->max_touches, diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c index 4d2d22a86977..3a4952935366 100644 --- a/drivers/input/touchscreen/raydium_i2c_ts.c +++ b/drivers/input/touchscreen/raydium_i2c_ts.c @@ -37,6 +37,7 @@ #define RM_CMD_BOOT_READ 0x44 /* send wait bl data ready*/ #define RM_BOOT_RDY 0xFF /* bl data ready */ +#define RM_BOOT_CMD_READHWID 0x0E /* read hwid */ /* I2C main commands */ #define RM_CMD_QUERY_BANK 0x2B @@ -290,6 +291,44 @@ static int raydium_i2c_sw_reset(struct i2c_client *client) return 0; } +static int raydium_i2c_query_ts_bootloader_info(struct raydium_data *ts) +{ + struct i2c_client *client = ts->client; + static const u8 get_hwid[] = { RM_BOOT_CMD_READHWID, + 0x10, 0xc0, 0x01, 0x00, 0x04, 0x00 }; + u8 rbuf[5] = { 0 }; + u32 hw_ver; + int error; + + error = raydium_i2c_send(client, RM_CMD_BOOT_WRT, + get_hwid, sizeof(get_hwid)); + if (error) { + dev_err(&client->dev, "WRT HWID command failed: %d\n", error); + return error; + } + + error = raydium_i2c_send(client, RM_CMD_BOOT_ACK, rbuf, 1); + if (error) { + dev_err(&client->dev, "Ack HWID command failed: %d\n", error); + return error; + } + + error = raydium_i2c_read(client, RM_CMD_BOOT_CHK, rbuf, sizeof(rbuf)); + if (error) { + dev_err(&client->dev, "Read HWID command failed: %d (%4ph)\n", + error, rbuf + 1); + hw_ver = 0xffffffffUL; + } else { + hw_ver = get_unaligned_be32(rbuf + 1); + } + + ts->info.hw_ver = cpu_to_le32(hw_ver); + ts->info.main_ver = 0xff; + ts->info.sub_ver = 0xff; + + return error; +} + static int raydium_i2c_query_ts_info(struct raydium_data *ts) { struct i2c_client *client = ts->client; @@ -388,13 +427,10 @@ static int raydium_i2c_initialize(struct raydium_data *ts) if (error) ts->boot_mode = RAYDIUM_TS_BLDR; - if (ts->boot_mode == RAYDIUM_TS_BLDR) { - ts->info.hw_ver = cpu_to_le32(0xffffffffUL); - ts->info.main_ver = 0xff; - ts->info.sub_ver = 0xff; - } else { + if (ts->boot_mode == RAYDIUM_TS_BLDR) + raydium_i2c_query_ts_bootloader_info(ts); + else raydium_i2c_query_ts_info(ts); - } return error; } @@ -1082,11 +1118,11 @@ static int raydium_i2c_probe(struct i2c_client *client, if (error) return error; - error = devm_add_action(&client->dev, raydium_i2c_power_off, ts); + error = devm_add_action_or_reset(&client->dev, + raydium_i2c_power_off, ts); if (error) { dev_err(&client->dev, "failed to install power off action: %d\n", error); - raydium_i2c_power_off(ts); return error; } @@ -1218,7 +1254,7 @@ static SIMPLE_DEV_PM_OPS(raydium_i2c_pm_ops, raydium_i2c_suspend, raydium_i2c_resume); static const struct i2c_device_id raydium_i2c_id[] = { - { "raydium_i2c" , 0 }, + { "raydium_i2c", 0 }, { "rm32380", 0 }, { /* sentinel */ } }; diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c index 6abae665ca71..e38ba3e4f183 100644 --- a/drivers/input/touchscreen/st1232.c +++ b/drivers/input/touchscreen/st1232.c @@ -92,7 +92,7 @@ static int st1232_ts_wait_ready(struct st1232_ts_data *ts) unsigned int retries; int error; - for (retries = 10; retries; retries--) { + for (retries = 100; retries; retries--) { error = st1232_ts_read_data(ts, REG_STATUS, 1); if (!error) { switch (ts->read_buf[0]) { @@ -389,6 +389,7 @@ static struct i2c_driver st1232_ts_driver = { .driver = { .name = ST1232_TS_NAME, .of_match_table = st1232_ts_dt_ids, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, .pm = &st1232_ts_pm_ops, }, }; diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c index 0272cedcc726..9fdd870c4c0b 100644 --- a/drivers/input/touchscreen/tsc2004.c +++ b/drivers/input/touchscreen/tsc2004.c @@ -45,7 +45,9 @@ static int tsc2004_probe(struct i2c_client *i2c, static int tsc2004_remove(struct i2c_client *i2c) { - return tsc200x_remove(&i2c->dev); + tsc200x_remove(&i2c->dev); + + return 0; } static const struct i2c_device_id tsc2004_idtable[] = { diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c index 923496bbb368..a2f55920b9b2 100644 --- a/drivers/input/touchscreen/tsc2005.c +++ b/drivers/input/touchscreen/tsc2005.c @@ -66,7 +66,9 @@ static int tsc2005_probe(struct spi_device *spi) static int tsc2005_remove(struct spi_device *spi) { - return tsc200x_remove(&spi->dev); + tsc200x_remove(&spi->dev); + + return 0; } #ifdef CONFIG_OF diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c index b8d720d52013..27810f6c69f6 100644 --- a/drivers/input/touchscreen/tsc200x-core.c +++ b/drivers/input/touchscreen/tsc200x-core.c @@ -577,15 +577,13 @@ disable_regulator: } EXPORT_SYMBOL_GPL(tsc200x_probe); -int tsc200x_remove(struct device *dev) +void tsc200x_remove(struct device *dev) { struct tsc200x *ts = dev_get_drvdata(dev); sysfs_remove_group(&dev->kobj, &tsc200x_attr_group); regulator_disable(ts->vio); - - return 0; } EXPORT_SYMBOL_GPL(tsc200x_remove); diff --git a/drivers/input/touchscreen/tsc200x-core.h b/drivers/input/touchscreen/tsc200x-core.h index a43c08ccfd3d..4ded34425b21 100644 --- a/drivers/input/touchscreen/tsc200x-core.h +++ b/drivers/input/touchscreen/tsc200x-core.h @@ -74,6 +74,6 @@ extern const struct dev_pm_ops tsc200x_pm_ops; int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)); -int tsc200x_remove(struct device *dev); +void tsc200x_remove(struct device *dev); #endif diff --git a/drivers/input/touchscreen/wacom_i2c.c b/drivers/input/touchscreen/wacom_i2c.c index 22826c387da5..fe4ea6204a4e 100644 --- a/drivers/input/touchscreen/wacom_i2c.c +++ b/drivers/input/touchscreen/wacom_i2c.c @@ -6,6 +6,7 @@ * <tobita.tatsunosuke@wacom.co.jp> */ +#include <linux/bits.h> #include <linux/module.h> #include <linux/input.h> #include <linux/i2c.h> @@ -14,6 +15,15 @@ #include <linux/interrupt.h> #include <asm/unaligned.h> +/* Bitmasks (for data[3]) */ +#define WACOM_TIP_SWITCH BIT(0) +#define WACOM_BARREL_SWITCH BIT(1) +#define WACOM_ERASER BIT(2) +#define WACOM_INVERT BIT(3) +#define WACOM_BARREL_SWITCH_2 BIT(4) +#define WACOM_IN_PROXIMITY BIT(5) + +/* Registers */ #define WACOM_CMD_QUERY0 0x04 #define WACOM_CMD_QUERY1 0x00 #define WACOM_CMD_QUERY2 0x33 @@ -99,19 +109,19 @@ static irqreturn_t wacom_i2c_irq(int irq, void *dev_id) if (error < 0) goto out; - tsw = data[3] & 0x01; - ers = data[3] & 0x04; - f1 = data[3] & 0x02; - f2 = data[3] & 0x10; + tsw = data[3] & WACOM_TIP_SWITCH; + ers = data[3] & WACOM_ERASER; + f1 = data[3] & WACOM_BARREL_SWITCH; + f2 = data[3] & WACOM_BARREL_SWITCH_2; x = le16_to_cpup((__le16 *)&data[4]); y = le16_to_cpup((__le16 *)&data[6]); pressure = le16_to_cpup((__le16 *)&data[8]); if (!wac_i2c->prox) - wac_i2c->tool = (data[3] & 0x0c) ? + wac_i2c->tool = (data[3] & (WACOM_ERASER | WACOM_INVERT)) ? BTN_TOOL_RUBBER : BTN_TOOL_PEN; - wac_i2c->prox = data[3] & 0x20; + wac_i2c->prox = data[3] & WACOM_IN_PROXIMITY; input_report_key(input, BTN_TOUCH, tsw || ers); input_report_key(input, wac_i2c->tool, wac_i2c->prox); diff --git a/drivers/media/i2c/imx319.c b/drivers/media/i2c/imx319.c index dba0854ab5aa..daa976858e29 100644 --- a/drivers/media/i2c/imx319.c +++ b/drivers/media/i2c/imx319.c @@ -140,6 +140,8 @@ struct imx319 { /* Streaming on/off */ bool streaming; + /* True if the device has been identified */ + bool identified; }; static const struct imx319_reg imx319_global_regs[] = { @@ -2084,6 +2086,31 @@ imx319_set_pad_format(struct v4l2_subdev *sd, return 0; } +/* Verify chip ID */ +static int imx319_identify_module(struct imx319 *imx319) +{ + struct i2c_client *client = v4l2_get_subdevdata(&imx319->sd); + int ret; + u32 val; + + if (imx319->identified) + return 0; + + ret = imx319_read_reg(imx319, IMX319_REG_CHIP_ID, 2, &val); + if (ret) + return ret; + + if (val != IMX319_CHIP_ID) { + dev_err(&client->dev, "chip id mismatch: %x!=%x", + IMX319_CHIP_ID, val); + return -EIO; + } + + imx319->identified = true; + + return 0; +} + /* Start streaming */ static int imx319_start_streaming(struct imx319 *imx319) { @@ -2091,6 +2118,10 @@ static int imx319_start_streaming(struct imx319 *imx319) const struct imx319_reg_list *reg_list; int ret; + ret = imx319_identify_module(imx319); + if (ret) + return ret; + /* Global Setting */ reg_list = &imx319_global_setting; ret = imx319_write_regs(imx319, reg_list->regs, reg_list->num_of_regs); @@ -2206,26 +2237,6 @@ error: return ret; } -/* Verify chip ID */ -static int imx319_identify_module(struct imx319 *imx319) -{ - struct i2c_client *client = v4l2_get_subdevdata(&imx319->sd); - int ret; - u32 val; - - ret = imx319_read_reg(imx319, IMX319_REG_CHIP_ID, 2, &val); - if (ret) - return ret; - - if (val != IMX319_CHIP_ID) { - dev_err(&client->dev, "chip id mismatch: %x!=%x", - IMX319_CHIP_ID, val); - return -EIO; - } - - return 0; -} - static const struct v4l2_subdev_core_ops imx319_subdev_core_ops = { .subscribe_event = v4l2_ctrl_subdev_subscribe_event, .unsubscribe_event = v4l2_event_subdev_unsubscribe, @@ -2420,6 +2431,7 @@ out_err: static int imx319_probe(struct i2c_client *client) { struct imx319 *imx319; + bool full_power; int ret; u32 i; @@ -2432,11 +2444,14 @@ static int imx319_probe(struct i2c_client *client) /* Initialize subdev */ v4l2_i2c_subdev_init(&imx319->sd, client, &imx319_subdev_ops); - /* Check module identity */ - ret = imx319_identify_module(imx319); - if (ret) { - dev_err(&client->dev, "failed to find sensor: %d", ret); - goto error_probe; + full_power = acpi_dev_state_d0(&client->dev); + if (full_power) { + /* Check module identity */ + ret = imx319_identify_module(imx319); + if (ret) { + dev_err(&client->dev, "failed to find sensor: %d", ret); + goto error_probe; + } } imx319->hwcfg = imx319_get_hwcfg(&client->dev); @@ -2488,11 +2503,9 @@ static int imx319_probe(struct i2c_client *client) if (ret < 0) goto error_media_entity; - /* - * Device is already turned on by i2c-core with ACPI domain PM. - * Enable runtime PM and turn off the device. - */ - pm_runtime_set_active(&client->dev); + /* Set the device's state to active if it's in D0 state. */ + if (full_power) + pm_runtime_set_active(&client->dev); pm_runtime_enable(&client->dev); pm_runtime_idle(&client->dev); @@ -2545,6 +2558,7 @@ static struct i2c_driver imx319_i2c_driver = { }, .probe_new = imx319_probe, .remove = imx319_remove, + .flags = I2C_DRV_ACPI_WAIVE_D0_PROBE, }; module_i2c_driver(imx319_i2c_driver); diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 81cee1a5daa6..546feef851ab 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -146,8 +146,8 @@ static int ec_device_probe(struct platform_device *pdev) ec->ec_dev = dev_get_drvdata(dev->parent); ec->dev = dev; ec->cmd_offset = ec_platform->cmd_offset; - ec->features[0] = -1U; /* Not cached yet */ - ec->features[1] = -1U; /* Not cached yet */ + ec->features.flags[0] = -1U; /* Not cached yet */ + ec->features.flags[1] = -1U; /* Not cached yet */ device_initialize(&ec->class_dev); for (i = 0; i < ARRAY_SIZE(cros_mcu_devices); i++) { diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index c1d3e7c116cf..56c61c99eb23 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -36,7 +36,6 @@ #include <linux/mfd/abx500/ab8500.h> #include <linux/regulator/db8500-prcmu.h> #include <linux/regulator/machine.h> -#include <linux/platform_data/ux500_wdt.h> #include "db8500-prcmu-regs.h" /* Index of different voltages to be used when accessing AVSData */ @@ -2939,18 +2938,8 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = { }, }; -static struct ux500_wdt_data db8500_wdt_pdata = { - .timeout = 600, /* 10 minutes */ - .has_28_bits_resolution = true, -}; - static const struct mfd_cell common_prcmu_devs[] = { - { - .name = "ux500_wdt", - .platform_data = &db8500_wdt_pdata, - .pdata_size = sizeof(db8500_wdt_pdata), - .id = -1, - }, + MFD_CELL_NAME("db8500_wdt"), MFD_CELL_NAME("db8500-cpuidle"), }; diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 305ffad131a2..49ab656e8a96 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -595,6 +595,7 @@ static int at24_probe(struct i2c_client *client) bool i2c_fn_i2c, i2c_fn_block; unsigned int i, num_addresses; struct at24_data *at24; + bool full_power; struct regmap *regmap; bool writable; u8 test_byte; @@ -747,14 +748,16 @@ static int at24_probe(struct i2c_client *client) i2c_set_clientdata(client, at24); - err = regulator_enable(at24->vcc_reg); - if (err) { - dev_err(dev, "Failed to enable vcc regulator\n"); - return err; - } + full_power = acpi_dev_state_d0(&client->dev); + if (full_power) { + err = regulator_enable(at24->vcc_reg); + if (err) { + dev_err(dev, "Failed to enable vcc regulator\n"); + return err; + } - /* enable runtime pm */ - pm_runtime_set_active(dev); + pm_runtime_set_active(dev); + } pm_runtime_enable(dev); at24->nvmem = devm_nvmem_register(dev, &nvmem_config); @@ -766,15 +769,18 @@ static int at24_probe(struct i2c_client *client) } /* - * Perform a one-byte test read to verify that the - * chip is functional. + * Perform a one-byte test read to verify that the chip is functional, + * unless powering on the device is to be avoided during probe (i.e. + * it's powered off right now). */ - err = at24_read(at24, 0, &test_byte, 1); - if (err) { - pm_runtime_disable(dev); - if (!pm_runtime_status_suspended(dev)) - regulator_disable(at24->vcc_reg); - return -ENODEV; + if (full_power) { + err = at24_read(at24, 0, &test_byte, 1); + if (err) { + pm_runtime_disable(dev); + if (!pm_runtime_status_suspended(dev)) + regulator_disable(at24->vcc_reg); + return -ENODEV; + } } pm_runtime_idle(dev); @@ -794,9 +800,11 @@ static int at24_remove(struct i2c_client *client) struct at24_data *at24 = i2c_get_clientdata(client); pm_runtime_disable(&client->dev); - if (!pm_runtime_status_suspended(&client->dev)) - regulator_disable(at24->vcc_reg); - pm_runtime_set_suspended(&client->dev); + if (acpi_dev_state_d0(&client->dev)) { + if (!pm_runtime_status_suspended(&client->dev)) + regulator_disable(at24->vcc_reg); + pm_runtime_set_suspended(&client->dev); + } return 0; } @@ -833,6 +841,7 @@ static struct i2c_driver at24_driver = { .probe_new = at24_probe, .remove = at24_remove, .id_table = at24_ids, + .flags = I2C_DRV_ACPI_WAIVE_D0_PROBE, }; static int __init at24_init(void) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 034dbd487c33..10506a4b66ef 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -294,6 +294,7 @@ config GTP config AMT tristate "Automatic Multicast Tunneling (AMT)" depends on INET && IP_MULTICAST + depends on IPV6 || !IPV6 select NET_UDP_TUNNEL help This allows one to create AMT(Automatic Multicast Tunneling) diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 60a7053a9cf7..47a04c330885 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -12,7 +12,6 @@ #include <linux/igmp.h> #include <linux/workqueue.h> #include <net/net_namespace.h> -#include <net/protocol.h> #include <net/ip.h> #include <net/udp.h> #include <net/udp_tunnel.h> @@ -23,7 +22,6 @@ #include <linux/security.h> #include <net/gro_cells.h> #include <net/ipv6.h> -#include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> @@ -2767,7 +2765,7 @@ static int amt_err_lookup(struct sock *sk, struct sk_buff *skb) rcu_read_lock_bh(); amt = rcu_dereference_sk_user_data(sk); if (!amt) - goto drop; + goto out; if (amt->mode != AMT_MODE_GATEWAY) goto drop; @@ -2789,6 +2787,7 @@ static int amt_err_lookup(struct sock *sk, struct sk_buff *skb) default: goto drop; } +out: rcu_read_unlock_bh(); return 0; drop: @@ -3259,8 +3258,10 @@ static int __init amt_init(void) goto unregister_notifier; amt_wq = alloc_workqueue("amt", WQ_UNBOUND, 1); - if (!amt_wq) + if (!amt_wq) { + err = -ENOMEM; goto rtnl_unregister; + } spin_lock_init(&source_gc_lock); spin_lock_bh(&source_gc_lock); @@ -3285,7 +3286,7 @@ static void __exit amt_fini(void) { rtnl_link_unregister(&amt_link_ops); unregister_netdevice_notifier(&amt_notifier_block); - flush_delayed_work(&source_gc_wq); + cancel_delayed_work(&source_gc_wq); __amt_source_gc_work(); destroy_workqueue(amt_wq); } diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index fd07561da034..6a6cdd0bb258 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -108,15 +108,15 @@ static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) } static SLAVE_ATTR_RO(ad_partner_oper_port_state); -static const struct slave_attribute *slave_attrs[] = { - &slave_attr_state, - &slave_attr_mii_status, - &slave_attr_link_failure_count, - &slave_attr_perm_hwaddr, - &slave_attr_queue_id, - &slave_attr_ad_aggregator_id, - &slave_attr_ad_actor_oper_port_state, - &slave_attr_ad_partner_oper_port_state, +static const struct attribute *slave_attrs[] = { + &slave_attr_state.attr, + &slave_attr_mii_status.attr, + &slave_attr_link_failure_count.attr, + &slave_attr_perm_hwaddr.attr, + &slave_attr_queue_id.attr, + &slave_attr_ad_aggregator_id.attr, + &slave_attr_ad_actor_oper_port_state.attr, + &slave_attr_ad_partner_oper_port_state.attr, NULL }; @@ -137,24 +137,10 @@ const struct sysfs_ops slave_sysfs_ops = { int bond_sysfs_slave_add(struct slave *slave) { - const struct slave_attribute **a; - int err; - - for (a = slave_attrs; *a; ++a) { - err = sysfs_create_file(&slave->kobj, &((*a)->attr)); - if (err) { - kobject_put(&slave->kobj); - return err; - } - } - - return 0; + return sysfs_create_files(&slave->kobj, slave_attrs); } void bond_sysfs_slave_del(struct slave *slave) { - const struct slave_attribute **a; - - for (a = slave_attrs; *a; ++a) - sysfs_remove_file(&slave->kobj, &((*a)->attr)); + sysfs_remove_files(&slave->kobj, slave_attrs); } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 673861ab665a..e16dc482f327 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -1092,7 +1092,7 @@ static int mcp251xfd_chip_start(struct mcp251xfd_priv *priv) err = mcp251xfd_chip_rx_int_enable(priv); if (err) - return err; + goto out_chip_stop; err = mcp251xfd_chip_ecc_init(priv); if (err) @@ -2290,8 +2290,10 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) * check will fail, too. So leave IRQ handler * directly. */ - if (priv->can.state == CAN_STATE_BUS_OFF) + if (priv->can.state == CAN_STATE_BUS_OFF) { + can_rx_offload_threaded_irq_finish(&priv->offload); return IRQ_HANDLED; + } } handled = IRQ_HANDLED; diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 96a13c770e4a..24627ab14626 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -664,7 +664,7 @@ int es58x_rx_err_msg(struct net_device *netdev, enum es58x_err error, struct can_device_stats *can_stats = &can->can_stats; struct can_frame *cf = NULL; struct sk_buff *skb; - int ret; + int ret = 0; if (!netif_running(netdev)) { if (net_ratelimit()) @@ -823,8 +823,6 @@ int es58x_rx_err_msg(struct net_device *netdev, enum es58x_err error, can->state = CAN_STATE_BUS_OFF; can_bus_off(netdev); ret = can->do_set_mode(netdev, CAN_MODE_STOP); - if (ret) - return ret; } break; @@ -881,7 +879,7 @@ int es58x_rx_err_msg(struct net_device *netdev, enum es58x_err error, ES58X_EVENT_BUSOFF, timestamp); } - return 0; + return ret; } /** diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 837b3fecd71e..876218752766 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -841,14 +841,14 @@ static int pcan_usb_start(struct peak_usb_device *dev) pdev->bec.rxerr = 0; pdev->bec.txerr = 0; - /* be notified on error counter changes (if requested by user) */ - if (dev->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { - err = pcan_usb_set_err_frame(dev, PCAN_USB_BERR_MASK); - if (err) - netdev_warn(dev->netdev, - "Asking for BERR reporting error %u\n", - err); - } + /* always ask the device for BERR reporting, to be able to switch from + * WARNING to PASSIVE state + */ + err = pcan_usb_set_err_frame(dev, PCAN_USB_BERR_MASK); + if (err) + netdev_warn(dev->netdev, + "Asking for BERR reporting error %u\n", + err); /* if revision greater than 3, can put silent mode on/off */ if (dev->device_rev > 3) { @@ -883,6 +883,11 @@ static int pcan_usb_init(struct peak_usb_device *dev) return err; } + dev_info(dev->netdev->dev.parent, + "PEAK-System %s adapter hwrev %u serial %08X (%u channel)\n", + pcan_usb.name, dev->device_rev, serial_number, + pcan_usb.ctrl_count); + /* Since rev 4.1, PCAN-USB is able to make single-shot as well as * looped back frames. */ @@ -896,11 +901,6 @@ static int pcan_usb_init(struct peak_usb_device *dev) "Firmware update available. Please contact support@peak-system.com\n"); } - dev_info(dev->netdev->dev.parent, - "PEAK-System %s adapter hwrev %u serial %08X (%u channel)\n", - pcan_usb.name, dev->device_rev, serial_number, - pcan_usb.ctrl_count); - return 0; } @@ -986,7 +986,6 @@ const struct peak_usb_adapter pcan_usb = { .device_id = PCAN_USB_PRODUCT_ID, .ctrl_count = 1, .ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY | - CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_CC_LEN8_DLC, .clock = { .freq = PCAN_USB_CRYSTAL_HZ / 2, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 14c678a9e41b..f00cbf5753b9 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -640,7 +640,10 @@ static void mv88e6393x_phylink_validate(struct mv88e6xxx_chip *chip, int port, unsigned long *mask, struct phylink_link_state *state) { - if (port == 0 || port == 9 || port == 10) { + bool is_6191x = + chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6191X; + + if (((port == 0 || port == 9) && !is_6191x) || port == 10) { phylink_set(mask, 10000baseT_Full); phylink_set(mask, 10000baseKR_Full); phylink_set(mask, 10000baseCR_Full); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 83808e7dbdda..327cc4654806 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1370,12 +1370,12 @@ out: static bool felix_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type) { - u8 *extraction = skb->data - ETH_HLEN - OCELOT_TAG_LEN; + u32 tstamp_lo = OCELOT_SKB_CB(skb)->tstamp_lo; struct skb_shared_hwtstamps *shhwtstamps; struct ocelot *ocelot = ds->priv; - u32 tstamp_lo, tstamp_hi; struct timespec64 ts; - u64 tstamp, val; + u32 tstamp_hi; + u64 tstamp; /* If the "no XTR IRQ" workaround is in use, tell DSA to defer this skb * for RX timestamping. Then free it, and poll for its copy through @@ -1390,9 +1390,6 @@ static bool felix_rxtstamp(struct dsa_switch *ds, int port, ocelot_ptp_gettime64(&ocelot->ptp_info, &ts); tstamp = ktime_set(ts.tv_sec, ts.tv_nsec); - ocelot_xfh_get_rew_val(extraction, &val); - tstamp_lo = (u32)val; - tstamp_hi = tstamp >> 32; if ((tstamp & 0xffffffff) < tstamp_lo) tstamp_hi--; diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index ea7f12778922..a429c9750add 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1109,6 +1109,14 @@ qca8k_setup(struct dsa_switch *ds) if (ret) return ret; + /* Make sure MAC06 is disabled */ + ret = qca8k_reg_clear(priv, QCA8K_REG_PORT0_PAD_CTRL, + QCA8K_PORT0_PAD_MAC06_EXCHANGE_EN); + if (ret) { + dev_err(priv->dev, "failed disabling MAC06 exchange"); + return ret; + } + /* Enable CPU Port */ ret = qca8k_reg_set(priv, QCA8K_REG_GLOBAL_FW_CTRL0, QCA8K_GLOBAL_FW_CTRL0_CPU_PORT_EN); diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index e10571a398c9..128b8cf85e08 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -34,6 +34,7 @@ #define QCA8K_MASK_CTRL_DEVICE_ID_MASK GENMASK(15, 8) #define QCA8K_MASK_CTRL_DEVICE_ID(x) ((x) >> 8) #define QCA8K_REG_PORT0_PAD_CTRL 0x004 +#define QCA8K_PORT0_PAD_MAC06_EXCHANGE_EN BIT(31) #define QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE BIT(19) #define QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE BIT(18) #define QCA8K_REG_PORT5_PAD_CTRL 0x008 diff --git a/drivers/net/ethernet/asix/ax88796c_main.c b/drivers/net/ethernet/asix/ax88796c_main.c index 4b0c5a09fd57..e230d8d0ff73 100644 --- a/drivers/net/ethernet/asix/ax88796c_main.c +++ b/drivers/net/ethernet/asix/ax88796c_main.c @@ -934,7 +934,7 @@ static const struct net_device_ops ax88796c_netdev_ops = { .ndo_stop = ax88796c_close, .ndo_start_xmit = ax88796c_start_xmit, .ndo_get_stats64 = ax88796c_get_stats64, - .ndo_do_ioctl = ax88796c_ioctl, + .ndo_eth_ioctl = ax88796c_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_set_features = ax88796c_set_features, }; @@ -1114,11 +1114,13 @@ static int ax88796c_remove(struct spi_device *spi) return 0; } +#ifdef CONFIG_OF static const struct of_device_id ax88796c_dt_ids[] = { { .compatible = "asix,ax88796c" }, {}, }; MODULE_DEVICE_TABLE(of, ax88796c_dt_ids); +#endif static const struct spi_device_id asix_id[] = { { "ax88796c", 0 }, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index ce790e9b45c3..5c464ea73576 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -443,7 +443,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: { if (BNXT_PF(bp) && bp->pf.active_vfs) { NL_SET_ERR_MSG_MOD(extack, - "reload is unsupported when VFs are allocated\n"); + "reload is unsupported when VFs are allocated"); return -EOPNOTSUPP; } rtnl_lock(); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index b1328c5524b5..85ca3909859d 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -5503,7 +5503,6 @@ static bool tg3_setup_fiber_hw_autoneg(struct tg3 *tp, u32 mac_status) int workaround, port_a; serdes_cfg = 0; - expected_sg_dig_ctrl = 0; workaround = 0; port_a = 1; current_link_up = false; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 5903bdb78916..129352bbe114 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -2015,12 +2015,15 @@ static int cxgb4_get_module_info(struct net_device *dev, if (ret) return ret; - if (!sff8472_comp || (sff_diag_type & 4)) { + if (!sff8472_comp || (sff_diag_type & SFP_DIAG_ADDRMODE)) { modinfo->type = ETH_MODULE_SFF_8079; modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; } else { modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + if (sff_diag_type & SFP_DIAG_IMPLEMENTED) + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + else + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN / 2; } break; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index 002fc62ea726..63bc956d2037 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -293,6 +293,8 @@ enum { #define I2C_PAGE_SIZE 0x100 #define SFP_DIAG_TYPE_ADDR 0x5c #define SFP_DIAG_TYPE_LEN 0x1 +#define SFP_DIAG_ADDRMODE BIT(2) +#define SFP_DIAG_IMPLEMENTED BIT(6) #define SFF_8472_COMP_ADDR 0x5e #define SFF_8472_COMP_LEN 0x1 #define SFF_REV_ADDR 0x1 diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 6b02ef432eda..59b66f679e46 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1137,7 +1137,7 @@ static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) goto reset; ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); - if (ntfy_idx > priv->num_ntfy_blks) + if (ntfy_idx >= priv->num_ntfy_blks) goto reset; block = &priv->ntfy_blocks[ntfy_idx]; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index c8500babbd1d..3d04b5aff331 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -500,7 +500,8 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, rx->rx_copied_pkt++; rx->rx_frag_copy_cnt++; rx->rx_copybreak_pkt++; - } u64_stats_update_end(&rx->statss); + u64_stats_update_end(&rx->statss); + } } else { if (rx->data.raw_addressing) { int recycle = gve_rx_can_recycle_buffer(page_info); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a2b993d62822..9ccebbaa0d69 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4210,6 +4210,13 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, } out: + /* sync head pointer before exiting, since hardware will calculate + * FBD number with head pointer + */ + if (unused_count > 0) + failure = failure || + hns3_nic_alloc_rx_buffers(ring, unused_count); + return failure ? budget : recv_pkts; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 9fdedd83f392..c8442b86df94 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -238,9 +238,11 @@ static void hns3_lb_clear_tx_ring(struct hns3_nic_priv *priv, u32 start_ringid, } /** - * hns3_lp_run_test - run loopback test + * hns3_lp_run_test - run loopback test * @ndev: net device * @mode: loopback type + * + * Return: %0 for success or a NIC loopback test error code on failure */ static int hns3_lp_run_test(struct net_device *ndev, enum hnae3_loop mode) { @@ -398,7 +400,7 @@ static void hns3_do_selftest(struct net_device *ndev, int (*st_param)[2], } /** - * hns3_nic_self_test - self test + * hns3_self_test - self test * @ndev: net device * @eth_test: test cmd * @data: test result diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index c327df9dbac4..c5d5466810bb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -483,6 +483,7 @@ static int hclge_firmware_compat_config(struct hclge_dev *hdev, bool en) if (hnae3_dev_phy_imp_supported(hdev)) hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1); hnae3_set_bit(compat, HCLGE_MAC_STATS_EXT_EN_B, 1); + hnae3_set_bit(compat, HCLGE_SYNC_RX_RING_HEAD_EN_B, 1); req->compat = cpu_to_le32(compat); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index c38b57fc6c6a..d24e59028798 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -1151,6 +1151,7 @@ struct hclge_query_ppu_pf_other_int_dfx_cmd { #define HCLGE_NCSI_ERROR_REPORT_EN_B 1 #define HCLGE_PHY_IMP_EN_B 2 #define HCLGE_MAC_STATS_EXT_EN_B 3 +#define HCLGE_SYNC_RX_RING_HEAD_EN_B 4 struct hclge_firmware_compat_cmd { __le32 compat; u8 rsv[20]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 91cb578f56b8..375ebf105a9a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -129,7 +129,7 @@ static int hclge_ets_sch_mode_validate(struct hclge_dev *hdev, u32 total_ets_bw = 0; u8 i; - for (i = 0; i < hdev->tc_max; i++) { + for (i = 0; i < HNAE3_MAX_TC; i++) { switch (ets->tc_tsa[i]) { case IEEE_8021QAZ_TSA_STRICT: if (hdev->tm_info.tc_info[i].tc_sch_mode != @@ -286,28 +286,24 @@ err_out: static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) { - u64 requests[HNAE3_MAX_TC], indications[HNAE3_MAX_TC]; struct hclge_vport *vport = hclge_get_vport(h); struct hclge_dev *hdev = vport->back; int ret; - u8 i; memset(pfc, 0, sizeof(*pfc)); pfc->pfc_cap = hdev->pfc_max; pfc->pfc_en = hdev->tm_info.pfc_en; - ret = hclge_pfc_tx_stats_get(hdev, requests); - if (ret) + ret = hclge_mac_update_stats(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to update MAC stats, ret = %d.\n", ret); return ret; + } - ret = hclge_pfc_rx_stats_get(hdev, indications); - if (ret) - return ret; + hclge_pfc_tx_stats_get(hdev, pfc->requests); + hclge_pfc_rx_stats_get(hdev, pfc->indications); - for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - pfc->requests[i] = requests[i]; - pfc->indications[i] = indications[i]; - } return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 2e41aa2d1df8..c2a58101144e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -26,8 +26,6 @@ #include "hclge_devlink.h" #define HCLGE_NAME "hclge" -#define HCLGE_STATS_READ(p, offset) (*(u64 *)((u8 *)(p) + (offset))) -#define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f)) #define HCLGE_BUF_SIZE_UNIT 256U #define HCLGE_BUF_MUL_BY 2 @@ -568,6 +566,16 @@ static int hclge_mac_query_reg_num(struct hclge_dev *hdev, u32 *reg_num) struct hclge_desc desc; int ret; + /* Driver needs total register number of both valid registers and + * reserved registers, but the old firmware only returns number + * of valid registers in device V2. To be compatible with these + * devices, driver uses a fixed value. + */ + if (hdev->ae_dev->dev_version == HNAE3_DEVICE_VERSION_V2) { + *reg_num = HCLGE_MAC_STATS_MAX_NUM_V1; + return 0; + } + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_MAC_REG_NUM, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -587,7 +595,7 @@ static int hclge_mac_query_reg_num(struct hclge_dev *hdev, u32 *reg_num) return 0; } -static int hclge_mac_update_stats(struct hclge_dev *hdev) +int hclge_mac_update_stats(struct hclge_dev *hdev) { /* The firmware supports the new statistics acquisition method */ if (hdev->ae_dev->dev_specs.mac_stats_num) @@ -2581,7 +2589,7 @@ static int hclge_init_roce_base_info(struct hclge_vport *vport) if (hdev->num_msi < hdev->num_nic_msi + hdev->num_roce_msi) return -EINVAL; - roce->rinfo.base_vector = hdev->roce_base_vector; + roce->rinfo.base_vector = hdev->num_nic_msi; roce->rinfo.netdev = nic->kinfo.netdev; roce->rinfo.roce_io_base = hdev->hw.io_base; @@ -2617,10 +2625,6 @@ static int hclge_init_msi(struct hclge_dev *hdev) hdev->num_msi = vectors; hdev->num_msi_left = vectors; - hdev->base_msi_vector = pdev->irq; - hdev->roce_base_vector = hdev->base_msi_vector + - hdev->num_nic_msi; - hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi, sizeof(u16), GFP_KERNEL); if (!hdev->vector_status) { @@ -8949,8 +8953,11 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, err_no_space: /* if already overflow, not to print each time */ - if (!(vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE)) + if (!(vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE)) { + vport->overflow_promisc_flags |= HNAE3_OVERFLOW_MPE; dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n"); + } + return -ENOSPC; } @@ -9006,12 +9013,17 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, static void hclge_sync_vport_mac_list(struct hclge_vport *vport, struct list_head *list, - int (*sync)(struct hclge_vport *, - const unsigned char *)) + enum HCLGE_MAC_ADDR_TYPE mac_type) { + int (*sync)(struct hclge_vport *vport, const unsigned char *addr); struct hclge_mac_node *mac_node, *tmp; int ret; + if (mac_type == HCLGE_MAC_ADDR_UC) + sync = hclge_add_uc_addr_common; + else + sync = hclge_add_mc_addr_common; + list_for_each_entry_safe(mac_node, tmp, list, node) { ret = sync(vport, mac_node->mac_addr); if (!ret) { @@ -9023,8 +9035,13 @@ static void hclge_sync_vport_mac_list(struct hclge_vport *vport, /* If one unicast mac address is existing in hardware, * we need to try whether other unicast mac addresses * are new addresses that can be added. + * Multicast mac address can be reusable, even though + * there is no space to add new multicast mac address, + * we should check whether other mac addresses are + * existing in hardware for reuse. */ - if (ret != -EEXIST) + if ((mac_type == HCLGE_MAC_ADDR_UC && ret != -EEXIST) || + (mac_type == HCLGE_MAC_ADDR_MC && ret != -ENOSPC)) break; } } @@ -9032,12 +9049,17 @@ static void hclge_sync_vport_mac_list(struct hclge_vport *vport, static void hclge_unsync_vport_mac_list(struct hclge_vport *vport, struct list_head *list, - int (*unsync)(struct hclge_vport *, - const unsigned char *)) + enum HCLGE_MAC_ADDR_TYPE mac_type) { + int (*unsync)(struct hclge_vport *vport, const unsigned char *addr); struct hclge_mac_node *mac_node, *tmp; int ret; + if (mac_type == HCLGE_MAC_ADDR_UC) + unsync = hclge_rm_uc_addr_common; + else + unsync = hclge_rm_mc_addr_common; + list_for_each_entry_safe(mac_node, tmp, list, node) { ret = unsync(vport, mac_node->mac_addr); if (!ret || ret == -ENOENT) { @@ -9168,17 +9190,8 @@ stop_traverse: spin_unlock_bh(&vport->mac_list_lock); /* delete first, in order to get max mac table space for adding */ - if (mac_type == HCLGE_MAC_ADDR_UC) { - hclge_unsync_vport_mac_list(vport, &tmp_del_list, - hclge_rm_uc_addr_common); - hclge_sync_vport_mac_list(vport, &tmp_add_list, - hclge_add_uc_addr_common); - } else { - hclge_unsync_vport_mac_list(vport, &tmp_del_list, - hclge_rm_mc_addr_common); - hclge_sync_vport_mac_list(vport, &tmp_add_list, - hclge_add_mc_addr_common); - } + hclge_unsync_vport_mac_list(vport, &tmp_del_list, mac_type); + hclge_sync_vport_mac_list(vport, &tmp_add_list, mac_type); /* if some mac addresses were added/deleted fail, move back to the * mac_list, and retry at next time. @@ -9337,12 +9350,7 @@ static void hclge_uninit_vport_mac_list(struct hclge_vport *vport, spin_unlock_bh(&vport->mac_list_lock); - if (mac_type == HCLGE_MAC_ADDR_UC) - hclge_unsync_vport_mac_list(vport, &tmp_del_list, - hclge_rm_uc_addr_common); - else - hclge_unsync_vport_mac_list(vport, &tmp_del_list, - hclge_rm_mc_addr_common); + hclge_unsync_vport_mac_list(vport, &tmp_del_list, mac_type); if (!list_empty(&tmp_del_list)) dev_warn(&hdev->pdev->dev, @@ -9410,36 +9418,6 @@ static int hclge_get_mac_ethertype_cmd_status(struct hclge_dev *hdev, return return_status; } -static bool hclge_check_vf_mac_exist(struct hclge_vport *vport, int vf_idx, - u8 *mac_addr) -{ - struct hclge_mac_vlan_tbl_entry_cmd req; - struct hclge_dev *hdev = vport->back; - struct hclge_desc desc; - u16 egress_port = 0; - int i; - - if (is_zero_ether_addr(mac_addr)) - return false; - - memset(&req, 0, sizeof(req)); - hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, - HCLGE_MAC_EPORT_VFID_S, vport->vport_id); - req.egress_port = cpu_to_le16(egress_port); - hclge_prepare_mac_addr(&req, mac_addr, false); - - if (hclge_lookup_mac_vlan_tbl(vport, &req, &desc, false) != -ENOENT) - return true; - - vf_idx += HCLGE_VF_VPORT_START_NUM; - for (i = HCLGE_VF_VPORT_START_NUM; i < hdev->num_alloc_vport; i++) - if (i != vf_idx && - ether_addr_equal(mac_addr, hdev->vport[i].vf_info.mac)) - return true; - - return false; -} - static int hclge_set_vf_mac(struct hnae3_handle *handle, int vf, u8 *mac_addr) { @@ -9457,12 +9435,6 @@ static int hclge_set_vf_mac(struct hnae3_handle *handle, int vf, return 0; } - if (hclge_check_vf_mac_exist(vport, vf, mac_addr)) { - dev_err(&hdev->pdev->dev, "Specified MAC(=%pM) exists!\n", - mac_addr); - return -EEXIST; - } - ether_addr_copy(vport->vf_info.mac, mac_addr); if (test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 9e1eede599ec..ebba603483a0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -404,7 +404,7 @@ struct hclge_tm_info { }; /* max number of mac statistics on each version */ -#define HCLGE_MAC_STATS_MAX_NUM_V1 84 +#define HCLGE_MAC_STATS_MAX_NUM_V1 87 #define HCLGE_MAC_STATS_MAX_NUM_V2 105 struct hclge_comm_stats_str { @@ -852,6 +852,9 @@ struct hclge_vf_vlan_cfg { (y) = (_k_ ^ ~_v_) & (_k_); \ } while (0) +#define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f)) +#define HCLGE_STATS_READ(p, offset) (*(u64 *)((u8 *)(p) + (offset))) + #define HCLGE_MAC_TNL_LOG_SIZE 8 #define HCLGE_VPORT_NUM 256 struct hclge_dev { @@ -904,12 +907,10 @@ struct hclge_dev { u16 num_msi; u16 num_msi_left; u16 num_msi_used; - u32 base_msi_vector; u16 *vector_status; int *vector_irq; u16 num_nic_msi; /* Num of nic vectors for this PF */ u16 num_roce_msi; /* Num of roce vectors for this PF */ - int roce_base_vector; unsigned long service_timer_period; unsigned long service_timer_previous; @@ -1168,4 +1169,5 @@ void hclge_inform_vf_promisc_info(struct hclge_vport *vport); int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len); int hclge_push_vf_link_status(struct hclge_vport *vport); int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en); +int hclge_mac_update_stats(struct hclge_dev *hdev); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 95074e91a846..429652a8cde1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -113,50 +113,50 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level, return 0; } -static int hclge_pfc_stats_get(struct hclge_dev *hdev, - enum hclge_opcode_type opcode, u64 *stats) -{ - struct hclge_desc desc[HCLGE_TM_PFC_PKT_GET_CMD_NUM]; - int ret, i, j; - - if (!(opcode == HCLGE_OPC_QUERY_PFC_RX_PKT_CNT || - opcode == HCLGE_OPC_QUERY_PFC_TX_PKT_CNT)) - return -EINVAL; - - for (i = 0; i < HCLGE_TM_PFC_PKT_GET_CMD_NUM - 1; i++) { - hclge_cmd_setup_basic_desc(&desc[i], opcode, true); - desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - } - - hclge_cmd_setup_basic_desc(&desc[i], opcode, true); +static const u16 hclge_pfc_tx_stats_offset[] = { + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri0_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri1_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri2_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri3_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri4_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri5_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri6_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri7_pkt_num) +}; - ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_TM_PFC_PKT_GET_CMD_NUM); - if (ret) - return ret; +static const u16 hclge_pfc_rx_stats_offset[] = { + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri0_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri1_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri2_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri3_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri4_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri5_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri6_pkt_num), + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri7_pkt_num) +}; - for (i = 0; i < HCLGE_TM_PFC_PKT_GET_CMD_NUM; i++) { - struct hclge_pfc_stats_cmd *pfc_stats = - (struct hclge_pfc_stats_cmd *)desc[i].data; +static void hclge_pfc_stats_get(struct hclge_dev *hdev, bool tx, u64 *stats) +{ + const u16 *offset; + int i; - for (j = 0; j < HCLGE_TM_PFC_NUM_GET_PER_CMD; j++) { - u32 index = i * HCLGE_TM_PFC_PKT_GET_CMD_NUM + j; + if (tx) + offset = hclge_pfc_tx_stats_offset; + else + offset = hclge_pfc_rx_stats_offset; - if (index < HCLGE_MAX_TC_NUM) - stats[index] = - le64_to_cpu(pfc_stats->pkt_num[j]); - } - } - return 0; + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) + stats[i] = HCLGE_STATS_READ(&hdev->mac_stats, offset[i]); } -int hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats) +void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats) { - return hclge_pfc_stats_get(hdev, HCLGE_OPC_QUERY_PFC_RX_PKT_CNT, stats); + hclge_pfc_stats_get(hdev, false, stats); } -int hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats) +void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats) { - return hclge_pfc_stats_get(hdev, HCLGE_OPC_QUERY_PFC_TX_PKT_CNT, stats); + hclge_pfc_stats_get(hdev, true, stats); } int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) @@ -1123,7 +1123,6 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev) static int hclge_tm_ets_tc_dwrr_cfg(struct hclge_dev *hdev) { -#define DEFAULT_TC_WEIGHT 1 #define DEFAULT_TC_OFFSET 14 struct hclge_ets_tc_weight_cmd *ets_weight; @@ -1136,13 +1135,7 @@ static int hclge_tm_ets_tc_dwrr_cfg(struct hclge_dev *hdev) for (i = 0; i < HNAE3_MAX_TC; i++) { struct hclge_pg_info *pg_info; - ets_weight->tc_weight[i] = DEFAULT_TC_WEIGHT; - - if (!(hdev->hw_tc_map & BIT(i))) - continue; - - pg_info = - &hdev->tm_info.pg_info[hdev->tm_info.tc_info[i].pgid]; + pg_info = &hdev->tm_info.pg_info[hdev->tm_info.tc_info[i].pgid]; ets_weight->tc_weight[i] = pg_info->tc_dwrr[i]; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 2ee9b795f71d..1db7f40b4525 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -228,8 +228,8 @@ int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev, bool init); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); -int hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); -int hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); +void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); +void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate); int hclge_tm_get_qset_num(struct hclge_dev *hdev, u16 *qset_num); int hclge_tm_get_pri_num(struct hclge_dev *hdev, u8 *pri_num); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index f89bfb352adf..e605c2c5bcce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -434,8 +434,28 @@ err_csq: return ret; } +static int hclgevf_firmware_compat_config(struct hclgevf_dev *hdev, bool en) +{ + struct hclgevf_firmware_compat_cmd *req; + struct hclgevf_desc desc; + u32 compat = 0; + + hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_IMP_COMPAT_CFG, false); + + if (en) { + req = (struct hclgevf_firmware_compat_cmd *)desc.data; + + hnae3_set_bit(compat, HCLGEVF_SYNC_RX_RING_HEAD_EN_B, 1); + + req->compat = cpu_to_le32(compat); + } + + return hclgevf_cmd_send(&hdev->hw, &desc, 1); +} + int hclgevf_cmd_init(struct hclgevf_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); int ret; spin_lock_bh(&hdev->hw.cmq.csq.lock); @@ -484,6 +504,17 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev) hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE0_MASK, HNAE3_FW_VERSION_BYTE0_SHIFT)); + if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) { + /* ask the firmware to enable some features, driver can work + * without it. + */ + ret = hclgevf_firmware_compat_config(hdev, true); + if (ret) + dev_warn(&hdev->pdev->dev, + "Firmware compatible features not enabled(%d).\n", + ret); + } + return 0; err_cmd_init: @@ -508,6 +539,7 @@ static void hclgevf_cmd_uninit_regs(struct hclgevf_hw *hw) void hclgevf_cmd_uninit(struct hclgevf_dev *hdev) { + hclgevf_firmware_compat_config(hdev, false); set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); /* wait to ensure that the firmware completes the possible left * over commands. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h index 39d0b589c720..edc9e154061a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h @@ -15,6 +15,12 @@ struct hclgevf_hw; struct hclgevf_dev; +#define HCLGEVF_SYNC_RX_RING_HEAD_EN_B 4 +struct hclgevf_firmware_compat_cmd { + __le32 compat; + u8 rsv[20]; +}; + struct hclgevf_desc { __le16 opcode; __le16 flag; @@ -107,6 +113,9 @@ enum hclgevf_opcode_type { HCLGEVF_OPC_RSS_TC_MODE = 0x0D08, /* Mailbox cmd */ HCLGEVF_OPC_MBX_VF_TO_PF = 0x2001, + + /* IMP stats command */ + HCLGEVF_OPC_IMP_COMPAT_CFG = 0x701A, }; #define HCLGEVF_TQP_REG_OFFSET 0x80000 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 645b2c0011e6..25c419d40066 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2557,7 +2557,7 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev) hdev->num_msi_left == 0) return -EINVAL; - roce->rinfo.base_vector = hdev->roce_base_vector; + roce->rinfo.base_vector = hdev->roce_base_msix_offset; roce->rinfo.netdev = nic->kinfo.netdev; roce->rinfo.roce_io_base = hdev->hw.io_base; @@ -2823,9 +2823,6 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev) hdev->num_msi = vectors; hdev->num_msi_left = vectors; - hdev->base_msi_vector = pdev->irq; - hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset; - hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi, sizeof(u16), GFP_KERNEL); if (!hdev->vector_status) { @@ -3013,7 +3010,10 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client, /* un-init roce, if it exists */ if (hdev->roce_client) { + while (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + msleep(HCLGEVF_WAIT_RESET_DONE); clear_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state); + hdev->roce_client->ops->uninit_instance(&hdev->roce, 0); hdev->roce_client = NULL; hdev->roce.client = NULL; @@ -3022,6 +3022,8 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client, /* un-init nic/unic, if this was not called by roce client */ if (client->ops->uninit_instance && hdev->nic_client && client->type != HNAE3_CLIENT_ROCE) { + while (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + msleep(HCLGEVF_WAIT_RESET_DONE); clear_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state); client->ops->uninit_instance(&hdev->nic, 0); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 28288d7e3303..f6f736c0091c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -109,6 +109,8 @@ #define HCLGEVF_VF_RST_ING 0x07008 #define HCLGEVF_VF_RST_ING_BIT BIT(16) +#define HCLGEVF_WAIT_RESET_DONE 100 + #define HCLGEVF_RSS_IND_TBL_SIZE 512 #define HCLGEVF_RSS_SET_BITMAP_MSK 0xffff #define HCLGEVF_RSS_KEY_SIZE 40 @@ -308,8 +310,6 @@ struct hclgevf_dev { u16 num_nic_msix; /* Num of nic vectors for this VF */ u16 num_roce_msix; /* Num of roce vectors for this VF */ u16 roce_base_msix_offset; - int roce_base_vector; - u32 base_msi_vector; u16 *vector_status; int *vector_irq; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index bf4ecd9a517c..b2db39ee5f85 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -165,13 +165,10 @@ #define ice_for_each_chnl_tc(i) \ for ((i) = ICE_CHNL_START_TC; (i) < ICE_CHNL_MAX_TC; (i)++) -#define ICE_UCAST_PROMISC_BITS (ICE_PROMISC_UCAST_TX | ICE_PROMISC_MCAST_TX | \ - ICE_PROMISC_UCAST_RX | ICE_PROMISC_MCAST_RX) +#define ICE_UCAST_PROMISC_BITS (ICE_PROMISC_UCAST_TX | ICE_PROMISC_UCAST_RX) #define ICE_UCAST_VLAN_PROMISC_BITS (ICE_PROMISC_UCAST_TX | \ - ICE_PROMISC_MCAST_TX | \ ICE_PROMISC_UCAST_RX | \ - ICE_PROMISC_MCAST_RX | \ ICE_PROMISC_VLAN_TX | \ ICE_PROMISC_VLAN_RX) diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index fa6cd63cbf1f..1efc635cc0f5 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -962,7 +962,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, } else if (status == ICE_ERR_DOES_NOT_EXIST) { dev_dbg(ice_pf_to_dev(vsi->back), "LAN Tx queues do not exist, nothing to disable\n"); } else if (status) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %s\n", + dev_dbg(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %s\n", ice_stat_str(status)); return -ENODEV; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 2ac21484b876..217ff5e9a6f1 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -638,8 +638,7 @@ void ice_free_vfs(struct ice_pf *pf) /* Avoid wait time by stopping all VFs at the same time */ ice_for_each_vf(pf, i) - if (test_bit(ICE_VF_STATE_QS_ENA, pf->vf[i].vf_states)) - ice_dis_vf_qs(&pf->vf[i]); + ice_dis_vf_qs(&pf->vf[i]); tmp = pf->num_alloc_vfs; pf->num_qps_per_vf = 0; @@ -651,6 +650,8 @@ void ice_free_vfs(struct ice_pf *pf) set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); ice_free_vf_res(&pf->vf[i]); } + + mutex_destroy(&pf->vf[i].cfg_lock); } if (ice_sriov_free_msix_res(pf)) @@ -1695,8 +1696,7 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) vsi = ice_get_vf_vsi(vf); - if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) - ice_dis_vf_qs(vf); + ice_dis_vf_qs(vf); /* Call Disable LAN Tx queue AQ whether or not queues are * enabled. This is needed for successful completion of VFR. @@ -1948,6 +1948,8 @@ static void ice_set_dflt_settings_vfs(struct ice_pf *pf) ice_vf_fdir_init(vf); ice_vc_set_dflt_vf_ops(&vf->vc_ops); + + mutex_init(&vf->cfg_lock); } } @@ -3013,6 +3015,7 @@ bool ice_is_any_vf_in_promisc(struct ice_pf *pf) static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + enum ice_status mcast_status = 0, ucast_status = 0; bool rm_promisc, alluni = false, allmulti = false; struct virtchnl_promisc_info *info = (struct virtchnl_promisc_info *)msg; @@ -3054,24 +3057,6 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) rm_promisc = !allmulti && !alluni; if (vsi->num_vlan || vf->port_vlan_info) { - struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); - struct net_device *pf_netdev; - - if (!pf_vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - pf_netdev = pf_vsi->netdev; - - ret = ice_set_vf_spoofchk(pf_netdev, vf->vf_id, rm_promisc); - if (ret) { - dev_err(dev, "Failed to update spoofchk to %s for VF %d VSI %d when setting promiscuous mode\n", - rm_promisc ? "ON" : "OFF", vf->vf_id, - vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - } - if (rm_promisc) ret = ice_cfg_vlan_pruning(vsi, true); else @@ -3105,52 +3090,51 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) goto error_param; } } else { - enum ice_status status; - u8 promisc_m; - - if (alluni) { - if (vf->port_vlan_info || vsi->num_vlan) - promisc_m = ICE_UCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_UCAST_PROMISC_BITS; - } else if (allmulti) { - if (vf->port_vlan_info || vsi->num_vlan) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; + u8 mcast_m, ucast_m; + + if (vf->port_vlan_info || vsi->num_vlan > 1) { + mcast_m = ICE_MCAST_VLAN_PROMISC_BITS; + ucast_m = ICE_UCAST_VLAN_PROMISC_BITS; } else { - if (vf->port_vlan_info || vsi->num_vlan) - promisc_m = ICE_UCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_UCAST_PROMISC_BITS; + mcast_m = ICE_MCAST_PROMISC_BITS; + ucast_m = ICE_UCAST_PROMISC_BITS; } - /* Configure multicast/unicast with or without VLAN promiscuous - * mode - */ - status = ice_vf_set_vsi_promisc(vf, vsi, promisc_m, rm_promisc); - if (status) { - dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed, error: %s\n", - rm_promisc ? "dis" : "en", vf->vf_id, - ice_stat_str(status)); - v_ret = ice_err_to_virt_err(status); - goto error_param; - } else { - dev_dbg(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d succeeded\n", - rm_promisc ? "dis" : "en", vf->vf_id); + ucast_status = ice_vf_set_vsi_promisc(vf, vsi, ucast_m, + !alluni); + if (ucast_status) { + dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed\n", + alluni ? "en" : "dis", vf->vf_id); + v_ret = ice_err_to_virt_err(ucast_status); + } + + mcast_status = ice_vf_set_vsi_promisc(vf, vsi, mcast_m, + !allmulti); + if (mcast_status) { + dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed\n", + allmulti ? "en" : "dis", vf->vf_id); + v_ret = ice_err_to_virt_err(mcast_status); } } - if (allmulti && - !test_and_set_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully set multicast promiscuous mode\n", vf->vf_id); - else if (!allmulti && test_and_clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully unset multicast promiscuous mode\n", vf->vf_id); + if (!mcast_status) { + if (allmulti && + !test_and_set_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) + dev_info(dev, "VF %u successfully set multicast promiscuous mode\n", + vf->vf_id); + else if (!allmulti && test_and_clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) + dev_info(dev, "VF %u successfully unset multicast promiscuous mode\n", + vf->vf_id); + } - if (alluni && !test_and_set_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully set unicast promiscuous mode\n", vf->vf_id); - else if (!alluni && test_and_clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully unset unicast promiscuous mode\n", vf->vf_id); + if (!ucast_status) { + if (alluni && !test_and_set_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) + dev_info(dev, "VF %u successfully set unicast promiscuous mode\n", + vf->vf_id); + else if (!alluni && test_and_clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) + dev_info(dev, "VF %u successfully unset unicast promiscuous mode\n", + vf->vf_id); + } error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, @@ -3824,6 +3808,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, struct device *dev = ice_pf_to_dev(vf->pf); u8 *mac_addr = vc_ether_addr->addr; enum ice_status status; + int ret = 0; /* device MAC already added */ if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) @@ -3836,20 +3821,23 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, status = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); if (status == ICE_ERR_ALREADY_EXISTS) { - dev_err(dev, "MAC %pM already exists for VF %d\n", mac_addr, + dev_dbg(dev, "MAC %pM already exists for VF %d\n", mac_addr, vf->vf_id); - return -EEXIST; + /* don't return since we might need to update + * the primary MAC in ice_vfhw_mac_add() below + */ + ret = -EEXIST; } else if (status) { dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %s\n", mac_addr, vf->vf_id, ice_stat_str(status)); return -EIO; + } else { + vf->num_mac++; } ice_vfhw_mac_add(vf, vc_ether_addr); - vf->num_mac++; - - return 0; + return ret; } /** @@ -4151,6 +4139,8 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, return 0; } + mutex_lock(&vf->cfg_lock); + vf->port_vlan_info = vlanprio; if (vf->port_vlan_info) @@ -4160,6 +4150,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id); ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); return 0; } @@ -4699,6 +4690,15 @@ error_handler: return; } + /* VF is being configured in another context that triggers a VFR, so no + * need to process this message + */ + if (!mutex_trylock(&vf->cfg_lock)) { + dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", + vf->vf_id); + return; + } + switch (v_opcode) { case VIRTCHNL_OP_VERSION: err = ops->get_ver_msg(vf, msg); @@ -4787,6 +4787,8 @@ error_handler: dev_info(dev, "PF failed to honor VF %d, opcode %d, error %d\n", vf_id, v_opcode, err); } + + mutex_unlock(&vf->cfg_lock); } /** @@ -4902,6 +4904,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) return -EINVAL; } + mutex_lock(&vf->cfg_lock); + /* VF is notified of its new MAC via the PF's response to the * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset */ @@ -4920,6 +4924,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) } ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); return 0; } @@ -4954,11 +4959,15 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) if (trusted == vf->trusted) return 0; + mutex_lock(&vf->cfg_lock); + vf->trusted = trusted; ice_vc_reset_vf(vf); dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", vf_id, trusted ? "" : "un"); + mutex_unlock(&vf->cfg_lock); + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 5ff93a08f54c..7e28ecbbe7af 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -100,6 +100,11 @@ struct ice_vc_vf_ops { struct ice_vf { struct ice_pf *pf; + /* Used during virtchnl message handling and NDO ops against the VF + * that will trigger a VFR + */ + struct mutex cfg_lock; + u16 vf_id; /* VF ID in the PF space */ u16 lan_vsi_idx; /* index into PF struct */ u16 ctrl_vsi_idx; diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 2258e3f19161..6433c909c6b2 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -262,7 +262,7 @@ ltq_etop_hw_init(struct net_device *dev) /* enable crc generation */ ltq_etop_w32(PPE32_CGEN, LQ_PPE32_ENET_MAC_CFG); - ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, rx_burst_len); + ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, priv->rx_burst_len); for (i = 0; i < MAX_DMA_CHAN; i++) { int irq = LTQ_DMA_CH0_INT + i; diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c index 3d9385a4989b..fdd99f0de424 100644 --- a/drivers/net/ethernet/litex/litex_liteeth.c +++ b/drivers/net/ethernet/litex/litex_liteeth.c @@ -242,10 +242,8 @@ static int liteeth_probe(struct platform_device *pdev) priv->dev = &pdev->dev; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(&pdev->dev, "Failed to get IRQ %d\n", irq); + if (irq < 0) return irq; - } netdev->irq = irq; priv->base = devm_platform_ioremap_resource_byname(pdev, "mac"); @@ -289,7 +287,6 @@ static int liteeth_remove(struct platform_device *pdev) struct net_device *netdev = platform_get_drvdata(pdev); unregister_netdev(netdev); - free_netdev(netdev); return 0; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 587def69a6f7..2b18d89d9756 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -1605,7 +1605,7 @@ static void mvpp22_gop_fca_set_periodic_timer(struct mvpp2_port *port) mvpp22_gop_fca_enable_periodic(port, true); } -static int mvpp22_gop_init(struct mvpp2_port *port) +static int mvpp22_gop_init(struct mvpp2_port *port, phy_interface_t interface) { struct mvpp2 *priv = port->priv; u32 val; @@ -1613,7 +1613,7 @@ static int mvpp22_gop_init(struct mvpp2_port *port) if (!priv->sysctrl_base) return 0; - switch (port->phy_interface) { + switch (interface) { case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: @@ -1743,15 +1743,15 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port) * lanes by the physical layer. This is why configurations like * "PPv2 (2500BaseX) - COMPHY (2500SGMII)" are valid. */ -static int mvpp22_comphy_init(struct mvpp2_port *port) +static int mvpp22_comphy_init(struct mvpp2_port *port, + phy_interface_t interface) { int ret; if (!port->comphy) return 0; - ret = phy_set_mode_ext(port->comphy, PHY_MODE_ETHERNET, - port->phy_interface); + ret = phy_set_mode_ext(port->comphy, PHY_MODE_ETHERNET, interface); if (ret) return ret; @@ -2172,7 +2172,8 @@ static void mvpp22_pcs_reset_assert(struct mvpp2_port *port) writel(val & ~MVPP22_XPCS_CFG0_RESET_DIS, xpcs + MVPP22_XPCS_CFG0); } -static void mvpp22_pcs_reset_deassert(struct mvpp2_port *port) +static void mvpp22_pcs_reset_deassert(struct mvpp2_port *port, + phy_interface_t interface) { struct mvpp2 *priv = port->priv; void __iomem *mpcs, *xpcs; @@ -2184,7 +2185,7 @@ static void mvpp22_pcs_reset_deassert(struct mvpp2_port *port) mpcs = priv->iface_base + MVPP22_MPCS_BASE(port->gop_id); xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id); - switch (port->phy_interface) { + switch (interface) { case PHY_INTERFACE_MODE_10GBASER: val = readl(mpcs + MVPP22_MPCS_CLK_RESET); val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX | @@ -4529,7 +4530,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) return rx_done; } -static void mvpp22_mode_reconfigure(struct mvpp2_port *port) +static void mvpp22_mode_reconfigure(struct mvpp2_port *port, + phy_interface_t interface) { u32 ctrl3; @@ -4540,18 +4542,18 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port) mvpp22_pcs_reset_assert(port); /* comphy reconfiguration */ - mvpp22_comphy_init(port); + mvpp22_comphy_init(port, interface); /* gop reconfiguration */ - mvpp22_gop_init(port); + mvpp22_gop_init(port, interface); - mvpp22_pcs_reset_deassert(port); + mvpp22_pcs_reset_deassert(port, interface); if (mvpp2_port_supports_xlg(port)) { ctrl3 = readl(port->base + MVPP22_XLG_CTRL3_REG); ctrl3 &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK; - if (mvpp2_is_xlg(port->phy_interface)) + if (mvpp2_is_xlg(interface)) ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_10G; else ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC; @@ -4559,7 +4561,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port) writel(ctrl3, port->base + MVPP22_XLG_CTRL3_REG); } - if (mvpp2_port_supports_xlg(port) && mvpp2_is_xlg(port->phy_interface)) + if (mvpp2_port_supports_xlg(port) && mvpp2_is_xlg(interface)) mvpp2_xlg_max_rx_size_set(port); else mvpp2_gmac_max_rx_size_set(port); @@ -4579,7 +4581,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) mvpp2_interrupts_enable(port); if (port->priv->hw_version >= MVPP22) - mvpp22_mode_reconfigure(port); + mvpp22_mode_reconfigure(port, port->phy_interface); if (port->phylink) { phylink_start(port->phylink); @@ -6444,6 +6446,9 @@ static int mvpp2__mac_prepare(struct phylink_config *config, unsigned int mode, mvpp22_gop_mask_irq(port); phy_power_off(port->comphy); + + /* Reconfigure the serdes lanes */ + mvpp22_mode_reconfigure(port, interface); } } @@ -6498,9 +6503,6 @@ static int mvpp2_mac_finish(struct phylink_config *config, unsigned int mode, port->phy_interface != interface) { port->phy_interface = interface; - /* Reconfigure the serdes lanes */ - mvpp22_mode_reconfigure(port); - /* Unmask interrupts */ mvpp22_gop_unmask_irq(port); } @@ -6961,7 +6963,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, * driver does this, we can remove this code. */ if (port->comphy) { - err = mvpp22_comphy_init(port); + err = mvpp22_comphy_init(port, port->phy_interface); if (err == 0) phy_power_off(port->comphy); } diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 3f982ccf2c85..639893d87055 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -31,6 +31,7 @@ config NDC_DIS_DYNAMIC_CACHING config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX + select NET_DEVLINK depends on (64BIT && COMPILE_TEST) || ARM64 depends on PCI depends on PTP_1588_CLOCK_OPTIONAL diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index bb6b42bbefa4..c0005a1feee6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2450,9 +2450,7 @@ alloc: bmap = mcam->bmap_reverse; start = mcam->bmap_entries - start; end = mcam->bmap_entries - end; - index = start; - start = end; - end = index; + swap(start, end); } else { bmap = mcam->bmap; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index e6cb8cd0787d..78944ad3492f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -501,7 +501,7 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_set_features = otx2vf_set_features, .ndo_get_stats64 = otx2_get_stats64, .ndo_tx_timeout = otx2_tx_timeout, - .ndo_do_ioctl = otx2_ioctl, + .ndo_eth_ioctl = otx2_ioctl, }; static int otx2_wq_init(struct otx2_nic *vf) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_ethtool.c b/drivers/net/ethernet/marvell/prestera/prestera_ethtool.c index 6011454dba71..40d5b89573bb 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_ethtool.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_ethtool.c @@ -499,7 +499,8 @@ static void prestera_port_mdix_get(struct ethtool_link_ksettings *ecmd, { struct prestera_port_phy_state *state = &port->state_phy; - if (prestera_hw_port_phy_mode_get(port, &state->mdix, NULL, NULL, NULL)) { + if (prestera_hw_port_phy_mode_get(port, + &state->mdix, NULL, NULL, NULL)) { netdev_warn(port->dev, "MDIX params get failed"); state->mdix = ETH_TP_MDI_INVALID; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_hw.c index 41ba17cb2965..9b8b1ed474fc 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_hw.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.c @@ -180,108 +180,113 @@ struct prestera_msg_common_resp { struct prestera_msg_ret ret; }; -union prestera_msg_switch_param { - u8 mac[ETH_ALEN]; - __le32 ageing_timeout_ms; -} __packed; - struct prestera_msg_switch_attr_req { struct prestera_msg_cmd cmd; __le32 attr; - union prestera_msg_switch_param param; + union { + __le32 ageing_timeout_ms; + struct { + u8 mac[ETH_ALEN]; + u8 __pad[2]; + }; + } param; }; struct prestera_msg_switch_init_resp { struct prestera_msg_ret ret; __le32 port_count; __le32 mtu_max; - u8 switch_id; - u8 lag_max; - u8 lag_member_max; __le32 size_tbl_router_nexthop; -} __packed __aligned(4); + u8 switch_id; + u8 lag_max; + u8 lag_member_max; +}; struct prestera_msg_event_port_param { union { struct { - u8 oper; __le32 mode; __le32 speed; + u8 oper; u8 duplex; u8 fc; u8 fec; - } __packed mac; + } mac; struct { - u8 mdix; __le64 lmode_bmap; + u8 mdix; u8 fc; - } __packed phy; - } __packed; -} __packed __aligned(4); + u8 __pad[2]; + } __packed phy; /* make sure always 12 bytes size */ + }; +}; struct prestera_msg_port_cap_param { __le64 link_mode; - u8 type; - u8 fec; - u8 fc; - u8 transceiver; + u8 type; + u8 fec; + u8 fc; + u8 transceiver; }; struct prestera_msg_port_flood_param { u8 type; u8 enable; + u8 __pad[2]; }; union prestera_msg_port_param { + __le32 mtu; + __le32 speed; + __le32 link_mode; u8 admin_state; u8 oper_state; - __le32 mtu; u8 mac[ETH_ALEN]; u8 accept_frm_type; - __le32 speed; u8 learning; u8 flood; - __le32 link_mode; u8 type; u8 duplex; u8 fec; u8 fc; - union { struct { - u8 admin:1; + u8 admin; u8 fc; u8 ap_enable; + u8 __reserved[5]; union { struct { __le32 mode; - u8 inband:1; __le32 speed; - u8 duplex; - u8 fec; - u8 fec_supp; - } __packed reg_mode; + u8 inband; + u8 duplex; + u8 fec; + u8 fec_supp; + } reg_mode; struct { __le32 mode; __le32 speed; - u8 fec; - u8 fec_supp; - } __packed ap_modes[PRESTERA_AP_PORT_MAX]; - } __packed; - } __packed mac; + u8 fec; + u8 fec_supp; + u8 __pad[2]; + } ap_modes[PRESTERA_AP_PORT_MAX]; + }; + } mac; struct { - u8 admin:1; - u8 adv_enable; __le64 modes; __le32 mode; + u8 admin; + u8 adv_enable; u8 mdix; - } __packed phy; - } __packed link; + u8 __pad; + } phy; + } link; struct prestera_msg_port_cap_param cap; struct prestera_msg_port_flood_param flood_ext; struct prestera_msg_event_port_param link_evt; -} __packed; +}; struct prestera_msg_port_attr_req { struct prestera_msg_cmd cmd; @@ -289,14 +294,12 @@ struct prestera_msg_port_attr_req { __le32 port; __le32 dev; union prestera_msg_port_param param; -} __packed __aligned(4); - +}; struct prestera_msg_port_attr_resp { struct prestera_msg_ret ret; union prestera_msg_port_param param; -} __packed __aligned(4); - +}; struct prestera_msg_port_stats_resp { struct prestera_msg_ret ret; @@ -313,6 +316,7 @@ struct prestera_msg_port_info_resp { __le32 hw_id; __le32 dev_id; __le16 fp_id; + u8 pad[2]; }; struct prestera_msg_vlan_req { @@ -320,13 +324,13 @@ struct prestera_msg_vlan_req { __le32 port; __le32 dev; __le16 vid; - u8 is_member; - u8 is_tagged; + u8 is_member; + u8 is_tagged; }; struct prestera_msg_fdb_req { struct prestera_msg_cmd cmd; - u8 dest_type; + __le32 flush_mode; union { struct { __le32 port; @@ -334,22 +338,25 @@ struct prestera_msg_fdb_req { }; __le16 lag_id; } dest; - u8 mac[ETH_ALEN]; __le16 vid; - u8 dynamic; - __le32 flush_mode; -} __packed __aligned(4); + u8 dest_type; + u8 dynamic; + u8 mac[ETH_ALEN]; + u8 __pad[2]; +}; struct prestera_msg_bridge_req { struct prestera_msg_cmd cmd; __le32 port; __le32 dev; __le16 bridge; + u8 pad[2]; }; struct prestera_msg_bridge_resp { struct prestera_msg_ret ret; __le16 bridge; + u8 pad[2]; }; struct prestera_msg_acl_action { @@ -359,11 +366,12 @@ struct prestera_msg_acl_action { struct prestera_msg_acl_match { __le32 type; + __le32 __reserved; union { struct { u8 key; u8 mask; - } __packed u8; + } u8; struct { __le16 key; __le16 mask; @@ -379,7 +387,7 @@ struct prestera_msg_acl_match { struct { u8 key[ETH_ALEN]; u8 mask[ETH_ALEN]; - } __packed mac; + } mac; } keymask; }; @@ -408,16 +416,19 @@ struct prestera_msg_acl_ruleset_bind_req { __le32 port; __le32 dev; __le16 ruleset_id; + u8 pad[2]; }; struct prestera_msg_acl_ruleset_req { struct prestera_msg_cmd cmd; __le16 id; + u8 pad[2]; }; struct prestera_msg_acl_ruleset_resp { struct prestera_msg_ret ret; __le16 id; + u8 pad[2]; }; struct prestera_msg_span_req { @@ -425,11 +436,13 @@ struct prestera_msg_span_req { __le32 port; __le32 dev; u8 id; + u8 pad[3]; }; struct prestera_msg_span_resp { struct prestera_msg_ret ret; u8 id; + u8 pad[3]; }; struct prestera_msg_stp_req { @@ -437,12 +450,14 @@ struct prestera_msg_stp_req { __le32 port; __le32 dev; __le16 vid; - u8 state; + u8 state; + u8 __pad; }; struct prestera_msg_rxtx_req { struct prestera_msg_cmd cmd; u8 use_sdma; + u8 pad[3]; }; struct prestera_msg_rxtx_resp { @@ -455,12 +470,14 @@ struct prestera_msg_lag_req { __le32 port; __le32 dev; __le16 lag_id; + u8 pad[2]; }; struct prestera_msg_cpu_code_counter_req { struct prestera_msg_cmd cmd; u8 counter_type; u8 code; + u8 pad[2]; }; struct mvsw_msg_cpu_code_counter_ret { @@ -485,21 +502,21 @@ union prestera_msg_event_fdb_param { struct prestera_msg_event_fdb { struct prestera_msg_event id; - u8 dest_type; + __le32 vid; union { __le32 port_id; __le16 lag_id; } dest; - __le32 vid; union prestera_msg_event_fdb_param param; -} __packed __aligned(4); + u8 dest_type; +}; -static inline void prestera_hw_build_tests(void) +static void prestera_hw_build_tests(void) { /* check requests */ BUILD_BUG_ON(sizeof(struct prestera_msg_common_req) != 4); BUILD_BUG_ON(sizeof(struct prestera_msg_switch_attr_req) != 16); - BUILD_BUG_ON(sizeof(struct prestera_msg_port_attr_req) != 120); + BUILD_BUG_ON(sizeof(struct prestera_msg_port_attr_req) != 144); BUILD_BUG_ON(sizeof(struct prestera_msg_port_info_req) != 8); BUILD_BUG_ON(sizeof(struct prestera_msg_vlan_req) != 16); BUILD_BUG_ON(sizeof(struct prestera_msg_fdb_req) != 28); @@ -516,7 +533,7 @@ static inline void prestera_hw_build_tests(void) /* check responses */ BUILD_BUG_ON(sizeof(struct prestera_msg_common_resp) != 8); BUILD_BUG_ON(sizeof(struct prestera_msg_switch_init_resp) != 24); - BUILD_BUG_ON(sizeof(struct prestera_msg_port_attr_resp) != 112); + BUILD_BUG_ON(sizeof(struct prestera_msg_port_attr_resp) != 136); BUILD_BUG_ON(sizeof(struct prestera_msg_port_stats_resp) != 248); BUILD_BUG_ON(sizeof(struct prestera_msg_port_info_resp) != 20); BUILD_BUG_ON(sizeof(struct prestera_msg_bridge_resp) != 12); @@ -549,9 +566,9 @@ static int __prestera_cmd_ret(struct prestera_switch *sw, if (err) return err; - if (__le32_to_cpu(ret->cmd.type) != PRESTERA_CMD_TYPE_ACK) + if (ret->cmd.type != __cpu_to_le32(PRESTERA_CMD_TYPE_ACK)) return -EBADE; - if (__le32_to_cpu(ret->status) != PRESTERA_CMD_ACK_OK) + if (ret->status != __cpu_to_le32(PRESTERA_CMD_ACK_OK)) return -EINVAL; return 0; @@ -1344,7 +1361,8 @@ int prestera_hw_port_speed_get(const struct prestera_port *port, u32 *speed) int prestera_hw_port_autoneg_restart(struct prestera_port *port) { struct prestera_msg_port_attr_req req = { - .attr = __cpu_to_le32(PRESTERA_CMD_PORT_ATTR_PHY_AUTONEG_RESTART), + .attr = + __cpu_to_le32(PRESTERA_CMD_PORT_ATTR_PHY_AUTONEG_RESTART), .port = __cpu_to_le32(port->hw_id), .dev = __cpu_to_le32(port->dev_id), }; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 625b40149fac..4369a3ffad45 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -405,7 +405,8 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) err = prestera_port_cfg_mac_write(port, &cfg_mac); if (err) { - dev_err(prestera_dev(sw), "Failed to set port(%u) mac mode\n", id); + dev_err(prestera_dev(sw), + "Failed to set port(%u) mac mode\n", id); goto err_port_init; } @@ -418,7 +419,8 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) false, 0, 0, port->cfg_phy.mdix); if (err) { - dev_err(prestera_dev(sw), "Failed to set port(%u) phy mode\n", id); + dev_err(prestera_dev(sw), + "Failed to set port(%u) phy mode\n", id); goto err_port_init; } } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index d650082496d6..f538a749ebd4 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -411,7 +411,8 @@ static int prestera_fw_cmd_send(struct prestera_fw *fw, int qid, goto cmd_exit; } - memcpy_fromio(out_msg, prestera_fw_cmdq_buf(fw, qid) + in_size, ret_size); + memcpy_fromio(out_msg, + prestera_fw_cmdq_buf(fw, qid) + in_size, ret_size); cmd_exit: prestera_fw_write(fw, PRESTERA_CMDQ_REQ_CTL_REG(qid), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index adc836b3d857..ad63dd45c8fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -289,7 +289,7 @@ mlx5_lag_create_definer(struct mlx5_lag *ldev, enum netdev_lag_hash hash, lag_definer = kzalloc(sizeof(*lag_definer), GFP_KERNEL); if (!lag_definer) - return ERR_PTR(ENOMEM); + return ERR_PTR(-ENOMEM); match_definer_mask = kvzalloc(MLX5_FLD_SZ_BYTES(match_definer, match_mask), diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index c96ac81212f7..636dfef24a6c 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1424,7 +1424,7 @@ static void mana_gd_shutdown(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); - dev_info(&pdev->dev, "Shutdown was calledd\n"); + dev_info(&pdev->dev, "Shutdown was called\n"); mana_remove(&gc->mana, true); diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index c68837a951f4..314c9c69eb0e 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -817,9 +817,7 @@ ef4_realloc_channels(struct ef4_nic *efx, u32 rxq_entries, u32 txq_entries) efx->rxq_entries = rxq_entries; efx->txq_entries = txq_entries; for (i = 0; i < efx->n_channels; i++) { - channel = efx->channel[i]; - efx->channel[i] = other_channel[i]; - other_channel[i] = channel; + swap(efx->channel[i], other_channel[i]); } /* Restart buffer table allocation */ @@ -863,9 +861,7 @@ rollback: efx->rxq_entries = old_rxq_entries; efx->txq_entries = old_txq_entries; for (i = 0; i < efx->n_channels; i++) { - channel = efx->channel[i]; - efx->channel[i] = other_channel[i]; - other_channel[i] = channel; + swap(efx->channel[i], other_channel[i]); } goto out; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 8160087ee92f..1c4ea0b1b845 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -786,8 +786,6 @@ static int tc_setup_taprio(struct stmmac_priv *priv, goto disable; if (qopt->num_entries >= dep) return -EINVAL; - if (!qopt->base_time) - return -ERANGE; if (!qopt->cycle_time) return -ERANGE; diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 0c75e0576ee1..1ef0aaef5c61 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -1299,10 +1299,8 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params) if (!ale) return ERR_PTR(-ENOMEM); - ale->p0_untag_vid_mask = - devm_kmalloc_array(params->dev, BITS_TO_LONGS(VLAN_N_VID), - sizeof(unsigned long), - GFP_KERNEL); + ale->p0_untag_vid_mask = devm_bitmap_zalloc(params->dev, VLAN_N_VID, + GFP_KERNEL); if (!ale->p0_untag_vid_mask) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 2d2dcf70563f..d55f06120ce7 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -420,8 +420,20 @@ static int emac_set_coalesce(struct net_device *ndev, u32 int_ctrl, num_interrupts = 0; u32 prescale = 0, addnl_dvdr = 1, coal_intvl = 0; - if (!coal->rx_coalesce_usecs) - return -EINVAL; + if (!coal->rx_coalesce_usecs) { + priv->coal_intvl = 0; + + switch (priv->version) { + case EMAC_VERSION_2: + emac_ctrl_write(EMAC_DM646X_CMINTCTRL, 0); + break; + default: + emac_ctrl_write(EMAC_CTRL_EWINTTCNT, 0); + break; + } + + return 0; + } coal_intvl = coal->rx_coalesce_usecs; diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 49f10053a794..bfdf89e54752 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -672,11 +672,13 @@ static void sixpack_close(struct tty_struct *tty) del_timer_sync(&sp->tx_t); del_timer_sync(&sp->resync_t); - /* Free all 6pack frame buffers. */ + unregister_netdev(sp->dev); + + /* Free all 6pack frame buffers after unreg. */ kfree(sp->rbuff); kfree(sp->xbuff); - unregister_netdev(sp->dev); + free_netdev(sp->dev); } /* Perform I/O control on an active 6pack channel. */ diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 867252a0247b..e2b332b54f06 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -792,13 +792,14 @@ static void mkiss_close(struct tty_struct *tty) */ netif_stop_queue(ax->dev); - /* Free all AX25 frame buffers. */ - kfree(ax->rbuff); - kfree(ax->xbuff); - ax->tty = NULL; unregister_netdev(ax->dev); + + /* Free all AX25 frame buffers after unreg. */ + kfree(ax->rbuff); + kfree(ax->xbuff); + free_netdev(ax->dev); } diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index a4de3d2081c5..bc50224d43dd 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -28,6 +28,11 @@ #define LAN87XX_MASK_LINK_UP (0x0004) #define LAN87XX_MASK_LINK_DOWN (0x0002) +/* MISC Control 1 Register */ +#define LAN87XX_CTRL_1 (0x11) +#define LAN87XX_MASK_RGMII_TXC_DLY_EN (0x4000) +#define LAN87XX_MASK_RGMII_RXC_DLY_EN (0x2000) + /* phyaccess nested types */ #define PHYACC_ATTR_MODE_READ 0 #define PHYACC_ATTR_MODE_WRITE 1 @@ -112,6 +117,43 @@ static int access_ereg_modify_changed(struct phy_device *phydev, return rc; } +static int lan87xx_config_rgmii_delay(struct phy_device *phydev) +{ + int rc; + + if (!phy_interface_is_rgmii(phydev)) + return 0; + + rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, + PHYACC_ATTR_BANK_MISC, LAN87XX_CTRL_1, 0); + if (rc < 0) + return rc; + + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + rc &= ~LAN87XX_MASK_RGMII_TXC_DLY_EN; + rc &= ~LAN87XX_MASK_RGMII_RXC_DLY_EN; + break; + case PHY_INTERFACE_MODE_RGMII_ID: + rc |= LAN87XX_MASK_RGMII_TXC_DLY_EN; + rc |= LAN87XX_MASK_RGMII_RXC_DLY_EN; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + rc &= ~LAN87XX_MASK_RGMII_TXC_DLY_EN; + rc |= LAN87XX_MASK_RGMII_RXC_DLY_EN; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + rc |= LAN87XX_MASK_RGMII_TXC_DLY_EN; + rc &= ~LAN87XX_MASK_RGMII_RXC_DLY_EN; + break; + default: + return 0; + } + + return access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, + PHYACC_ATTR_BANK_MISC, LAN87XX_CTRL_1, rc); +} + static int lan87xx_phy_init(struct phy_device *phydev) { static const struct access_ereg_val init[] = { @@ -185,7 +227,7 @@ static int lan87xx_phy_init(struct phy_device *phydev) return rc; } - return 0; + return lan87xx_config_rgmii_delay(phydev); } static int lan87xx_phy_config_intr(struct phy_device *phydev) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index a3bfb156c83d..beb2b66da132 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -815,7 +815,12 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; /* Restart the PHY */ - _phy_start_aneg(phydev); + if (phy_is_started(phydev)) { + phydev->state = PHY_UP; + phy_trigger_machine(phydev); + } else { + _phy_start_aneg(phydev); + } mutex_unlock(&phydev->lock); return 0; diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c index 291fa449993f..4daac5fda073 100644 --- a/drivers/net/sungem_phy.c +++ b/drivers/net/sungem_phy.c @@ -409,7 +409,7 @@ static int genmii_read_link(struct mii_phy *phy) * though magic-aneg shouldn't prevent this case from occurring */ - return 0; + return 0; } static int generic_suspend(struct mii_phy* phy) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index b885a6570235..825e8e5ffb2a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -394,12 +394,10 @@ void ipc_imem_sys_devlink_close(struct iosm_devlink *ipc_devlink) int boot_check_timeout = BOOT_CHECK_DEFAULT_TIMEOUT; enum ipc_mem_exec_stage exec_stage; struct ipc_mem_channel *channel; - enum ipc_phase curr_phase; int status = 0; u32 tail = 0; channel = ipc_imem->ipc_devlink->devlink_sio.channel; - curr_phase = ipc_imem->phase; /* Increase the total wait time to boot_check_timeout */ do { exec_stage = ipc_mmio_get_exec_stage(ipc_imem->mmio); diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index 787bcbd290f7..a491db46e3bd 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -2216,7 +2216,7 @@ static int pn533_fill_fragment_skbs(struct pn533 *dev, struct sk_buff *skb) frag = pn533_alloc_skb(dev, frag_size); if (!frag) { skb_queue_purge(&dev->fragment_skb); - break; + return -ENOMEM; } if (!dev->tgt_mode) { @@ -2285,7 +2285,7 @@ static int pn533_transceive(struct nfc_dev *nfc_dev, /* jumbo frame ? */ if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) { rc = pn533_fill_fragment_skbs(dev, skb); - if (rc <= 0) + if (rc < 0) goto error; skb = skb_dequeue(&dev->fragment_skb); @@ -2353,7 +2353,7 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb) /* let's split in multiple chunks if size's too big */ if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) { rc = pn533_fill_fragment_skbs(dev, skb); - if (rc <= 0) + if (rc < 0) goto error; /* get the first skb */ diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 16ceb763594f..d7db1a0e6be1 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -624,7 +624,7 @@ static void port100_recv_response(struct urb *urb) break; /* success */ case -ECONNRESET: case -ENOENT: - nfc_err(&dev->interface->dev, + nfc_dbg(&dev->interface->dev, "The urb has been canceled (status %d)\n", urb->status); goto sched_wq; case -ESHUTDOWN: @@ -678,7 +678,7 @@ static void port100_recv_ack(struct urb *urb) break; /* success */ case -ECONNRESET: case -ENOENT: - nfc_err(&dev->interface->dev, + nfc_dbg(&dev->interface->dev, "The urb has been stopped (status %d)\n", urb->status); goto sched_wq; case -ESHUTDOWN: @@ -942,7 +942,7 @@ static void port100_send_complete(struct urb *urb) break; /* success */ case -ECONNRESET: case -ENOENT: - nfc_err(&dev->interface->dev, + nfc_dbg(&dev->interface->dev, "The urb has been stopped (status %d)\n", urb->status); break; case -ESHUTDOWN: diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 37fc03058556..fe7ece1534e1 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -327,6 +327,49 @@ static const struct dax_operations pmem_dax_ops = { .zero_page_range = pmem_dax_zero_page_range, }; +static ssize_t write_cache_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pmem_device *pmem = dev_to_disk(dev)->private_data; + + return sprintf(buf, "%d\n", !!dax_write_cache_enabled(pmem->dax_dev)); +} + +static ssize_t write_cache_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct pmem_device *pmem = dev_to_disk(dev)->private_data; + bool write_cache; + int rc; + + rc = strtobool(buf, &write_cache); + if (rc) + return rc; + dax_write_cache(pmem->dax_dev, write_cache); + return len; +} +static DEVICE_ATTR_RW(write_cache); + +static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n) +{ +#ifndef CONFIG_ARCH_HAS_PMEM_API + if (a == &dev_attr_write_cache.attr) + return 0; +#endif + return a->mode; +} + +static struct attribute *dax_attributes[] = { + &dev_attr_write_cache.attr, + NULL, +}; + +static const struct attribute_group dax_attribute_group = { + .name = "dax", + .attrs = dax_attributes, + .is_visible = dax_visible, +}; + static const struct attribute_group *pmem_attribute_groups[] = { &dax_attribute_group, NULL, diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 04b4691a8aac..3057beabd370 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2348,12 +2348,12 @@ static void _opp_detach_genpd(struct opp_table *opp_table) * "required-opps" are added in DT. */ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, - const char **names, struct device ***virt_devs) + const char * const *names, struct device ***virt_devs) { struct opp_table *opp_table; struct device *virt_dev; int index = 0, ret = -EINVAL; - const char **name = names; + const char * const *name = names; opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) @@ -2457,7 +2457,7 @@ static void devm_pm_opp_detach_genpd(void *data) * * Return: 0 on success and errorno otherwise. */ -int devm_pm_opp_attach_genpd(struct device *dev, const char **names, +int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs) { struct opp_table *opp_table; diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 2a97c6535c4c..2f40afa4e65c 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -170,7 +170,7 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, } count = of_count_phandle_with_args(np, "required-opps", NULL); - if (!count) + if (count <= 0) goto put_np; required_opp_tables = kcalloc(count, sizeof(*required_opp_tables), @@ -921,7 +921,7 @@ free_required_opps: free_opp: _opp_free(new_opp); - return ERR_PTR(ret); + return ret ? ERR_PTR(ret) : NULL; } /* Initializes OPP tables based on new bindings */ @@ -1081,6 +1081,17 @@ static void devm_pm_opp_of_table_release(void *data) dev_pm_opp_of_remove_table(data); } +static int _devm_of_add_table_indexed(struct device *dev, int index, bool getclk) +{ + int ret; + + ret = _of_add_table_indexed(dev, index, getclk); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_pm_opp_of_table_release, dev); +} + /** * devm_pm_opp_of_add_table() - Initialize opp table from device tree * @dev: device pointer used to lookup OPP table. @@ -1102,13 +1113,7 @@ static void devm_pm_opp_of_table_release(void *data) */ int devm_pm_opp_of_add_table(struct device *dev) { - int ret; - - ret = dev_pm_opp_of_add_table(dev); - if (ret) - return ret; - - return devm_add_action_or_reset(dev, devm_pm_opp_of_table_release, dev); + return _devm_of_add_table_indexed(dev, 0, true); } EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table); @@ -1152,6 +1157,19 @@ int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed); /** + * devm_pm_opp_of_add_table_indexed() - Initialize indexed opp table from device tree + * @dev: device pointer used to lookup OPP table. + * @index: Index number. + * + * This is a resource-managed variant of dev_pm_opp_of_add_table_indexed(). + */ +int devm_pm_opp_of_add_table_indexed(struct device *dev, int index) +{ + return _devm_of_add_table_indexed(dev, index, true); +} +EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table_indexed); + +/** * dev_pm_opp_of_add_table_noclk() - Initialize indexed opp table from device * tree without getting clk for device. * @dev: device pointer used to lookup OPP table. @@ -1169,6 +1187,20 @@ int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) } EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_noclk); +/** + * devm_pm_opp_of_add_table_noclk() - Initialize indexed opp table from device + * tree without getting clk for device. + * @dev: device pointer used to lookup OPP table. + * @index: Index number. + * + * This is a resource-managed variant of dev_pm_opp_of_add_table_noclk(). + */ +int devm_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return _devm_of_add_table_indexed(dev, index, false); +} +EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table_noclk); + /* CPU device specific helpers */ /** diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index e917bb3652bb..93b141110537 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -270,7 +270,8 @@ config VMD config PCIE_BRCMSTB tristate "Broadcom Brcmstb PCIe host controller" - depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCM4908 || COMPILE_TEST + depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCM4908 || \ + BMIPS_GENERIC || COMPILE_TEST depends on OF depends on PCI_MSI_IRQ_DOMAIN default ARCH_BRCMSTB diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index dcefdb42ac46..a89b7de72dcf 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -57,6 +57,29 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) return zpci_deconfigure_device(zdev); } +static int reset_slot(struct hotplug_slot *hotplug_slot, bool probe) +{ + struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, + hotplug_slot); + + if (zdev->state != ZPCI_FN_STATE_CONFIGURED) + return -EIO; + /* + * We can't take the zdev->lock as reset_slot may be called during + * probing and/or device removal which already happens under the + * zdev->lock. Instead the user should use the higher level + * pci_reset_function() or pci_bus_reset() which hold the PCI device + * lock preventing concurrent removal. If not using these functions + * holding the PCI device lock is required. + */ + + /* As long as the function is configured we can reset */ + if (probe) + return 0; + + return zpci_hot_reset_device(zdev); +} + static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, @@ -76,6 +99,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) static const struct hotplug_slot_ops s390_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, + .reset_slot = reset_slot, .get_power_status = get_power_status, .get_adapter_status = get_adapter_status, }; diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 1d7a7c5b5307..0267977c9f17 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -164,15 +164,13 @@ static ssize_t sriov_vf_total_msix_show(struct device *dev, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); - struct pci_driver *pdrv; u32 vf_total_msix = 0; device_lock(dev); - pdrv = to_pci_driver(dev->driver); - if (!pdrv || !pdrv->sriov_get_vf_total_msix) + if (!pdev->driver || !pdev->driver->sriov_get_vf_total_msix) goto unlock; - vf_total_msix = pdrv->sriov_get_vf_total_msix(pdev); + vf_total_msix = pdev->driver->sriov_get_vf_total_msix(pdev); unlock: device_unlock(dev); return sysfs_emit(buf, "%u\n", vf_total_msix); @@ -185,7 +183,6 @@ static ssize_t sriov_vf_msix_count_store(struct device *dev, { struct pci_dev *vf_dev = to_pci_dev(dev); struct pci_dev *pdev = pci_physfn(vf_dev); - struct pci_driver *pdrv; int val, ret = 0; if (kstrtoint(buf, 0, &val) < 0) @@ -195,14 +192,13 @@ static ssize_t sriov_vf_msix_count_store(struct device *dev, return -EINVAL; device_lock(&pdev->dev); - pdrv = to_pci_driver(dev->driver); - if (!pdrv || !pdrv->sriov_set_msix_vec_count) { + if (!pdev->driver || !pdev->driver->sriov_set_msix_vec_count) { ret = -EOPNOTSUPP; goto err_pdev; } device_lock(&vf_dev->dev); - if (to_pci_driver(vf_dev->dev.driver)) { + if (vf_dev->driver) { /* * A driver is already attached to this VF and has configured * itself based on the current MSI-X vector count. Changing @@ -212,7 +208,7 @@ static ssize_t sriov_vf_msix_count_store(struct device *dev, goto err_dev; } - ret = pdrv->sriov_set_msix_vec_count(vf_dev, val); + ret = pdev->driver->sriov_set_msix_vec_count(vf_dev, val); err_dev: device_unlock(&vf_dev->dev); @@ -379,7 +375,6 @@ static ssize_t sriov_numvfs_store(struct device *dev, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - struct pci_driver *pdrv; int ret = 0; u16 num_vfs; @@ -395,15 +390,14 @@ static ssize_t sriov_numvfs_store(struct device *dev, goto exit; /* is PF driver loaded */ - pdrv = to_pci_driver(dev->driver); - if (!pdrv) { + if (!pdev->driver) { pci_info(pdev, "no driver bound to device; cannot configure SR-IOV\n"); ret = -ENOENT; goto exit; } /* is PF driver loaded w/callback */ - if (!pdrv->sriov_configure) { + if (!pdev->driver->sriov_configure) { pci_info(pdev, "driver does not support SR-IOV configuration via sysfs\n"); ret = -ENOENT; goto exit; @@ -411,7 +405,7 @@ static ssize_t sriov_numvfs_store(struct device *dev, if (num_vfs == 0) { /* disable VFs */ - ret = pdrv->sriov_configure(pdev, 0); + ret = pdev->driver->sriov_configure(pdev, 0); goto exit; } @@ -423,7 +417,7 @@ static ssize_t sriov_numvfs_store(struct device *dev, goto exit; } - ret = pdrv->sriov_configure(pdev, num_vfs); + ret = pdev->driver->sriov_configure(pdev, num_vfs); if (ret < 0) goto exit; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 1d98c974381c..588588cfda48 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -319,10 +319,12 @@ static long local_pci_probe(void *_ddi) * its remove routine. */ pm_runtime_get_sync(dev); + pci_dev->driver = pci_drv; rc = pci_drv->probe(pci_dev, ddi->id); if (!rc) return rc; if (rc < 0) { + pci_dev->driver = NULL; pm_runtime_put_sync(dev); return rc; } @@ -388,6 +390,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, * @pci_dev: PCI device being probed * * returns 0 on success, else error. + * side-effect: pci_dev->driver is set to drv when drv claims pci_dev. */ static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev) { @@ -454,7 +457,7 @@ static int pci_device_probe(struct device *dev) static void pci_device_remove(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = to_pci_driver(dev->driver); + struct pci_driver *drv = pci_dev->driver; if (drv->remove) { pm_runtime_get_sync(dev); @@ -462,6 +465,7 @@ static void pci_device_remove(struct device *dev) pm_runtime_put_noidle(dev); } pcibios_free_irq(pci_dev); + pci_dev->driver = NULL; pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ @@ -489,7 +493,7 @@ static void pci_device_remove(struct device *dev) static void pci_device_shutdown(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = to_pci_driver(dev->driver); + struct pci_driver *drv = pci_dev->driver; pm_runtime_resume(dev); @@ -585,7 +589,7 @@ static int pci_pm_reenable_device(struct pci_dev *pci_dev) static int pci_legacy_suspend(struct device *dev, pm_message_t state) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = to_pci_driver(dev->driver); + struct pci_driver *drv = pci_dev->driver; if (drv && drv->suspend) { pci_power_t prev = pci_dev->current_state; @@ -626,7 +630,7 @@ static int pci_legacy_suspend_late(struct device *dev, pm_message_t state) static int pci_legacy_resume(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = to_pci_driver(dev->driver); + struct pci_driver *drv = pci_dev->driver; pci_fixup_device(pci_fixup_resume, pci_dev); @@ -645,7 +649,7 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev) static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) { - struct pci_driver *drv = to_pci_driver(pci_dev->dev.driver); + struct pci_driver *drv = pci_dev->driver; bool ret = drv && (drv->suspend || drv->resume); /* @@ -1238,11 +1242,11 @@ static int pci_pm_runtime_suspend(struct device *dev) int error; /* - * If the device has no driver, we leave it in D0, but it may go to - * D3cold when the bridge above it runtime suspends. Save its - * config space in case that happens. + * If pci_dev->driver is not set (unbound), we leave the device in D0, + * but it may go to D3cold when the bridge above it runtime suspends. + * Save its config space in case that happens. */ - if (!to_pci_driver(dev->driver)) { + if (!pci_dev->driver) { pci_save_state(pci_dev); return 0; } @@ -1299,7 +1303,7 @@ static int pci_pm_runtime_resume(struct device *dev) */ pci_restore_standard_config(pci_dev); - if (!to_pci_driver(dev->driver)) + if (!pci_dev->driver) return 0; pci_fixup_device(pci_fixup_resume_early, pci_dev); @@ -1318,13 +1322,14 @@ static int pci_pm_runtime_resume(struct device *dev) static int pci_pm_runtime_idle(struct device *dev) { + struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; /* - * If the device has no driver, it should always remain in D0 - * regardless of the runtime PM status + * If pci_dev->driver is not set (unbound), the device should + * always remain in D0 regardless of the runtime PM status */ - if (!to_pci_driver(dev->driver)) + if (!pci_dev->driver) return 0; if (!pm) @@ -1431,10 +1436,8 @@ static struct pci_driver pci_compat_driver = { */ struct pci_driver *pci_dev_driver(const struct pci_dev *dev) { - struct pci_driver *drv = to_pci_driver(dev->dev.driver); - - if (drv) - return drv; + if (dev->driver) + return dev->driver; else { int i; for (i = 0; i <= PCI_ROM_RESOURCE; i++) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index f2cd11130737..3d2fb394986a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5106,12 +5106,13 @@ static int pci_reset_bus_function(struct pci_dev *dev, bool probe) return pci_parent_bus_reset(dev, probe); } -static void pci_dev_lock(struct pci_dev *dev) +void pci_dev_lock(struct pci_dev *dev) { pci_cfg_access_lock(dev); /* block PM suspend, driver probe, etc. */ device_lock(&dev->dev); } +EXPORT_SYMBOL_GPL(pci_dev_lock); /* Return 1 on successful lock, 0 on contention */ int pci_dev_trylock(struct pci_dev *dev) @@ -5135,14 +5136,13 @@ EXPORT_SYMBOL_GPL(pci_dev_unlock); static void pci_dev_save_and_disable(struct pci_dev *dev) { - struct pci_driver *drv = to_pci_driver(dev->dev.driver); const struct pci_error_handlers *err_handler = - drv ? drv->err_handler : NULL; + dev->driver ? dev->driver->err_handler : NULL; /* - * drv->err_handler->reset_prepare() is protected against races - * with ->remove() by the device lock, which must be held by the - * caller. + * dev->driver->err_handler->reset_prepare() is protected against + * races with ->remove() by the device lock, which must be held by + * the caller. */ if (err_handler && err_handler->reset_prepare) err_handler->reset_prepare(dev); @@ -5167,15 +5167,15 @@ static void pci_dev_save_and_disable(struct pci_dev *dev) static void pci_dev_restore(struct pci_dev *dev) { - struct pci_driver *drv = to_pci_driver(dev->dev.driver); const struct pci_error_handlers *err_handler = - drv ? drv->err_handler : NULL; + dev->driver ? dev->driver->err_handler : NULL; pci_restore_state(dev); /* - * drv->err_handler->reset_done() is protected against races with - * ->remove() by the device lock, which must be held by the caller. + * dev->driver->err_handler->reset_done() is protected against + * races with ->remove() by the device lock, which must be held by + * the caller. */ if (err_handler && err_handler->reset_done) err_handler->reset_done(dev); diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 356b9317297e..0c5a143025af 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -54,7 +54,7 @@ static int report_error_detected(struct pci_dev *dev, const struct pci_error_handlers *err_handler; device_lock(&dev->dev); - pdrv = to_pci_driver(dev->dev.driver); + pdrv = dev->driver; if (!pci_dev_set_io_state(dev, state) || !pdrv || !pdrv->err_handler || @@ -98,7 +98,7 @@ static int report_mmio_enabled(struct pci_dev *dev, void *data) const struct pci_error_handlers *err_handler; device_lock(&dev->dev); - pdrv = to_pci_driver(dev->dev.driver); + pdrv = dev->driver; if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->mmio_enabled) @@ -119,7 +119,7 @@ static int report_slot_reset(struct pci_dev *dev, void *data) const struct pci_error_handlers *err_handler; device_lock(&dev->dev); - pdrv = to_pci_driver(dev->dev.driver); + pdrv = dev->driver; if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->slot_reset) @@ -139,7 +139,7 @@ static int report_resume(struct pci_dev *dev, void *data) const struct pci_error_handlers *err_handler; device_lock(&dev->dev); - pdrv = to_pci_driver(dev->dev.driver); + pdrv = dev->driver; if (!pci_dev_set_io_state(dev, pci_channel_io_normal) || !pdrv || !pdrv->err_handler || diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 1f7861944044..d6306d2a096f 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -156,7 +156,7 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_CMD, 1, &sum); if (ec_response_timed_out()) { - dev_warn(ec->dev, "EC responsed timed out\n"); + dev_warn(ec->dev, "EC response timed out\n"); ret = -EIO; goto done; } @@ -238,7 +238,7 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_CMD, 1, &sum); if (ec_response_timed_out()) { - dev_warn(ec->dev, "EC responsed timed out\n"); + dev_warn(ec->dev, "EC response timed out\n"); ret = -EIO; goto done; } diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index a7404d69b2d3..c4caf2e2de82 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -808,38 +808,27 @@ EXPORT_SYMBOL(cros_ec_get_host_event); * * Call this function to test whether the ChromeOS EC supports a feature. * - * Return: 1 if supported, 0 if not + * Return: true if supported, false if not (or if an error was encountered). */ -int cros_ec_check_features(struct cros_ec_dev *ec, int feature) +bool cros_ec_check_features(struct cros_ec_dev *ec, int feature) { - struct cros_ec_command *msg; + struct ec_response_get_features *features = &ec->features; int ret; - if (ec->features[0] == -1U && ec->features[1] == -1U) { + if (features->flags[0] == -1U && features->flags[1] == -1U) { /* features bitmap not read yet */ - msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; - msg->insize = sizeof(ec->features); - - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + ret = cros_ec_command(ec->ec_dev, 0, EC_CMD_GET_FEATURES + ec->cmd_offset, + NULL, 0, features, sizeof(*features)); if (ret < 0) { - dev_warn(ec->dev, "cannot get EC features: %d/%d\n", - ret, msg->result); - memset(ec->features, 0, sizeof(ec->features)); - } else { - memcpy(ec->features, msg->data, sizeof(ec->features)); + dev_warn(ec->dev, "cannot get EC features: %d\n", ret); + memset(features, 0, sizeof(*features)); } dev_dbg(ec->dev, "EC features %08x %08x\n", - ec->features[0], ec->features[1]); - - kfree(msg); + features->flags[0], features->flags[1]); } - return ec->features[feature / 32] & EC_FEATURE_MASK_0(feature); + return !!(features->flags[feature / 32] & EC_FEATURE_MASK_0(feature)); } EXPORT_SYMBOL_GPL(cros_ec_check_features); @@ -908,3 +897,51 @@ int cros_ec_get_sensor_count(struct cros_ec_dev *ec) return sensor_count; } EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); + +/** + * cros_ec_command - Send a command to the EC. + * + * @ec_dev: EC device + * @version: EC command version + * @command: EC command + * @outdata: EC command output data + * @outsize: Size of outdata + * @indata: EC command input data + * @insize: Size of indata + * + * Return: >= 0 on success, negative error number on failure. + */ +int cros_ec_command(struct cros_ec_device *ec_dev, + unsigned int version, + int command, + void *outdata, + int outsize, + void *indata, + int insize) +{ + struct cros_ec_command *msg; + int ret; + + msg = kzalloc(sizeof(*msg) + max(insize, outsize), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = version; + msg->command = command; + msg->outsize = outsize; + msg->insize = insize; + + if (outsize) + memcpy(msg->data, outdata, outsize); + + ret = cros_ec_cmd_xfer_status(ec_dev, msg); + if (ret < 0) + goto error; + + if (insize) + memcpy(indata, msg->data, insize); +error: + kfree(msg); + return ret; +} +EXPORT_SYMBOL_GPL(cros_ec_command); diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c index 9c4af76a9956..31fb8bdaad5a 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub.c +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -224,8 +224,7 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) */ static int cros_ec_sensorhub_suspend(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct cros_ec_sensorhub *sensorhub = platform_get_drvdata(pdev); + struct cros_ec_sensorhub *sensorhub = dev_get_drvdata(dev); struct cros_ec_dev *ec = sensorhub->ec; if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) @@ -235,8 +234,7 @@ static int cros_ec_sensorhub_suspend(struct device *dev) static int cros_ec_sensorhub_resume(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct cros_ec_sensorhub *sensorhub = platform_get_drvdata(pdev); + struct cros_ec_sensorhub *sensorhub = dev_get_drvdata(dev); struct cros_ec_dev *ec = sensorhub->ec; if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 262a891eded3..5de0bfb0bc4d 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -379,37 +379,6 @@ unregister_ports: return ret; } -static int cros_typec_ec_command(struct cros_typec_data *typec, - unsigned int version, - unsigned int command, - void *outdata, - unsigned int outsize, - void *indata, - unsigned int insize) -{ - struct cros_ec_command *msg; - int ret; - - msg = kzalloc(sizeof(*msg) + max(outsize, insize), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->version = version; - msg->command = command; - msg->outsize = outsize; - msg->insize = insize; - - if (outsize) - memcpy(msg->data, outdata, outsize); - - ret = cros_ec_cmd_xfer_status(typec->ec, msg); - if (ret >= 0 && insize) - memcpy(indata, msg->data, insize); - - kfree(msg); - return ret; -} - static int cros_typec_usb_safe_state(struct cros_typec_port *port) { port->state.mode = TYPEC_STATE_SAFE; @@ -596,8 +565,8 @@ mux_ack: /* Sending Acknowledgment to EC */ mux_ack.port = port_num; - if (cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_MUX_ACK, &mux_ack, - sizeof(mux_ack), NULL, 0) < 0) + if (cros_ec_command(typec->ec, 0, EC_CMD_USB_PD_MUX_ACK, &mux_ack, + sizeof(mux_ack), NULL, 0) < 0) dev_warn(typec->dev, "Failed to send Mux ACK to EC for port: %d\n", port_num); @@ -668,8 +637,8 @@ static int cros_typec_get_mux_info(struct cros_typec_data *typec, int port_num, .port = port_num, }; - return cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_MUX_INFO, &req, - sizeof(req), resp, sizeof(*resp)); + return cros_ec_command(typec->ec, 0, EC_CMD_USB_PD_MUX_INFO, &req, + sizeof(req), resp, sizeof(*resp)); } /* @@ -776,8 +745,8 @@ static int cros_typec_handle_sop_prime_disc(struct cros_typec_data *typec, int p int ret = 0; memset(disc, 0, EC_PROTO2_MAX_RESPONSE_SIZE); - ret = cros_typec_ec_command(typec, 0, EC_CMD_TYPEC_DISCOVERY, &req, sizeof(req), - disc, EC_PROTO2_MAX_RESPONSE_SIZE); + ret = cros_ec_command(typec->ec, 0, EC_CMD_TYPEC_DISCOVERY, &req, sizeof(req), + disc, EC_PROTO2_MAX_RESPONSE_SIZE); if (ret < 0) { dev_err(typec->dev, "Failed to get SOP' discovery data for port: %d\n", port_num); goto sop_prime_disc_exit; @@ -859,8 +828,8 @@ static int cros_typec_handle_sop_disc(struct cros_typec_data *typec, int port_nu typec_partner_set_pd_revision(port->partner, pd_revision); memset(sop_disc, 0, EC_PROTO2_MAX_RESPONSE_SIZE); - ret = cros_typec_ec_command(typec, 0, EC_CMD_TYPEC_DISCOVERY, &req, sizeof(req), - sop_disc, EC_PROTO2_MAX_RESPONSE_SIZE); + ret = cros_ec_command(typec->ec, 0, EC_CMD_TYPEC_DISCOVERY, &req, sizeof(req), + sop_disc, EC_PROTO2_MAX_RESPONSE_SIZE); if (ret < 0) { dev_err(typec->dev, "Failed to get SOP discovery data for port: %d\n", port_num); goto disc_exit; @@ -892,8 +861,8 @@ static int cros_typec_send_clear_event(struct cros_typec_data *typec, int port_n .clear_events_mask = events_mask, }; - return cros_typec_ec_command(typec, 0, EC_CMD_TYPEC_CONTROL, &req, - sizeof(req), NULL, 0); + return cros_ec_command(typec->ec, 0, EC_CMD_TYPEC_CONTROL, &req, + sizeof(req), NULL, 0); } static void cros_typec_handle_status(struct cros_typec_data *typec, int port_num) @@ -904,8 +873,8 @@ static void cros_typec_handle_status(struct cros_typec_data *typec, int port_num }; int ret; - ret = cros_typec_ec_command(typec, 0, EC_CMD_TYPEC_STATUS, &req, sizeof(req), - &resp, sizeof(resp)); + ret = cros_ec_command(typec->ec, 0, EC_CMD_TYPEC_STATUS, &req, sizeof(req), + &resp, sizeof(resp)); if (ret < 0) { dev_warn(typec->dev, "EC_CMD_TYPEC_STATUS failed for port: %d\n", port_num); return; @@ -983,9 +952,9 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) req.mux = USB_PD_CTRL_MUX_NO_CHANGE; req.swap = USB_PD_CTRL_SWAP_NONE; - ret = cros_typec_ec_command(typec, typec->pd_ctrl_ver, - EC_CMD_USB_PD_CONTROL, &req, sizeof(req), - &resp, sizeof(resp)); + ret = cros_ec_command(typec->ec, typec->pd_ctrl_ver, + EC_CMD_USB_PD_CONTROL, &req, sizeof(req), + &resp, sizeof(resp)); if (ret < 0) return ret; @@ -1035,8 +1004,8 @@ static int cros_typec_get_cmd_version(struct cros_typec_data *typec) /* We're interested in the PD control command version. */ req_v1.cmd = EC_CMD_USB_PD_CONTROL; - ret = cros_typec_ec_command(typec, 1, EC_CMD_GET_CMD_VERSIONS, - &req_v1, sizeof(req_v1), &resp, + ret = cros_ec_command(typec->ec, 1, EC_CMD_GET_CMD_VERSIONS, + &req_v1, sizeof(req_v1), &resp, sizeof(resp)); if (ret < 0) return ret; @@ -1116,12 +1085,11 @@ static int cros_typec_probe(struct platform_device *pdev) } ec_dev = dev_get_drvdata(&typec->ec->ec->dev); - typec->typec_cmd_supported = !!cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_CMD); - typec->needs_mux_ack = !!cros_ec_check_features(ec_dev, - EC_FEATURE_TYPEC_MUX_REQUIRE_AP_ACK); + typec->typec_cmd_supported = cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_CMD); + typec->needs_mux_ack = cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_MUX_REQUIRE_AP_ACK); - ret = cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_PORTS, NULL, 0, - &resp, sizeof(resp)); + ret = cros_ec_command(typec->ec, 0, EC_CMD_USB_PD_PORTS, NULL, 0, + &resp, sizeof(resp)); if (ret < 0) return ret; diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c index 48a6617aa12f..91ce6be91aac 100644 --- a/drivers/platform/chrome/cros_usbpd_notify.c +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -53,50 +53,6 @@ void cros_usbpd_unregister_notify(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(cros_usbpd_unregister_notify); -/** - * cros_ec_pd_command - Send a command to the EC. - * - * @ec_dev: EC device - * @command: EC command - * @outdata: EC command output data - * @outsize: Size of outdata - * @indata: EC command input data - * @insize: Size of indata - * - * Return: >= 0 on success, negative error number on failure. - */ -static int cros_ec_pd_command(struct cros_ec_device *ec_dev, - int command, - uint8_t *outdata, - int outsize, - uint8_t *indata, - int insize) -{ - struct cros_ec_command *msg; - int ret; - - msg = kzalloc(sizeof(*msg) + max(insize, outsize), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->command = command; - msg->outsize = outsize; - msg->insize = insize; - - if (outsize) - memcpy(msg->data, outdata, outsize); - - ret = cros_ec_cmd_xfer_status(ec_dev, msg); - if (ret < 0) - goto error; - - if (insize) - memcpy(indata, msg->data, insize); -error: - kfree(msg); - return ret; -} - static void cros_usbpd_get_event_and_notify(struct device *dev, struct cros_ec_device *ec_dev) { @@ -115,10 +71,8 @@ static void cros_usbpd_get_event_and_notify(struct device *dev, } /* Check for PD host events on EC. */ - ret = cros_ec_pd_command(ec_dev, EC_CMD_PD_HOST_EVENT_STATUS, - NULL, 0, - (uint8_t *)&host_event_status, - sizeof(host_event_status)); + ret = cros_ec_command(ec_dev, 0, EC_CMD_PD_HOST_EVENT_STATUS, + NULL, 0, &host_event_status, sizeof(host_event_status)); if (ret < 0) { dev_warn(dev, "Can't get host event status (err: %d)\n", ret); goto send_notify; diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig index aa29841bbb79..21e3b05a5153 100644 --- a/drivers/pwm/Kconfig +++ b/drivers/pwm/Kconfig @@ -476,7 +476,9 @@ config PWM_SAMSUNG depends on PLAT_SAMSUNG || ARCH_S5PV210 || ARCH_EXYNOS || COMPILE_TEST depends on HAS_IOMEM help - Generic PWM framework driver for Samsung. + Generic PWM framework driver for Samsung S3C24xx, S3C64xx, S5Pv210 + and Exynos SoCs. + Choose Y here only if you build for such Samsung SoC. To compile this driver as a module, choose M here: the module will be called pwm-samsung. diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 4527f09a5c50..fb04a439462c 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -532,6 +532,15 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) struct pwm_chip *chip; int err; + /* + * Some lowlevel driver's implementations of .apply() make use of + * mutexes, also with some drivers only returning when the new + * configuration is active calling pwm_apply_state() from atomic context + * is a bad idea. So make it explicit that calling this function might + * sleep. + */ + might_sleep(); + if (!pwm || !state || !state->period || state->duty_cycle > state->period) return -EINVAL; diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c index e748604403cc..98b34ea9f38e 100644 --- a/drivers/pwm/pwm-atmel.c +++ b/drivers/pwm/pwm-atmel.c @@ -24,7 +24,6 @@ #include <linux/err.h> #include <linux/io.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/platform_device.h> diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c index dd94c4312a0c..0a4ff55fad04 100644 --- a/drivers/pwm/pwm-samsung.c +++ b/drivers/pwm/pwm-samsung.c @@ -117,6 +117,20 @@ static inline unsigned int to_tcon_channel(unsigned int channel) return (channel == 0) ? 0 : (channel + 1); } +static void __pwm_samsung_manual_update(struct samsung_pwm_chip *chip, + struct pwm_device *pwm) +{ + unsigned int tcon_chan = to_tcon_channel(pwm->hwpwm); + u32 tcon; + + tcon = readl(chip->base + REG_TCON); + tcon |= TCON_MANUALUPDATE(tcon_chan); + writel(tcon, chip->base + REG_TCON); + + tcon &= ~TCON_MANUALUPDATE(tcon_chan); + writel(tcon, chip->base + REG_TCON); +} + static void pwm_samsung_set_divisor(struct samsung_pwm_chip *pwm, unsigned int channel, u8 divisor) { @@ -276,6 +290,13 @@ static void pwm_samsung_disable(struct pwm_chip *chip, struct pwm_device *pwm) tcon &= ~TCON_AUTORELOAD(tcon_chan); writel(tcon, our_chip->base + REG_TCON); + /* + * In case the PWM is at 100% duty cycle, force a manual + * update to prevent the signal from staying high. + */ + if (readl(our_chip->base + REG_TCMPB(pwm->hwpwm)) == (u32)-1U) + __pwm_samsung_manual_update(our_chip, pwm); + our_chip->disabled_mask |= BIT(pwm->hwpwm); spin_unlock_irqrestore(&samsung_pwm_lock, flags); @@ -284,18 +305,11 @@ static void pwm_samsung_disable(struct pwm_chip *chip, struct pwm_device *pwm) static void pwm_samsung_manual_update(struct samsung_pwm_chip *chip, struct pwm_device *pwm) { - unsigned int tcon_chan = to_tcon_channel(pwm->hwpwm); - u32 tcon; unsigned long flags; spin_lock_irqsave(&samsung_pwm_lock, flags); - tcon = readl(chip->base + REG_TCON); - tcon |= TCON_MANUALUPDATE(tcon_chan); - writel(tcon, chip->base + REG_TCON); - - tcon &= ~TCON_MANUALUPDATE(tcon_chan); - writel(tcon, chip->base + REG_TCON); + __pwm_samsung_manual_update(chip, pwm); spin_unlock_irqrestore(&samsung_pwm_lock, flags); } diff --git a/drivers/pwm/pwm-visconti.c b/drivers/pwm/pwm-visconti.c index af4e37d3e3a6..927c4cbb1daf 100644 --- a/drivers/pwm/pwm-visconti.c +++ b/drivers/pwm/pwm-visconti.c @@ -144,28 +144,17 @@ static int visconti_pwm_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); - platform_set_drvdata(pdev, priv); - priv->chip.dev = dev; priv->chip.ops = &visconti_pwm_ops; priv->chip.npwm = 4; - ret = pwmchip_add(&priv->chip); + ret = devm_pwmchip_add(&pdev->dev, &priv->chip); if (ret < 0) return dev_err_probe(&pdev->dev, ret, "Cannot register visconti PWM\n"); return 0; } -static int visconti_pwm_remove(struct platform_device *pdev) -{ - struct visconti_pwm_chip *priv = platform_get_drvdata(pdev); - - pwmchip_remove(&priv->chip); - - return 0; -} - static const struct of_device_id visconti_pwm_of_match[] = { { .compatible = "toshiba,visconti-pwm", }, { } @@ -178,7 +167,6 @@ static struct platform_driver visconti_pwm_driver = { .of_match_table = visconti_pwm_of_match, }, .probe = visconti_pwm_probe, - .remove = visconti_pwm_remove, }; module_platform_driver(visconti_pwm_driver); diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c index ea2aa151080a..480bfc29782f 100644 --- a/drivers/pwm/pwm-vt8500.c +++ b/drivers/pwm/pwm-vt8500.c @@ -56,7 +56,7 @@ struct vt8500_chip { #define to_vt8500_chip(chip) container_of(chip, struct vt8500_chip, chip) #define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t) -static inline void pwm_busy_wait(struct vt8500_chip *vt8500, int nr, u8 bitmask) +static inline void vt8500_pwm_busy_wait(struct vt8500_chip *vt8500, int nr, u8 bitmask) { int loops = msecs_to_loops(10); u32 mask = bitmask << (nr << 8); @@ -106,18 +106,18 @@ static int vt8500_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, dc = c; writel(prescale, vt8500->base + REG_SCALAR(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_SCALAR_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_SCALAR_UPDATE); writel(pv, vt8500->base + REG_PERIOD(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_PERIOD_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_PERIOD_UPDATE); writel(dc, vt8500->base + REG_DUTY(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_DUTY_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_DUTY_UPDATE); val = readl(vt8500->base + REG_CTRL(pwm->hwpwm)); val |= CTRL_AUTOLOAD; writel(val, vt8500->base + REG_CTRL(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); clk_disable(vt8500->clk); return 0; @@ -138,7 +138,7 @@ static int vt8500_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) val = readl(vt8500->base + REG_CTRL(pwm->hwpwm)); val |= CTRL_ENABLE; writel(val, vt8500->base + REG_CTRL(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); return 0; } @@ -151,7 +151,7 @@ static void vt8500_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) val = readl(vt8500->base + REG_CTRL(pwm->hwpwm)); val &= ~CTRL_ENABLE; writel(val, vt8500->base + REG_CTRL(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); clk_disable(vt8500->clk); } @@ -171,7 +171,7 @@ static int vt8500_pwm_set_polarity(struct pwm_chip *chip, val &= ~CTRL_INVERT; writel(val, vt8500->base + REG_CTRL(pwm->hwpwm)); - pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); + vt8500_pwm_busy_wait(vt8500, pwm->hwpwm, STATUS_CTRL_UPDATE); return 0; } diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 9a6eedc3994a..f2e961f998ca 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -34,6 +34,17 @@ config IMX_REMOTEPROC It's safe to say N here. +config IMX_DSP_REMOTEPROC + tristate "i.MX DSP remoteproc support" + depends on ARCH_MXC + depends on HAVE_ARM_SMCCC + select MAILBOX + help + Say y here to support iMX's DSP remote processors via the remote + processor framework. + + It's safe to say N here. + config INGENIC_VPU_RPROC tristate "Ingenic JZ47xx VPU remoteproc support" depends on MIPS || COMPILE_TEST @@ -127,6 +138,17 @@ config KEYSTONE_REMOTEPROC It's safe to say N here if you're not interested in the Keystone DSPs or just want to use a bare minimum kernel. +config MESON_MX_AO_ARC_REMOTEPROC + tristate "Amlogic Meson6/8/8b/8m2 AO ARC remote processor support" + depends on HAS_IOMEM + depends on (ARM && ARCH_MESON) || COMPILE_TEST + select GENERIC_ALLOCATOR + help + Say m or y here to have support for the AO ARC remote processor + on Amlogic Meson6/Meson8/Meson8b/Meson8m2 SoCs. This is + typically used for system suspend. + If unsure say N. + config PRU_REMOTEPROC tristate "TI PRU remoteproc support" depends on TI_PRUSS @@ -154,7 +176,7 @@ config QCOM_Q6V5_ADSP tristate "Qualcomm Technology Inc ADSP Peripheral Image Loader" depends on OF && ARCH_QCOM depends on QCOM_SMEM - depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_SMD || RPMSG_QCOM_SMD=n depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n @@ -173,7 +195,7 @@ config QCOM_Q6V5_MSS tristate "Qualcomm Hexagon V5 self-authenticating modem subsystem support" depends on OF && ARCH_QCOM depends on QCOM_SMEM - depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_SMD || RPMSG_QCOM_SMD=n depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n @@ -192,7 +214,7 @@ config QCOM_Q6V5_PAS tristate "Qualcomm Hexagon v5 Peripheral Authentication Service support" depends on OF && ARCH_QCOM depends on QCOM_SMEM - depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_SMD || RPMSG_QCOM_SMD=n depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n @@ -213,7 +235,7 @@ config QCOM_Q6V5_WCSS tristate "Qualcomm Hexagon based WCSS Peripheral Image Loader" depends on OF && ARCH_QCOM depends on QCOM_SMEM - depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_SMD || RPMSG_QCOM_SMD=n depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n @@ -246,7 +268,7 @@ config QCOM_SYSMON config QCOM_WCNSS_PIL tristate "Qualcomm WCNSS Peripheral Image Loader" depends on OF && ARCH_QCOM - depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n) + depends on RPMSG_QCOM_SMD || RPMSG_QCOM_SMD=n depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SMEM depends on QCOM_SYSMON || QCOM_SYSMON=n diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index bb26c9e4ef9c..0ac256b6c977 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -12,12 +12,14 @@ remoteproc-y += remoteproc_virtio.o remoteproc-y += remoteproc_elf_loader.o obj-$(CONFIG_REMOTEPROC_CDEV) += remoteproc_cdev.o obj-$(CONFIG_IMX_REMOTEPROC) += imx_rproc.o +obj-$(CONFIG_IMX_DSP_REMOTEPROC) += imx_dsp_rproc.o obj-$(CONFIG_INGENIC_VPU_RPROC) += ingenic_rproc.o obj-$(CONFIG_MTK_SCP) += mtk_scp.o mtk_scp_ipi.o obj-$(CONFIG_OMAP_REMOTEPROC) += omap_remoteproc.o obj-$(CONFIG_WKUP_M3_RPROC) += wkup_m3_rproc.o obj-$(CONFIG_DA8XX_REMOTEPROC) += da8xx_remoteproc.o obj-$(CONFIG_KEYSTONE_REMOTEPROC) += keystone_remoteproc.o +obj-$(CONFIG_MESON_MX_AO_ARC_REMOTEPROC)+= meson_mx_ao_arc.o obj-$(CONFIG_PRU_REMOTEPROC) += pru_rproc.o obj-$(CONFIG_QCOM_PIL_INFO) += qcom_pil_info.o obj-$(CONFIG_QCOM_RPROC_COMMON) += qcom_common.o diff --git a/drivers/remoteproc/imx_dsp_rproc.c b/drivers/remoteproc/imx_dsp_rproc.c new file mode 100644 index 000000000000..2abee78df96e --- /dev/null +++ b/drivers/remoteproc/imx_dsp_rproc.c @@ -0,0 +1,1206 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2021 NXP */ + +#include <dt-bindings/firmware/imx/rsrc.h> +#include <linux/arm-smccc.h> +#include <linux/clk.h> +#include <linux/err.h> +#include <linux/firmware.h> +#include <linux/firmware/imx/sci.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/mailbox_client.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_reserved_mem.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/remoteproc.h> +#include <linux/slab.h> + +#include "imx_rproc.h" +#include "remoteproc_elf_helpers.h" +#include "remoteproc_internal.h" + +#define DSP_RPROC_CLK_MAX 5 + +#define REMOTE_IS_READY BIT(0) +#define REMOTE_READY_WAIT_MAX_RETRIES 500 + +/* att flags */ +/* DSP own area */ +#define ATT_OWN BIT(31) +/* DSP instruction area */ +#define ATT_IRAM BIT(30) + +/* Definitions for i.MX8MP */ +/* DAP registers */ +#define IMX8M_DAP_DEBUG 0x28800000 +#define IMX8M_DAP_DEBUG_SIZE (64 * 1024) +#define IMX8M_DAP_PWRCTL (0x4000 + 0x3020) +#define IMX8M_PWRCTL_CORERESET BIT(16) + +/* DSP audio mix registers */ +#define IMX8M_AudioDSP_REG0 0x100 +#define IMX8M_AudioDSP_REG1 0x104 +#define IMX8M_AudioDSP_REG2 0x108 +#define IMX8M_AudioDSP_REG3 0x10c + +#define IMX8M_AudioDSP_REG2_RUNSTALL BIT(5) +#define IMX8M_AudioDSP_REG2_PWAITMODE BIT(1) + +/* Definitions for i.MX8ULP */ +#define IMX8ULP_SIM_LPAV_REG_SYSCTRL0 0x8 +#define IMX8ULP_SYSCTRL0_DSP_DBG_RST BIT(25) +#define IMX8ULP_SYSCTRL0_DSP_PLAT_CLK_EN BIT(19) +#define IMX8ULP_SYSCTRL0_DSP_PBCLK_EN BIT(18) +#define IMX8ULP_SYSCTRL0_DSP_CLK_EN BIT(17) +#define IMX8ULP_SYSCTRL0_DSP_RST BIT(16) +#define IMX8ULP_SYSCTRL0_DSP_OCD_HALT BIT(14) +#define IMX8ULP_SYSCTRL0_DSP_STALL BIT(13) + +#define IMX8ULP_SIP_HIFI_XRDC 0xc200000e + +/* + * enum - Predefined Mailbox Messages + * + * @RP_MBOX_SUSPEND_SYSTEM: system suspend request for the remote processor + * + * @RP_MBOX_SUSPEND_ACK: successful response from remote processor for a + * suspend request + * + * @RP_MBOX_RESUME_SYSTEM: system resume request for the remote processor + * + * @RP_MBOX_RESUME_ACK: successful response from remote processor for a + * resume request + */ +enum imx_dsp_rp_mbox_messages { + RP_MBOX_SUSPEND_SYSTEM = 0xFF11, + RP_MBOX_SUSPEND_ACK = 0xFF12, + RP_MBOX_RESUME_SYSTEM = 0xFF13, + RP_MBOX_RESUME_ACK = 0xFF14, +}; + +/** + * struct imx_dsp_rproc - DSP remote processor state + * @regmap: regmap handler + * @rproc: rproc handler + * @dsp_dcfg: device configuration pointer + * @clks: clocks needed by this device + * @cl: mailbox client to request the mailbox channel + * @cl_rxdb: mailbox client to request the mailbox channel for doorbell + * @tx_ch: mailbox tx channel handle + * @rx_ch: mailbox rx channel handle + * @rxdb_ch: mailbox rx doorbell channel handle + * @pd_dev: power domain device + * @pd_dev_link: power domain device link + * @ipc_handle: System Control Unit ipc handle + * @rproc_work: work for processing virtio interrupts + * @pm_comp: completion primitive to sync for suspend response + * @num_domains: power domain number + * @flags: control flags + */ +struct imx_dsp_rproc { + struct regmap *regmap; + struct rproc *rproc; + const struct imx_dsp_rproc_dcfg *dsp_dcfg; + struct clk_bulk_data clks[DSP_RPROC_CLK_MAX]; + struct mbox_client cl; + struct mbox_client cl_rxdb; + struct mbox_chan *tx_ch; + struct mbox_chan *rx_ch; + struct mbox_chan *rxdb_ch; + struct device **pd_dev; + struct device_link **pd_dev_link; + struct imx_sc_ipc *ipc_handle; + struct work_struct rproc_work; + struct completion pm_comp; + int num_domains; + u32 flags; +}; + +/** + * struct imx_dsp_rproc_dcfg - DSP remote processor configuration + * @dcfg: imx_rproc_dcfg handler + * @reset: reset callback function + */ +struct imx_dsp_rproc_dcfg { + const struct imx_rproc_dcfg *dcfg; + int (*reset)(struct imx_dsp_rproc *priv); +}; + +static const struct imx_rproc_att imx_dsp_rproc_att_imx8qm[] = { + /* dev addr , sys addr , size , flags */ + { 0x596e8000, 0x556e8000, 0x00008000, ATT_OWN }, + { 0x596f0000, 0x556f0000, 0x00008000, ATT_OWN }, + { 0x596f8000, 0x556f8000, 0x00000800, ATT_OWN | ATT_IRAM}, + { 0x55700000, 0x55700000, 0x00070000, ATT_OWN }, + /* DDR (Data) */ + { 0x80000000, 0x80000000, 0x60000000, 0}, +}; + +static const struct imx_rproc_att imx_dsp_rproc_att_imx8qxp[] = { + /* dev addr , sys addr , size , flags */ + { 0x596e8000, 0x596e8000, 0x00008000, ATT_OWN }, + { 0x596f0000, 0x596f0000, 0x00008000, ATT_OWN }, + { 0x596f8000, 0x596f8000, 0x00000800, ATT_OWN | ATT_IRAM}, + { 0x59700000, 0x59700000, 0x00070000, ATT_OWN }, + /* DDR (Data) */ + { 0x80000000, 0x80000000, 0x60000000, 0}, +}; + +static const struct imx_rproc_att imx_dsp_rproc_att_imx8mp[] = { + /* dev addr , sys addr , size , flags */ + { 0x3b6e8000, 0x3b6e8000, 0x00008000, ATT_OWN }, + { 0x3b6f0000, 0x3b6f0000, 0x00008000, ATT_OWN }, + { 0x3b6f8000, 0x3b6f8000, 0x00000800, ATT_OWN | ATT_IRAM}, + { 0x3b700000, 0x3b700000, 0x00040000, ATT_OWN }, + /* DDR (Data) */ + { 0x40000000, 0x40000000, 0x80000000, 0}, +}; + +static const struct imx_rproc_att imx_dsp_rproc_att_imx8ulp[] = { + /* dev addr , sys addr , size , flags */ + { 0x21170000, 0x21170000, 0x00010000, ATT_OWN | ATT_IRAM}, + { 0x21180000, 0x21180000, 0x00010000, ATT_OWN }, + /* DDR (Data) */ + { 0x0c000000, 0x80000000, 0x10000000, 0}, + { 0x30000000, 0x90000000, 0x10000000, 0}, +}; + +/* Reset function for DSP on i.MX8MP */ +static int imx8mp_dsp_reset(struct imx_dsp_rproc *priv) +{ + void __iomem *dap = ioremap_wc(IMX8M_DAP_DEBUG, IMX8M_DAP_DEBUG_SIZE); + int pwrctl; + + /* Put DSP into reset and stall */ + pwrctl = readl(dap + IMX8M_DAP_PWRCTL); + pwrctl |= IMX8M_PWRCTL_CORERESET; + writel(pwrctl, dap + IMX8M_DAP_PWRCTL); + + /* Keep reset asserted for 10 cycles */ + usleep_range(1, 2); + + regmap_update_bits(priv->regmap, IMX8M_AudioDSP_REG2, + IMX8M_AudioDSP_REG2_RUNSTALL, + IMX8M_AudioDSP_REG2_RUNSTALL); + + /* Take the DSP out of reset and keep stalled for FW loading */ + pwrctl = readl(dap + IMX8M_DAP_PWRCTL); + pwrctl &= ~IMX8M_PWRCTL_CORERESET; + writel(pwrctl, dap + IMX8M_DAP_PWRCTL); + + iounmap(dap); + return 0; +} + +/* Reset function for DSP on i.MX8ULP */ +static int imx8ulp_dsp_reset(struct imx_dsp_rproc *priv) +{ + struct arm_smccc_res res; + + /* Put DSP into reset and stall */ + regmap_update_bits(priv->regmap, IMX8ULP_SIM_LPAV_REG_SYSCTRL0, + IMX8ULP_SYSCTRL0_DSP_RST, IMX8ULP_SYSCTRL0_DSP_RST); + regmap_update_bits(priv->regmap, IMX8ULP_SIM_LPAV_REG_SYSCTRL0, + IMX8ULP_SYSCTRL0_DSP_STALL, + IMX8ULP_SYSCTRL0_DSP_STALL); + + /* Configure resources of DSP through TFA */ + arm_smccc_smc(IMX8ULP_SIP_HIFI_XRDC, 0, 0, 0, 0, 0, 0, 0, &res); + + /* Take the DSP out of reset and keep stalled for FW loading */ + regmap_update_bits(priv->regmap, IMX8ULP_SIM_LPAV_REG_SYSCTRL0, + IMX8ULP_SYSCTRL0_DSP_RST, 0); + regmap_update_bits(priv->regmap, IMX8ULP_SIM_LPAV_REG_SYSCTRL0, + IMX8ULP_SYSCTRL0_DSP_DBG_RST, 0); + + return 0; +} + +/* Specific configuration for i.MX8MP */ +static const struct imx_rproc_dcfg dsp_rproc_cfg_imx8mp = { + .src_reg = IMX8M_AudioDSP_REG2, + .src_mask = IMX8M_AudioDSP_REG2_RUNSTALL, + .src_start = 0, + .src_stop = IMX8M_AudioDSP_REG2_RUNSTALL, + .att = imx_dsp_rproc_att_imx8mp, + .att_size = ARRAY_SIZE(imx_dsp_rproc_att_imx8mp), + .method = IMX_RPROC_MMIO, +}; + +static const struct imx_dsp_rproc_dcfg imx_dsp_rproc_cfg_imx8mp = { + .dcfg = &dsp_rproc_cfg_imx8mp, + .reset = imx8mp_dsp_reset, +}; + +/* Specific configuration for i.MX8ULP */ +static const struct imx_rproc_dcfg dsp_rproc_cfg_imx8ulp = { + .src_reg = IMX8ULP_SIM_LPAV_REG_SYSCTRL0, + .src_mask = IMX8ULP_SYSCTRL0_DSP_STALL, + .src_start = 0, + .src_stop = IMX8ULP_SYSCTRL0_DSP_STALL, + .att = imx_dsp_rproc_att_imx8ulp, + .att_size = ARRAY_SIZE(imx_dsp_rproc_att_imx8ulp), + .method = IMX_RPROC_MMIO, +}; + +static const struct imx_dsp_rproc_dcfg imx_dsp_rproc_cfg_imx8ulp = { + .dcfg = &dsp_rproc_cfg_imx8ulp, + .reset = imx8ulp_dsp_reset, +}; + +/* Specific configuration for i.MX8QXP */ +static const struct imx_rproc_dcfg dsp_rproc_cfg_imx8qxp = { + .att = imx_dsp_rproc_att_imx8qxp, + .att_size = ARRAY_SIZE(imx_dsp_rproc_att_imx8qxp), + .method = IMX_RPROC_SCU_API, +}; + +static const struct imx_dsp_rproc_dcfg imx_dsp_rproc_cfg_imx8qxp = { + .dcfg = &dsp_rproc_cfg_imx8qxp, +}; + +/* Specific configuration for i.MX8QM */ +static const struct imx_rproc_dcfg dsp_rproc_cfg_imx8qm = { + .att = imx_dsp_rproc_att_imx8qm, + .att_size = ARRAY_SIZE(imx_dsp_rproc_att_imx8qm), + .method = IMX_RPROC_SCU_API, +}; + +static const struct imx_dsp_rproc_dcfg imx_dsp_rproc_cfg_imx8qm = { + .dcfg = &dsp_rproc_cfg_imx8qm, +}; + +static int imx_dsp_rproc_ready(struct rproc *rproc) +{ + struct imx_dsp_rproc *priv = rproc->priv; + int i; + + if (!priv->rxdb_ch) + return 0; + + for (i = 0; i < REMOTE_READY_WAIT_MAX_RETRIES; i++) { + if (priv->flags & REMOTE_IS_READY) + return 0; + usleep_range(100, 200); + } + + return -ETIMEDOUT; +} + +/* + * Start function for rproc_ops + * + * There is a handshake for start procedure: when DSP starts, it + * will send a doorbell message to this driver, then the + * REMOTE_IS_READY flags is set, then driver will kick + * a message to DSP. + */ +static int imx_dsp_rproc_start(struct rproc *rproc) +{ + struct imx_dsp_rproc *priv = rproc->priv; + const struct imx_dsp_rproc_dcfg *dsp_dcfg = priv->dsp_dcfg; + const struct imx_rproc_dcfg *dcfg = dsp_dcfg->dcfg; + struct device *dev = rproc->dev.parent; + int ret; + + switch (dcfg->method) { + case IMX_RPROC_MMIO: + ret = regmap_update_bits(priv->regmap, + dcfg->src_reg, + dcfg->src_mask, + dcfg->src_start); + break; + case IMX_RPROC_SCU_API: + ret = imx_sc_pm_cpu_start(priv->ipc_handle, + IMX_SC_R_DSP, + true, + rproc->bootaddr); + break; + default: + return -EOPNOTSUPP; + } + + if (ret) + dev_err(dev, "Failed to enable remote core!\n"); + else + ret = imx_dsp_rproc_ready(rproc); + + return ret; +} + +/* + * Stop function for rproc_ops + * It clears the REMOTE_IS_READY flags + */ +static int imx_dsp_rproc_stop(struct rproc *rproc) +{ + struct imx_dsp_rproc *priv = rproc->priv; + const struct imx_dsp_rproc_dcfg *dsp_dcfg = priv->dsp_dcfg; + const struct imx_rproc_dcfg *dcfg = dsp_dcfg->dcfg; + struct device *dev = rproc->dev.parent; + int ret = 0; + + /* Make sure work is finished */ + flush_work(&priv->rproc_work); + + if (rproc->state == RPROC_CRASHED) { + priv->flags &= ~REMOTE_IS_READY; + return 0; + } + + switch (dcfg->method) { + case IMX_RPROC_MMIO: + ret = regmap_update_bits(priv->regmap, dcfg->src_reg, dcfg->src_mask, + dcfg->src_stop); + break; + case IMX_RPROC_SCU_API: + ret = imx_sc_pm_cpu_start(priv->ipc_handle, + IMX_SC_R_DSP, + false, + rproc->bootaddr); + break; + default: + return -EOPNOTSUPP; + } + + if (ret) + dev_err(dev, "Failed to stop remote core\n"); + else + priv->flags &= ~REMOTE_IS_READY; + + return ret; +} + +/** + * imx_dsp_rproc_sys_to_da() - internal memory translation helper + * @priv: private data pointer + * @sys: system address (DDR address) + * @len: length of the memory buffer + * @da: device address to translate + * + * Convert system address (DDR address) to device address (DSP) + * for there may be memory remap for device. + */ +static int imx_dsp_rproc_sys_to_da(struct imx_dsp_rproc *priv, u64 sys, + size_t len, u64 *da) +{ + const struct imx_dsp_rproc_dcfg *dsp_dcfg = priv->dsp_dcfg; + const struct imx_rproc_dcfg *dcfg = dsp_dcfg->dcfg; + int i; + + /* Parse address translation table */ + for (i = 0; i < dcfg->att_size; i++) { + const struct imx_rproc_att *att = &dcfg->att[i]; + + if (sys >= att->sa && sys + len <= att->sa + att->size) { + unsigned int offset = sys - att->sa; + + *da = att->da + offset; + return 0; + } + } + + return -ENOENT; +} + +/* Main virtqueue message work function + * + * This function is executed upon scheduling of the i.MX DSP remoteproc + * driver's workqueue. The workqueue is scheduled by the mailbox rx + * handler. + * + * This work function processes both the Tx and Rx virtqueue indices on + * every invocation. The rproc_vq_interrupt function can detect if there + * are new unprocessed messages or not (returns IRQ_NONE vs IRQ_HANDLED), + * but there is no need to check for these return values. The index 0 + * triggering will process all pending Rx buffers, and the index 1 triggering + * will process all newly available Tx buffers and will wakeup any potentially + * blocked senders. + * + * NOTE: + * The current logic is based on an inherent design assumption of supporting + * only 2 vrings, but this can be changed if needed. + */ +static void imx_dsp_rproc_vq_work(struct work_struct *work) +{ + struct imx_dsp_rproc *priv = container_of(work, struct imx_dsp_rproc, + rproc_work); + + rproc_vq_interrupt(priv->rproc, 0); + rproc_vq_interrupt(priv->rproc, 1); +} + +/** + * imx_dsp_rproc_rx_tx_callback() - inbound mailbox message handler + * @cl: mailbox client pointer used for requesting the mailbox channel + * @data: mailbox payload + * + * This handler is invoked by mailbox driver whenever a mailbox + * message is received. Usually, the SUSPEND and RESUME related messages + * are handled in this function, other messages are handled by remoteproc core + */ +static void imx_dsp_rproc_rx_tx_callback(struct mbox_client *cl, void *data) +{ + struct rproc *rproc = dev_get_drvdata(cl->dev); + struct imx_dsp_rproc *priv = rproc->priv; + struct device *dev = rproc->dev.parent; + u32 message = (u32)(*(u32 *)data); + + dev_dbg(dev, "mbox msg: 0x%x\n", message); + + switch (message) { + case RP_MBOX_SUSPEND_ACK: + complete(&priv->pm_comp); + break; + case RP_MBOX_RESUME_ACK: + complete(&priv->pm_comp); + break; + default: + schedule_work(&priv->rproc_work); + break; + } +} + +/** + * imx_dsp_rproc_rxdb_callback() - inbound mailbox message handler + * @cl: mailbox client pointer used for requesting the mailbox channel + * @data: mailbox payload + * + * For doorbell, there is no message specified, just set REMOTE_IS_READY + * flag. + */ +static void imx_dsp_rproc_rxdb_callback(struct mbox_client *cl, void *data) +{ + struct rproc *rproc = dev_get_drvdata(cl->dev); + struct imx_dsp_rproc *priv = rproc->priv; + + /* Remote is ready after firmware is loaded and running */ + priv->flags |= REMOTE_IS_READY; +} + +/** + * imx_dsp_rproc_mbox_init() - request mailbox channels + * @priv: private data pointer + * + * Request three mailbox channels (tx, rx, rxdb). + */ +static int imx_dsp_rproc_mbox_init(struct imx_dsp_rproc *priv) +{ + struct device *dev = priv->rproc->dev.parent; + struct mbox_client *cl; + int ret; + + if (!of_get_property(dev->of_node, "mbox-names", NULL)) + return 0; + + cl = &priv->cl; + cl->dev = dev; + cl->tx_block = true; + cl->tx_tout = 100; + cl->knows_txdone = false; + cl->rx_callback = imx_dsp_rproc_rx_tx_callback; + + /* Channel for sending message */ + priv->tx_ch = mbox_request_channel_byname(cl, "tx"); + if (IS_ERR(priv->tx_ch)) { + ret = PTR_ERR(priv->tx_ch); + dev_dbg(cl->dev, "failed to request tx mailbox channel: %d\n", + ret); + goto err_out; + } + + /* Channel for receiving message */ + priv->rx_ch = mbox_request_channel_byname(cl, "rx"); + if (IS_ERR(priv->rx_ch)) { + ret = PTR_ERR(priv->rx_ch); + dev_dbg(cl->dev, "failed to request rx mailbox channel: %d\n", + ret); + goto err_out; + } + + cl = &priv->cl_rxdb; + cl->dev = dev; + cl->rx_callback = imx_dsp_rproc_rxdb_callback; + + /* + * RX door bell is used to receive the ready signal from remote + * after firmware loaded. + */ + priv->rxdb_ch = mbox_request_channel_byname(cl, "rxdb"); + if (IS_ERR(priv->rxdb_ch)) { + ret = PTR_ERR(priv->rxdb_ch); + dev_dbg(cl->dev, "failed to request mbox chan rxdb, ret %d\n", + ret); + goto err_out; + } + + return 0; + +err_out: + if (!IS_ERR(priv->tx_ch)) + mbox_free_channel(priv->tx_ch); + if (!IS_ERR(priv->rx_ch)) + mbox_free_channel(priv->rx_ch); + if (!IS_ERR(priv->rxdb_ch)) + mbox_free_channel(priv->rxdb_ch); + + return ret; +} + +static void imx_dsp_rproc_free_mbox(struct imx_dsp_rproc *priv) +{ + mbox_free_channel(priv->tx_ch); + mbox_free_channel(priv->rx_ch); + mbox_free_channel(priv->rxdb_ch); +} + +/** + * imx_dsp_rproc_add_carveout() - request mailbox channels + * @priv: private data pointer + * + * This function registers specified memory entry in @rproc carveouts list + * The carveouts can help to mapping the memory address for DSP. + */ +static int imx_dsp_rproc_add_carveout(struct imx_dsp_rproc *priv) +{ + const struct imx_dsp_rproc_dcfg *dsp_dcfg = priv->dsp_dcfg; + const struct imx_rproc_dcfg *dcfg = dsp_dcfg->dcfg; + struct rproc *rproc = priv->rproc; + struct device *dev = rproc->dev.parent; + struct device_node *np = dev->of_node; + struct of_phandle_iterator it; + struct rproc_mem_entry *mem; + struct reserved_mem *rmem; + void __iomem *cpu_addr; + int a; + u64 da; + + /* Remap required addresses */ + for (a = 0; a < dcfg->att_size; a++) { + const struct imx_rproc_att *att = &dcfg->att[a]; + + if (!(att->flags & ATT_OWN)) + continue; + + if (imx_dsp_rproc_sys_to_da(priv, att->sa, att->size, &da)) + return -EINVAL; + + cpu_addr = devm_ioremap_wc(dev, att->sa, att->size); + if (!cpu_addr) { + dev_err(dev, "failed to map memory %p\n", &att->sa); + return -ENOMEM; + } + + /* Register memory region */ + mem = rproc_mem_entry_init(dev, cpu_addr, (dma_addr_t)att->sa, + att->size, da, NULL, NULL, "dsp_mem"); + + if (mem) + rproc_coredump_add_segment(rproc, da, att->size); + else + return -ENOMEM; + + rproc_add_carveout(rproc, mem); + } + + of_phandle_iterator_init(&it, np, "memory-region", NULL, 0); + while (of_phandle_iterator_next(&it) == 0) { + /* + * Ignore the first memory region which will be used vdev buffer. + * No need to do extra handlings, rproc_add_virtio_dev will handle it. + */ + if (!strcmp(it.node->name, "vdev0buffer")) + continue; + + rmem = of_reserved_mem_lookup(it.node); + if (!rmem) { + dev_err(dev, "unable to acquire memory-region\n"); + return -EINVAL; + } + + if (imx_dsp_rproc_sys_to_da(priv, rmem->base, rmem->size, &da)) + return -EINVAL; + + cpu_addr = devm_ioremap_wc(dev, rmem->base, rmem->size); + if (!cpu_addr) { + dev_err(dev, "failed to map memory %p\n", &rmem->base); + return -ENOMEM; + } + + /* Register memory region */ + mem = rproc_mem_entry_init(dev, cpu_addr, (dma_addr_t)rmem->base, + rmem->size, da, NULL, NULL, it.node->name); + + if (mem) + rproc_coredump_add_segment(rproc, da, rmem->size); + else + return -ENOMEM; + + rproc_add_carveout(rproc, mem); + } + + return 0; +} + +/** + * imx_dsp_rproc_elf_load_segments() - load firmware segments to memory + * @rproc: remote processor which will be booted using these fw segments + * @fw: the ELF firmware image + * + * This function specially checks if memsz is zero or not, otherwise it + * is mostly same as rproc_elf_load_segments(). + */ +static int imx_dsp_rproc_elf_load_segments(struct rproc *rproc, + const struct firmware *fw) +{ + struct device *dev = &rproc->dev; + u8 class = fw_elf_get_class(fw); + u32 elf_phdr_get_size = elf_size_of_phdr(class); + const u8 *elf_data = fw->data; + const void *ehdr, *phdr; + int i, ret = 0; + u16 phnum; + + ehdr = elf_data; + phnum = elf_hdr_get_e_phnum(class, ehdr); + phdr = elf_data + elf_hdr_get_e_phoff(class, ehdr); + + /* go through the available ELF segments */ + for (i = 0; i < phnum; i++, phdr += elf_phdr_get_size) { + u64 da = elf_phdr_get_p_paddr(class, phdr); + u64 memsz = elf_phdr_get_p_memsz(class, phdr); + u64 filesz = elf_phdr_get_p_filesz(class, phdr); + u64 offset = elf_phdr_get_p_offset(class, phdr); + u32 type = elf_phdr_get_p_type(class, phdr); + void *ptr; + + /* + * There is a case that with PT_LOAD type, the + * filesz = memsz = 0. If memsz = 0, rproc_da_to_va + * should return NULL ptr, then error is returned. + * So this case should be skipped from the loop. + * Add !memsz checking here. + */ + if (type != PT_LOAD || !memsz) + continue; + + dev_dbg(dev, "phdr: type %d da 0x%llx memsz 0x%llx filesz 0x%llx\n", + type, da, memsz, filesz); + + if (filesz > memsz) { + dev_err(dev, "bad phdr filesz 0x%llx memsz 0x%llx\n", + filesz, memsz); + ret = -EINVAL; + break; + } + + if (offset + filesz > fw->size) { + dev_err(dev, "truncated fw: need 0x%llx avail 0x%zx\n", + offset + filesz, fw->size); + ret = -EINVAL; + break; + } + + if (!rproc_u64_fit_in_size_t(memsz)) { + dev_err(dev, "size (%llx) does not fit in size_t type\n", + memsz); + ret = -EOVERFLOW; + break; + } + + /* grab the kernel address for this device address */ + ptr = rproc_da_to_va(rproc, da, memsz, NULL); + if (!ptr) { + dev_err(dev, "bad phdr da 0x%llx mem 0x%llx\n", da, + memsz); + ret = -EINVAL; + break; + } + + /* put the segment where the remote processor expects it */ + if (filesz) + memcpy(ptr, elf_data + offset, filesz); + + /* + * Zero out remaining memory for this segment. + * + * This isn't strictly required since dma_alloc_coherent already + * did this for us. albeit harmless, we may consider removing + * this. + */ + if (memsz > filesz) + memset(ptr + filesz, 0, memsz - filesz); + } + + return ret; +} + +/* Prepare function for rproc_ops */ +static int imx_dsp_rproc_prepare(struct rproc *rproc) +{ + struct imx_dsp_rproc *priv = rproc->priv; + struct device *dev = rproc->dev.parent; + struct rproc_mem_entry *carveout; + int ret; + + ret = imx_dsp_rproc_add_carveout(priv); + if (ret) { + dev_err(dev, "failed on imx_dsp_rproc_add_carveout\n"); + return ret; + } + + pm_runtime_get_sync(dev); + + /* + * Clear buffers after pm rumtime for internal ocram is not + * accessible if power and clock are not enabled. + */ + list_for_each_entry(carveout, &rproc->carveouts, node) { + if (carveout->va) + memset(carveout->va, 0, carveout->len); + } + + return 0; +} + +/* Unprepare function for rproc_ops */ +static int imx_dsp_rproc_unprepare(struct rproc *rproc) +{ + pm_runtime_put_sync(rproc->dev.parent); + + return 0; +} + +/* Kick function for rproc_ops */ +static void imx_dsp_rproc_kick(struct rproc *rproc, int vqid) +{ + struct imx_dsp_rproc *priv = rproc->priv; + struct device *dev = rproc->dev.parent; + int err; + __u32 mmsg; + + if (!priv->tx_ch) { + dev_err(dev, "No initialized mbox tx channel\n"); + return; + } + + /* + * Send the index of the triggered virtqueue as the mu payload. + * Let remote processor know which virtqueue is used. + */ + mmsg = vqid; + + err = mbox_send_message(priv->tx_ch, (void *)&mmsg); + if (err < 0) + dev_err(dev, "%s: failed (%d, err:%d)\n", __func__, vqid, err); +} + +static const struct rproc_ops imx_dsp_rproc_ops = { + .prepare = imx_dsp_rproc_prepare, + .unprepare = imx_dsp_rproc_unprepare, + .start = imx_dsp_rproc_start, + .stop = imx_dsp_rproc_stop, + .kick = imx_dsp_rproc_kick, + .load = imx_dsp_rproc_elf_load_segments, + .parse_fw = rproc_elf_load_rsc_table, + .sanity_check = rproc_elf_sanity_check, + .get_boot_addr = rproc_elf_get_boot_addr, +}; + +/** + * imx_dsp_attach_pm_domains() - attach the power domains + * @priv: private data pointer + * + * On i.MX8QM and i.MX8QXP there is multiple power domains + * required, so need to link them. + */ +static int imx_dsp_attach_pm_domains(struct imx_dsp_rproc *priv) +{ + struct device *dev = priv->rproc->dev.parent; + int ret, i; + + priv->num_domains = of_count_phandle_with_args(dev->of_node, + "power-domains", + "#power-domain-cells"); + + /* If only one domain, then no need to link the device */ + if (priv->num_domains <= 1) + return 0; + + priv->pd_dev = devm_kmalloc_array(dev, priv->num_domains, + sizeof(*priv->pd_dev), + GFP_KERNEL); + if (!priv->pd_dev) + return -ENOMEM; + + priv->pd_dev_link = devm_kmalloc_array(dev, priv->num_domains, + sizeof(*priv->pd_dev_link), + GFP_KERNEL); + if (!priv->pd_dev_link) + return -ENOMEM; + + for (i = 0; i < priv->num_domains; i++) { + priv->pd_dev[i] = dev_pm_domain_attach_by_id(dev, i); + if (IS_ERR(priv->pd_dev[i])) { + ret = PTR_ERR(priv->pd_dev[i]); + goto detach_pm; + } + + /* + * device_link_add will check priv->pd_dev[i], if it is + * NULL, then will break. + */ + priv->pd_dev_link[i] = device_link_add(dev, + priv->pd_dev[i], + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME); + if (!priv->pd_dev_link[i]) { + dev_pm_domain_detach(priv->pd_dev[i], false); + ret = -EINVAL; + goto detach_pm; + } + } + + return 0; + +detach_pm: + while (--i >= 0) { + device_link_del(priv->pd_dev_link[i]); + dev_pm_domain_detach(priv->pd_dev[i], false); + } + + return ret; +} + +static int imx_dsp_detach_pm_domains(struct imx_dsp_rproc *priv) +{ + int i; + + if (priv->num_domains <= 1) + return 0; + + for (i = 0; i < priv->num_domains; i++) { + device_link_del(priv->pd_dev_link[i]); + dev_pm_domain_detach(priv->pd_dev[i], false); + } + + return 0; +} + +/** + * imx_dsp_rproc_detect_mode() - detect DSP control mode + * @priv: private data pointer + * + * Different platform has different control method for DSP, which depends + * on how the DSP is integrated in platform. + * + * For i.MX8QXP and i.MX8QM, DSP should be started and stopped by System + * Control Unit. + * For i.MX8MP and i.MX8ULP, DSP should be started and stopped by system + * integration module. + */ +static int imx_dsp_rproc_detect_mode(struct imx_dsp_rproc *priv) +{ + const struct imx_dsp_rproc_dcfg *dsp_dcfg = priv->dsp_dcfg; + struct device *dev = priv->rproc->dev.parent; + struct regmap *regmap; + int ret = 0; + + switch (dsp_dcfg->dcfg->method) { + case IMX_RPROC_SCU_API: + ret = imx_scu_get_handle(&priv->ipc_handle); + if (ret) + return ret; + break; + case IMX_RPROC_MMIO: + regmap = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,dsp-ctrl"); + if (IS_ERR(regmap)) { + dev_err(dev, "failed to find syscon\n"); + return PTR_ERR(regmap); + } + + priv->regmap = regmap; + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +static const char *imx_dsp_clks_names[DSP_RPROC_CLK_MAX] = { + /* DSP clocks */ + "core", "ocram", "debug", "ipg", "mu", +}; + +static int imx_dsp_rproc_clk_get(struct imx_dsp_rproc *priv) +{ + struct device *dev = priv->rproc->dev.parent; + struct clk_bulk_data *clks = priv->clks; + int i; + + for (i = 0; i < DSP_RPROC_CLK_MAX; i++) + clks[i].id = imx_dsp_clks_names[i]; + + return devm_clk_bulk_get_optional(dev, DSP_RPROC_CLK_MAX, clks); +} + +static int imx_dsp_rproc_probe(struct platform_device *pdev) +{ + const struct imx_dsp_rproc_dcfg *dsp_dcfg; + struct device *dev = &pdev->dev; + struct imx_dsp_rproc *priv; + struct rproc *rproc; + const char *fw_name; + int ret; + + dsp_dcfg = of_device_get_match_data(dev); + if (!dsp_dcfg) + return -ENODEV; + + ret = rproc_of_parse_firmware(dev, 0, &fw_name); + if (ret) { + dev_err(dev, "failed to parse firmware-name property, ret = %d\n", + ret); + return ret; + } + + rproc = rproc_alloc(dev, "imx-dsp-rproc", &imx_dsp_rproc_ops, fw_name, + sizeof(*priv)); + if (!rproc) + return -ENOMEM; + + priv = rproc->priv; + priv->rproc = rproc; + priv->dsp_dcfg = dsp_dcfg; + + dev_set_drvdata(dev, rproc); + + INIT_WORK(&priv->rproc_work, imx_dsp_rproc_vq_work); + + ret = imx_dsp_rproc_detect_mode(priv); + if (ret) { + dev_err(dev, "failed on imx_dsp_rproc_detect_mode\n"); + goto err_put_rproc; + } + + /* There are multiple power domains required by DSP on some platform */ + ret = imx_dsp_attach_pm_domains(priv); + if (ret) { + dev_err(dev, "failed on imx_dsp_attach_pm_domains\n"); + goto err_put_rproc; + } + /* Get clocks */ + ret = imx_dsp_rproc_clk_get(priv); + if (ret) { + dev_err(dev, "failed on imx_dsp_rproc_clk_get\n"); + goto err_detach_domains; + } + + init_completion(&priv->pm_comp); + rproc->auto_boot = false; + ret = rproc_add(rproc); + if (ret) { + dev_err(dev, "rproc_add failed\n"); + goto err_detach_domains; + } + + pm_runtime_enable(dev); + + return 0; + +err_detach_domains: + imx_dsp_detach_pm_domains(priv); +err_put_rproc: + rproc_free(rproc); + + return ret; +} + +static int imx_dsp_rproc_remove(struct platform_device *pdev) +{ + struct rproc *rproc = platform_get_drvdata(pdev); + struct imx_dsp_rproc *priv = rproc->priv; + + pm_runtime_disable(&pdev->dev); + rproc_del(rproc); + imx_dsp_detach_pm_domains(priv); + rproc_free(rproc); + + return 0; +} + +/* pm runtime functions */ +static int imx_dsp_runtime_resume(struct device *dev) +{ + struct rproc *rproc = dev_get_drvdata(dev); + struct imx_dsp_rproc *priv = rproc->priv; + const struct imx_dsp_rproc_dcfg *dsp_dcfg = priv->dsp_dcfg; + int ret; + + /* + * There is power domain attached with mailbox, if setup mailbox + * in probe(), then the power of mailbox is always enabled, + * the power can't be saved. + * So move setup of mailbox to runtime resume. + */ + ret = imx_dsp_rproc_mbox_init(priv); + if (ret) { + dev_err(dev, "failed on imx_dsp_rproc_mbox_init\n"); + return ret; + } + + ret = clk_bulk_prepare_enable(DSP_RPROC_CLK_MAX, priv->clks); + if (ret) { + dev_err(dev, "failed on clk_bulk_prepare_enable\n"); + return ret; + } + + /* Reset DSP if needed */ + if (dsp_dcfg->reset) + dsp_dcfg->reset(priv); + + return 0; +} + +static int imx_dsp_runtime_suspend(struct device *dev) +{ + struct rproc *rproc = dev_get_drvdata(dev); + struct imx_dsp_rproc *priv = rproc->priv; + + clk_bulk_disable_unprepare(DSP_RPROC_CLK_MAX, priv->clks); + + imx_dsp_rproc_free_mbox(priv); + + return 0; +} + +static void imx_dsp_load_firmware(const struct firmware *fw, void *context) +{ + struct rproc *rproc = context; + int ret; + + /* + * Same flow as start procedure. + * Load the ELF segments to memory firstly. + */ + ret = rproc_load_segments(rproc, fw); + if (ret) + goto out; + + /* Start the remote processor */ + ret = rproc->ops->start(rproc); + if (ret) + goto out; + + rproc->ops->kick(rproc, 0); + +out: + release_firmware(fw); +} + +static __maybe_unused int imx_dsp_suspend(struct device *dev) +{ + struct rproc *rproc = dev_get_drvdata(dev); + struct imx_dsp_rproc *priv = rproc->priv; + __u32 mmsg = RP_MBOX_SUSPEND_SYSTEM; + int ret; + + if (rproc->state != RPROC_RUNNING) + goto out; + + reinit_completion(&priv->pm_comp); + + /* Tell DSP that suspend is happening */ + ret = mbox_send_message(priv->tx_ch, (void *)&mmsg); + if (ret < 0) { + dev_err(dev, "PM mbox_send_message failed: %d\n", ret); + return ret; + } + + /* + * DSP need to save the context at suspend. + * Here waiting the response for DSP, then power can be disabled. + */ + if (!wait_for_completion_timeout(&priv->pm_comp, msecs_to_jiffies(100))) + return -EBUSY; + +out: + /* + * The power of DSP is disabled in suspend, so force pm runtime + * to be suspend, then we can reenable the power and clocks at + * resume stage. + */ + return pm_runtime_force_suspend(dev); +} + +static __maybe_unused int imx_dsp_resume(struct device *dev) +{ + struct rproc *rproc = dev_get_drvdata(dev); + int ret = 0; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + if (rproc->state != RPROC_RUNNING) + return 0; + + /* + * The power of DSP is disabled at suspend, the memory of dsp + * is reset, the image segments are lost. So need to reload + * firmware and restart the DSP if it is in running state. + */ + ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT, + rproc->firmware, dev, GFP_KERNEL, + rproc, imx_dsp_load_firmware); + if (ret < 0) { + dev_err(dev, "load firmware failed: %d\n", ret); + goto err; + } + + return 0; + +err: + pm_runtime_force_suspend(dev); + + return ret; +} + +static const struct dev_pm_ops imx_dsp_rproc_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(imx_dsp_suspend, imx_dsp_resume) + SET_RUNTIME_PM_OPS(imx_dsp_runtime_suspend, + imx_dsp_runtime_resume, NULL) +}; + +static const struct of_device_id imx_dsp_rproc_of_match[] = { + { .compatible = "fsl,imx8qxp-hifi4", .data = &imx_dsp_rproc_cfg_imx8qxp }, + { .compatible = "fsl,imx8qm-hifi4", .data = &imx_dsp_rproc_cfg_imx8qm }, + { .compatible = "fsl,imx8mp-hifi4", .data = &imx_dsp_rproc_cfg_imx8mp }, + { .compatible = "fsl,imx8ulp-hifi4", .data = &imx_dsp_rproc_cfg_imx8ulp }, + {}, +}; +MODULE_DEVICE_TABLE(of, imx_dsp_rproc_of_match); + +static struct platform_driver imx_dsp_rproc_driver = { + .probe = imx_dsp_rproc_probe, + .remove = imx_dsp_rproc_remove, + .driver = { + .name = "imx-dsp-rproc", + .of_match_table = imx_dsp_rproc_of_match, + .pm = &imx_dsp_rproc_pm_ops, + }, +}; +module_platform_driver(imx_dsp_rproc_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("i.MX HiFi Core Remote Processor Control Driver"); +MODULE_AUTHOR("Shengjiu Wang <shengjiu.wang@nxp.com>"); diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index d88f76f5305e..ff8170dbbc3c 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -19,6 +19,7 @@ #include <linux/remoteproc.h> #include <linux/workqueue.h> +#include "imx_rproc.h" #include "remoteproc_internal.h" #define IMX7D_SRC_SCR 0x0C @@ -71,33 +72,7 @@ struct imx_rproc_mem { /* att flags */ /* M4 own area. Can be mapped at probe */ #define ATT_OWN BIT(1) - -/* address translation table */ -struct imx_rproc_att { - u32 da; /* device address (From Cortex M4 view)*/ - u32 sa; /* system bus address */ - u32 size; /* size of reg range */ - int flags; -}; - -/* Remote core start/stop method */ -enum imx_rproc_method { - IMX_RPROC_NONE, - /* Through syscon regmap */ - IMX_RPROC_MMIO, - /* Through ARM SMCCC */ - IMX_RPROC_SMC, -}; - -struct imx_rproc_dcfg { - u32 src_reg; - u32 src_mask; - u32 src_start; - u32 src_stop; - const struct imx_rproc_att *att; - size_t att_size; - enum imx_rproc_method method; -}; +#define ATT_IOMEM BIT(2) struct imx_rproc { struct device *dev; @@ -117,7 +92,7 @@ struct imx_rproc { static const struct imx_rproc_att imx_rproc_att_imx8mn[] = { /* dev addr , sys addr , size , flags */ /* ITCM */ - { 0x00000000, 0x007E0000, 0x00020000, ATT_OWN }, + { 0x00000000, 0x007E0000, 0x00020000, ATT_OWN | ATT_IOMEM }, /* OCRAM_S */ { 0x00180000, 0x00180000, 0x00009000, 0 }, /* OCRAM */ @@ -131,7 +106,7 @@ static const struct imx_rproc_att imx_rproc_att_imx8mn[] = { /* DDR (Code) - alias */ { 0x10000000, 0x40000000, 0x0FFE0000, 0 }, /* DTCM */ - { 0x20000000, 0x00800000, 0x00020000, ATT_OWN }, + { 0x20000000, 0x00800000, 0x00020000, ATT_OWN | ATT_IOMEM }, /* OCRAM_S - alias */ { 0x20180000, 0x00180000, 0x00008000, ATT_OWN }, /* OCRAM */ @@ -147,7 +122,7 @@ static const struct imx_rproc_att imx_rproc_att_imx8mn[] = { static const struct imx_rproc_att imx_rproc_att_imx8mq[] = { /* dev addr , sys addr , size , flags */ /* TCML - alias */ - { 0x00000000, 0x007e0000, 0x00020000, 0 }, + { 0x00000000, 0x007e0000, 0x00020000, ATT_IOMEM}, /* OCRAM_S */ { 0x00180000, 0x00180000, 0x00008000, 0 }, /* OCRAM */ @@ -159,9 +134,9 @@ static const struct imx_rproc_att imx_rproc_att_imx8mq[] = { /* DDR (Code) - alias */ { 0x10000000, 0x80000000, 0x0FFE0000, 0 }, /* TCML */ - { 0x1FFE0000, 0x007E0000, 0x00020000, ATT_OWN }, + { 0x1FFE0000, 0x007E0000, 0x00020000, ATT_OWN | ATT_IOMEM}, /* TCMU */ - { 0x20000000, 0x00800000, 0x00020000, ATT_OWN }, + { 0x20000000, 0x00800000, 0x00020000, ATT_OWN | ATT_IOMEM}, /* OCRAM_S */ { 0x20180000, 0x00180000, 0x00008000, ATT_OWN }, /* OCRAM */ @@ -199,12 +174,12 @@ static const struct imx_rproc_att imx_rproc_att_imx7d[] = { /* OCRAM_PXP (Code) - alias */ { 0x00940000, 0x00940000, 0x00008000, 0 }, /* TCML (Code) */ - { 0x1FFF8000, 0x007F8000, 0x00008000, ATT_OWN }, + { 0x1FFF8000, 0x007F8000, 0x00008000, ATT_OWN | ATT_IOMEM }, /* DDR (Code) - alias, first part of DDR (Data) */ { 0x10000000, 0x80000000, 0x0FFF0000, 0 }, /* TCMU (Data) */ - { 0x20000000, 0x00800000, 0x00008000, ATT_OWN }, + { 0x20000000, 0x00800000, 0x00008000, ATT_OWN | ATT_IOMEM }, /* OCRAM (Data) */ { 0x20200000, 0x00900000, 0x00020000, 0 }, /* OCRAM_EPDC (Data) */ @@ -218,18 +193,18 @@ static const struct imx_rproc_att imx_rproc_att_imx7d[] = { static const struct imx_rproc_att imx_rproc_att_imx6sx[] = { /* dev addr , sys addr , size , flags */ /* TCML (M4 Boot Code) - alias */ - { 0x00000000, 0x007F8000, 0x00008000, 0 }, + { 0x00000000, 0x007F8000, 0x00008000, ATT_IOMEM }, /* OCRAM_S (Code) */ { 0x00180000, 0x008F8000, 0x00004000, 0 }, /* OCRAM_S (Code) - alias */ { 0x00180000, 0x008FC000, 0x00004000, 0 }, /* TCML (Code) */ - { 0x1FFF8000, 0x007F8000, 0x00008000, ATT_OWN }, + { 0x1FFF8000, 0x007F8000, 0x00008000, ATT_OWN | ATT_IOMEM }, /* DDR (Code) - alias, first part of DDR (Data) */ { 0x10000000, 0x80000000, 0x0FFF8000, 0 }, /* TCMU (Data) */ - { 0x20000000, 0x00800000, 0x00008000, ATT_OWN }, + { 0x20000000, 0x00800000, 0x00008000, ATT_OWN | ATT_IOMEM }, /* OCRAM_S (Data) - alias? */ { 0x208F8000, 0x008F8000, 0x00004000, 0 }, /* DDR (Data) */ @@ -341,7 +316,7 @@ static int imx_rproc_stop(struct rproc *rproc) } static int imx_rproc_da_to_sys(struct imx_rproc *priv, u64 da, - size_t len, u64 *sys) + size_t len, u64 *sys, bool *is_iomem) { const struct imx_rproc_dcfg *dcfg = priv->dcfg; int i; @@ -354,6 +329,8 @@ static int imx_rproc_da_to_sys(struct imx_rproc *priv, u64 da, unsigned int offset = da - att->da; *sys = att->sa + offset; + if (is_iomem) + *is_iomem = att->flags & ATT_IOMEM; return 0; } } @@ -377,7 +354,7 @@ static void *imx_rproc_da_to_va(struct rproc *rproc, u64 da, size_t len, bool *i * On device side we have many aliases, so we need to convert device * address (M4) to system bus address first. */ - if (imx_rproc_da_to_sys(priv, da, len, &sys)) + if (imx_rproc_da_to_sys(priv, da, len, &sys, is_iomem)) return NULL; for (i = 0; i < IMX_RPROC_MEM_MAX; i++) { @@ -553,8 +530,12 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, if (b >= IMX_RPROC_MEM_MAX) break; - priv->mem[b].cpu_addr = devm_ioremap(&pdev->dev, - att->sa, att->size); + if (att->flags & ATT_IOMEM) + priv->mem[b].cpu_addr = devm_ioremap(&pdev->dev, + att->sa, att->size); + else + priv->mem[b].cpu_addr = devm_ioremap_wc(&pdev->dev, + att->sa, att->size); if (!priv->mem[b].cpu_addr) { dev_err(dev, "failed to remap %#x bytes from %#x\n", att->size, att->sa); return -ENOMEM; @@ -575,8 +556,8 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, struct resource res; node = of_parse_phandle(np, "memory-region", a); - /* Not map vdev region */ - if (!strcmp(node->name, "vdev")) + /* Not map vdevbuffer, vdevring region */ + if (!strncmp(node->name, "vdev", strlen("vdev"))) continue; err = of_address_to_resource(node, 0, &res); if (err) { @@ -590,14 +571,14 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, break; /* Not use resource version, because we might share region */ - priv->mem[b].cpu_addr = devm_ioremap(&pdev->dev, res.start, resource_size(&res)); + priv->mem[b].cpu_addr = devm_ioremap_wc(&pdev->dev, res.start, resource_size(&res)); if (!priv->mem[b].cpu_addr) { dev_err(dev, "failed to remap %pr\n", &res); return -ENOMEM; } priv->mem[b].sys_addr = res.start; priv->mem[b].size = resource_size(&res); - if (!strcmp(node->name, "rsc_table")) + if (!strcmp(node->name, "rsc-table")) priv->rsc_table = priv->mem[b].cpu_addr; b++; } diff --git a/drivers/remoteproc/imx_rproc.h b/drivers/remoteproc/imx_rproc.h new file mode 100644 index 000000000000..1c7e2127c758 --- /dev/null +++ b/drivers/remoteproc/imx_rproc.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> + * Copyright 2021 NXP + */ + +#ifndef _IMX_RPROC_H +#define _IMX_RPROC_H + +/* address translation table */ +struct imx_rproc_att { + u32 da; /* device address (From Cortex M4 view)*/ + u32 sa; /* system bus address */ + u32 size; /* size of reg range */ + int flags; +}; + +/* Remote core start/stop method */ +enum imx_rproc_method { + IMX_RPROC_NONE, + /* Through syscon regmap */ + IMX_RPROC_MMIO, + /* Through ARM SMCCC */ + IMX_RPROC_SMC, + /* Through System Control Unit API */ + IMX_RPROC_SCU_API, +}; + +struct imx_rproc_dcfg { + u32 src_reg; + u32 src_mask; + u32 src_start; + u32 src_stop; + const struct imx_rproc_att *att; + size_t att_size; + enum imx_rproc_method method; +}; + +#endif /* _IMX_RPROC_H */ diff --git a/drivers/remoteproc/meson_mx_ao_arc.c b/drivers/remoteproc/meson_mx_ao_arc.c new file mode 100644 index 000000000000..462cddab6518 --- /dev/null +++ b/drivers/remoteproc/meson_mx_ao_arc.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2020 Martin Blumenstingl <martin.blumenstingl@googlemail.com> + */ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/genalloc.h> +#include <linux/io.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/property.h> +#include <linux/regmap.h> +#include <linux/remoteproc.h> +#include <linux/reset.h> +#include <linux/sizes.h> + +#include "remoteproc_internal.h" + +#define AO_REMAP_REG0 0x0 +#define AO_REMAP_REG0_REMAP_AHB_SRAM_BITS_17_14_FOR_ARM_CPU GENMASK(3, 0) + +#define AO_REMAP_REG1 0x4 +#define AO_REMAP_REG1_MOVE_AHB_SRAM_TO_0X0_INSTEAD_OF_DDR BIT(4) +#define AO_REMAP_REG1_REMAP_AHB_SRAM_BITS_17_14_FOR_MEDIA_CPU GENMASK(3, 0) + +#define AO_CPU_CNTL 0x0 +#define AO_CPU_CNTL_AHB_SRAM_BITS_31_20 GENMASK(28, 16) +#define AO_CPU_CNTL_HALT BIT(9) +#define AO_CPU_CNTL_UNKNONWN BIT(8) +#define AO_CPU_CNTL_RUN BIT(0) + +#define AO_CPU_STAT 0x4 + +#define AO_SECURE_REG0 0x0 +#define AO_SECURE_REG0_AHB_SRAM_BITS_19_12 GENMASK(15, 8) + +/* Only bits [31:20] and [17:14] are usable, all other bits must be zero */ +#define MESON_AO_RPROC_SRAM_USABLE_BITS 0xfff3c000ULL + +#define MESON_AO_RPROC_MEMORY_OFFSET 0x10000000 + +struct meson_mx_ao_arc_rproc_priv { + void __iomem *remap_base; + void __iomem *cpu_base; + unsigned long sram_va; + phys_addr_t sram_pa; + size_t sram_size; + struct gen_pool *sram_pool; + struct reset_control *arc_reset; + struct clk *arc_pclk; + struct regmap *secbus2_regmap; +}; + +static int meson_mx_ao_arc_rproc_start(struct rproc *rproc) +{ + struct meson_mx_ao_arc_rproc_priv *priv = rproc->priv; + phys_addr_t translated_sram_addr; + u32 tmp; + int ret; + + ret = clk_prepare_enable(priv->arc_pclk); + if (ret) + return ret; + + tmp = FIELD_PREP(AO_REMAP_REG0_REMAP_AHB_SRAM_BITS_17_14_FOR_ARM_CPU, + priv->sram_pa >> 14); + writel(tmp, priv->remap_base + AO_REMAP_REG0); + + /* + * The SRAM content as seen by the ARC core always starts at 0x0 + * regardless of the value given here (this was discovered by trial and + * error). For SoCs older than Meson6 we probably have to set + * AO_REMAP_REG1_MOVE_AHB_SRAM_TO_0X0_INSTEAD_OF_DDR to achieve the + * same. (At least) For Meson8 and newer that bit must not be set. + */ + writel(0x0, priv->remap_base + AO_REMAP_REG1); + + regmap_update_bits(priv->secbus2_regmap, AO_SECURE_REG0, + AO_SECURE_REG0_AHB_SRAM_BITS_19_12, + FIELD_PREP(AO_SECURE_REG0_AHB_SRAM_BITS_19_12, + priv->sram_pa >> 12)); + + ret = reset_control_reset(priv->arc_reset); + if (ret) { + clk_disable_unprepare(priv->arc_pclk); + return ret; + } + + usleep_range(10, 100); + + /* + * Convert from 0xd9000000 to 0xc9000000 as the vendor driver does. + * This only seems to be relevant for the AO_CPU_CNTL register. It is + * unknown why this is needed. + */ + translated_sram_addr = priv->sram_pa - MESON_AO_RPROC_MEMORY_OFFSET; + + tmp = FIELD_PREP(AO_CPU_CNTL_AHB_SRAM_BITS_31_20, + translated_sram_addr >> 20); + tmp |= AO_CPU_CNTL_UNKNONWN | AO_CPU_CNTL_RUN; + writel(tmp, priv->cpu_base + AO_CPU_CNTL); + + usleep_range(20, 200); + + return 0; +} + +static int meson_mx_ao_arc_rproc_stop(struct rproc *rproc) +{ + struct meson_mx_ao_arc_rproc_priv *priv = rproc->priv; + + writel(AO_CPU_CNTL_HALT, priv->cpu_base + AO_CPU_CNTL); + + clk_disable_unprepare(priv->arc_pclk); + + return 0; +} + +static void *meson_mx_ao_arc_rproc_da_to_va(struct rproc *rproc, u64 da, + size_t len, bool *is_iomem) +{ + struct meson_mx_ao_arc_rproc_priv *priv = rproc->priv; + + /* The memory from the ARC core's perspective always starts at 0x0. */ + if ((da + len) > priv->sram_size) + return NULL; + + return (void *)priv->sram_va + da; +} + +static struct rproc_ops meson_mx_ao_arc_rproc_ops = { + .start = meson_mx_ao_arc_rproc_start, + .stop = meson_mx_ao_arc_rproc_stop, + .da_to_va = meson_mx_ao_arc_rproc_da_to_va, + .get_boot_addr = rproc_elf_get_boot_addr, + .load = rproc_elf_load_segments, + .sanity_check = rproc_elf_sanity_check, +}; + +static int meson_mx_ao_arc_rproc_probe(struct platform_device *pdev) +{ + struct meson_mx_ao_arc_rproc_priv *priv; + struct device *dev = &pdev->dev; + const char *fw_name = NULL; + struct rproc *rproc; + int ret; + + device_property_read_string(dev, "firmware-name", &fw_name); + + rproc = devm_rproc_alloc(dev, "meson-mx-ao-arc", + &meson_mx_ao_arc_rproc_ops, fw_name, + sizeof(*priv)); + if (!rproc) + return -ENOMEM; + + rproc->has_iommu = false; + priv = rproc->priv; + + priv->sram_pool = of_gen_pool_get(dev->of_node, "sram", 0); + if (!priv->sram_pool) { + dev_err(dev, "Could not get SRAM pool\n"); + return -ENODEV; + } + + priv->sram_size = gen_pool_avail(priv->sram_pool); + + priv->sram_va = gen_pool_alloc(priv->sram_pool, priv->sram_size); + if (!priv->sram_va) { + dev_err(dev, "Could not alloc memory in SRAM pool\n"); + return -ENOMEM; + } + + priv->sram_pa = gen_pool_virt_to_phys(priv->sram_pool, priv->sram_va); + if (priv->sram_pa & ~MESON_AO_RPROC_SRAM_USABLE_BITS) { + dev_err(dev, "SRAM address contains unusable bits\n"); + ret = -EINVAL; + goto err_free_genpool; + } + + priv->secbus2_regmap = syscon_regmap_lookup_by_phandle(dev->of_node, + "amlogic,secbus2"); + if (IS_ERR(priv->secbus2_regmap)) { + dev_err(dev, "Failed to find SECBUS2 regmap\n"); + ret = PTR_ERR(priv->secbus2_regmap); + goto err_free_genpool; + } + + priv->remap_base = devm_platform_ioremap_resource_byname(pdev, "remap"); + if (IS_ERR(priv->remap_base)) { + ret = PTR_ERR(priv->remap_base); + goto err_free_genpool; + } + + priv->cpu_base = devm_platform_ioremap_resource_byname(pdev, "cpu"); + if (IS_ERR(priv->cpu_base)) { + ret = PTR_ERR(priv->cpu_base); + goto err_free_genpool; + } + + priv->arc_reset = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(priv->arc_reset)) { + dev_err(dev, "Failed to get ARC reset\n"); + ret = PTR_ERR(priv->arc_reset); + goto err_free_genpool; + } + + priv->arc_pclk = devm_clk_get(dev, NULL); + if (IS_ERR(priv->arc_pclk)) { + dev_err(dev, "Failed to get the ARC PCLK\n"); + ret = PTR_ERR(priv->arc_pclk); + goto err_free_genpool; + } + + platform_set_drvdata(pdev, rproc); + + ret = rproc_add(rproc); + if (ret) + goto err_free_genpool; + + return 0; + +err_free_genpool: + gen_pool_free(priv->sram_pool, priv->sram_va, priv->sram_size); + return ret; +} + +static int meson_mx_ao_arc_rproc_remove(struct platform_device *pdev) +{ + struct rproc *rproc = platform_get_drvdata(pdev); + struct meson_mx_ao_arc_rproc_priv *priv = rproc->priv; + + rproc_del(rproc); + gen_pool_free(priv->sram_pool, priv->sram_va, priv->sram_size); + + return 0; +} + +static const struct of_device_id meson_mx_ao_arc_rproc_match[] = { + { .compatible = "amlogic,meson8-ao-arc" }, + { .compatible = "amlogic,meson8b-ao-arc" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, meson_mx_ao_arc_rproc_match); + +static struct platform_driver meson_mx_ao_arc_rproc_driver = { + .probe = meson_mx_ao_arc_rproc_probe, + .remove = meson_mx_ao_arc_rproc_remove, + .driver = { + .name = "meson-mx-ao-arc-rproc", + .of_match_table = meson_mx_ao_arc_rproc_match, + }, +}; +module_platform_driver(meson_mx_ao_arc_rproc_driver); + +MODULE_DESCRIPTION("Amlogic Meson6/8/8b/8m2 AO ARC remote processor driver"); +MODULE_AUTHOR("Martin Blumenstingl <martin.blumenstingl@googlemail.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/remoteproc/mtk_common.h b/drivers/remoteproc/mtk_common.h index 61901f5efa05..5ff3867c72f3 100644 --- a/drivers/remoteproc/mtk_common.h +++ b/drivers/remoteproc/mtk_common.h @@ -72,6 +72,7 @@ struct scp_ipi_desc { struct mtk_scp; struct mtk_scp_of_data { + int (*scp_clk_get)(struct mtk_scp *scp); int (*scp_before_load)(struct mtk_scp *scp); void (*scp_irq_handler)(struct mtk_scp *scp); void (*scp_reset_assert)(struct mtk_scp *scp); diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index 9679cc26895e..36e48cf58ed6 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -312,6 +312,32 @@ static int scp_elf_read_ipi_buf_addr(struct mtk_scp *scp, return -ENOENT; } +static int mt8183_scp_clk_get(struct mtk_scp *scp) +{ + struct device *dev = scp->dev; + int ret = 0; + + scp->clk = devm_clk_get(dev, "main"); + if (IS_ERR(scp->clk)) { + dev_err(dev, "Failed to get clock\n"); + ret = PTR_ERR(scp->clk); + } + + return ret; +} + +static int mt8192_scp_clk_get(struct mtk_scp *scp) +{ + return mt8183_scp_clk_get(scp); +} + +static int mt8195_scp_clk_get(struct mtk_scp *scp) +{ + scp->clk = NULL; + + return 0; +} + static int mt8183_scp_before_load(struct mtk_scp *scp) { /* Clear SCP to host interrupt */ @@ -785,12 +811,9 @@ static int scp_probe(struct platform_device *pdev) if (ret) goto destroy_mutex; - scp->clk = devm_clk_get(dev, "main"); - if (IS_ERR(scp->clk)) { - dev_err(dev, "Failed to get clock\n"); - ret = PTR_ERR(scp->clk); + ret = scp->data->scp_clk_get(scp); + if (ret) goto release_dev_mem; - } /* register SCP initialization IPI */ ret = scp_ipi_register(scp, SCP_IPI_INIT, scp_init_ipi_handler, scp); @@ -852,6 +875,7 @@ static int scp_remove(struct platform_device *pdev) } static const struct mtk_scp_of_data mt8183_of_data = { + .scp_clk_get = mt8183_scp_clk_get, .scp_before_load = mt8183_scp_before_load, .scp_irq_handler = mt8183_scp_irq_handler, .scp_reset_assert = mt8183_scp_reset_assert, @@ -864,6 +888,19 @@ static const struct mtk_scp_of_data mt8183_of_data = { }; static const struct mtk_scp_of_data mt8192_of_data = { + .scp_clk_get = mt8192_scp_clk_get, + .scp_before_load = mt8192_scp_before_load, + .scp_irq_handler = mt8192_scp_irq_handler, + .scp_reset_assert = mt8192_scp_reset_assert, + .scp_reset_deassert = mt8192_scp_reset_deassert, + .scp_stop = mt8192_scp_stop, + .scp_da_to_va = mt8192_scp_da_to_va, + .host_to_scp_reg = MT8192_GIPC_IN_SET, + .host_to_scp_int_bit = MT8192_HOST_IPC_INT_BIT, +}; + +static const struct mtk_scp_of_data mt8195_of_data = { + .scp_clk_get = mt8195_scp_clk_get, .scp_before_load = mt8192_scp_before_load, .scp_irq_handler = mt8192_scp_irq_handler, .scp_reset_assert = mt8192_scp_reset_assert, @@ -877,6 +914,7 @@ static const struct mtk_scp_of_data mt8192_of_data = { static const struct of_device_id mtk_scp_of_match[] = { { .compatible = "mediatek,mt8183-scp", .data = &mt8183_of_data }, { .compatible = "mediatek,mt8192-scp", .data = &mt8192_of_data }, + { .compatible = "mediatek,mt8195-scp", .data = &mt8195_of_data }, {}, }; MODULE_DEVICE_TABLE(of, mtk_scp_of_match); diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c index 43531caa1959..32a588fefbdc 100644 --- a/drivers/remoteproc/omap_remoteproc.c +++ b/drivers/remoteproc/omap_remoteproc.c @@ -901,8 +901,7 @@ out: static int __maybe_unused omap_rproc_suspend(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct rproc *rproc = platform_get_drvdata(pdev); + struct rproc *rproc = dev_get_drvdata(dev); struct omap_rproc *oproc = rproc->priv; int ret = 0; @@ -938,8 +937,7 @@ out: static int __maybe_unused omap_rproc_resume(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct rproc *rproc = platform_get_drvdata(pdev); + struct rproc *rproc = dev_get_drvdata(dev); struct omap_rproc *oproc = rproc->priv; int ret = 0; diff --git a/drivers/remoteproc/qcom_q6v5.c b/drivers/remoteproc/qcom_q6v5.c index 7e9244c748da..eada7e34f3af 100644 --- a/drivers/remoteproc/qcom_q6v5.c +++ b/drivers/remoteproc/qcom_q6v5.c @@ -16,8 +16,30 @@ #include "qcom_common.h" #include "qcom_q6v5.h" +#define Q6V5_LOAD_STATE_MSG_LEN 64 #define Q6V5_PANIC_DELAY_MS 200 +static int q6v5_load_state_toggle(struct qcom_q6v5 *q6v5, bool enable) +{ + char buf[Q6V5_LOAD_STATE_MSG_LEN]; + int ret; + + if (!q6v5->qmp) + return 0; + + ret = snprintf(buf, sizeof(buf), + "{class: image, res: load_state, name: %s, val: %s}", + q6v5->load_state, enable ? "on" : "off"); + + WARN_ON(ret >= Q6V5_LOAD_STATE_MSG_LEN); + + ret = qmp_send(q6v5->qmp, buf, sizeof(buf)); + if (ret) + dev_err(q6v5->dev, "failed to toggle load state\n"); + + return ret; +} + /** * qcom_q6v5_prepare() - reinitialize the qcom_q6v5 context before start * @q6v5: reference to qcom_q6v5 context to be reinitialized @@ -26,6 +48,12 @@ */ int qcom_q6v5_prepare(struct qcom_q6v5 *q6v5) { + int ret; + + ret = q6v5_load_state_toggle(q6v5, true); + if (ret) + return ret; + reinit_completion(&q6v5->start_done); reinit_completion(&q6v5->stop_done); @@ -47,6 +75,7 @@ EXPORT_SYMBOL_GPL(qcom_q6v5_prepare); int qcom_q6v5_unprepare(struct qcom_q6v5 *q6v5) { disable_irq(q6v5->handover_irq); + q6v5_load_state_toggle(q6v5, false); return !q6v5->handover_issued; } @@ -196,12 +225,13 @@ EXPORT_SYMBOL_GPL(qcom_q6v5_panic); * @pdev: platform_device reference for acquiring resources * @rproc: associated remoteproc instance * @crash_reason: SMEM id for crash reason string, or 0 if none + * @load_state: load state resource string * @handover: function to be called when proxy resources should be released * * Return: 0 on success, negative errno on failure */ int qcom_q6v5_init(struct qcom_q6v5 *q6v5, struct platform_device *pdev, - struct rproc *rproc, int crash_reason, + struct rproc *rproc, int crash_reason, const char *load_state, void (*handover)(struct qcom_q6v5 *q6v5)) { int ret; @@ -286,9 +316,34 @@ int qcom_q6v5_init(struct qcom_q6v5 *q6v5, struct platform_device *pdev, return PTR_ERR(q6v5->state); } + q6v5->load_state = devm_kstrdup_const(&pdev->dev, load_state, GFP_KERNEL); + q6v5->qmp = qmp_get(&pdev->dev); + if (IS_ERR(q6v5->qmp)) { + if (PTR_ERR(q6v5->qmp) != -ENODEV) + return dev_err_probe(&pdev->dev, PTR_ERR(q6v5->qmp), + "failed to acquire load state\n"); + q6v5->qmp = NULL; + } else if (!q6v5->load_state) { + if (!load_state) + dev_err(&pdev->dev, "load state resource string empty\n"); + + qmp_put(q6v5->qmp); + return load_state ? -ENOMEM : -EINVAL; + } + return 0; } EXPORT_SYMBOL_GPL(qcom_q6v5_init); +/** + * qcom_q6v5_deinit() - deinitialize the q6v5 common struct + * @q6v5: reference to qcom_q6v5 context to be deinitialized + */ +void qcom_q6v5_deinit(struct qcom_q6v5 *q6v5) +{ + qmp_put(q6v5->qmp); +} +EXPORT_SYMBOL_GPL(qcom_q6v5_deinit); + MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Qualcomm Peripheral Image Loader for Q6V5"); diff --git a/drivers/remoteproc/qcom_q6v5.h b/drivers/remoteproc/qcom_q6v5.h index 1c212f670cbc..f35e04471ed7 100644 --- a/drivers/remoteproc/qcom_q6v5.h +++ b/drivers/remoteproc/qcom_q6v5.h @@ -5,6 +5,7 @@ #include <linux/kernel.h> #include <linux/completion.h> +#include <linux/soc/qcom/qcom_aoss.h> struct rproc; struct qcom_smem_state; @@ -15,6 +16,8 @@ struct qcom_q6v5 { struct rproc *rproc; struct qcom_smem_state *state; + struct qmp *qmp; + unsigned stop_bit; int wdog_irq; @@ -32,12 +35,14 @@ struct qcom_q6v5 { bool running; + const char *load_state; void (*handover)(struct qcom_q6v5 *q6v5); }; int qcom_q6v5_init(struct qcom_q6v5 *q6v5, struct platform_device *pdev, - struct rproc *rproc, int crash_reason, + struct rproc *rproc, int crash_reason, const char *load_state, void (*handover)(struct qcom_q6v5 *q6v5)); +void qcom_q6v5_deinit(struct qcom_q6v5 *q6v5); int qcom_q6v5_prepare(struct qcom_q6v5 *q6v5); int qcom_q6v5_unprepare(struct qcom_q6v5 *q6v5); diff --git a/drivers/remoteproc/qcom_q6v5_adsp.c b/drivers/remoteproc/qcom_q6v5_adsp.c index 8b0d8bbacd2e..098362e6e233 100644 --- a/drivers/remoteproc/qcom_q6v5_adsp.c +++ b/drivers/remoteproc/qcom_q6v5_adsp.c @@ -185,7 +185,9 @@ static int adsp_start(struct rproc *rproc) int ret; unsigned int val; - qcom_q6v5_prepare(&adsp->q6v5); + ret = qcom_q6v5_prepare(&adsp->q6v5); + if (ret) + return ret; ret = clk_prepare_enable(adsp->xo); if (ret) @@ -465,7 +467,7 @@ static int adsp_probe(struct platform_device *pdev) if (ret) goto disable_pm; - ret = qcom_q6v5_init(&adsp->q6v5, pdev, rproc, desc->crash_reason_smem, + ret = qcom_q6v5_init(&adsp->q6v5, pdev, rproc, desc->crash_reason_smem, NULL, qcom_adsp_pil_handover); if (ret) goto disable_pm; @@ -500,6 +502,7 @@ static int adsp_remove(struct platform_device *pdev) rproc_del(adsp->rproc); + qcom_q6v5_deinit(&adsp->q6v5); qcom_remove_glink_subdev(adsp->rproc, &adsp->glink_subdev); qcom_remove_sysmon_subdev(adsp->sysmon); qcom_remove_ssr_subdev(adsp->rproc, &adsp->ssr_subdev); diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 423b31dfa574..43ea8455546c 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -77,6 +77,14 @@ #define HALT_ACK_TIMEOUT_US 100000 +/* QACCEPT Register Offsets */ +#define QACCEPT_ACCEPT_REG 0x0 +#define QACCEPT_ACTIVE_REG 0x4 +#define QACCEPT_DENY_REG 0x8 +#define QACCEPT_REQ_REG 0xC + +#define QACCEPT_TIMEOUT_US 50 + /* QDSP6SS_RESET */ #define Q6SS_STOP_CORE BIT(0) #define Q6SS_CORE_ARES BIT(1) @@ -137,13 +145,15 @@ struct rproc_hexagon_res { char **proxy_clk_names; char **reset_clk_names; char **active_clk_names; - char **active_pd_names; char **proxy_pd_names; int version; bool need_mem_protection; bool has_alt_reset; bool has_mba_logs; bool has_spare_reg; + bool has_qaccept_regs; + bool has_ext_cntl_regs; + bool has_vq6; }; struct q6v5 { @@ -159,8 +169,18 @@ struct q6v5 { u32 halt_q6; u32 halt_modem; u32 halt_nc; + u32 halt_vq6; u32 conn_box; + u32 qaccept_mdm; + u32 qaccept_cx; + u32 qaccept_axi; + + u32 axim1_clk_off; + u32 crypto_clk_off; + u32 force_clk_on; + u32 rscc_disable; + struct reset_control *mss_restart; struct reset_control *pdc_reset; @@ -169,12 +189,10 @@ struct q6v5 { struct clk *active_clks[8]; struct clk *reset_clks[4]; struct clk *proxy_clks[4]; - struct device *active_pds[1]; struct device *proxy_pds[3]; int active_clk_count; int reset_clk_count; int proxy_clk_count; - int active_pd_count; int proxy_pd_count; struct reg_info active_regs[1]; @@ -204,6 +222,9 @@ struct q6v5 { bool has_alt_reset; bool has_mba_logs; bool has_spare_reg; + bool has_qaccept_regs; + bool has_ext_cntl_regs; + bool has_vq6; int mpss_perm; int mba_perm; const char *hexagon_mdt_image; @@ -216,6 +237,7 @@ enum { MSS_MSM8996, MSS_MSM8998, MSS_SC7180, + MSS_SC7280, MSS_SDM845, }; @@ -476,6 +498,12 @@ static int q6v5_reset_assert(struct q6v5 *qproc) regmap_update_bits(qproc->conn_map, qproc->conn_box, AXI_GATING_VALID_OVERRIDE, 0); ret = reset_control_deassert(qproc->mss_restart); + } else if (qproc->has_ext_cntl_regs) { + regmap_write(qproc->conn_map, qproc->rscc_disable, 0); + reset_control_assert(qproc->pdc_reset); + reset_control_assert(qproc->mss_restart); + reset_control_deassert(qproc->pdc_reset); + ret = reset_control_deassert(qproc->mss_restart); } else { ret = reset_control_assert(qproc->mss_restart); } @@ -493,7 +521,7 @@ static int q6v5_reset_deassert(struct q6v5 *qproc) ret = reset_control_reset(qproc->mss_restart); writel(0, qproc->rmb_base + RMB_MBA_ALT_RESET); reset_control_deassert(qproc->pdc_reset); - } else if (qproc->has_spare_reg) { + } else if (qproc->has_spare_reg || qproc->has_ext_cntl_regs) { ret = reset_control_reset(qproc->mss_restart); } else { ret = reset_control_deassert(qproc->mss_restart); @@ -607,7 +635,7 @@ static int q6v5proc_reset(struct q6v5 *qproc) } goto pbl_wait; - } else if (qproc->version == MSS_SC7180) { + } else if (qproc->version == MSS_SC7180 || qproc->version == MSS_SC7280) { val = readl(qproc->reg_base + QDSP6SS_SLEEP); val |= Q6SS_CBCR_CLKEN; writel(val, qproc->reg_base + QDSP6SS_SLEEP); @@ -790,6 +818,89 @@ pbl_wait: return ret; } +static int q6v5proc_enable_qchannel(struct q6v5 *qproc, struct regmap *map, u32 offset) +{ + unsigned int val; + int ret; + + if (!qproc->has_qaccept_regs) + return 0; + + if (qproc->has_ext_cntl_regs) { + regmap_write(qproc->conn_map, qproc->rscc_disable, 0); + regmap_write(qproc->conn_map, qproc->force_clk_on, 1); + + ret = regmap_read_poll_timeout(qproc->halt_map, qproc->axim1_clk_off, val, + !val, 1, Q6SS_CBCR_TIMEOUT_US); + if (ret) { + dev_err(qproc->dev, "failed to enable axim1 clock\n"); + return -ETIMEDOUT; + } + } + + regmap_write(map, offset + QACCEPT_REQ_REG, 1); + + /* Wait for accept */ + ret = regmap_read_poll_timeout(map, offset + QACCEPT_ACCEPT_REG, val, val, 5, + QACCEPT_TIMEOUT_US); + if (ret) { + dev_err(qproc->dev, "qchannel enable failed\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static void q6v5proc_disable_qchannel(struct q6v5 *qproc, struct regmap *map, u32 offset) +{ + int ret; + unsigned int val, retry; + unsigned int nretry = 10; + bool takedown_complete = false; + + if (!qproc->has_qaccept_regs) + return; + + while (!takedown_complete && nretry) { + nretry--; + + /* Wait for active transactions to complete */ + regmap_read_poll_timeout(map, offset + QACCEPT_ACTIVE_REG, val, !val, 5, + QACCEPT_TIMEOUT_US); + + /* Request Q-channel transaction takedown */ + regmap_write(map, offset + QACCEPT_REQ_REG, 0); + + /* + * If the request is denied, reset the Q-channel takedown request, + * wait for active transactions to complete and retry takedown. + */ + retry = 10; + while (retry) { + usleep_range(5, 10); + retry--; + ret = regmap_read(map, offset + QACCEPT_DENY_REG, &val); + if (!ret && val) { + regmap_write(map, offset + QACCEPT_REQ_REG, 1); + break; + } + + ret = regmap_read(map, offset + QACCEPT_ACCEPT_REG, &val); + if (!ret && !val) { + takedown_complete = true; + break; + } + } + + if (!retry) + break; + } + + /* Rely on mss_restart to clear out pending transactions on takedown failure */ + if (!takedown_complete) + dev_err(qproc->dev, "qchannel takedown failed\n"); +} + static void q6v5proc_halt_axi_port(struct q6v5 *qproc, struct regmap *halt_map, u32 offset) @@ -895,18 +1006,14 @@ static int q6v5_mba_load(struct q6v5 *qproc) int xfermemop_ret; bool mba_load_err = false; - qcom_q6v5_prepare(&qproc->q6v5); - - ret = q6v5_pds_enable(qproc, qproc->active_pds, qproc->active_pd_count); - if (ret < 0) { - dev_err(qproc->dev, "failed to enable active power domains\n"); - goto disable_irqs; - } + ret = qcom_q6v5_prepare(&qproc->q6v5); + if (ret) + return ret; ret = q6v5_pds_enable(qproc, qproc->proxy_pds, qproc->proxy_pd_count); if (ret < 0) { dev_err(qproc->dev, "failed to enable proxy power domains\n"); - goto disable_active_pds; + goto disable_irqs; } ret = q6v5_regulator_enable(qproc, qproc->fallback_proxy_regs, @@ -957,6 +1064,12 @@ static int q6v5_mba_load(struct q6v5 *qproc) goto assert_reset; } + ret = q6v5proc_enable_qchannel(qproc, qproc->halt_map, qproc->qaccept_axi); + if (ret) { + dev_err(qproc->dev, "failed to enable axi bridge\n"); + goto disable_active_clks; + } + /* * Some versions of the MBA firmware will upon boot wipe the MPSS region as well, so provide * the Q6 access to this region. @@ -1003,8 +1116,13 @@ static int q6v5_mba_load(struct q6v5 *qproc) halt_axi_ports: q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6); + if (qproc->has_vq6) + q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_vq6); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc); + q6v5proc_disable_qchannel(qproc, qproc->halt_map, qproc->qaccept_mdm); + q6v5proc_disable_qchannel(qproc, qproc->halt_map, qproc->qaccept_cx); + q6v5proc_disable_qchannel(qproc, qproc->halt_map, qproc->qaccept_axi); mba_load_err = true; reclaim_mba: xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, true, @@ -1039,8 +1157,6 @@ disable_fallback_proxy_reg: qproc->fallback_proxy_reg_count); disable_proxy_pds: q6v5_pds_disable(qproc, qproc->proxy_pds, qproc->proxy_pd_count); -disable_active_pds: - q6v5_pds_disable(qproc, qproc->active_pds, qproc->active_pd_count); disable_irqs: qcom_q6v5_unprepare(&qproc->q6v5); @@ -1056,6 +1172,8 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc) qproc->dp_size = 0; q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6); + if (qproc->has_vq6) + q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_vq6); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc); if (qproc->version == MSS_MSM8996) { @@ -1068,6 +1186,24 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc) writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG); } + if (qproc->has_ext_cntl_regs) { + regmap_write(qproc->conn_map, qproc->rscc_disable, 1); + + ret = regmap_read_poll_timeout(qproc->halt_map, qproc->axim1_clk_off, val, + !val, 1, Q6SS_CBCR_TIMEOUT_US); + if (ret) + dev_err(qproc->dev, "failed to enable axim1 clock\n"); + + ret = regmap_read_poll_timeout(qproc->halt_map, qproc->crypto_clk_off, val, + !val, 1, Q6SS_CBCR_TIMEOUT_US); + if (ret) + dev_err(qproc->dev, "failed to enable crypto clock\n"); + } + + q6v5proc_disable_qchannel(qproc, qproc->halt_map, qproc->qaccept_mdm); + q6v5proc_disable_qchannel(qproc, qproc->halt_map, qproc->qaccept_cx); + q6v5proc_disable_qchannel(qproc, qproc->halt_map, qproc->qaccept_axi); + q6v5_reset_assert(qproc); q6v5_clk_disable(qproc->dev, qproc->reset_clks, @@ -1076,7 +1212,6 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc) qproc->active_clk_count); q6v5_regulator_disable(qproc, qproc->active_regs, qproc->active_reg_count); - q6v5_pds_disable(qproc, qproc->active_pds, qproc->active_pd_count); /* In case of failure or coredump scenario where reclaiming MBA memory * could not happen reclaim it here. @@ -1480,21 +1615,22 @@ static void qcom_msa_handover(struct qcom_q6v5 *q6v5) static int q6v5_init_mem(struct q6v5 *qproc, struct platform_device *pdev) { struct of_phandle_args args; - struct resource *res; + int halt_cell_cnt = 3; int ret; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qdsp6"); - qproc->reg_base = devm_ioremap_resource(&pdev->dev, res); + qproc->reg_base = devm_platform_ioremap_resource_byname(pdev, "qdsp6"); if (IS_ERR(qproc->reg_base)) return PTR_ERR(qproc->reg_base); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rmb"); - qproc->rmb_base = devm_ioremap_resource(&pdev->dev, res); + qproc->rmb_base = devm_platform_ioremap_resource_byname(pdev, "rmb"); if (IS_ERR(qproc->rmb_base)) return PTR_ERR(qproc->rmb_base); + if (qproc->has_vq6) + halt_cell_cnt++; + ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node, - "qcom,halt-regs", 3, 0, &args); + "qcom,halt-regs", halt_cell_cnt, 0, &args); if (ret < 0) { dev_err(&pdev->dev, "failed to parse qcom,halt-regs\n"); return -EINVAL; @@ -1509,6 +1645,52 @@ static int q6v5_init_mem(struct q6v5 *qproc, struct platform_device *pdev) qproc->halt_modem = args.args[1]; qproc->halt_nc = args.args[2]; + if (qproc->has_vq6) + qproc->halt_vq6 = args.args[3]; + + if (qproc->has_qaccept_regs) { + ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node, + "qcom,qaccept-regs", + 3, 0, &args); + if (ret < 0) { + dev_err(&pdev->dev, "failed to parse qaccept-regs\n"); + return -EINVAL; + } + + qproc->qaccept_mdm = args.args[0]; + qproc->qaccept_cx = args.args[1]; + qproc->qaccept_axi = args.args[2]; + } + + if (qproc->has_ext_cntl_regs) { + ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node, + "qcom,ext-regs", + 2, 0, &args); + if (ret < 0) { + dev_err(&pdev->dev, "failed to parse ext-regs index 0\n"); + return -EINVAL; + } + + qproc->conn_map = syscon_node_to_regmap(args.np); + of_node_put(args.np); + if (IS_ERR(qproc->conn_map)) + return PTR_ERR(qproc->conn_map); + + qproc->force_clk_on = args.args[0]; + qproc->rscc_disable = args.args[1]; + + ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node, + "qcom,ext-regs", + 2, 1, &args); + if (ret < 0) { + dev_err(&pdev->dev, "failed to parse ext-regs index 1\n"); + return -EINVAL; + } + + qproc->axim1_clk_off = args.args[0]; + qproc->crypto_clk_off = args.args[1]; + } + if (qproc->has_spare_reg) { ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node, "qcom,spare-regs", @@ -1600,7 +1782,7 @@ static int q6v5_init_reset(struct q6v5 *qproc) return PTR_ERR(qproc->mss_restart); } - if (qproc->has_alt_reset || qproc->has_spare_reg) { + if (qproc->has_alt_reset || qproc->has_spare_reg || qproc->has_ext_cntl_regs) { qproc->pdc_reset = devm_reset_control_get_exclusive(qproc->dev, "pdc_reset"); if (IS_ERR(qproc->pdc_reset)) { @@ -1707,6 +1889,9 @@ static int q6v5_probe(struct platform_device *pdev) platform_set_drvdata(pdev, qproc); + qproc->has_qaccept_regs = desc->has_qaccept_regs; + qproc->has_ext_cntl_regs = desc->has_ext_cntl_regs; + qproc->has_vq6 = desc->has_vq6; qproc->has_spare_reg = desc->has_spare_reg; ret = q6v5_init_mem(qproc, pdev); if (ret) @@ -1756,14 +1941,6 @@ static int q6v5_probe(struct platform_device *pdev) } qproc->active_reg_count = ret; - ret = q6v5_pds_attach(&pdev->dev, qproc->active_pds, - desc->active_pd_names); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to attach active power domains\n"); - goto free_rproc; - } - qproc->active_pd_count = ret; - ret = q6v5_pds_attach(&pdev->dev, qproc->proxy_pds, desc->proxy_pd_names); /* Fallback to regulators for old device trees */ @@ -1773,12 +1950,12 @@ static int q6v5_probe(struct platform_device *pdev) desc->fallback_proxy_supply); if (ret < 0) { dev_err(&pdev->dev, "Failed to get fallback proxy regulators.\n"); - goto detach_active_pds; + goto free_rproc; } qproc->fallback_proxy_reg_count = ret; } else if (ret < 0) { dev_err(&pdev->dev, "Failed to init power domains\n"); - goto detach_active_pds; + goto free_rproc; } else { qproc->proxy_pd_count = ret; } @@ -1792,7 +1969,7 @@ static int q6v5_probe(struct platform_device *pdev) qproc->need_mem_protection = desc->need_mem_protection; qproc->has_mba_logs = desc->has_mba_logs; - ret = qcom_q6v5_init(&qproc->q6v5, pdev, rproc, MPSS_CRASH_REASON_SMEM, + ret = qcom_q6v5_init(&qproc->q6v5, pdev, rproc, MPSS_CRASH_REASON_SMEM, "modem", qcom_msa_handover); if (ret) goto detach_proxy_pds; @@ -1822,8 +1999,6 @@ remove_subdevs: qcom_remove_glink_subdev(rproc, &qproc->glink_subdev); detach_proxy_pds: q6v5_pds_detach(qproc, qproc->proxy_pds, qproc->proxy_pd_count); -detach_active_pds: - q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count); free_rproc: rproc_free(rproc); @@ -1837,13 +2012,13 @@ static int q6v5_remove(struct platform_device *pdev) rproc_del(rproc); + qcom_q6v5_deinit(&qproc->q6v5); qcom_remove_sysmon_subdev(qproc->sysmon); qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev); qcom_remove_smd_subdev(rproc, &qproc->smd_subdev); qcom_remove_glink_subdev(rproc, &qproc->glink_subdev); q6v5_pds_detach(qproc, qproc->proxy_pds, qproc->proxy_pd_count); - q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count); rproc_free(rproc); @@ -1867,10 +2042,6 @@ static const struct rproc_hexagon_res sc7180_mss = { "nav", NULL }, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", "mx", @@ -1881,9 +2052,40 @@ static const struct rproc_hexagon_res sc7180_mss = { .has_alt_reset = false, .has_mba_logs = true, .has_spare_reg = true, + .has_qaccept_regs = false, + .has_ext_cntl_regs = false, + .has_vq6 = false, .version = MSS_SC7180, }; +static const struct rproc_hexagon_res sc7280_mss = { + .hexagon_mba_image = "mba.mbn", + .proxy_clk_names = (char*[]){ + "xo", + "pka", + NULL + }, + .active_clk_names = (char*[]){ + "iface", + "offline", + "snoc_axi", + NULL + }, + .proxy_pd_names = (char*[]){ + "cx", + "mss", + NULL + }, + .need_mem_protection = true, + .has_alt_reset = false, + .has_mba_logs = true, + .has_spare_reg = false, + .has_qaccept_regs = true, + .has_ext_cntl_regs = true, + .has_vq6 = true, + .version = MSS_SC7280, +}; + static const struct rproc_hexagon_res sdm845_mss = { .hexagon_mba_image = "mba.mbn", .proxy_clk_names = (char*[]){ @@ -1903,10 +2105,6 @@ static const struct rproc_hexagon_res sdm845_mss = { "mnoc_axi", NULL }, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", "mx", @@ -1917,6 +2115,9 @@ static const struct rproc_hexagon_res sdm845_mss = { .has_alt_reset = true, .has_mba_logs = false, .has_spare_reg = false, + .has_qaccept_regs = false, + .has_ext_cntl_regs = false, + .has_vq6 = false, .version = MSS_SDM845, }; @@ -1945,6 +2146,9 @@ static const struct rproc_hexagon_res msm8998_mss = { .has_alt_reset = false, .has_mba_logs = false, .has_spare_reg = false, + .has_qaccept_regs = false, + .has_ext_cntl_regs = false, + .has_vq6 = false, .version = MSS_MSM8998, }; @@ -1976,6 +2180,9 @@ static const struct rproc_hexagon_res msm8996_mss = { .has_alt_reset = false, .has_mba_logs = false, .has_spare_reg = false, + .has_qaccept_regs = false, + .has_ext_cntl_regs = false, + .has_vq6 = false, .version = MSS_MSM8996, }; @@ -2018,6 +2225,9 @@ static const struct rproc_hexagon_res msm8916_mss = { .has_alt_reset = false, .has_mba_logs = false, .has_spare_reg = false, + .has_qaccept_regs = false, + .has_ext_cntl_regs = false, + .has_vq6 = false, .version = MSS_MSM8916, }; @@ -2068,6 +2278,9 @@ static const struct rproc_hexagon_res msm8974_mss = { .has_alt_reset = false, .has_mba_logs = false, .has_spare_reg = false, + .has_qaccept_regs = false, + .has_ext_cntl_regs = false, + .has_vq6 = false, .version = MSS_MSM8974, }; @@ -2078,6 +2291,7 @@ static const struct of_device_id q6v5_of_match[] = { { .compatible = "qcom,msm8996-mss-pil", .data = &msm8996_mss}, { .compatible = "qcom,msm8998-mss-pil", .data = &msm8998_mss}, { .compatible = "qcom,sc7180-mss-pil", .data = &sc7180_mss}, + { .compatible = "qcom,sc7280-mss-pil", .data = &sc7280_mss}, { .compatible = "qcom,sdm845-mss-pil", .data = &sdm845_mss}, { }, }; diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index 401b1ec90785..03857dc9cdc1 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -37,9 +37,9 @@ struct adsp_data { bool has_aggre2_clk; bool auto_boot; - char **active_pd_names; char **proxy_pd_names; + const char *load_state; const char *ssr_name; const char *sysmon_name; int ssctl_id; @@ -57,10 +57,8 @@ struct qcom_adsp { struct regulator *cx_supply; struct regulator *px_supply; - struct device *active_pds[1]; struct device *proxy_pds[3]; - int active_pd_count; int proxy_pd_count; int pas_id; @@ -149,15 +147,13 @@ static int adsp_start(struct rproc *rproc) struct qcom_adsp *adsp = (struct qcom_adsp *)rproc->priv; int ret; - qcom_q6v5_prepare(&adsp->q6v5); - - ret = adsp_pds_enable(adsp, adsp->active_pds, adsp->active_pd_count); - if (ret < 0) - goto disable_irqs; + ret = qcom_q6v5_prepare(&adsp->q6v5); + if (ret) + return ret; ret = adsp_pds_enable(adsp, adsp->proxy_pds, adsp->proxy_pd_count); if (ret < 0) - goto disable_active_pds; + goto disable_irqs; ret = clk_prepare_enable(adsp->xo); if (ret) @@ -201,8 +197,6 @@ disable_xo_clk: clk_disable_unprepare(adsp->xo); disable_proxy_pds: adsp_pds_disable(adsp, adsp->proxy_pds, adsp->proxy_pd_count); -disable_active_pds: - adsp_pds_disable(adsp, adsp->active_pds, adsp->active_pd_count); disable_irqs: qcom_q6v5_unprepare(&adsp->q6v5); @@ -234,7 +228,6 @@ static int adsp_stop(struct rproc *rproc) if (ret) dev_err(adsp->dev, "failed to shutdown: %d\n", ret); - adsp_pds_disable(adsp, adsp->active_pds, adsp->active_pd_count); handover = qcom_q6v5_unprepare(&adsp->q6v5); if (handover) qcom_pas_handover(&adsp->q6v5); @@ -456,19 +449,13 @@ static int adsp_probe(struct platform_device *pdev) if (ret) goto free_rproc; - ret = adsp_pds_attach(&pdev->dev, adsp->active_pds, - desc->active_pd_names); - if (ret < 0) - goto free_rproc; - adsp->active_pd_count = ret; - ret = adsp_pds_attach(&pdev->dev, adsp->proxy_pds, desc->proxy_pd_names); if (ret < 0) - goto detach_active_pds; + goto free_rproc; adsp->proxy_pd_count = ret; - ret = qcom_q6v5_init(&adsp->q6v5, pdev, rproc, desc->crash_reason_smem, + ret = qcom_q6v5_init(&adsp->q6v5, pdev, rproc, desc->crash_reason_smem, desc->load_state, qcom_pas_handover); if (ret) goto detach_proxy_pds; @@ -492,8 +479,6 @@ static int adsp_probe(struct platform_device *pdev) detach_proxy_pds: adsp_pds_detach(adsp, adsp->proxy_pds, adsp->proxy_pd_count); -detach_active_pds: - adsp_pds_detach(adsp, adsp->active_pds, adsp->active_pd_count); free_rproc: rproc_free(rproc); @@ -506,6 +491,7 @@ static int adsp_remove(struct platform_device *pdev) rproc_del(adsp->rproc); + qcom_q6v5_deinit(&adsp->q6v5); qcom_remove_glink_subdev(adsp->rproc, &adsp->glink_subdev); qcom_remove_sysmon_subdev(adsp->sysmon); qcom_remove_smd_subdev(adsp->rproc, &adsp->smd_subdev); @@ -526,20 +512,29 @@ static const struct adsp_data adsp_resource_init = { .ssctl_id = 0x14, }; +static const struct adsp_data sdm845_adsp_resource_init = { + .crash_reason_smem = 423, + .firmware_name = "adsp.mdt", + .pas_id = 1, + .has_aggre2_clk = false, + .auto_boot = true, + .load_state = "adsp", + .ssr_name = "lpass", + .sysmon_name = "adsp", + .ssctl_id = 0x14, +}; + static const struct adsp_data sm8150_adsp_resource = { .crash_reason_smem = 423, .firmware_name = "adsp.mdt", .pas_id = 1, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", NULL }, + .load_state = "adsp", .ssr_name = "lpass", .sysmon_name = "adsp", .ssctl_id = 0x14, @@ -551,15 +546,12 @@ static const struct adsp_data sm8250_adsp_resource = { .pas_id = 1, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "lcx", "lmx", NULL }, + .load_state = "adsp", .ssr_name = "lpass", .sysmon_name = "adsp", .ssctl_id = 0x14, @@ -571,21 +563,18 @@ static const struct adsp_data sm8350_adsp_resource = { .pas_id = 1, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "lcx", "lmx", NULL }, + .load_state = "adsp", .ssr_name = "lpass", .sysmon_name = "adsp", .ssctl_id = 0x14, }; -static const struct adsp_data msm8998_adsp_resource = { +static const struct adsp_data msm8996_adsp_resource = { .crash_reason_smem = 423, .firmware_name = "adsp.mdt", .pas_id = 1, @@ -611,20 +600,29 @@ static const struct adsp_data cdsp_resource_init = { .ssctl_id = 0x17, }; +static const struct adsp_data sdm845_cdsp_resource_init = { + .crash_reason_smem = 601, + .firmware_name = "cdsp.mdt", + .pas_id = 18, + .has_aggre2_clk = false, + .auto_boot = true, + .load_state = "cdsp", + .ssr_name = "cdsp", + .sysmon_name = "cdsp", + .ssctl_id = 0x17, +}; + static const struct adsp_data sm8150_cdsp_resource = { .crash_reason_smem = 601, .firmware_name = "cdsp.mdt", .pas_id = 18, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", NULL }, + .load_state = "cdsp", .ssr_name = "cdsp", .sysmon_name = "cdsp", .ssctl_id = 0x17, @@ -636,14 +634,11 @@ static const struct adsp_data sm8250_cdsp_resource = { .pas_id = 18, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", NULL }, + .load_state = "cdsp", .ssr_name = "cdsp", .sysmon_name = "cdsp", .ssctl_id = 0x17, @@ -655,14 +650,11 @@ static const struct adsp_data sm8350_cdsp_resource = { .pas_id = 18, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", NULL }, + .load_state = "cdsp", .ssr_name = "cdsp", .sysmon_name = "cdsp", .ssctl_id = 0x17, @@ -675,15 +667,12 @@ static const struct adsp_data mpss_resource_init = { .minidump_id = 3, .has_aggre2_clk = false, .auto_boot = false, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", "mss", NULL }, + .load_state = "modem", .ssr_name = "mpss", .sysmon_name = "modem", .ssctl_id = 0x12, @@ -695,14 +684,11 @@ static const struct adsp_data sc8180x_mpss_resource = { .pas_id = 4, .has_aggre2_clk = false, .auto_boot = false, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "cx", NULL }, + .load_state = "modem", .ssr_name = "mpss", .sysmon_name = "modem", .ssctl_id = 0x12, @@ -714,6 +700,10 @@ static const struct adsp_data slpi_resource_init = { .pas_id = 12, .has_aggre2_clk = true, .auto_boot = true, + .proxy_pd_names = (char*[]){ + "ssc_cx", + NULL + }, .ssr_name = "dsps", .sysmon_name = "slpi", .ssctl_id = 0x16, @@ -725,15 +715,12 @@ static const struct adsp_data sm8150_slpi_resource = { .pas_id = 12, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "lcx", "lmx", NULL }, + .load_state = "slpi", .ssr_name = "dsps", .sysmon_name = "slpi", .ssctl_id = 0x16, @@ -745,15 +732,12 @@ static const struct adsp_data sm8250_slpi_resource = { .pas_id = 12, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "lcx", "lmx", NULL }, + .load_state = "slpi", .ssr_name = "dsps", .sysmon_name = "slpi", .ssctl_id = 0x16, @@ -765,35 +749,17 @@ static const struct adsp_data sm8350_slpi_resource = { .pas_id = 12, .has_aggre2_clk = false, .auto_boot = true, - .active_pd_names = (char*[]){ - "load_state", - NULL - }, .proxy_pd_names = (char*[]){ "lcx", "lmx", NULL }, + .load_state = "slpi", .ssr_name = "dsps", .sysmon_name = "slpi", .ssctl_id = 0x16, }; -static const struct adsp_data msm8998_slpi_resource = { - .crash_reason_smem = 424, - .firmware_name = "slpi.mdt", - .pas_id = 12, - .has_aggre2_clk = true, - .auto_boot = true, - .proxy_pd_names = (char*[]){ - "ssc_cx", - NULL - }, - .ssr_name = "dsps", - .sysmon_name = "slpi", - .ssctl_id = 0x16, -}; - static const struct adsp_data wcss_resource_init = { .crash_reason_smem = 421, .firmware_name = "wcnss.mdt", @@ -822,20 +788,21 @@ static const struct adsp_data sdx55_mpss_resource = { static const struct of_device_id adsp_of_match[] = { { .compatible = "qcom,msm8974-adsp-pil", .data = &adsp_resource_init}, - { .compatible = "qcom,msm8996-adsp-pil", .data = &adsp_resource_init}, + { .compatible = "qcom,msm8996-adsp-pil", .data = &msm8996_adsp_resource}, { .compatible = "qcom,msm8996-slpi-pil", .data = &slpi_resource_init}, - { .compatible = "qcom,msm8998-adsp-pas", .data = &msm8998_adsp_resource}, - { .compatible = "qcom,msm8998-slpi-pas", .data = &msm8998_slpi_resource}, + { .compatible = "qcom,msm8998-adsp-pas", .data = &msm8996_adsp_resource}, + { .compatible = "qcom,msm8998-slpi-pas", .data = &slpi_resource_init}, { .compatible = "qcom,qcs404-adsp-pas", .data = &adsp_resource_init }, { .compatible = "qcom,qcs404-cdsp-pas", .data = &cdsp_resource_init }, { .compatible = "qcom,qcs404-wcss-pas", .data = &wcss_resource_init }, { .compatible = "qcom,sc7180-mpss-pas", .data = &mpss_resource_init}, + { .compatible = "qcom,sc7280-mpss-pas", .data = &mpss_resource_init}, { .compatible = "qcom,sc8180x-adsp-pas", .data = &sm8150_adsp_resource}, { .compatible = "qcom,sc8180x-cdsp-pas", .data = &sm8150_cdsp_resource}, { .compatible = "qcom,sc8180x-mpss-pas", .data = &sc8180x_mpss_resource}, { .compatible = "qcom,sdm660-adsp-pas", .data = &adsp_resource_init}, - { .compatible = "qcom,sdm845-adsp-pas", .data = &adsp_resource_init}, - { .compatible = "qcom,sdm845-cdsp-pas", .data = &cdsp_resource_init}, + { .compatible = "qcom,sdm845-adsp-pas", .data = &sdm845_adsp_resource_init}, + { .compatible = "qcom,sdm845-cdsp-pas", .data = &sdm845_cdsp_resource_init}, { .compatible = "qcom,sdx55-mpss-pas", .data = &sdx55_mpss_resource}, { .compatible = "qcom,sm8150-adsp-pas", .data = &sm8150_adsp_resource}, { .compatible = "qcom,sm8150-cdsp-pas", .data = &sm8150_cdsp_resource}, diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c index 20d50ec7eff1..bb0947f7770e 100644 --- a/drivers/remoteproc/qcom_q6v5_wcss.c +++ b/drivers/remoteproc/qcom_q6v5_wcss.c @@ -1044,8 +1044,7 @@ static int q6v5_wcss_probe(struct platform_device *pdev) if (ret) goto free_rproc; - ret = qcom_q6v5_init(&wcss->q6v5, pdev, rproc, desc->crash_reason_smem, - NULL); + ret = qcom_q6v5_init(&wcss->q6v5, pdev, rproc, desc->crash_reason_smem, NULL, NULL); if (ret) goto free_rproc; @@ -1074,7 +1073,9 @@ free_rproc: static int q6v5_wcss_remove(struct platform_device *pdev) { struct rproc *rproc = platform_get_drvdata(pdev); + struct q6v5_wcss *wcss = rproc->priv; + qcom_q6v5_deinit(&wcss->q6v5); rproc_del(rproc); rproc_free(rproc); diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c index ebadc6c08e11..80bbafee9846 100644 --- a/drivers/remoteproc/qcom_wcnss.c +++ b/drivers/remoteproc/qcom_wcnss.c @@ -25,7 +25,6 @@ #include <linux/soc/qcom/mdt_loader.h> #include <linux/soc/qcom/smem.h> #include <linux/soc/qcom/smem_state.h> -#include <linux/rpmsg/qcom_smd.h> #include "qcom_common.h" #include "remoteproc_internal.h" diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 502b6604b757..775df165eb45 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -556,9 +556,6 @@ static int rproc_handle_vdev(struct rproc *rproc, void *ptr, /* Initialise vdev subdevice */ snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index); rvdev->dev.parent = &rproc->dev; - ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent); - if (ret) - return ret; rvdev->dev.release = rproc_rvdev_release; dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name); dev_set_drvdata(&rvdev->dev, rvdev); @@ -568,6 +565,11 @@ static int rproc_handle_vdev(struct rproc *rproc, void *ptr, put_device(&rvdev->dev); return ret; } + + ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent); + if (ret) + goto free_rvdev; + /* Make device dma capable by inheriting from parent's capabilities */ set_dma_ops(&rvdev->dev, get_dma_ops(rproc->dev.parent)); diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c index aee657cc08c6..c892f433a323 100644 --- a/drivers/remoteproc/remoteproc_coredump.c +++ b/drivers/remoteproc/remoteproc_coredump.c @@ -152,8 +152,8 @@ static void rproc_copy_segment(struct rproc *rproc, void *dest, struct rproc_dump_segment *segment, size_t offset, size_t size) { + bool is_iomem = false; void *ptr; - bool is_iomem; if (segment->dump) { segment->dump(rproc, segment, dest, offset, size); diff --git a/drivers/remoteproc/remoteproc_elf_loader.c b/drivers/remoteproc/remoteproc_elf_loader.c index 469c52e62faf..d635d19a5aa8 100644 --- a/drivers/remoteproc/remoteproc_elf_loader.c +++ b/drivers/remoteproc/remoteproc_elf_loader.c @@ -178,8 +178,8 @@ int rproc_elf_load_segments(struct rproc *rproc, const struct firmware *fw) u64 filesz = elf_phdr_get_p_filesz(class, phdr); u64 offset = elf_phdr_get_p_offset(class, phdr); u32 type = elf_phdr_get_p_type(class, phdr); + bool is_iomem = false; void *ptr; - bool is_iomem; if (type != PT_LOAD) continue; @@ -220,7 +220,7 @@ int rproc_elf_load_segments(struct rproc *rproc, const struct firmware *fw) /* put the segment where the remote processor expects it */ if (filesz) { if (is_iomem) - memcpy_fromio(ptr, (void __iomem *)(elf_data + offset), filesz); + memcpy_toio((void __iomem *)ptr, elf_data + offset, filesz); else memcpy(ptr, elf_data + offset, filesz); } diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c index cf4d54e98e6a..70ab496d0431 100644 --- a/drivers/remoteproc/remoteproc_virtio.c +++ b/drivers/remoteproc/remoteproc_virtio.c @@ -23,6 +23,18 @@ #include "remoteproc_internal.h" +static struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) +{ + return container_of(vdev->dev.parent, struct rproc_vdev, dev); +} + +static struct rproc *vdev_to_rproc(struct virtio_device *vdev) +{ + struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); + + return rvdev->rproc; +} + /* kick the remote processor, and let it know which virtqueue to poke at */ static bool rproc_virtio_notify(struct virtqueue *vq) { diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c index fd4eb67a6681..c352fa277c8d 100644 --- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c +++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c @@ -481,7 +481,7 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc) return -EINVAL; } if (num_rmems < 2) { - dev_err(dev, "device needs atleast two memory regions to be defined, num = %d\n", + dev_err(dev, "device needs at least two memory regions to be defined, num = %d\n", num_rmems); return -EINVAL; } diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c index 71615210df3e..6499302d00c3 100644 --- a/drivers/remoteproc/ti_k3_r5_remoteproc.c +++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c @@ -876,7 +876,7 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc) return -EINVAL; } if (num_rmems < 2) { - dev_err(dev, "device needs atleast two memory regions to be defined, num = %d\n", + dev_err(dev, "device needs at least two memory regions to be defined, num = %d\n", num_rmems); return -EINVAL; } diff --git a/drivers/rpmsg/mtk_rpmsg.c b/drivers/rpmsg/mtk_rpmsg.c index 96a17ec29140..5b4404b8be4c 100644 --- a/drivers/rpmsg/mtk_rpmsg.c +++ b/drivers/rpmsg/mtk_rpmsg.c @@ -183,7 +183,7 @@ mtk_rpmsg_match_device_subnode(struct device_node *node, const char *channel) int ret; for_each_available_child_of_node(node, child) { - ret = of_property_read_string(child, "mtk,rpmsg-name", &name); + ret = of_property_read_string(child, "mediatek,rpmsg-name", &name); if (ret) continue; diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 05533c71b10e..3f377a795b33 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -92,6 +92,8 @@ struct glink_core_rx_intent { * @rcids: idr of all channels with a known remote channel id * @features: remote features * @intentless: flag to indicate that there is no intent + * @tx_avail_notify: Waitqueue for pending tx tasks + * @sent_read_notify: flag to check cmd sent or not */ struct qcom_glink { struct device *dev; @@ -118,6 +120,8 @@ struct qcom_glink { unsigned long features; bool intentless; + wait_queue_head_t tx_avail_notify; + bool sent_read_notify; }; enum { @@ -301,6 +305,20 @@ static void qcom_glink_tx_write(struct qcom_glink *glink, glink->tx_pipe->write(glink->tx_pipe, hdr, hlen, data, dlen); } +static void qcom_glink_send_read_notify(struct qcom_glink *glink) +{ + struct glink_msg msg; + + msg.cmd = cpu_to_le16(RPM_CMD_READ_NOTIF); + msg.param1 = 0; + msg.param2 = 0; + + qcom_glink_tx_write(glink, &msg, sizeof(msg), NULL, 0); + + mbox_send_message(glink->mbox_chan, NULL); + mbox_client_txdone(glink->mbox_chan, 0); +} + static int qcom_glink_tx(struct qcom_glink *glink, const void *hdr, size_t hlen, const void *data, size_t dlen, bool wait) @@ -321,12 +339,21 @@ static int qcom_glink_tx(struct qcom_glink *glink, goto out; } + if (!glink->sent_read_notify) { + glink->sent_read_notify = true; + qcom_glink_send_read_notify(glink); + } + /* Wait without holding the tx_lock */ spin_unlock_irqrestore(&glink->tx_lock, flags); - usleep_range(10000, 15000); + wait_event_timeout(glink->tx_avail_notify, + qcom_glink_tx_avail(glink) >= tlen, 10 * HZ); spin_lock_irqsave(&glink->tx_lock, flags); + + if (qcom_glink_tx_avail(glink) >= tlen) + glink->sent_read_notify = false; } qcom_glink_tx_write(glink, hdr, hlen, data, dlen); @@ -986,6 +1013,9 @@ static irqreturn_t qcom_glink_native_intr(int irq, void *data) unsigned int cmd; int ret = 0; + /* To wakeup any blocking writers */ + wake_up_all(&glink->tx_avail_notify); + for (;;) { avail = qcom_glink_rx_avail(glink); if (avail < sizeof(msg)) @@ -1271,6 +1301,8 @@ static int __qcom_glink_send(struct glink_channel *channel, } __packed req; int ret; unsigned long flags; + int chunk_size = len; + int left_size = 0; if (!glink->intentless) { while (!intent) { @@ -1304,18 +1336,46 @@ static int __qcom_glink_send(struct glink_channel *channel, iid = intent->id; } + if (wait && chunk_size > SZ_8K) { + chunk_size = SZ_8K; + left_size = len - chunk_size; + } req.msg.cmd = cpu_to_le16(RPM_CMD_TX_DATA); req.msg.param1 = cpu_to_le16(channel->lcid); req.msg.param2 = cpu_to_le32(iid); - req.chunk_size = cpu_to_le32(len); - req.left_size = cpu_to_le32(0); + req.chunk_size = cpu_to_le32(chunk_size); + req.left_size = cpu_to_le32(left_size); - ret = qcom_glink_tx(glink, &req, sizeof(req), data, len, wait); + ret = qcom_glink_tx(glink, &req, sizeof(req), data, chunk_size, wait); /* Mark intent available if we failed */ - if (ret && intent) + if (ret && intent) { intent->in_use = false; + return ret; + } + while (left_size > 0) { + data = (void *)((char *)data + chunk_size); + chunk_size = left_size; + if (chunk_size > SZ_8K) + chunk_size = SZ_8K; + left_size -= chunk_size; + + req.msg.cmd = cpu_to_le16(RPM_CMD_TX_DATA_CONT); + req.msg.param1 = cpu_to_le16(channel->lcid); + req.msg.param2 = cpu_to_le32(iid); + req.chunk_size = cpu_to_le32(chunk_size); + req.left_size = cpu_to_le32(left_size); + + ret = qcom_glink_tx(glink, &req, sizeof(req), data, + chunk_size, wait); + + /* Mark intent available if we failed */ + if (ret && intent) { + intent->in_use = false; + break; + } + } return ret; } @@ -1387,9 +1447,7 @@ static const struct rpmsg_endpoint_ops glink_endpoint_ops = { static void qcom_glink_rpdev_release(struct device *dev) { struct rpmsg_device *rpdev = to_rpmsg_device(dev); - struct glink_channel *channel = to_glink_channel(rpdev->ept); - channel->rpdev = NULL; kfree(rpdev); } @@ -1440,7 +1498,7 @@ static int qcom_glink_rx_open(struct qcom_glink *glink, unsigned int rcid, } rpdev->ept = &channel->ept; - strncpy(rpdev->id.name, name, RPMSG_NAME_SIZE); + strscpy_pad(rpdev->id.name, name, RPMSG_NAME_SIZE); rpdev->src = RPMSG_ADDR_ANY; rpdev->dst = RPMSG_ADDR_ANY; rpdev->ops = &glink_device_ops; @@ -1494,6 +1552,7 @@ static void qcom_glink_rx_close(struct qcom_glink *glink, unsigned int rcid) rpmsg_unregister_device(glink->dev, &chinfo); } + channel->rpdev = NULL; qcom_glink_send_close_ack(glink, channel->rcid); @@ -1507,9 +1566,13 @@ static void qcom_glink_rx_close(struct qcom_glink *glink, unsigned int rcid) static void qcom_glink_rx_close_ack(struct qcom_glink *glink, unsigned int lcid) { + struct rpmsg_channel_info chinfo; struct glink_channel *channel; unsigned long flags; + /* To wakeup any blocking writers */ + wake_up_all(&glink->tx_avail_notify); + spin_lock_irqsave(&glink->idr_lock, flags); channel = idr_find(&glink->lcids, lcid); if (WARN(!channel, "close ack on unknown channel\n")) { @@ -1521,6 +1584,16 @@ static void qcom_glink_rx_close_ack(struct qcom_glink *glink, unsigned int lcid) channel->lcid = 0; spin_unlock_irqrestore(&glink->idr_lock, flags); + /* Decouple the potential rpdev from the channel */ + if (channel->rpdev) { + strscpy(chinfo.name, channel->name, sizeof(chinfo.name)); + chinfo.src = RPMSG_ADDR_ANY; + chinfo.dst = RPMSG_ADDR_ANY; + + rpmsg_unregister_device(glink->dev, &chinfo); + } + channel->rpdev = NULL; + kref_put(&channel->refcount, qcom_glink_channel_release); } @@ -1670,6 +1743,7 @@ struct qcom_glink *qcom_glink_native_probe(struct device *dev, spin_lock_init(&glink->rx_lock); INIT_LIST_HEAD(&glink->rx_queue); INIT_WORK(&glink->rx_work, qcom_glink_work); + init_waitqueue_head(&glink->tx_avail_notify); spin_lock_init(&glink->idr_lock); idr_init(&glink->lcids); diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index 2bebc9b2d163..b5907b80727c 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -22,8 +22,6 @@ #include <linux/uaccess.h> #include <uapi/linux/rpmsg.h> -#include "rpmsg_internal.h" - #define RPMSG_DEV_MAX (MINORMASK + 1) static dev_t rpmsg_major; diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 05fd06fc67e9..9c112aa65040 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -17,7 +17,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> -#include <linux/of_device.h> #include <linux/rpmsg.h> #include <linux/rpmsg/byteorder.h> #include <linux/rpmsg/ns.h> @@ -759,7 +758,7 @@ static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev, /* farewell, ept, we don't need you anymore */ kref_put(&ept->refcount, __ept_release); } else - dev_warn(dev, "msg received with no recipient\n"); + dev_warn_ratelimited(dev, "msg received with no recipient\n"); /* publish the real size of the buffer */ rpmsg_sg_init(&sg, msg, vrp->buf_size); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 7208eeb8459a..058e56a10ab8 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -441,6 +441,7 @@ config RTC_DRV_X1205 config RTC_DRV_PCF8523 tristate "NXP PCF8523" + select REGMAP_I2C help If you say yes here you get support for the NXP PCF8523 RTC chips. @@ -582,14 +583,6 @@ config RTC_DRV_TPS65910 This driver can also be built as a module. If so, the module will be called rtc-tps65910. -config RTC_DRV_TPS80031 - tristate "TI TPS80031/TPS80032 RTC driver" - depends on MFD_TPS80031 - help - TI Power Management IC TPS80031 supports RTC functionality - along with alarm. This driver supports the RTC driver for - the TPS80031 RTC module. - config RTC_DRV_RC5T583 tristate "RICOH 5T583 RTC driver" depends on MFD_RC5T583 @@ -1929,4 +1922,14 @@ config RTC_DRV_WILCO_EC This can also be built as a module. If so, the module will be named "rtc_wilco_ec". +config RTC_DRV_MSC313 + tristate "MStar MSC313 RTC" + depends on ARCH_MSTARV7 || COMPILE_TEST + help + If you say yes here you get support for the Mstar MSC313e On-Chip + Real Time Clock. + + This driver can also be built as a module, if so, the module + will be called "rtc-msc313". + endif # RTC_CLASS diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 5ceeafe4d5b2..678a8ef4abae 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_RTC_DRV_MCP795) += rtc-mcp795.o obj-$(CONFIG_RTC_DRV_MESON) += rtc-meson.o obj-$(CONFIG_RTC_DRV_MOXART) += rtc-moxart.o obj-$(CONFIG_RTC_DRV_MPC5121) += rtc-mpc5121.o +obj-$(CONFIG_RTC_DRV_MSC313) += rtc-msc313.o obj-$(CONFIG_RTC_DRV_MSM6242) += rtc-msm6242.o obj-$(CONFIG_RTC_DRV_MT2712) += rtc-mt2712.o obj-$(CONFIG_RTC_DRV_MT6397) += rtc-mt6397.o @@ -169,7 +170,6 @@ obj-$(CONFIG_RTC_DRV_TEGRA) += rtc-tegra.o obj-$(CONFIG_RTC_DRV_TEST) += rtc-test.o obj-$(CONFIG_RTC_DRV_TPS6586X) += rtc-tps6586x.o obj-$(CONFIG_RTC_DRV_TPS65910) += rtc-tps65910.o -obj-$(CONFIG_RTC_DRV_TPS80031) += rtc-tps80031.o obj-$(CONFIG_RTC_DRV_TWL4030) += rtc-twl.o obj-$(CONFIG_RTC_DRV_V3020) += rtc-v3020.o obj-$(CONFIG_RTC_DRV_VR41XX) += rtc-vr41xx.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index f77bc089eb6b..4b460c61f1d8 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -232,6 +232,7 @@ static struct rtc_device *rtc_allocate_device(void) rtc->pie_enabled = 0; set_bit(RTC_FEATURE_ALARM, rtc->features); + set_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); return rtc; } @@ -334,7 +335,8 @@ static void devm_rtc_unregister_device(void *data) * letting any rtc_class_open() users access it again */ rtc_proc_del_device(rtc); - cdev_device_del(&rtc->char_dev, &rtc->dev); + if (!test_bit(RTC_NO_CDEV, &rtc->flags)) + cdev_device_del(&rtc->char_dev, &rtc->dev); rtc->ops = NULL; mutex_unlock(&rtc->ops_lock); } @@ -363,7 +365,9 @@ struct rtc_device *devm_rtc_allocate_device(struct device *dev) rtc->id = id; rtc->dev.parent = dev; - dev_set_name(&rtc->dev, "rtc%d", id); + err = dev_set_name(&rtc->dev, "rtc%d", id); + if (err) + return ERR_PTR(err); err = devm_add_action_or_reset(dev, devm_rtc_release_device, rtc); if (err) @@ -386,6 +390,12 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) if (!rtc->ops->set_alarm) clear_bit(RTC_FEATURE_ALARM, rtc->features); + if (rtc->uie_unsupported) + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); + + if (rtc->ops->set_offset) + set_bit(RTC_FEATURE_CORRECTION, rtc->features); + rtc->owner = owner; rtc_device_get_offset(rtc); @@ -397,12 +407,14 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) rtc_dev_prepare(rtc); err = cdev_device_add(&rtc->char_dev, &rtc->dev); - if (err) + if (err) { + set_bit(RTC_NO_CDEV, &rtc->flags); dev_warn(rtc->dev.parent, "failed to add char device %d:%d\n", MAJOR(rtc->dev.devt), rtc->id); - else + } else { dev_dbg(rtc->dev.parent, "char device (%d:%d)\n", MAJOR(rtc->dev.devt), rtc->id); + } rtc_proc_add_device(rtc); diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 5b8ebe86124a..e104972a28fd 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -208,6 +208,7 @@ static long rtc_dev_ioctl(struct file *file, const struct rtc_class_ops *ops = rtc->ops; struct rtc_time tm; struct rtc_wkalrm alarm; + struct rtc_param param; void __user *uarg = (void __user *)arg; err = mutex_lock_interruptible(&rtc->ops_lock); @@ -221,6 +222,7 @@ static long rtc_dev_ioctl(struct file *file, switch (cmd) { case RTC_EPOCH_SET: case RTC_SET_TIME: + case RTC_PARAM_SET: if (!capable(CAP_SYS_TIME)) err = -EACCES; break; @@ -382,6 +384,69 @@ static long rtc_dev_ioctl(struct file *file, err = -EFAULT; return err; + case RTC_PARAM_GET: + if (copy_from_user(¶m, uarg, sizeof(param))) { + mutex_unlock(&rtc->ops_lock); + return -EFAULT; + } + + switch(param.param) { + long offset; + case RTC_PARAM_FEATURES: + if (param.index != 0) + err = -EINVAL; + param.uvalue = rtc->features[0]; + break; + + case RTC_PARAM_CORRECTION: + mutex_unlock(&rtc->ops_lock); + if (param.index != 0) + return -EINVAL; + err = rtc_read_offset(rtc, &offset); + mutex_lock(&rtc->ops_lock); + if (err == 0) + param.svalue = offset; + break; + + default: + if (rtc->ops->param_get) + err = rtc->ops->param_get(rtc->dev.parent, ¶m); + else + err = -EINVAL; + } + + if (!err) + if (copy_to_user(uarg, ¶m, sizeof(param))) + err = -EFAULT; + + break; + + case RTC_PARAM_SET: + if (copy_from_user(¶m, uarg, sizeof(param))) { + mutex_unlock(&rtc->ops_lock); + return -EFAULT; + } + + switch(param.param) { + case RTC_PARAM_FEATURES: + err = -EINVAL; + break; + + case RTC_PARAM_CORRECTION: + mutex_unlock(&rtc->ops_lock); + if (param.index != 0) + return -EINVAL; + return rtc_set_offset(rtc, param.svalue); + + default: + if (rtc->ops->param_set) + err = rtc->ops->param_set(rtc->dev.parent, ¶m); + else + err = -EINVAL; + } + + break; + default: /* Finally try the driver's ioctl interface */ if (ops->ioctl) { diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 9a2bd4947007..d8e835798153 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -423,6 +423,7 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (err) return err; now = rtc_tm_to_time64(&tm); + if (scheduled <= now) return -ETIME; /* @@ -447,6 +448,7 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { + ktime_t alarm_time; int err; if (!rtc->ops) @@ -468,7 +470,15 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (rtc->aie_timer.enabled) rtc_timer_remove(rtc, &rtc->aie_timer); - rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time); + alarm_time = rtc_tm_to_ktime(alarm->time); + /* + * Round down so we never miss a deadline, checking for past deadline is + * done in __rtc_set_alarm + */ + if (test_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->features)) + alarm_time = ktime_sub_ns(alarm_time, (u64)alarm->time.tm_sec * NSEC_PER_SEC); + + rtc->aie_timer.node.expires = alarm_time; rtc->aie_timer.period = 0; if (alarm->enabled) err = rtc_timer_enqueue(rtc, &rtc->aie_timer); @@ -561,7 +571,8 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled) if (rtc->uie_rtctimer.enabled == enabled) goto out; - if (rtc->uie_unsupported || !test_bit(RTC_FEATURE_ALARM, rtc->features)) { + if (!test_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features) || + !test_bit(RTC_FEATURE_ALARM, rtc->features)) { mutex_unlock(&rtc->ops_lock); #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL return rtc_dev_update_irq_enable_emul(rtc, enabled); diff --git a/drivers/rtc/rtc-ab-eoz9.c b/drivers/rtc/rtc-ab-eoz9.c index a9b355510cd4..e188ab517f1e 100644 --- a/drivers/rtc/rtc-ab-eoz9.c +++ b/drivers/rtc/rtc-ab-eoz9.c @@ -534,7 +534,6 @@ static int abeoz9_probe(struct i2c_client *client, data->rtc->ops = &rtc_ops; data->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; data->rtc->range_max = RTC_TIMESTAMP_END_2099; - data->rtc->uie_unsupported = 1; clear_bit(RTC_FEATURE_ALARM, data->rtc->features); if (client->irq > 0) { @@ -546,6 +545,8 @@ static int abeoz9_probe(struct i2c_client *client, dev_err(dev, "failed to request alarm irq\n"); return ret; } + } else { + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, data->rtc->features); } if (client->irq > 0 || device_property_read_bool(dev, "wakeup-source")) { diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c index b40048871295..ea33e149d545 100644 --- a/drivers/rtc/rtc-ab8500.c +++ b/drivers/rtc/rtc-ab8500.c @@ -184,25 +184,9 @@ static int ab8500_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) { int retval, i; unsigned char buf[ARRAY_SIZE(ab8500_rtc_alarm_regs)]; - unsigned long mins, secs = 0, cursec = 0; - struct rtc_time curtm; + unsigned long mins; - /* Get the number of seconds since 1970 */ - secs = rtc_tm_to_time64(&alarm->time); - - /* - * Check whether alarm is set less than 1min. - * Since our RTC doesn't support alarm resolution less than 1min, - * return -EINVAL, so UIE EMUL can take it up, incase of UIE_ON - */ - ab8500_rtc_read_time(dev, &curtm); /* Read current time */ - cursec = rtc_tm_to_time64(&curtm); - if ((secs - cursec) < 59) { - dev_dbg(dev, "Alarm less than 1 minute not supported\r\n"); - return -EINVAL; - } - - mins = secs / 60; + mins = (unsigned long)rtc_tm_to_time64(&alarm->time) / 60; buf[2] = mins & 0xFF; buf[1] = (mins >> 8) & 0xFF; @@ -394,7 +378,8 @@ static int ab8500_rtc_probe(struct platform_device *pdev) dev_pm_set_wake_irq(&pdev->dev, irq); platform_set_drvdata(pdev, rtc); - rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); rtc->range_max = (1ULL << 24) * 60 - 1; // 24-bit minutes + 59 secs rtc->start_secs = RTC_TIMESTAMP_BEGIN_2000; diff --git a/drivers/rtc/rtc-ds1302.c b/drivers/rtc/rtc-ds1302.c index b3de6d2e680a..2f83adef966e 100644 --- a/drivers/rtc/rtc-ds1302.c +++ b/drivers/rtc/rtc-ds1302.c @@ -199,11 +199,18 @@ static const struct of_device_id ds1302_dt_ids[] = { MODULE_DEVICE_TABLE(of, ds1302_dt_ids); #endif +static const struct spi_device_id ds1302_spi_ids[] = { + { .name = "ds1302", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(spi, ds1302_spi_ids); + static struct spi_driver ds1302_driver = { .driver.name = "rtc-ds1302", .driver.of_match_table = of_match_ptr(ds1302_dt_ids), .probe = ds1302_probe, .remove = ds1302_remove, + .id_table = ds1302_spi_ids, }; module_spi_driver(ds1302_driver); diff --git a/drivers/rtc/rtc-ds1390.c b/drivers/rtc/rtc-ds1390.c index 66fc8617d07e..93ce72b9ae59 100644 --- a/drivers/rtc/rtc-ds1390.c +++ b/drivers/rtc/rtc-ds1390.c @@ -219,12 +219,19 @@ static const struct of_device_id ds1390_of_match[] = { }; MODULE_DEVICE_TABLE(of, ds1390_of_match); +static const struct spi_device_id ds1390_spi_ids[] = { + { .name = "ds1390" }, + {} +}; +MODULE_DEVICE_TABLE(spi, ds1390_spi_ids); + static struct spi_driver ds1390_driver = { .driver = { .name = "rtc-ds1390", .of_match_table = of_match_ptr(ds1390_of_match), }, .probe = ds1390_probe, + .id_table = ds1390_spi_ids, }; module_spi_driver(ds1390_driver); diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index f736f8c22e96..6d383b629d20 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -557,7 +557,7 @@ static struct clk *m41t80_sqw_register_clk(struct m41t80_data *m41t80) * registered automatically when being referenced. */ of_node_put(fixed_clock); - return 0; + return NULL; } /* First disable the clock */ diff --git a/drivers/rtc/rtc-mcp795.c b/drivers/rtc/rtc-mcp795.c index bad7792b6ca5..0d515b3df571 100644 --- a/drivers/rtc/rtc-mcp795.c +++ b/drivers/rtc/rtc-mcp795.c @@ -430,12 +430,19 @@ static const struct of_device_id mcp795_of_match[] = { MODULE_DEVICE_TABLE(of, mcp795_of_match); #endif +static const struct spi_device_id mcp795_spi_ids[] = { + { .name = "mcp795" }, + { } +}; +MODULE_DEVICE_TABLE(spi, mcp795_spi_ids); + static struct spi_driver mcp795_driver = { .driver = { .name = "rtc-mcp795", .of_match_table = of_match_ptr(mcp795_of_match), }, .probe = mcp795_probe, + .id_table = mcp795_spi_ids, }; module_spi_driver(mcp795_driver); diff --git a/drivers/rtc/rtc-msc313.c b/drivers/rtc/rtc-msc313.c new file mode 100644 index 000000000000..f3fde013c4b8 --- /dev/null +++ b/drivers/rtc/rtc-msc313.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Real time clocks driver for MStar/SigmaStar ARMv7 SoCs. + * Based on "Real Time Clock driver for msb252x." that was contained + * in various MStar kernels. + * + * (C) 2019 Daniel Palmer + * (C) 2021 Romain Perier + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/platform_device.h> +#include <linux/rtc.h> + +/* Registers */ +#define REG_RTC_CTRL 0x00 +#define REG_RTC_FREQ_CW_L 0x04 +#define REG_RTC_FREQ_CW_H 0x08 +#define REG_RTC_LOAD_VAL_L 0x0C +#define REG_RTC_LOAD_VAL_H 0x10 +#define REG_RTC_MATCH_VAL_L 0x14 +#define REG_RTC_MATCH_VAL_H 0x18 +#define REG_RTC_STATUS_INT 0x1C +#define REG_RTC_CNT_VAL_L 0x20 +#define REG_RTC_CNT_VAL_H 0x24 + +/* Control bits for REG_RTC_CTRL */ +#define SOFT_RSTZ_BIT BIT(0) +#define CNT_EN_BIT BIT(1) +#define WRAP_EN_BIT BIT(2) +#define LOAD_EN_BIT BIT(3) +#define READ_EN_BIT BIT(4) +#define INT_MASK_BIT BIT(5) +#define INT_FORCE_BIT BIT(6) +#define INT_CLEAR_BIT BIT(7) + +/* Control bits for REG_RTC_STATUS_INT */ +#define RAW_INT_BIT BIT(0) +#define ALM_INT_BIT BIT(1) + +struct msc313_rtc { + struct rtc_device *rtc_dev; + void __iomem *rtc_base; +}; + +static int msc313_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) +{ + struct msc313_rtc *priv = dev_get_drvdata(dev); + unsigned long seconds; + + seconds = readw(priv->rtc_base + REG_RTC_MATCH_VAL_L) + | ((unsigned long)readw(priv->rtc_base + REG_RTC_MATCH_VAL_H) << 16); + + rtc_time64_to_tm(seconds, &alarm->time); + + if (!(readw(priv->rtc_base + REG_RTC_CTRL) & INT_MASK_BIT)) + alarm->enabled = 1; + + return 0; +} + +static int msc313_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct msc313_rtc *priv = dev_get_drvdata(dev); + u16 reg; + + reg = readw(priv->rtc_base + REG_RTC_CTRL); + if (enabled) + reg &= ~INT_MASK_BIT; + else + reg |= INT_MASK_BIT; + writew(reg, priv->rtc_base + REG_RTC_CTRL); + return 0; +} + +static int msc313_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) +{ + struct msc313_rtc *priv = dev_get_drvdata(dev); + unsigned long seconds; + + seconds = rtc_tm_to_time64(&alarm->time); + writew((seconds & 0xFFFF), priv->rtc_base + REG_RTC_MATCH_VAL_L); + writew((seconds >> 16) & 0xFFFF, priv->rtc_base + REG_RTC_MATCH_VAL_H); + + msc313_rtc_alarm_irq_enable(dev, alarm->enabled); + + return 0; +} + +static bool msc313_rtc_get_enabled(struct msc313_rtc *priv) +{ + return readw(priv->rtc_base + REG_RTC_CTRL) & CNT_EN_BIT; +} + +static void msc313_rtc_set_enabled(struct msc313_rtc *priv) +{ + u16 reg; + + reg = readw(priv->rtc_base + REG_RTC_CTRL); + reg |= CNT_EN_BIT; + writew(reg, priv->rtc_base + REG_RTC_CTRL); +} + +static int msc313_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + struct msc313_rtc *priv = dev_get_drvdata(dev); + u32 seconds; + u16 reg; + + if (!msc313_rtc_get_enabled(priv)) + return -EINVAL; + + reg = readw(priv->rtc_base + REG_RTC_CTRL); + writew(reg | READ_EN_BIT, priv->rtc_base + REG_RTC_CTRL); + + /* Wait for HW latch done */ + while (readw(priv->rtc_base + REG_RTC_CTRL) & READ_EN_BIT) + udelay(1); + + seconds = readw(priv->rtc_base + REG_RTC_CNT_VAL_L) + | ((unsigned long)readw(priv->rtc_base + REG_RTC_CNT_VAL_H) << 16); + + rtc_time64_to_tm(seconds, tm); + + return 0; +} + +static int msc313_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct msc313_rtc *priv = dev_get_drvdata(dev); + unsigned long seconds; + u16 reg; + + seconds = rtc_tm_to_time64(tm); + writew(seconds & 0xFFFF, priv->rtc_base + REG_RTC_LOAD_VAL_L); + writew((seconds >> 16) & 0xFFFF, priv->rtc_base + REG_RTC_LOAD_VAL_H); + + /* Enable load for loading value into internal RTC counter */ + reg = readw(priv->rtc_base + REG_RTC_CTRL); + writew(reg | LOAD_EN_BIT, priv->rtc_base + REG_RTC_CTRL); + + /* Wait for HW latch done */ + while (readw(priv->rtc_base + REG_RTC_CTRL) & LOAD_EN_BIT) + udelay(1); + msc313_rtc_set_enabled(priv); + return 0; +} + +static const struct rtc_class_ops msc313_rtc_ops = { + .read_time = msc313_rtc_read_time, + .set_time = msc313_rtc_set_time, + .read_alarm = msc313_rtc_read_alarm, + .set_alarm = msc313_rtc_set_alarm, + .alarm_irq_enable = msc313_rtc_alarm_irq_enable, +}; + +static irqreturn_t msc313_rtc_interrupt(s32 irq, void *dev_id) +{ + struct msc313_rtc *priv = dev_get_drvdata(dev_id); + u16 reg; + + reg = readw(priv->rtc_base + REG_RTC_STATUS_INT); + if (!(reg & ALM_INT_BIT)) + return IRQ_NONE; + + reg = readw(priv->rtc_base + REG_RTC_CTRL); + reg |= INT_CLEAR_BIT; + reg &= ~INT_FORCE_BIT; + writew(reg, priv->rtc_base + REG_RTC_CTRL); + + rtc_update_irq(priv->rtc_dev, 1, RTC_IRQF | RTC_AF); + + return IRQ_HANDLED; +} + +static int msc313_rtc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct msc313_rtc *priv; + unsigned long rate; + struct clk *clk; + int ret; + int irq; + + priv = devm_kzalloc(&pdev->dev, sizeof(struct msc313_rtc), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->rtc_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->rtc_base)) + return PTR_ERR(priv->rtc_base); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return -EINVAL; + + priv->rtc_dev = devm_rtc_allocate_device(dev); + if (IS_ERR(priv->rtc_dev)) + return PTR_ERR(priv->rtc_dev); + + priv->rtc_dev->ops = &msc313_rtc_ops; + priv->rtc_dev->range_max = U32_MAX; + + ret = devm_request_irq(dev, irq, msc313_rtc_interrupt, IRQF_SHARED, + dev_name(&pdev->dev), &pdev->dev); + if (ret) { + dev_err(dev, "Could not request IRQ\n"); + return ret; + } + + clk = devm_clk_get(dev, NULL); + if (IS_ERR(clk)) { + dev_err(dev, "No input reference clock\n"); + return PTR_ERR(clk); + } + + ret = clk_prepare_enable(clk); + if (ret) { + dev_err(dev, "Failed to enable the reference clock, %d\n", ret); + return ret; + } + + ret = devm_add_action_or_reset(dev, (void (*) (void *))clk_disable_unprepare, clk); + if (ret) + return ret; + + rate = clk_get_rate(clk); + writew(rate & 0xFFFF, priv->rtc_base + REG_RTC_FREQ_CW_L); + writew((rate >> 16) & 0xFFFF, priv->rtc_base + REG_RTC_FREQ_CW_H); + + platform_set_drvdata(pdev, priv); + + return devm_rtc_register_device(priv->rtc_dev); +} + +static const struct of_device_id msc313_rtc_of_match_table[] = { + { .compatible = "mstar,msc313-rtc" }, + { } +}; +MODULE_DEVICE_TABLE(of, msc313_rtc_of_match_table); + +static struct platform_driver msc313_rtc_driver = { + .probe = msc313_rtc_probe, + .driver = { + .name = "msc313-rtc", + .of_match_table = msc313_rtc_of_match_table, + }, +}; + +module_platform_driver(msc313_rtc_driver); + +MODULE_AUTHOR("Daniel Palmer <daniel@thingy.jp>"); +MODULE_AUTHOR("Romain Perier <romain.perier@gmail.com>"); +MODULE_DESCRIPTION("MStar RTC Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index d46e0f0cc502..4d4f3b1a7309 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -1029,6 +1029,5 @@ static struct platform_driver omap_rtc_driver = { module_platform_driver(omap_rtc_driver); -MODULE_ALIAS("platform:omap_rtc"); MODULE_AUTHOR("George G. Davis (and others)"); MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c index 0f58cac81d8c..7473e6c8a183 100644 --- a/drivers/rtc/rtc-pcf2123.c +++ b/drivers/rtc/rtc-pcf2123.c @@ -451,12 +451,21 @@ static const struct of_device_id pcf2123_dt_ids[] = { MODULE_DEVICE_TABLE(of, pcf2123_dt_ids); #endif +static const struct spi_device_id pcf2123_spi_ids[] = { + { .name = "pcf2123", }, + { .name = "rv2123", }, + { .name = "rtc-pcf2123", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(spi, pcf2123_spi_ids); + static struct spi_driver pcf2123_driver = { .driver = { .name = "rtc-pcf2123", .of_match_table = of_match_ptr(pcf2123_dt_ids), }, .probe = pcf2123_probe, + .id_table = pcf2123_spi_ids, }; module_spi_driver(pcf2123_driver); diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index 14da4ab30104..15e50bb10cf0 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -34,6 +34,7 @@ #define PCF85063_REG_CTRL1 0x00 /* status */ #define PCF85063_REG_CTRL1_CAP_SEL BIT(0) #define PCF85063_REG_CTRL1_STOP BIT(5) +#define PCF85063_REG_CTRL1_EXT_TEST BIT(7) #define PCF85063_REG_CTRL2 0x01 #define PCF85063_CTRL2_AF BIT(6) @@ -117,6 +118,7 @@ static int pcf85063_rtc_set_time(struct device *dev, struct rtc_time *tm) * reset state until all time/date registers are written */ rc = regmap_update_bits(pcf85063->regmap, PCF85063_REG_CTRL1, + PCF85063_REG_CTRL1_EXT_TEST | PCF85063_REG_CTRL1_STOP, PCF85063_REG_CTRL1_STOP); if (rc) @@ -297,7 +299,7 @@ static int pcf85063_ioctl(struct device *dev, unsigned int cmd, if (ret < 0) return ret; - status = status & PCF85063_REG_SC_OS ? RTC_VL_DATA_INVALID : 0; + status = (status & PCF85063_REG_SC_OS) ? RTC_VL_DATA_INVALID : 0; return put_user(status, (unsigned int __user *)arg); @@ -479,6 +481,18 @@ static struct clk *pcf85063_clkout_register_clk(struct pcf85063 *pcf85063) struct clk *clk; struct clk_init_data init; struct device_node *node = pcf85063->rtc->dev.parent->of_node; + struct device_node *fixed_clock; + + fixed_clock = of_get_child_by_name(node, "clock"); + if (fixed_clock) { + /* + * skip registering square wave clock when a fixed + * clock has been registered. The fixed clock is + * registered automatically when being referenced. + */ + of_node_put(fixed_clock); + return NULL; + } init.name = "pcf85063-clkout"; init.ops = &pcf85063_clkout_ops; diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index 8b6fb20774bf..c93acade7205 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -4,8 +4,10 @@ */ #include <linux/bcd.h> +#include <linux/bitfield.h> #include <linux/i2c.h> #include <linux/module.h> +#include <linux/regmap.h> #include <linux/rtc.h> #include <linux/of.h> #include <linux/pm_wakeirq.h> @@ -19,11 +21,10 @@ #define PCF8523_CONTROL2_AF BIT(3) #define PCF8523_REG_CONTROL3 0x02 -#define PCF8523_CONTROL3_PM_BLD BIT(7) /* battery low detection disabled */ -#define PCF8523_CONTROL3_PM_VDD BIT(6) /* switch-over disabled */ -#define PCF8523_CONTROL3_PM_DSM BIT(5) /* direct switching mode */ -#define PCF8523_CONTROL3_PM_MASK 0xe0 +#define PCF8523_CONTROL3_PM GENMASK(7,5) +#define PCF8523_PM_STANDBY 0x7 #define PCF8523_CONTROL3_BLF BIT(2) /* battery low bit, read-only */ +#define PCF8523_CONTROL3_BSF BIT(3) #define PCF8523_REG_SECONDS 0x03 #define PCF8523_SECONDS_OS BIT(7) @@ -48,127 +49,45 @@ struct pcf8523 { struct rtc_device *rtc; - struct i2c_client *client; + struct regmap *regmap; }; -static int pcf8523_read(struct i2c_client *client, u8 reg, u8 *valuep) +static int pcf8523_load_capacitance(struct pcf8523 *pcf8523, struct device_node *node) { - struct i2c_msg msgs[2]; - u8 value = 0; - int err; - - msgs[0].addr = client->addr; - msgs[0].flags = 0; - msgs[0].len = sizeof(reg); - msgs[0].buf = ® - - msgs[1].addr = client->addr; - msgs[1].flags = I2C_M_RD; - msgs[1].len = sizeof(value); - msgs[1].buf = &value; - - err = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (err < 0) - return err; - - *valuep = value; - - return 0; -} - -static int pcf8523_write(struct i2c_client *client, u8 reg, u8 value) -{ - u8 buffer[2] = { reg, value }; - struct i2c_msg msg; - int err; - - msg.addr = client->addr; - msg.flags = 0; - msg.len = sizeof(buffer); - msg.buf = buffer; - - err = i2c_transfer(client->adapter, &msg, 1); - if (err < 0) - return err; - - return 0; -} - -static int pcf8523_voltage_low(struct i2c_client *client) -{ - u8 value; - int err; - - err = pcf8523_read(client, PCF8523_REG_CONTROL3, &value); - if (err < 0) - return err; - - return !!(value & PCF8523_CONTROL3_BLF); -} - -static int pcf8523_load_capacitance(struct i2c_client *client) -{ - u32 load; - u8 value; - int err; - - err = pcf8523_read(client, PCF8523_REG_CONTROL1, &value); - if (err < 0) - return err; + u32 load, value = 0; load = 12500; - of_property_read_u32(client->dev.of_node, "quartz-load-femtofarads", - &load); + of_property_read_u32(node, "quartz-load-femtofarads", &load); switch (load) { default: - dev_warn(&client->dev, "Unknown quartz-load-femtofarads value: %d. Assuming 12500", + dev_warn(&pcf8523->rtc->dev, "Unknown quartz-load-femtofarads value: %d. Assuming 12500", load); fallthrough; case 12500: value |= PCF8523_CONTROL1_CAP_SEL; break; case 7000: - value &= ~PCF8523_CONTROL1_CAP_SEL; break; } - err = pcf8523_write(client, PCF8523_REG_CONTROL1, value); - - return err; -} - -static int pcf8523_set_pm(struct i2c_client *client, u8 pm) -{ - u8 value; - int err; - - err = pcf8523_read(client, PCF8523_REG_CONTROL3, &value); - if (err < 0) - return err; - - value = (value & ~PCF8523_CONTROL3_PM_MASK) | pm; - - err = pcf8523_write(client, PCF8523_REG_CONTROL3, value); - if (err < 0) - return err; - - return 0; + return regmap_update_bits(pcf8523->regmap, PCF8523_REG_CONTROL1, + PCF8523_CONTROL1_CAP_SEL, value); } static irqreturn_t pcf8523_irq(int irq, void *dev_id) { - struct pcf8523 *pcf8523 = i2c_get_clientdata(dev_id); - u8 value; + struct pcf8523 *pcf8523 = dev_id; + u32 value; int err; - err = pcf8523_read(pcf8523->client, PCF8523_REG_CONTROL2, &value); + err = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL2, &value); if (err < 0) return IRQ_HANDLED; if (value & PCF8523_CONTROL2_AF) { value &= ~PCF8523_CONTROL2_AF; - pcf8523_write(pcf8523->client, PCF8523_REG_CONTROL2, value); + regmap_write(pcf8523->regmap, PCF8523_REG_CONTROL2, value); rtc_update_irq(pcf8523->rtc, 1, RTC_IRQF | RTC_AF); return IRQ_HANDLED; @@ -177,68 +96,14 @@ static irqreturn_t pcf8523_irq(int irq, void *dev_id) return IRQ_NONE; } -static int pcf8523_stop_rtc(struct i2c_client *client) -{ - u8 value; - int err; - - err = pcf8523_read(client, PCF8523_REG_CONTROL1, &value); - if (err < 0) - return err; - - value |= PCF8523_CONTROL1_STOP; - - err = pcf8523_write(client, PCF8523_REG_CONTROL1, value); - if (err < 0) - return err; - - return 0; -} - -static int pcf8523_start_rtc(struct i2c_client *client) -{ - u8 value; - int err; - - err = pcf8523_read(client, PCF8523_REG_CONTROL1, &value); - if (err < 0) - return err; - - value &= ~PCF8523_CONTROL1_STOP; - - err = pcf8523_write(client, PCF8523_REG_CONTROL1, value); - if (err < 0) - return err; - - return 0; -} - static int pcf8523_rtc_read_time(struct device *dev, struct rtc_time *tm) { - struct i2c_client *client = to_i2c_client(dev); - u8 start = PCF8523_REG_SECONDS, regs[7]; - struct i2c_msg msgs[2]; + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); + u8 regs[7]; int err; - err = pcf8523_voltage_low(client); - if (err < 0) { - return err; - } else if (err > 0) { - dev_err(dev, "low voltage detected, time is unreliable\n"); - return -EINVAL; - } - - msgs[0].addr = client->addr; - msgs[0].flags = 0; - msgs[0].len = 1; - msgs[0].buf = &start; - - msgs[1].addr = client->addr; - msgs[1].flags = I2C_M_RD; - msgs[1].len = sizeof(regs); - msgs[1].buf = regs; - - err = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + err = regmap_bulk_read(pcf8523->regmap, PCF8523_REG_SECONDS, regs, + sizeof(regs)); if (err < 0) return err; @@ -258,63 +123,50 @@ static int pcf8523_rtc_read_time(struct device *dev, struct rtc_time *tm) static int pcf8523_rtc_set_time(struct device *dev, struct rtc_time *tm) { - struct i2c_client *client = to_i2c_client(dev); - struct i2c_msg msg; - u8 regs[8]; + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); + u8 regs[7]; int err; - err = pcf8523_stop_rtc(client); + err = regmap_update_bits(pcf8523->regmap, PCF8523_REG_CONTROL1, + PCF8523_CONTROL1_STOP, PCF8523_CONTROL1_STOP); if (err < 0) return err; - regs[0] = PCF8523_REG_SECONDS; /* This will purposely overwrite PCF8523_SECONDS_OS */ - regs[1] = bin2bcd(tm->tm_sec); - regs[2] = bin2bcd(tm->tm_min); - regs[3] = bin2bcd(tm->tm_hour); - regs[4] = bin2bcd(tm->tm_mday); - regs[5] = tm->tm_wday; - regs[6] = bin2bcd(tm->tm_mon + 1); - regs[7] = bin2bcd(tm->tm_year - 100); - - msg.addr = client->addr; - msg.flags = 0; - msg.len = sizeof(regs); - msg.buf = regs; - - err = i2c_transfer(client->adapter, &msg, 1); + regs[0] = bin2bcd(tm->tm_sec); + regs[1] = bin2bcd(tm->tm_min); + regs[2] = bin2bcd(tm->tm_hour); + regs[3] = bin2bcd(tm->tm_mday); + regs[4] = tm->tm_wday; + regs[5] = bin2bcd(tm->tm_mon + 1); + regs[6] = bin2bcd(tm->tm_year - 100); + + err = regmap_bulk_write(pcf8523->regmap, PCF8523_REG_SECONDS, regs, + sizeof(regs)); if (err < 0) { /* * If the time cannot be set, restart the RTC anyway. Note * that errors are ignored if the RTC cannot be started so * that we have a chance to propagate the original error. */ - pcf8523_start_rtc(client); + regmap_update_bits(pcf8523->regmap, PCF8523_REG_CONTROL1, + PCF8523_CONTROL1_STOP, 0); return err; } - return pcf8523_start_rtc(client); + return regmap_update_bits(pcf8523->regmap, PCF8523_REG_CONTROL1, + PCF8523_CONTROL1_STOP, 0); } static int pcf8523_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *tm) { - struct i2c_client *client = to_i2c_client(dev); - u8 start = PCF8523_REG_MINUTE_ALARM, regs[4]; - struct i2c_msg msgs[2]; - u8 value; + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); + u8 regs[4]; + u32 value; int err; - msgs[0].addr = client->addr; - msgs[0].flags = 0; - msgs[0].len = 1; - msgs[0].buf = &start; - - msgs[1].addr = client->addr; - msgs[1].flags = I2C_M_RD; - msgs[1].len = sizeof(regs); - msgs[1].buf = regs; - - err = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + err = regmap_bulk_read(pcf8523->regmap, PCF8523_REG_MINUTE_ALARM, regs, + sizeof(regs)); if (err < 0) return err; @@ -324,12 +176,12 @@ static int pcf8523_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *tm) tm->time.tm_mday = bcd2bin(regs[2] & 0x3F); tm->time.tm_wday = bcd2bin(regs[3] & 0x7); - err = pcf8523_read(client, PCF8523_REG_CONTROL1, &value); + err = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL1, &value); if (err < 0) return err; tm->enabled = !!(value & PCF8523_CONTROL1_AIE); - err = pcf8523_read(client, PCF8523_REG_CONTROL2, &value); + err = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL2, &value); if (err < 0) return err; tm->pending = !!(value & PCF8523_CONTROL2_AF); @@ -339,30 +191,16 @@ static int pcf8523_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *tm) static int pcf8523_irq_enable(struct device *dev, unsigned int enabled) { - struct i2c_client *client = to_i2c_client(dev); - u8 value; - int err; - - err = pcf8523_read(client, PCF8523_REG_CONTROL1, &value); - if (err < 0) - return err; - - value &= PCF8523_CONTROL1_AIE; + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); - if (enabled) - value |= PCF8523_CONTROL1_AIE; - - err = pcf8523_write(client, PCF8523_REG_CONTROL1, value); - if (err < 0) - return err; - - return 0; + return regmap_update_bits(pcf8523->regmap, PCF8523_REG_CONTROL1, + PCF8523_CONTROL1_AIE, enabled ? + PCF8523_CONTROL1_AIE : 0); } static int pcf8523_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm) { - struct i2c_client *client = to_i2c_client(dev); - struct i2c_msg msg; + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); u8 regs[5]; int err; @@ -370,7 +208,7 @@ static int pcf8523_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm) if (err) return err; - err = pcf8523_write(client, PCF8523_REG_CONTROL2, 0); + err = regmap_write(pcf8523->regmap, PCF8523_REG_CONTROL2, 0); if (err < 0) return err; @@ -382,16 +220,13 @@ static int pcf8523_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm) rtc_time64_to_tm(alarm_time, &tm->time); } - regs[0] = PCF8523_REG_MINUTE_ALARM; - regs[1] = bin2bcd(tm->time.tm_min); - regs[2] = bin2bcd(tm->time.tm_hour); - regs[3] = bin2bcd(tm->time.tm_mday); - regs[4] = ALARM_DIS; - msg.addr = client->addr; - msg.flags = 0; - msg.len = sizeof(regs); - msg.buf = regs; - err = i2c_transfer(client->adapter, &msg, 1); + regs[0] = bin2bcd(tm->time.tm_min); + regs[1] = bin2bcd(tm->time.tm_hour); + regs[2] = bin2bcd(tm->time.tm_mday); + regs[3] = ALARM_DIS; + + err = regmap_bulk_write(pcf8523->regmap, PCF8523_REG_MINUTE_ALARM, regs, + sizeof(regs)); if (err < 0) return err; @@ -401,24 +236,101 @@ static int pcf8523_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm) return 0; } -#ifdef CONFIG_RTC_INTF_DEV +static int pcf8523_param_get(struct device *dev, struct rtc_param *param) +{ + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); + int ret; + + switch(param->param) { + u32 value; + + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL3, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(PCF8523_CONTROL3_PM, value); + + switch(value) { + case 0x0: + case 0x4: + param->uvalue = RTC_BSM_LEVEL; + break; + case 0x1: + case 0x5: + param->uvalue = RTC_BSM_DIRECT; + break; + case PCF8523_PM_STANDBY: + param->uvalue = RTC_BSM_STANDBY; + break; + default: + param->uvalue = RTC_BSM_DISABLED; + } + + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int pcf8523_param_set(struct device *dev, struct rtc_param *param) +{ + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); + + switch(param->param) { + u8 mode; + case RTC_PARAM_BACKUP_SWITCH_MODE: + switch (param->uvalue) { + case RTC_BSM_DISABLED: + mode = 0x2; + break; + case RTC_BSM_DIRECT: + mode = 0x1; + break; + case RTC_BSM_LEVEL: + mode = 0x0; + break; + case RTC_BSM_STANDBY: + mode = PCF8523_PM_STANDBY; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(pcf8523->regmap, PCF8523_REG_CONTROL3, + PCF8523_CONTROL3_PM, + FIELD_PREP(PCF8523_CONTROL3_PM, mode)); + + break; + + default: + return -EINVAL; + } + + return 0; +} + static int pcf8523_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { - struct i2c_client *client = to_i2c_client(dev); + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); unsigned int flags = 0; - u8 value; + u32 value; int ret; switch (cmd) { case RTC_VL_READ: - ret = pcf8523_voltage_low(client); + ret = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL3, &value); if (ret < 0) return ret; - if (ret) + + if (value & PCF8523_CONTROL3_BLF) flags |= RTC_VL_BACKUP_LOW; - ret = pcf8523_read(client, PCF8523_REG_SECONDS, &value); + ret = regmap_read(pcf8523->regmap, PCF8523_REG_SECONDS, &value); if (ret < 0) return ret; @@ -431,18 +343,15 @@ static int pcf8523_rtc_ioctl(struct device *dev, unsigned int cmd, return -ENOIOCTLCMD; } } -#else -#define pcf8523_rtc_ioctl NULL -#endif static int pcf8523_rtc_read_offset(struct device *dev, long *offset) { - struct i2c_client *client = to_i2c_client(dev); + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); int err; - u8 value; + u32 value; s8 val; - err = pcf8523_read(client, PCF8523_REG_OFFSET, &value); + err = regmap_read(pcf8523->regmap, PCF8523_REG_OFFSET, &value); if (err < 0) return err; @@ -455,9 +364,9 @@ static int pcf8523_rtc_read_offset(struct device *dev, long *offset) static int pcf8523_rtc_set_offset(struct device *dev, long offset) { - struct i2c_client *client = to_i2c_client(dev); + struct pcf8523 *pcf8523 = dev_get_drvdata(dev); long reg_m0, reg_m1; - u8 value; + u32 value; reg_m0 = clamp(DIV_ROUND_CLOSEST(offset, 4340), -64L, 63L); reg_m1 = clamp(DIV_ROUND_CLOSEST(offset, 4069), -64L, 63L); @@ -467,7 +376,7 @@ static int pcf8523_rtc_set_offset(struct device *dev, long offset) else value = (reg_m1 & 0x7f) | PCF8523_OFFSET_MODE; - return pcf8523_write(client, PCF8523_REG_OFFSET, value); + return regmap_write(pcf8523->regmap, PCF8523_REG_OFFSET, value); } static const struct rtc_class_ops pcf8523_rtc_ops = { @@ -479,6 +388,14 @@ static const struct rtc_class_ops pcf8523_rtc_ops = { .ioctl = pcf8523_rtc_ioctl, .read_offset = pcf8523_rtc_read_offset, .set_offset = pcf8523_rtc_set_offset, + .param_get = pcf8523_param_get, + .param_set = pcf8523_param_set, +}; + +static const struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x13, }; static int pcf8523_probe(struct i2c_client *client, @@ -487,6 +404,7 @@ static int pcf8523_probe(struct i2c_client *client, struct pcf8523 *pcf8523; struct rtc_device *rtc; bool wakeup_source = false; + u32 value; int err; if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) @@ -496,46 +414,60 @@ static int pcf8523_probe(struct i2c_client *client, if (!pcf8523) return -ENOMEM; + pcf8523->regmap = devm_regmap_init_i2c(client, ®map_config); + if (IS_ERR(pcf8523->regmap)) + return PTR_ERR(pcf8523->regmap); + i2c_set_clientdata(client, pcf8523); - pcf8523->client = client; - err = pcf8523_load_capacitance(client); + rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + pcf8523->rtc = rtc; + + err = pcf8523_load_capacitance(pcf8523, client->dev.of_node); if (err < 0) dev_warn(&client->dev, "failed to set xtal load capacitance: %d", err); - err = pcf8523_set_pm(client, 0); + err = regmap_read(pcf8523->regmap, PCF8523_REG_SECONDS, &value); if (err < 0) return err; - rtc = devm_rtc_allocate_device(&client->dev); - if (IS_ERR(rtc)) - return PTR_ERR(rtc); + if (value & PCF8523_SECONDS_OS) { + err = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL3, &value); + if (err < 0) + return err; + + if (FIELD_GET(PCF8523_CONTROL3_PM, value) == PCF8523_PM_STANDBY) { + err = regmap_write(pcf8523->regmap, PCF8523_REG_CONTROL3, + value & ~PCF8523_CONTROL3_PM); + if (err < 0) + return err; + } + } - pcf8523->rtc = rtc; rtc->ops = &pcf8523_rtc_ops; rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; rtc->range_max = RTC_TIMESTAMP_END_2099; rtc->uie_unsupported = 1; if (client->irq > 0) { - err = pcf8523_write(client, PCF8523_TMR_CLKOUT_CTRL, 0x38); + err = regmap_write(pcf8523->regmap, PCF8523_TMR_CLKOUT_CTRL, 0x38); if (err < 0) return err; err = devm_request_threaded_irq(&client->dev, client->irq, NULL, pcf8523_irq, IRQF_SHARED | IRQF_ONESHOT | IRQF_TRIGGER_LOW, - dev_name(&rtc->dev), client); + dev_name(&rtc->dev), pcf8523); if (err) return err; dev_pm_set_wake_irq(&client->dev, client->irq); } -#ifdef CONFIG_OF wakeup_source = of_property_read_bool(client->dev.of_node, "wakeup-source"); -#endif if (client->irq > 0 || wakeup_source) device_init_wakeup(&client->dev, true); @@ -548,19 +480,17 @@ static const struct i2c_device_id pcf8523_id[] = { }; MODULE_DEVICE_TABLE(i2c, pcf8523_id); -#ifdef CONFIG_OF static const struct of_device_id pcf8523_of_match[] = { { .compatible = "nxp,pcf8523" }, { .compatible = "microcrystal,rv8523" }, { } }; MODULE_DEVICE_TABLE(of, pcf8523_of_match); -#endif static struct i2c_driver pcf8523_driver = { .driver = { .name = "rtc-pcf8523", - .of_match_table = of_match_ptr(pcf8523_of_match), + .of_match_table = pcf8523_of_match, }, .probe = pcf8523_probe, .id_table = pcf8523_id, diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c index 12c807306893..cdc623b3e365 100644 --- a/drivers/rtc/rtc-rv3028.c +++ b/drivers/rtc/rtc-rv3028.c @@ -10,6 +10,7 @@ #include <linux/clk-provider.h> #include <linux/bcd.h> +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/i2c.h> #include <linux/interrupt.h> @@ -80,6 +81,10 @@ #define RV3028_BACKUP_TCE BIT(5) #define RV3028_BACKUP_TCR_MASK GENMASK(1,0) +#define RV3028_BACKUP_BSM GENMASK(3,2) + +#define RV3028_BACKUP_BSM_DSM 0x1 +#define RV3028_BACKUP_BSM_LSM 0x3 #define OFFSET_STEP_PPT 953674 @@ -512,6 +517,71 @@ exit_eerd: } +static int rv3028_param_get(struct device *dev, struct rtc_param *param) +{ + struct rv3028_data *rv3028 = dev_get_drvdata(dev); + int ret; + + switch(param->param) { + u32 value; + + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(rv3028->regmap, RV3028_BACKUP, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(RV3028_BACKUP_BSM, value); + + switch(value) { + case RV3028_BACKUP_BSM_DSM: + param->uvalue = RTC_BSM_DIRECT; + break; + case RV3028_BACKUP_BSM_LSM: + param->uvalue = RTC_BSM_LEVEL; + break; + default: + param->uvalue = RTC_BSM_DISABLED; + } + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int rv3028_param_set(struct device *dev, struct rtc_param *param) +{ + struct rv3028_data *rv3028 = dev_get_drvdata(dev); + + switch(param->param) { + u8 mode; + case RTC_PARAM_BACKUP_SWITCH_MODE: + switch (param->uvalue) { + case RTC_BSM_DISABLED: + mode = 0; + break; + case RTC_BSM_DIRECT: + mode = RV3028_BACKUP_BSM_DSM; + break; + case RTC_BSM_LEVEL: + mode = RV3028_BACKUP_BSM_LSM; + break; + default: + return -EINVAL; + } + + return rv3028_update_cfg(rv3028, RV3028_BACKUP, RV3028_BACKUP_BSM, + FIELD_PREP(RV3028_BACKUP_BSM, mode)); + + default: + return -EINVAL; + } + + return 0; +} + static int rv3028_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { struct rv3028_data *rv3028 = dev_get_drvdata(dev); @@ -776,6 +846,8 @@ static const struct rtc_class_ops rv3028_rtc_ops = { .read_offset = rv3028_read_offset, .set_offset = rv3028_set_offset, .ioctl = rv3028_ioctl, + .param_get = rv3028_param_get, + .param_set = rv3028_param_set, }; static const struct regmap_config regmap_config = { @@ -878,6 +950,8 @@ static int rv3028_probe(struct i2c_client *client) if (ret) return ret; + set_bit(RTC_FEATURE_BACKUP_SWITCH_MODE, rv3028->rtc->features); + rv3028->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; rv3028->rtc->range_max = RTC_TIMESTAMP_END_2099; rv3028->rtc->ops = &rv3028_rtc_ops; diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c index d63102d5cb1e..c3bee305eacc 100644 --- a/drivers/rtc/rtc-rv3032.c +++ b/drivers/rtc/rtc-rv3032.c @@ -106,6 +106,7 @@ struct rv3032_data { struct regmap *regmap; struct rtc_device *rtc; + bool trickle_charger_set; #ifdef CONFIG_COMMON_CLK struct clk_hw clkout_hw; #endif @@ -310,14 +311,6 @@ static int rv3032_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) u8 ctrl = 0; int ret; - /* The alarm has no seconds, round up to nearest minute */ - if (alrm->time.tm_sec) { - time64_t alarm_time = rtc_tm_to_time64(&alrm->time); - - alarm_time += 60 - alrm->time.tm_sec; - rtc_time64_to_tm(alarm_time, &alrm->time); - } - ret = regmap_update_bits(rv3032->regmap, RV3032_CTRL2, RV3032_CTRL2_AIE | RV3032_CTRL2_UIE, 0); if (ret) @@ -402,6 +395,75 @@ static int rv3032_set_offset(struct device *dev, long offset) FIELD_PREP(RV3032_OFFSET_MSK, offset)); } +static int rv3032_param_get(struct device *dev, struct rtc_param *param) +{ + struct rv3032_data *rv3032 = dev_get_drvdata(dev); + int ret; + + switch(param->param) { + u32 value; + + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(rv3032->regmap, RV3032_PMU, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(RV3032_PMU_BSM, value); + + switch(value) { + case RV3032_PMU_BSM_DSM: + param->uvalue = RTC_BSM_DIRECT; + break; + case RV3032_PMU_BSM_LSM: + param->uvalue = RTC_BSM_LEVEL; + break; + default: + param->uvalue = RTC_BSM_DISABLED; + } + + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int rv3032_param_set(struct device *dev, struct rtc_param *param) +{ + struct rv3032_data *rv3032 = dev_get_drvdata(dev); + + switch(param->param) { + u8 mode; + case RTC_PARAM_BACKUP_SWITCH_MODE: + if (rv3032->trickle_charger_set) + return -EINVAL; + + switch (param->uvalue) { + case RTC_BSM_DISABLED: + mode = 0; + break; + case RTC_BSM_DIRECT: + mode = RV3032_PMU_BSM_DSM; + break; + case RTC_BSM_LEVEL: + mode = RV3032_PMU_BSM_LSM; + break; + default: + return -EINVAL; + } + + return rv3032_update_cfg(rv3032, RV3032_PMU, RV3032_PMU_BSM, + FIELD_PREP(RV3032_PMU_BSM, mode)); + + default: + return -EINVAL; + } + + return 0; +} + static int rv3032_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { struct rv3032_data *rv3032 = dev_get_drvdata(dev); @@ -541,6 +603,8 @@ static int rv3032_trickle_charger_setup(struct device *dev, struct rv3032_data * return 0; } + rv3032->trickle_charger_set = true; + return rv3032_update_cfg(rv3032, RV3032_PMU, RV3032_PMU_TCR | RV3032_PMU_TCM | RV3032_PMU_BSM, val | FIELD_PREP(RV3032_PMU_TCR, i)); @@ -617,11 +681,11 @@ static int rv3032_clkout_set_rate(struct clk_hw *hw, unsigned long rate, ret = rv3032_enter_eerd(rv3032, &eerd); if (ret) - goto exit_eerd; + return ret; ret = regmap_write(rv3032->regmap, RV3032_CLKOUT1, hfd & 0xff); if (ret) - return ret; + goto exit_eerd; ret = regmap_write(rv3032->regmap, RV3032_CLKOUT2, RV3032_CLKOUT2_OS | FIELD_PREP(RV3032_CLKOUT2_HFD_MSK, hfd >> 8)); @@ -813,6 +877,8 @@ static const struct rtc_class_ops rv3032_rtc_ops = { .read_alarm = rv3032_get_alarm, .set_alarm = rv3032_set_alarm, .alarm_irq_enable = rv3032_alarm_irq_enable, + .param_get = rv3032_param_get, + .param_set = rv3032_param_set, }; static const struct regmap_config regmap_config = { @@ -883,6 +949,9 @@ static int rv3032_probe(struct i2c_client *client) rv3032_trickle_charger_setup(&client->dev, rv3032); + set_bit(RTC_FEATURE_BACKUP_SWITCH_MODE, rv3032->rtc->features); + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rv3032->rtc->features); + rv3032->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; rv3032->rtc->range_max = RTC_TIMESTAMP_END_2099; rv3032->rtc->ops = &rv3032_rtc_ops; diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c index 72adef5a5ebe..0d5ed38bf60c 100644 --- a/drivers/rtc/rtc-rv8803.c +++ b/drivers/rtc/rtc-rv8803.c @@ -340,8 +340,8 @@ static int rv8803_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) } } - ctrl[1] &= ~RV8803_FLAG_AF; - err = rv8803_write_reg(rv8803->client, RV8803_FLAG, ctrl[1]); + ctrl[0] &= ~RV8803_FLAG_AF; + err = rv8803_write_reg(rv8803->client, RV8803_FLAG, ctrl[0]); mutex_unlock(&rv8803->flags_lock); if (err) return err; diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c index f4d425002f7f..758fd6e11a15 100644 --- a/drivers/rtc/rtc-rx6110.c +++ b/drivers/rtc/rtc-rx6110.c @@ -422,7 +422,7 @@ static struct regmap_config regmap_i2c_config = { static int rx6110_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { - struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent); + struct i2c_adapter *adapter = client->adapter; struct rx6110_data *rx6110; if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c index d38aaf08108c..5bfdd34a72ff 100644 --- a/drivers/rtc/rtc-rx8025.c +++ b/drivers/rtc/rtc-rx8025.c @@ -248,9 +248,6 @@ static int rx8025_set_time(struct device *dev, struct rtc_time *dt) u8 date[7]; int ret; - if ((dt->tm_year < 100) || (dt->tm_year > 199)) - return -EINVAL; - /* * Here the read-only bits are written as "0". I'm not sure if that * is sound. @@ -318,9 +315,6 @@ static int rx8025_read_alarm(struct device *dev, struct rtc_wkalrm *t) u8 ald[2]; int ctrl2, err; - if (client->irq <= 0) - return -EINVAL; - err = rx8025_read_regs(client, RX8025_REG_ALDMIN, 2, ald); if (err) return err; @@ -355,20 +349,6 @@ static int rx8025_set_alarm(struct device *dev, struct rtc_wkalrm *t) u8 ald[2]; int err; - if (client->irq <= 0) - return -EINVAL; - - /* - * Hardware alarm precision is 1 minute! - * round up to nearest minute - */ - if (t->time.tm_sec) { - time64_t alarm_time = rtc_tm_to_time64(&t->time); - - alarm_time += 60 - t->time.tm_sec; - rtc_time64_to_tm(alarm_time, &t->time); - } - ald[0] = bin2bcd(t->time.tm_min); if (rx8025->ctrl1 & RX8025_BIT_CTRL1_1224) ald[1] = bin2bcd(t->time.tm_hour); @@ -423,17 +403,7 @@ static int rx8025_alarm_irq_enable(struct device *dev, unsigned int enabled) return 0; } -static const struct rtc_class_ops rx8025_rtc_ops = { - .read_time = rx8025_get_time, - .set_time = rx8025_set_time, - .read_alarm = rx8025_read_alarm, - .set_alarm = rx8025_set_alarm, - .alarm_irq_enable = rx8025_alarm_irq_enable, -}; - /* - * Clock precision adjustment support - * * According to the RX8025 SA/NB application manual the frequency and * temperature characteristics can be approximated using the following * equation: @@ -444,11 +414,8 @@ static const struct rtc_class_ops rx8025_rtc_ops = { * a : Coefficient = (-35 +-5) * 10**-9 * ut: Ultimate temperature in degree = +25 +-5 degree * t : Any temperature in degree - * - * Note that the clock adjustment in ppb must be entered (which is - * the negative value of the deviation). */ -static int rx8025_get_clock_adjust(struct device *dev, int *adj) +static int rx8025_read_offset(struct device *dev, long *offset) { struct i2c_client *client = to_i2c_client(dev); int digoff; @@ -457,63 +424,75 @@ static int rx8025_get_clock_adjust(struct device *dev, int *adj) if (digoff < 0) return digoff; - *adj = digoff >= 64 ? digoff - 128 : digoff; - if (*adj > 0) - (*adj)--; - *adj *= -RX8025_ADJ_RESOLUTION; + *offset = digoff >= 64 ? digoff - 128 : digoff; + if (*offset > 0) + (*offset)--; + *offset *= RX8025_ADJ_RESOLUTION; return 0; } -static int rx8025_set_clock_adjust(struct device *dev, int adj) +static int rx8025_set_offset(struct device *dev, long offset) { struct i2c_client *client = to_i2c_client(dev); u8 digoff; int err; - adj /= -RX8025_ADJ_RESOLUTION; - if (adj > RX8025_ADJ_DATA_MAX) - adj = RX8025_ADJ_DATA_MAX; - else if (adj < RX8025_ADJ_DATA_MIN) - adj = RX8025_ADJ_DATA_MIN; - else if (adj > 0) - adj++; - else if (adj < 0) - adj += 128; - digoff = adj; + offset /= RX8025_ADJ_RESOLUTION; + if (offset > RX8025_ADJ_DATA_MAX) + offset = RX8025_ADJ_DATA_MAX; + else if (offset < RX8025_ADJ_DATA_MIN) + offset = RX8025_ADJ_DATA_MIN; + else if (offset > 0) + offset++; + else if (offset < 0) + offset += 128; + digoff = offset; err = rx8025_write_reg(client, RX8025_REG_DIGOFF, digoff); if (err) return err; - dev_dbg(dev, "%s: write 0x%02x\n", __func__, digoff); - return 0; } +static const struct rtc_class_ops rx8025_rtc_ops = { + .read_time = rx8025_get_time, + .set_time = rx8025_set_time, + .read_alarm = rx8025_read_alarm, + .set_alarm = rx8025_set_alarm, + .alarm_irq_enable = rx8025_alarm_irq_enable, + .read_offset = rx8025_read_offset, + .set_offset = rx8025_set_offset, +}; + static ssize_t rx8025_sysfs_show_clock_adjust(struct device *dev, struct device_attribute *attr, char *buf) { - int err, adj; + long adj; + int err; - err = rx8025_get_clock_adjust(dev, &adj); + dev_warn_once(dev, "clock_adjust_ppb is deprecated, use offset\n"); + err = rx8025_read_offset(dev, &adj); if (err) return err; - return sprintf(buf, "%d\n", adj); + return sprintf(buf, "%ld\n", -adj); } static ssize_t rx8025_sysfs_store_clock_adjust(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - int adj, err; + long adj; + int err; - if (sscanf(buf, "%i", &adj) != 1) + dev_warn_once(dev, "clock_adjust_ppb is deprecated, use offset\n"); + if (kstrtol(buf, 10, &adj) != 0) return -EINVAL; - err = rx8025_set_clock_adjust(dev, adj); + err = rx8025_set_offset(dev, -adj); return err ? err : count; } @@ -522,15 +501,14 @@ static DEVICE_ATTR(clock_adjust_ppb, S_IRUGO | S_IWUSR, rx8025_sysfs_show_clock_adjust, rx8025_sysfs_store_clock_adjust); -static int rx8025_sysfs_register(struct device *dev) -{ - return device_create_file(dev, &dev_attr_clock_adjust_ppb); -} +static struct attribute *rx8025_attrs[] = { + &dev_attr_clock_adjust_ppb.attr, + NULL +}; -static void rx8025_sysfs_unregister(struct device *dev) -{ - device_remove_file(dev, &dev_attr_clock_adjust_ppb); -} +static const struct attribute_group rx8025_attr_group = { + .attrs = rx8025_attrs, +}; static int rx8025_probe(struct i2c_client *client, const struct i2c_device_id *id) @@ -559,12 +537,13 @@ static int rx8025_probe(struct i2c_client *client, if (err) return err; - rx8025->rtc = devm_rtc_device_register(&client->dev, client->name, - &rx8025_rtc_ops, THIS_MODULE); - if (IS_ERR(rx8025->rtc)) { - dev_err(&client->dev, "unable to register the class device\n"); + rx8025->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(rx8025->rtc)) return PTR_ERR(rx8025->rtc); - } + + rx8025->rtc->ops = &rx8025_rtc_ops; + rx8025->rtc->range_min = RTC_TIMESTAMP_BEGIN_1900; + rx8025->rtc->range_max = RTC_TIMESTAMP_END_2099; if (client->irq > 0) { dev_info(&client->dev, "IRQ %d supplied\n", client->irq); @@ -572,25 +551,20 @@ static int rx8025_probe(struct i2c_client *client, rx8025_handle_irq, IRQF_ONESHOT, "rx8025", client); - if (err) { - dev_err(&client->dev, "unable to request IRQ, alarms disabled\n"); - client->irq = 0; - } + if (err) + clear_bit(RTC_FEATURE_ALARM, rx8025->rtc->features); } rx8025->rtc->max_user_freq = 1; - /* the rx8025 alarm only supports a minute accuracy */ - rx8025->rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rx8025->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rx8025->rtc->features); - err = rx8025_sysfs_register(&client->dev); - return err; -} + err = rtc_add_group(rx8025->rtc, &rx8025_attr_group); + if (err) + return err; -static int rx8025_remove(struct i2c_client *client) -{ - rx8025_sysfs_unregister(&client->dev); - return 0; + return devm_rtc_register_device(rx8025->rtc); } static struct i2c_driver rx8025_driver = { @@ -598,7 +572,6 @@ static struct i2c_driver rx8025_driver = { .name = "rtc-rx8025", }, .probe = rx8025_probe, - .remove = rx8025_remove, .id_table = rx8025_id, }; diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c index b5bdeda7d767..26278c770731 100644 --- a/drivers/rtc/rtc-s35390a.c +++ b/drivers/rtc/rtc-s35390a.c @@ -285,9 +285,6 @@ static int s35390a_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) alm->time.tm_min, alm->time.tm_hour, alm->time.tm_mday, alm->time.tm_mon, alm->time.tm_year, alm->time.tm_wday); - if (alm->time.tm_sec != 0) - dev_warn(&client->dev, "Alarms are only supported on a per minute basis!\n"); - /* disable interrupt (which deasserts the irq line) */ err = s35390a_set_reg(s35390a, S35390A_CMD_STATUS2, &sts, sizeof(sts)); if (err < 0) @@ -491,8 +488,8 @@ static int s35390a_probe(struct i2c_client *client, s35390a->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; s35390a->rtc->range_max = RTC_TIMESTAMP_END_2099; - /* supports per-minute alarms only, therefore set uie_unsupported */ - s35390a->rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, s35390a->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, s35390a->rtc->features ); if (status1 & S35390A_FLAG_INT2) rtc_update_irq(s35390a->rtc, 1, RTC_AF); diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index e57d3ca70a78..db529733c9c4 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -127,10 +127,9 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled) return ret; } -/* Time read/write */ -static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) +/* Read time from RTC and convert it from BCD */ +static int s3c_rtc_read_time(struct s3c_rtc *info, struct rtc_time *tm) { - struct s3c_rtc *info = dev_get_drvdata(dev); unsigned int have_retried = 0; int ret; @@ -139,54 +138,40 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) return ret; retry_get_time: - rtc_tm->tm_min = readb(info->base + S3C2410_RTCMIN); - rtc_tm->tm_hour = readb(info->base + S3C2410_RTCHOUR); - rtc_tm->tm_mday = readb(info->base + S3C2410_RTCDATE); - rtc_tm->tm_mon = readb(info->base + S3C2410_RTCMON); - rtc_tm->tm_year = readb(info->base + S3C2410_RTCYEAR); - rtc_tm->tm_sec = readb(info->base + S3C2410_RTCSEC); - - /* the only way to work out whether the system was mid-update + tm->tm_min = readb(info->base + S3C2410_RTCMIN); + tm->tm_hour = readb(info->base + S3C2410_RTCHOUR); + tm->tm_mday = readb(info->base + S3C2410_RTCDATE); + tm->tm_mon = readb(info->base + S3C2410_RTCMON); + tm->tm_year = readb(info->base + S3C2410_RTCYEAR); + tm->tm_sec = readb(info->base + S3C2410_RTCSEC); + + /* + * The only way to work out whether the system was mid-update * when we read it is to check the second counter, and if it * is zero, then we re-try the entire read */ - - if (rtc_tm->tm_sec == 0 && !have_retried) { + if (tm->tm_sec == 0 && !have_retried) { have_retried = 1; goto retry_get_time; } - rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec); - rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min); - rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour); - rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday); - rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon); - rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year); - s3c_rtc_disable_clk(info); - rtc_tm->tm_year += 100; - rtc_tm->tm_mon -= 1; + tm->tm_sec = bcd2bin(tm->tm_sec); + tm->tm_min = bcd2bin(tm->tm_min); + tm->tm_hour = bcd2bin(tm->tm_hour); + tm->tm_mday = bcd2bin(tm->tm_mday); + tm->tm_mon = bcd2bin(tm->tm_mon); + tm->tm_year = bcd2bin(tm->tm_year); - dev_dbg(dev, "read time %ptR\n", rtc_tm); return 0; } -static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) +/* Convert time to BCD and write it to RTC */ +static int s3c_rtc_write_time(struct s3c_rtc *info, const struct rtc_time *tm) { - struct s3c_rtc *info = dev_get_drvdata(dev); - int year = tm->tm_year - 100; int ret; - dev_dbg(dev, "set time %ptR\n", tm); - - /* we get around y2k by simply not supporting it */ - - if (year < 0 || year >= 100) { - dev_err(dev, "rtc only supports 100 years\n"); - return -EINVAL; - } - ret = s3c_rtc_enable_clk(info); if (ret) return ret; @@ -195,14 +180,48 @@ static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) writeb(bin2bcd(tm->tm_min), info->base + S3C2410_RTCMIN); writeb(bin2bcd(tm->tm_hour), info->base + S3C2410_RTCHOUR); writeb(bin2bcd(tm->tm_mday), info->base + S3C2410_RTCDATE); - writeb(bin2bcd(tm->tm_mon + 1), info->base + S3C2410_RTCMON); - writeb(bin2bcd(year), info->base + S3C2410_RTCYEAR); + writeb(bin2bcd(tm->tm_mon), info->base + S3C2410_RTCMON); + writeb(bin2bcd(tm->tm_year), info->base + S3C2410_RTCYEAR); s3c_rtc_disable_clk(info); return 0; } +static int s3c_rtc_gettime(struct device *dev, struct rtc_time *tm) +{ + struct s3c_rtc *info = dev_get_drvdata(dev); + int ret; + + ret = s3c_rtc_read_time(info, tm); + if (ret) + return ret; + + /* Convert internal representation to actual date/time */ + tm->tm_year += 100; + tm->tm_mon -= 1; + + dev_dbg(dev, "read time %ptR\n", tm); + return 0; +} + +static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) +{ + struct s3c_rtc *info = dev_get_drvdata(dev); + struct rtc_time rtc_tm = *tm; + + dev_dbg(dev, "set time %ptR\n", tm); + + /* + * Convert actual date/time to internal representation. + * We get around Y2K by simply not supporting it. + */ + rtc_tm.tm_year -= 100; + rtc_tm.tm_mon += 1; + + return s3c_rtc_write_time(info, &rtc_tm); +} + static int s3c_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm) { struct s3c_rtc *info = dev_get_drvdata(dev); @@ -447,15 +466,20 @@ static int s3c_rtc_probe(struct platform_device *pdev) device_init_wakeup(&pdev->dev, 1); - /* register RTC and exit */ - info->rtc = devm_rtc_device_register(&pdev->dev, "s3c", &s3c_rtcops, - THIS_MODULE); + info->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(info->rtc)) { - dev_err(&pdev->dev, "cannot attach rtc\n"); ret = PTR_ERR(info->rtc); goto err_nortc; } + info->rtc->ops = &s3c_rtcops; + info->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + info->rtc->range_max = RTC_TIMESTAMP_END_2099; + + ret = devm_rtc_register_device(info->rtc); + if (ret) + goto err_nortc; + ret = devm_request_irq(&pdev->dev, info->irq_alarm, s3c_rtc_alarmirq, 0, "s3c2410-rtc alarm", info); if (ret) { diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index fb9c6b709e13..4243fe6d3842 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -861,4 +861,3 @@ module_platform_driver(s5m_rtc_driver); MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>"); MODULE_DESCRIPTION("Samsung S5M/S2MPS14 RTC driver"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:s5m-rtc"); diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index adec1b14a8de..711832c758ae 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -673,8 +673,17 @@ static int sun6i_rtc_probe(struct platform_device *pdev) struct sun6i_rtc_dev *chip = sun6i_rtc; int ret; - if (!chip) - return -ENODEV; + if (!chip) { + chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + spin_lock_init(&chip->lock); + + chip->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(chip->base)) + return PTR_ERR(chip->base); + } platform_set_drvdata(pdev, chip); diff --git a/drivers/rtc/rtc-tps80031.c b/drivers/rtc/rtc-tps80031.c deleted file mode 100644 index c77b8eab94a0..000000000000 --- a/drivers/rtc/rtc-tps80031.c +++ /dev/null @@ -1,324 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * rtc-tps80031.c -- TI TPS80031/TPS80032 RTC driver - * - * RTC driver for TI TPS80031/TPS80032 Fully Integrated - * Power Management with Power Path and Battery Charger - * - * Copyright (c) 2012, NVIDIA Corporation. - * - * Author: Laxman Dewangan <ldewangan@nvidia.com> - */ - -#include <linux/bcd.h> -#include <linux/device.h> -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/mfd/tps80031.h> -#include <linux/platform_device.h> -#include <linux/pm.h> -#include <linux/rtc.h> -#include <linux/slab.h> - -#define ENABLE_ALARM_INT 0x08 -#define ALARM_INT_STATUS 0x40 - -/** - * Setting bit to 1 in STOP_RTC will run the RTC and - * setting this bit to 0 will freeze RTC. - */ -#define STOP_RTC 0x1 - -/* Power on reset Values of RTC registers */ -#define TPS80031_RTC_POR_YEAR 0 -#define TPS80031_RTC_POR_MONTH 1 -#define TPS80031_RTC_POR_DAY 1 - -/* Numbers of registers for time and alarms */ -#define TPS80031_RTC_TIME_NUM_REGS 7 -#define TPS80031_RTC_ALARM_NUM_REGS 6 - -/** - * PMU RTC have only 2 nibbles to store year information, so using an - * offset of 100 to set the base year as 2000 for our driver. - */ -#define RTC_YEAR_OFFSET 100 - -struct tps80031_rtc { - struct rtc_device *rtc; - int irq; -}; - -static int tps80031_rtc_read_time(struct device *dev, struct rtc_time *tm) -{ - u8 buff[TPS80031_RTC_TIME_NUM_REGS]; - int ret; - - ret = tps80031_reads(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_SECONDS_REG, TPS80031_RTC_TIME_NUM_REGS, buff); - if (ret < 0) { - dev_err(dev, "reading RTC_SECONDS_REG failed, err = %d\n", ret); - return ret; - } - - tm->tm_sec = bcd2bin(buff[0]); - tm->tm_min = bcd2bin(buff[1]); - tm->tm_hour = bcd2bin(buff[2]); - tm->tm_mday = bcd2bin(buff[3]); - tm->tm_mon = bcd2bin(buff[4]) - 1; - tm->tm_year = bcd2bin(buff[5]) + RTC_YEAR_OFFSET; - tm->tm_wday = bcd2bin(buff[6]); - return 0; -} - -static int tps80031_rtc_set_time(struct device *dev, struct rtc_time *tm) -{ - u8 buff[7]; - int ret; - - buff[0] = bin2bcd(tm->tm_sec); - buff[1] = bin2bcd(tm->tm_min); - buff[2] = bin2bcd(tm->tm_hour); - buff[3] = bin2bcd(tm->tm_mday); - buff[4] = bin2bcd(tm->tm_mon + 1); - buff[5] = bin2bcd(tm->tm_year % RTC_YEAR_OFFSET); - buff[6] = bin2bcd(tm->tm_wday); - - /* Stop RTC while updating the RTC time registers */ - ret = tps80031_clr_bits(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_CTRL_REG, STOP_RTC); - if (ret < 0) { - dev_err(dev->parent, "Stop RTC failed, err = %d\n", ret); - return ret; - } - - ret = tps80031_writes(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_SECONDS_REG, - TPS80031_RTC_TIME_NUM_REGS, buff); - if (ret < 0) { - dev_err(dev, "writing RTC_SECONDS_REG failed, err %d\n", ret); - return ret; - } - - ret = tps80031_set_bits(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_CTRL_REG, STOP_RTC); - if (ret < 0) - dev_err(dev->parent, "Start RTC failed, err = %d\n", ret); - return ret; -} - -static int tps80031_rtc_alarm_irq_enable(struct device *dev, - unsigned int enable) -{ - int ret; - - if (enable) - ret = tps80031_set_bits(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_INTERRUPTS_REG, ENABLE_ALARM_INT); - else - ret = tps80031_clr_bits(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_INTERRUPTS_REG, ENABLE_ALARM_INT); - if (ret < 0) { - dev_err(dev, "Update on RTC_INT failed, err = %d\n", ret); - return ret; - } - return 0; -} - -static int tps80031_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) -{ - u8 buff[TPS80031_RTC_ALARM_NUM_REGS]; - int ret; - - buff[0] = bin2bcd(alrm->time.tm_sec); - buff[1] = bin2bcd(alrm->time.tm_min); - buff[2] = bin2bcd(alrm->time.tm_hour); - buff[3] = bin2bcd(alrm->time.tm_mday); - buff[4] = bin2bcd(alrm->time.tm_mon + 1); - buff[5] = bin2bcd(alrm->time.tm_year % RTC_YEAR_OFFSET); - ret = tps80031_writes(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_ALARM_SECONDS_REG, - TPS80031_RTC_ALARM_NUM_REGS, buff); - if (ret < 0) { - dev_err(dev, "Writing RTC_ALARM failed, err %d\n", ret); - return ret; - } - return tps80031_rtc_alarm_irq_enable(dev, alrm->enabled); -} - -static int tps80031_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) -{ - u8 buff[6]; - int ret; - - ret = tps80031_reads(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_ALARM_SECONDS_REG, - TPS80031_RTC_ALARM_NUM_REGS, buff); - if (ret < 0) { - dev_err(dev->parent, - "reading RTC_ALARM failed, err = %d\n", ret); - return ret; - } - - alrm->time.tm_sec = bcd2bin(buff[0]); - alrm->time.tm_min = bcd2bin(buff[1]); - alrm->time.tm_hour = bcd2bin(buff[2]); - alrm->time.tm_mday = bcd2bin(buff[3]); - alrm->time.tm_mon = bcd2bin(buff[4]) - 1; - alrm->time.tm_year = bcd2bin(buff[5]) + RTC_YEAR_OFFSET; - return 0; -} - -static int clear_alarm_int_status(struct device *dev, struct tps80031_rtc *rtc) -{ - int ret; - u8 buf; - - /** - * As per datasheet, A dummy read of this RTC_STATUS_REG register - * is necessary before each I2C read in order to update the status - * register value. - */ - ret = tps80031_read(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_STATUS_REG, &buf); - if (ret < 0) { - dev_err(dev, "reading RTC_STATUS failed. err = %d\n", ret); - return ret; - } - - /* clear Alarm status bits.*/ - ret = tps80031_set_bits(dev->parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_STATUS_REG, ALARM_INT_STATUS); - if (ret < 0) { - dev_err(dev, "clear Alarm INT failed, err = %d\n", ret); - return ret; - } - return 0; -} - -static irqreturn_t tps80031_rtc_irq(int irq, void *data) -{ - struct device *dev = data; - struct tps80031_rtc *rtc = dev_get_drvdata(dev); - int ret; - - ret = clear_alarm_int_status(dev, rtc); - if (ret < 0) - return ret; - - rtc_update_irq(rtc->rtc, 1, RTC_IRQF | RTC_AF); - return IRQ_HANDLED; -} - -static const struct rtc_class_ops tps80031_rtc_ops = { - .read_time = tps80031_rtc_read_time, - .set_time = tps80031_rtc_set_time, - .set_alarm = tps80031_rtc_set_alarm, - .read_alarm = tps80031_rtc_read_alarm, - .alarm_irq_enable = tps80031_rtc_alarm_irq_enable, -}; - -static int tps80031_rtc_probe(struct platform_device *pdev) -{ - struct tps80031_rtc *rtc; - struct rtc_time tm; - int ret; - - rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); - if (!rtc) - return -ENOMEM; - - rtc->irq = platform_get_irq(pdev, 0); - platform_set_drvdata(pdev, rtc); - - /* Start RTC */ - ret = tps80031_set_bits(pdev->dev.parent, TPS80031_SLAVE_ID1, - TPS80031_RTC_CTRL_REG, STOP_RTC); - if (ret < 0) { - dev_err(&pdev->dev, "failed to start RTC. err = %d\n", ret); - return ret; - } - - /* If RTC have POR values, set time 01:01:2000 */ - tps80031_rtc_read_time(&pdev->dev, &tm); - if ((tm.tm_year == RTC_YEAR_OFFSET + TPS80031_RTC_POR_YEAR) && - (tm.tm_mon == (TPS80031_RTC_POR_MONTH - 1)) && - (tm.tm_mday == TPS80031_RTC_POR_DAY)) { - tm.tm_year = 2000; - tm.tm_mday = 1; - tm.tm_mon = 1; - ret = tps80031_rtc_set_time(&pdev->dev, &tm); - if (ret < 0) { - dev_err(&pdev->dev, - "RTC set time failed, err = %d\n", ret); - return ret; - } - } - - /* Clear alarm intretupt status if it is there */ - ret = clear_alarm_int_status(&pdev->dev, rtc); - if (ret < 0) { - dev_err(&pdev->dev, "Clear alarm int failed, err = %d\n", ret); - return ret; - } - - rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, - &tps80031_rtc_ops, THIS_MODULE); - if (IS_ERR(rtc->rtc)) { - ret = PTR_ERR(rtc->rtc); - dev_err(&pdev->dev, "RTC registration failed, err %d\n", ret); - return ret; - } - - ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL, - tps80031_rtc_irq, - IRQF_ONESHOT, - dev_name(&pdev->dev), rtc); - if (ret < 0) { - dev_err(&pdev->dev, "request IRQ:%d failed, err = %d\n", - rtc->irq, ret); - return ret; - } - device_set_wakeup_capable(&pdev->dev, 1); - return 0; -} - -#ifdef CONFIG_PM_SLEEP -static int tps80031_rtc_suspend(struct device *dev) -{ - struct tps80031_rtc *rtc = dev_get_drvdata(dev); - - if (device_may_wakeup(dev)) - enable_irq_wake(rtc->irq); - return 0; -} - -static int tps80031_rtc_resume(struct device *dev) -{ - struct tps80031_rtc *rtc = dev_get_drvdata(dev); - - if (device_may_wakeup(dev)) - disable_irq_wake(rtc->irq); - return 0; -}; -#endif - -static SIMPLE_DEV_PM_OPS(tps80031_pm_ops, tps80031_rtc_suspend, - tps80031_rtc_resume); - -static struct platform_driver tps80031_rtc_driver = { - .driver = { - .name = "tps80031-rtc", - .pm = &tps80031_pm_ops, - }, - .probe = tps80031_rtc_probe, -}; - -module_platform_driver(tps80031_rtc_driver); - -MODULE_ALIAS("platform:tps80031-rtc"); -MODULE_DESCRIPTION("TI TPS80031/TPS80032 RTC driver"); -MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/s390/char/tape_std.c b/drivers/s390/char/tape_std.c index 1f5fab617b67..f7e75d9fedf6 100644 --- a/drivers/s390/char/tape_std.c +++ b/drivers/s390/char/tape_std.c @@ -53,7 +53,6 @@ int tape_std_assign(struct tape_device *device) { int rc; - struct timer_list timeout; struct tape_request *request; request = tape_alloc_request(2, 11); @@ -70,7 +69,7 @@ tape_std_assign(struct tape_device *device) * So we set up a timeout for this call. */ timer_setup(&request->timer, tape_std_assign_timeout, 0); - mod_timer(&timeout, jiffies + 2 * HZ); + mod_timer(&request->timer, jiffies + msecs_to_jiffies(2000)); rc = tape_do_io_interruptible(device, request); diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 2bc55ccf3f23..ce9e7517430f 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -437,8 +437,8 @@ static ssize_t dev_busid_show(struct device *dev, struct subchannel *sch = to_subchannel(dev); struct pmcw *pmcw = &sch->schib.pmcw; - if ((pmcw->st == SUBCHANNEL_TYPE_IO || - pmcw->st == SUBCHANNEL_TYPE_MSG) && pmcw->dnv) + if ((pmcw->st == SUBCHANNEL_TYPE_IO && pmcw->dnv) || + (pmcw->st == SUBCHANNEL_TYPE_MSG && pmcw->w)) return sysfs_emit(buf, "0.%x.%04x\n", sch->schid.ssid, pmcw->dev); else diff --git a/drivers/scsi/elx/libefc_sli/sli4.c b/drivers/scsi/elx/libefc_sli/sli4.c index 6c6c04e1b74d..907d67aeac23 100644 --- a/drivers/scsi/elx/libefc_sli/sli4.c +++ b/drivers/scsi/elx/libefc_sli/sli4.c @@ -4145,7 +4145,7 @@ static int sli_get_read_config(struct sli4 *sli4) { struct sli4_rsp_read_config *conf = sli4->bmbx.virt; - u32 i, total, total_size; + u32 i, total; u32 *base; if (sli_cmd_read_config(sli4, sli4->bmbx.virt)) { @@ -4203,8 +4203,7 @@ sli_get_read_config(struct sli4 *sli4) for (i = 0; i < SLI4_RSRC_MAX; i++) { total = sli4->ext[i].number * sli4->ext[i].size; - total_size = BITS_TO_LONGS(total) * sizeof(long); - sli4->ext[i].use_map = kzalloc(total_size, GFP_KERNEL); + sli4->ext[i].use_map = bitmap_zalloc(total, GFP_KERNEL); if (!sli4->ext[i].use_map) { efc_log_err(sli4, "bitmap memory allocation failed %d\n", i); @@ -4743,7 +4742,7 @@ sli_reset(struct sli4 *sli4) sli4->ext[0].base = NULL; for (i = 0; i < SLI4_RSRC_MAX; i++) { - kfree(sli4->ext[i].use_map); + bitmap_free(sli4->ext[i].use_map); sli4->ext[i].use_map = NULL; sli4->ext[i].base = NULL; } @@ -4784,7 +4783,7 @@ sli_teardown(struct sli4 *sli4) for (i = 0; i < SLI4_RSRC_MAX; i++) { sli4->ext[i].base = NULL; - kfree(sli4->ext[i].use_map); + bitmap_free(sli4->ext[i].use_map); sli4->ext[i].use_map = NULL; } diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index cda0135c43db..8049b00b6766 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -388,6 +388,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost->shost_state = SHOST_CREATED; INIT_LIST_HEAD(&shost->__devices); INIT_LIST_HEAD(&shost->__targets); + INIT_LIST_HEAD(&shost->eh_abort_list); INIT_LIST_HEAD(&shost->eh_cmd_q); INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 30f9545d2285..032efb294ee5 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2762,7 +2762,12 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) if (fcport->loop_id != FC_NO_LOOP_ID) fcport->logout_on_delete = 1; - qlt_schedule_sess_for_deletion(fcport); + if (!EDIF_NEGOTIATION_PENDING(fcport)) { + ql_dbg(ql_dbg_disc, fcport->vha, 0x911e, + "%s %d schedule session deletion\n", __func__, + __LINE__); + qlt_schedule_sess_for_deletion(fcport); + } } else { qla2x00_port_logout(fcport->vha, fcport); } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 8924eeb9367d..9ebf4a234d9a 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -639,9 +639,9 @@ struct qla_els_pt_arg { u8 els_opcode; u8 vp_idx; __le16 nport_handle; - u16 control_flags; + u16 control_flags, ox_id; __le32 rx_xchg_address; - port_id_t did; + port_id_t did, sid; u32 tx_len, tx_byte_count, rx_len, rx_byte_count; dma_addr_t tx_addr, rx_addr; diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index ad746c62f0d4..2e37b189cb75 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -218,7 +218,7 @@ fc_port_t *fcport) "%s edif not enabled\n", __func__); goto done; } - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { ql_dbg(ql_dbg_edif, vha, 0x09102, "%s doorbell not enabled\n", __func__); goto done; @@ -290,63 +290,6 @@ qla_edif_app_check(scsi_qla_host_t *vha, struct app_id appid) return false; } -static void qla_edif_reset_auth_wait(struct fc_port *fcport, int state, - int waitonly) -{ - int cnt, max_cnt = 200; - bool traced = false; - - fcport->keep_nport_handle = 1; - - if (!waitonly) { - qla2x00_set_fcport_disc_state(fcport, state); - qlt_schedule_sess_for_deletion(fcport); - } else { - qla2x00_set_fcport_disc_state(fcport, state); - } - - ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, - "%s: waiting for session, max_cnt=%u\n", - __func__, max_cnt); - - cnt = 0; - - if (waitonly) { - /* Marker wait min 10 msecs. */ - msleep(50); - cnt += 50; - } - while (1) { - if (!traced) { - ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, - "%s: session sleep.\n", - __func__); - traced = true; - } - msleep(20); - cnt++; - if (waitonly && (fcport->disc_state == state || - fcport->disc_state == DSC_LOGIN_COMPLETE)) - break; - if (fcport->disc_state == DSC_LOGIN_AUTH_PEND) - break; - if (cnt > max_cnt) - break; - } - - if (!waitonly) { - ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, - "%s: waited for session - %8phC, loopid=%x portid=%06x fcport=%p state=%u, cnt=%u\n", - __func__, fcport->port_name, fcport->loop_id, - fcport->d_id.b24, fcport, fcport->disc_state, cnt); - } else { - ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, - "%s: waited ONLY for session - %8phC, loopid=%x portid=%06x fcport=%p state=%u, cnt=%u\n", - __func__, fcport->port_name, fcport->loop_id, - fcport->d_id.b24, fcport, fcport->disc_state, cnt); - } -} - static void qla_edif_free_sa_ctl(fc_port_t *fcport, struct edif_sa_ctl *sa_ctl, int index) @@ -529,7 +472,8 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job) struct app_start_reply appreply; struct fc_port *fcport, *tf; - ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app start\n", __func__); + ql_log(ql_log_info, vha, 0x1313, + "EDIF application registration with driver, FC device connections will be re-established.\n"); sg_copy_to_buffer(bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt, &appstart, @@ -538,9 +482,9 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job) ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app_vid=%x app_start_flags %x\n", __func__, appstart.app_info.app_vid, appstart.app_start_flags); - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { /* mark doorbell as active since an app is now present */ - vha->e_dbell.db_flags = EDB_ACTIVE; + vha->e_dbell.db_flags |= EDB_ACTIVE; } else { ql_dbg(ql_dbg_edif, vha, 0x911e, "%s doorbell already active\n", __func__); @@ -554,37 +498,36 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job) qla2xxx_wake_dpc(vha); } else { list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { + ql_dbg(ql_dbg_edif, vha, 0x2058, + "FCSP - nn %8phN pn %8phN portid=%06x.\n", + fcport->node_name, fcport->port_name, + fcport->d_id.b24); ql_dbg(ql_dbg_edif, vha, 0xf084, - "%s: sess %p %8phC lid %#04x s_id %06x logout %d\n", - __func__, fcport, fcport->port_name, - fcport->loop_id, fcport->d_id.b24, - fcport->logout_on_delete); - - ql_dbg(ql_dbg_edif, vha, 0xf084, - "keep %d els_logo %d disc state %d auth state %d stop state %d\n", - fcport->keep_nport_handle, - fcport->send_els_logo, fcport->disc_state, - fcport->edif.auth_state, fcport->edif.app_stop); + "%s: se_sess %p / sess %p from port %8phC " + "loop_id %#04x s_id %06x logout %d " + "keep %d els_logo %d disc state %d auth state %d" + "stop state %d\n", + __func__, fcport->se_sess, fcport, + fcport->port_name, fcport->loop_id, + fcport->d_id.b24, fcport->logout_on_delete, + fcport->keep_nport_handle, fcport->send_els_logo, + fcport->disc_state, fcport->edif.auth_state, + fcport->edif.app_stop); if (atomic_read(&vha->loop_state) == LOOP_DOWN) break; - if (!(fcport->flags & FCF_FCSP_DEVICE)) - continue; fcport->edif.app_started = 1; - if (fcport->edif.app_stop || - (fcport->disc_state != DSC_LOGIN_COMPLETE && - fcport->disc_state != DSC_LOGIN_PEND && - fcport->disc_state != DSC_DELETED)) { - /* no activity */ - fcport->edif.app_stop = 0; - - ql_dbg(ql_dbg_edif, vha, 0x911e, - "%s wwpn %8phC calling qla_edif_reset_auth_wait\n", - __func__, fcport->port_name); - fcport->edif.app_sess_online = 1; - qla_edif_reset_auth_wait(fcport, DSC_LOGIN_PEND, 0); - } + fcport->login_retry = vha->hw->login_retry_count; + + /* no activity */ + fcport->edif.app_stop = 0; + + ql_dbg(ql_dbg_edif, vha, 0x911e, + "%s wwpn %8phC calling qla_edif_reset_auth_wait\n", + __func__, fcport->port_name); + fcport->edif.app_sess_online = 0; + qlt_schedule_sess_for_deletion(fcport); qla_edif_sa_ctl_init(vha, fcport); } } @@ -601,14 +544,14 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job) appreply.edif_enode_active = vha->pur_cinfo.enode_flags; appreply.edif_edb_active = vha->e_dbell.db_flags; - bsg_job->reply_len = sizeof(struct fc_bsg_reply) + - sizeof(struct app_start_reply); + bsg_job->reply_len = sizeof(struct fc_bsg_reply); SET_DID_STATUS(bsg_reply->result, DID_OK); - sg_copy_from_buffer(bsg_job->reply_payload.sg_list, - bsg_job->reply_payload.sg_cnt, &appreply, - sizeof(struct app_start_reply)); + bsg_reply->reply_payload_rcv_len = sg_copy_from_buffer(bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, + &appreply, + sizeof(struct app_start_reply)); ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app start completed with 0x%x\n", @@ -800,15 +743,15 @@ qla_edif_app_authok(scsi_qla_host_t *vha, struct bsg_job *bsg_job) ql_dbg(ql_dbg_edif, vha, 0x911e, "%s AUTH complete - RESUME with prli for wwpn %8phC\n", __func__, fcport->port_name); - qla_edif_reset_auth_wait(fcport, DSC_LOGIN_PEND, 1); qla24xx_post_prli_work(vha, fcport); } errstate_exit: bsg_job->reply_len = sizeof(struct fc_bsg_reply); - sg_copy_from_buffer(bsg_job->reply_payload.sg_list, - bsg_job->reply_payload.sg_cnt, &appplogireply, - sizeof(struct app_plogi_reply)); + bsg_reply->reply_payload_rcv_len = sg_copy_from_buffer(bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, + &appplogireply, + sizeof(struct app_plogi_reply)); return rval; } @@ -873,7 +816,7 @@ qla_edif_app_authfail(scsi_qla_host_t *vha, struct bsg_job *bsg_job) if (qla_ini_mode_enabled(fcport->vha)) { fcport->send_els_logo = 1; - qla_edif_reset_auth_wait(fcport, DSC_LOGIN_PEND, 0); + qlt_schedule_sess_for_deletion(fcport); } } @@ -891,7 +834,7 @@ static int qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job) { int32_t rval = 0; - int32_t num_cnt; + int32_t pcnt = 0; struct fc_bsg_reply *bsg_reply = bsg_job->reply; struct app_pinfo_req app_req; struct app_pinfo_reply *app_reply; @@ -903,16 +846,14 @@ qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job) bsg_job->request_payload.sg_cnt, &app_req, sizeof(struct app_pinfo_req)); - num_cnt = app_req.num_ports; /* num of ports alloc'd by app */ - app_reply = kzalloc((sizeof(struct app_pinfo_reply) + - sizeof(struct app_pinfo) * num_cnt), GFP_KERNEL); + sizeof(struct app_pinfo) * app_req.num_ports), GFP_KERNEL); + if (!app_reply) { SET_DID_STATUS(bsg_reply->result, DID_ERROR); rval = -1; } else { struct fc_port *fcport = NULL, *tf; - uint32_t pcnt = 0; list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { if (!(fcport->flags & FCF_FCSP_DEVICE)) @@ -981,9 +922,11 @@ qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job) SET_DID_STATUS(bsg_reply->result, DID_OK); } - sg_copy_from_buffer(bsg_job->reply_payload.sg_list, - bsg_job->reply_payload.sg_cnt, app_reply, - sizeof(struct app_pinfo_reply) + sizeof(struct app_pinfo) * num_cnt); + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + bsg_reply->reply_payload_rcv_len = sg_copy_from_buffer(bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, + app_reply, + sizeof(struct app_pinfo_reply) + sizeof(struct app_pinfo) * pcnt); kfree(app_reply); @@ -1000,10 +943,11 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job) { int32_t rval = 0; struct fc_bsg_reply *bsg_reply = bsg_job->reply; - uint32_t ret_size, size; + uint32_t size; struct app_sinfo_req app_req; struct app_stats_reply *app_reply; + uint32_t pcnt = 0; sg_copy_to_buffer(bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt, &app_req, @@ -1019,18 +963,12 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job) size = sizeof(struct app_stats_reply) + (sizeof(struct app_sinfo) * app_req.num_ports); - if (size > bsg_job->reply_payload.payload_len) - ret_size = bsg_job->reply_payload.payload_len; - else - ret_size = size; - app_reply = kzalloc(size, GFP_KERNEL); if (!app_reply) { SET_DID_STATUS(bsg_reply->result, DID_ERROR); rval = -1; } else { struct fc_port *fcport = NULL, *tf; - uint32_t pcnt = 0; list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { if (fcport->edif.enable) { @@ -1054,9 +992,11 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job) SET_DID_STATUS(bsg_reply->result, DID_OK); } + bsg_job->reply_len = sizeof(struct fc_bsg_reply); bsg_reply->reply_payload_rcv_len = sg_copy_from_buffer(bsg_job->reply_payload.sg_list, - bsg_job->reply_payload.sg_cnt, app_reply, ret_size); + bsg_job->reply_payload.sg_cnt, app_reply, + sizeof(struct app_stats_reply) + (sizeof(struct app_sinfo) * pcnt)); kfree(app_reply); @@ -1130,8 +1070,7 @@ qla_edif_app_mgmt(struct bsg_job *bsg_job) __func__, bsg_request->rqst_data.h_vendor.vendor_cmd[1]); rval = EXT_STATUS_INVALID_PARAM; - bsg_job->reply_len = sizeof(struct fc_bsg_reply); - SET_DID_STATUS(bsg_reply->result, DID_ERROR); + done = false; break; } @@ -1330,7 +1269,7 @@ qla24xx_sadb_update(struct bsg_job *bsg_job) goto done; } - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { ql_log(ql_log_warn, vha, 0x70a1, "App not started\n"); rval = -EIO; SET_DID_STATUS(bsg_reply->result, DID_ERROR); @@ -1651,6 +1590,40 @@ qla_enode_stop(scsi_qla_host_t *vha) spin_unlock_irqrestore(&vha->pur_cinfo.pur_lock, flags); } +static void qla_enode_clear(scsi_qla_host_t *vha, port_id_t portid) +{ + unsigned long flags; + struct enode *e, *tmp; + struct purexevent *purex; + LIST_HEAD(enode_list); + + if (vha->pur_cinfo.enode_flags != ENODE_ACTIVE) { + ql_dbg(ql_dbg_edif, vha, 0x09102, + "%s enode not active\n", __func__); + return; + } + spin_lock_irqsave(&vha->pur_cinfo.pur_lock, flags); + list_for_each_entry_safe(e, tmp, &vha->pur_cinfo.head, list) { + purex = &e->u.purexinfo; + if (purex->pur_info.pur_sid.b24 == portid.b24) { + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s free ELS sid=%06x. xchg %x, nb=%xh\n", + __func__, portid.b24, + purex->pur_info.pur_rx_xchg_address, + purex->pur_info.pur_bytes_rcvd); + + list_del_init(&e->list); + list_add_tail(&e->list, &enode_list); + } + } + spin_unlock_irqrestore(&vha->pur_cinfo.pur_lock, flags); + + list_for_each_entry_safe(e, tmp, &enode_list, list) { + list_del_init(&e->list); + qla_enode_free(vha, e); + } +} + /* * allocate enode struct and populate buffer * returns: enode pointer with buffers @@ -1695,41 +1668,25 @@ static struct enode * qla_enode_find(scsi_qla_host_t *vha, uint32_t ntype, uint32_t p1, uint32_t p2) { struct enode *node_rtn = NULL; - struct enode *list_node = NULL; + struct enode *list_node, *q; unsigned long flags; - struct list_head *pos, *q; uint32_t sid; - uint32_t rw_flag; struct purexevent *purex; /* secure the list from moving under us */ spin_lock_irqsave(&vha->pur_cinfo.pur_lock, flags); - list_for_each_safe(pos, q, &vha->pur_cinfo.head) { - list_node = list_entry(pos, struct enode, list); + list_for_each_entry_safe(list_node, q, &vha->pur_cinfo.head, list) { /* node type determines what p1 and p2 are */ purex = &list_node->u.purexinfo; sid = p1; - rw_flag = p2; if (purex->pur_info.pur_sid.b24 == sid) { - if (purex->pur_info.pur_pend == 1 && - rw_flag == PUR_GET) { - /* - * if the receive is in progress - * and its a read/get then can't - * transfer yet - */ - ql_dbg(ql_dbg_edif, vha, 0x9106, - "%s purex xfer in progress for sid=%x\n", - __func__, sid); - } else { - /* found it and its complete */ - node_rtn = list_node; - list_del(pos); - break; - } + /* found it and its complete */ + node_rtn = list_node; + list_del(&list_node->list); + break; } } @@ -1802,7 +1759,8 @@ qla_els_reject_iocb(scsi_qla_host_t *vha, struct qla_qpair *qp, qla_els_pt_iocb(vha, els_iocb, a); ql_dbg(ql_dbg_edif, vha, 0x0183, - "Sending ELS reject...\n"); + "Sending ELS reject ox_id %04x s:%06x -> d:%06x\n", + a->ox_id, a->sid.b24, a->did.b24); ql_dump_buffer(ql_dbg_edif + ql_dbg_verbose, vha, 0x0185, vha->hw->elsrej.c, sizeof(*vha->hw->elsrej.c)); /* flush iocb to mem before notifying hw doorbell */ @@ -1814,7 +1772,7 @@ qla_els_reject_iocb(scsi_qla_host_t *vha, struct qla_qpair *qp, void qla_edb_init(scsi_qla_host_t *vha) { - if (vha->e_dbell.db_flags == EDB_ACTIVE) { + if (DBELL_ACTIVE(vha)) { /* list already init'd - error */ ql_dbg(ql_dbg_edif, vha, 0x09102, "edif db already initialized, cannot reinit\n"); @@ -1850,6 +1808,57 @@ qla_edb_node_free(scsi_qla_host_t *vha, struct edb_node *node) node->ntype = N_UNDEF; } +static void qla_edb_clear(scsi_qla_host_t *vha, port_id_t portid) +{ + unsigned long flags; + struct edb_node *e, *tmp; + port_id_t sid; + LIST_HEAD(edb_list); + + if (DBELL_INACTIVE(vha)) { + /* doorbell list not enabled */ + ql_dbg(ql_dbg_edif, vha, 0x09102, + "%s doorbell not enabled\n", __func__); + return; + } + + /* grab lock so list doesn't move */ + spin_lock_irqsave(&vha->e_dbell.db_lock, flags); + list_for_each_entry_safe(e, tmp, &vha->e_dbell.head, list) { + switch (e->ntype) { + case VND_CMD_AUTH_STATE_NEEDED: + case VND_CMD_AUTH_STATE_SESSION_SHUTDOWN: + sid = e->u.plogi_did; + break; + case VND_CMD_AUTH_STATE_ELS_RCVD: + sid = e->u.els_sid; + break; + case VND_CMD_AUTH_STATE_SAUPDATE_COMPL: + /* app wants to see this */ + continue; + default: + ql_log(ql_log_warn, vha, 0x09102, + "%s unknown node type: %x\n", __func__, e->ntype); + sid.b24 = 0; + break; + } + if (sid.b24 == portid.b24) { + ql_dbg(ql_dbg_edif, vha, 0x910f, + "%s free doorbell event : node type = %x %p\n", + __func__, e->ntype, e); + list_del_init(&e->list); + list_add_tail(&e->list, &edb_list); + } + } + spin_unlock_irqrestore(&vha->e_dbell.db_lock, flags); + + list_for_each_entry_safe(e, tmp, &edb_list, list) { + qla_edb_node_free(vha, e); + list_del_init(&e->list); + kfree(e); + } +} + /* function called when app is stopping */ void @@ -1858,7 +1867,7 @@ qla_edb_stop(scsi_qla_host_t *vha) unsigned long flags; struct edb_node *node, *q; - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { /* doorbell list not enabled */ ql_dbg(ql_dbg_edif, vha, 0x09102, "%s doorbell not enabled\n", __func__); @@ -1909,7 +1918,7 @@ qla_edb_node_add(scsi_qla_host_t *vha, struct edb_node *ptr) { unsigned long flags; - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { /* doorbell list not enabled */ ql_dbg(ql_dbg_edif, vha, 0x09102, "%s doorbell not enabled\n", __func__); @@ -1940,7 +1949,7 @@ qla_edb_eventcreate(scsi_qla_host_t *vha, uint32_t dbtype, return; } - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { if (fcport) fcport->edif.auth_state = dbtype; /* doorbell list not enabled */ @@ -2035,7 +2044,7 @@ qla_edif_timer(scsi_qla_host_t *vha) struct qla_hw_data *ha = vha->hw; if (!vha->vp_idx && N2N_TOPO(ha) && ha->flags.n2n_fw_acc_sec) { - if (vha->e_dbell.db_flags != EDB_ACTIVE && + if (DBELL_INACTIVE(vha) && ha->edif_post_stop_cnt_down) { ha->edif_post_stop_cnt_down--; @@ -2073,7 +2082,7 @@ edif_doorbell_show(struct device *dev, struct device_attribute *attr, sz = 256; /* stop new threads from waiting if we're not init'd */ - if (vha->e_dbell.db_flags != EDB_ACTIVE) { + if (DBELL_INACTIVE(vha)) { ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x09122, "%s error - edif db not enabled\n", __func__); return 0; @@ -2346,6 +2355,7 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) a.tx_addr = vha->hw->elsrej.cdma; a.vp_idx = vha->vp_idx; a.control_flags = EPD_ELS_RJT; + a.ox_id = le16_to_cpu(p->ox_id); sid = p->s_id[0] | (p->s_id[1] << 8) | (p->s_id[2] << 16); @@ -2357,7 +2367,7 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) return; } - if (totlen > MAX_PAYLOAD) { + if (totlen > ELS_MAX_PAYLOAD) { ql_dbg(ql_dbg_edif, vha, 0x0910d, "%s WARNING: verbose ELS frame received (totlen=%x)\n", __func__, totlen); @@ -2387,7 +2397,6 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) purex = &ptr->u.purexinfo; purex->pur_info.pur_sid = a.did; - purex->pur_info.pur_pend = 0; purex->pur_info.pur_bytes_rcvd = totlen; purex->pur_info.pur_rx_xchg_address = le32_to_cpu(p->rx_xchg_addr); purex->pur_info.pur_nphdl = le16_to_cpu(p->nport_handle); @@ -2396,6 +2405,8 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) purex->pur_info.pur_did.b.al_pa = p->d_id[0]; purex->pur_info.vp_idx = p->vp_idx; + a.sid = purex->pur_info.pur_did; + rc = __qla_copy_purex_to_buffer(vha, pkt, rsp, purex->msgp, purex->msgp_len); if (rc) { @@ -2419,7 +2430,7 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) fcport = qla2x00_find_fcport_by_pid(host, &purex->pur_info.pur_sid); - if (host->e_dbell.db_flags != EDB_ACTIVE || + if (DBELL_INACTIVE(vha) || (fcport && EDIF_SESSION_DOWN(fcport))) { ql_dbg(ql_dbg_edif, host, 0x0910c, "%s e_dbell.db_flags =%x %06x\n", __func__, host->e_dbell.db_flags, @@ -2436,7 +2447,7 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) ql_dbg(ql_dbg_edif, host, 0x0910c, "%s COMPLETE purex->pur_info.pur_bytes_rcvd =%xh s:%06x -> d:%06x xchg=%xh\n", __func__, purex->pur_info.pur_bytes_rcvd, purex->pur_info.pur_sid.b24, - purex->pur_info.pur_did.b24, p->rx_xchg_addr); + purex->pur_info.pur_did.b24, purex->pur_info.pur_rx_xchg_address); qla_edb_eventcreate(host, VND_CMD_AUTH_STATE_ELS_RCVD, sid, 0, NULL); } @@ -3139,18 +3150,14 @@ static uint16_t qla_edif_sadb_get_sa_index(fc_port_t *fcport, /* release any sadb entries -- only done at teardown */ void qla_edif_sadb_release(struct qla_hw_data *ha) { - struct list_head *pos; - struct list_head *tmp; - struct edif_sa_index_entry *entry; + struct edif_sa_index_entry *entry, *tmp; - list_for_each_safe(pos, tmp, &ha->sadb_rx_index_list) { - entry = list_entry(pos, struct edif_sa_index_entry, next); + list_for_each_entry_safe(entry, tmp, &ha->sadb_rx_index_list, next) { list_del(&entry->next); kfree(entry); } - list_for_each_safe(pos, tmp, &ha->sadb_tx_index_list) { - entry = list_entry(pos, struct edif_sa_index_entry, next); + list_for_each_entry_safe(entry, tmp, &ha->sadb_tx_index_list, next) { list_del(&entry->next); kfree(entry); } @@ -3449,7 +3456,7 @@ done: void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess) { - if (sess->edif.app_sess_online && vha->e_dbell.db_flags & EDB_ACTIVE) { + if (sess->edif.app_sess_online && DBELL_ACTIVE(vha)) { ql_dbg(ql_dbg_disc, vha, 0xf09c, "%s: sess %8phN send port_offline event\n", __func__, sess->port_name); @@ -3459,3 +3466,12 @@ void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess) qla2x00_post_aen_work(vha, FCH_EVT_PORT_OFFLINE, sess->d_id.b24); } } + +void qla_edif_clear_appdata(struct scsi_qla_host *vha, struct fc_port *fcport) +{ + if (!(fcport->flags & FCF_FCSP_DEVICE)) + return; + + qla_edb_clear(vha, fcport->d_id); + qla_enode_clear(vha, fcport->d_id); +} diff --git a/drivers/scsi/qla2xxx/qla_edif.h b/drivers/scsi/qla2xxx/qla_edif.h index 9e8f28d0caa1..a965ca8e47ce 100644 --- a/drivers/scsi/qla2xxx/qla_edif.h +++ b/drivers/scsi/qla2xxx/qla_edif.h @@ -41,9 +41,12 @@ struct pur_core { }; enum db_flags_t { - EDB_ACTIVE = 0x1, + EDB_ACTIVE = BIT_0, }; +#define DBELL_ACTIVE(_v) (_v->e_dbell.db_flags & EDB_ACTIVE) +#define DBELL_INACTIVE(_v) (!(_v->e_dbell.db_flags & EDB_ACTIVE)) + struct edif_dbell { enum db_flags_t db_flags; spinlock_t db_lock; @@ -93,7 +96,6 @@ struct sa_update_28xx { }; #define NUM_ENTRIES 256 -#define MAX_PAYLOAD 1024 #define PUR_GET 1 struct dinfo { @@ -102,7 +104,6 @@ struct dinfo { }; struct pur_ninfo { - unsigned int pur_pend:1; port_id_t pur_sid; port_id_t pur_did; uint8_t vp_idx; @@ -128,9 +129,15 @@ struct enode { } u; }; +#define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES)) + #define EDIF_SESSION_DOWN(_s) \ (qla_ini_mode_enabled(_s->vha) && (_s->disc_state == DSC_DELETE_PEND || \ _s->disc_state == DSC_DELETED || \ !_s->edif.app_sess_online)) +#define EDIF_NEGOTIATION_PENDING(_fcport) \ + (DBELL_ACTIVE(_fcport->vha) && \ + (_fcport->disc_state == DSC_LOGIN_AUTH_PEND)) + #endif /* __QLA_EDIF_H */ diff --git a/drivers/scsi/qla2xxx/qla_edif_bsg.h b/drivers/scsi/qla2xxx/qla_edif_bsg.h index 58b718d35d19..53026d82ebff 100644 --- a/drivers/scsi/qla2xxx/qla_edif_bsg.h +++ b/drivers/scsi/qla2xxx/qla_edif_bsg.h @@ -8,7 +8,7 @@ #define __QLA_EDIF_BSG_H /* BSG Vendor specific commands */ -#define ELS_MAX_PAYLOAD 1024 +#define ELS_MAX_PAYLOAD 2112 #ifndef WWN_SIZE #define WWN_SIZE 8 #endif diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 3c4fa8bac88d..8d8503a28479 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -142,6 +142,8 @@ void qlt_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, fc_port_t *fcport, void qla2x00_release_all_sadb(struct scsi_qla_host *vha, struct fc_port *fcport); int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsgjob); void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess); +void qla_edif_clear_appdata(struct scsi_qla_host *vha, + struct fc_port *fcport); const char *sc_to_str(uint16_t cmd); /* @@ -171,7 +173,6 @@ extern int ql2xasynctmfenable; extern int ql2xgffidenable; extern int ql2xenabledif; extern int ql2xenablehba_err_chk; -extern int ql2xtargetreset; extern int ql2xdontresethba; extern uint64_t ql2xmaxlun; extern int ql2xmdcapmask; @@ -818,7 +819,6 @@ extern void qlafx00_abort_iocb(srb_t *, struct abort_iocb_entry_fx00 *); extern void qlafx00_fxdisc_iocb(srb_t *, struct fxdisc_entry_fx00 *); extern void qlafx00_timer_routine(scsi_qla_host_t *); extern int qlafx00_rescan_isp(scsi_qla_host_t *); -extern int qlafx00_loop_reset(scsi_qla_host_t *vha); /* qla82xx related functions */ diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 908a72ebf7c2..070b636802d0 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -330,12 +330,9 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport, lio->u.logio.flags |= SRB_LOGIN_PRLI_ONLY; } else { if (vha->hw->flags.edif_enabled && - vha->e_dbell.db_flags & EDB_ACTIVE) { + DBELL_ACTIVE(vha)) { lio->u.logio.flags |= (SRB_LOGIN_FCSP | SRB_LOGIN_SKIP_PRLI); - ql_dbg(ql_dbg_disc, vha, 0x2072, - "Async-login: w/ FCSP %8phC hdl=%x, loopid=%x portid=%06x\n", - fcport->port_name, sp->handle, fcport->loop_id, fcport->d_id.b24); } else { lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI; } @@ -344,12 +341,14 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport, if (NVME_TARGET(vha->hw, fcport)) lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI; + rval = qla2x00_start_sp(sp); + ql_dbg(ql_dbg_disc, vha, 0x2072, - "Async-login - %8phC hdl=%x, loopid=%x portid=%06x retries=%d.\n", + "Async-login - %8phC hdl=%x, loopid=%x portid=%06x retries=%d %s.\n", fcport->port_name, sp->handle, fcport->loop_id, - fcport->d_id.b24, fcport->login_retry); + fcport->d_id.b24, fcport->login_retry, + lio->u.logio.flags & SRB_LOGIN_FCSP ? "FCSP" : ""); - rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { fcport->flags |= FCF_LOGIN_NEEDED; set_bit(RELOGIN_NEEDED, &vha->dpc_flags); @@ -862,7 +861,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, break; case DSC_LS_PLOGI_COMP: if (vha->hw->flags.edif_enabled && - vha->e_dbell.db_flags & EDB_ACTIVE) { + DBELL_ACTIVE(vha)) { /* check to see if App support secure or not */ qla24xx_post_gpdb_work(vha, fcport, 0); break; @@ -987,8 +986,6 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res) sp->name, res, sp->u.iocb_cmd.u.mbx.in_mb[1], sp->u.iocb_cmd.u.mbx.in_mb[2]); - if (res == QLA_FUNCTION_TIMEOUT) - return; sp->fcport->flags &= ~(FCF_ASYNC_SENT|FCF_ASYNC_ACTIVE); memset(&ea, 0, sizeof(ea)); @@ -1026,8 +1023,8 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res) spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); list_for_each_entry_safe(fcport, tf, &h, gnl_entry) { - list_del_init(&fcport->gnl_entry); spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + list_del_init(&fcport->gnl_entry); fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); ea.fcport = fcport; @@ -1454,7 +1451,7 @@ static int qla_chk_secure_login(scsi_qla_host_t *vha, fc_port_t *fcport, qla2x00_post_aen_work(vha, FCH_EVT_PORT_ONLINE, fcport->d_id.b24); - if (vha->e_dbell.db_flags == EDB_ACTIVE) { + if (DBELL_ACTIVE(vha)) { ql_dbg(ql_dbg_disc, vha, 0x20ef, "%s %d %8phC EDIF: post DB_AUTH: AUTH needed\n", __func__, __LINE__, fcport->port_name); @@ -1786,16 +1783,72 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea) fc_port_t *fcport; unsigned long flags; - fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1); - if (fcport) { - if (fcport->flags & FCF_FCP2_DEVICE) { - ql_dbg(ql_dbg_disc, vha, 0x2115, - "Delaying session delete for FCP2 portid=%06x %8phC ", - fcport->d_id.b24, fcport->port_name); - return; + switch (ea->id.b.rsvd_1) { + case RSCN_PORT_ADDR: + fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1); + if (fcport) { + if (fcport->flags & FCF_FCP2_DEVICE) { + ql_dbg(ql_dbg_disc, vha, 0x2115, + "Delaying session delete for FCP2 portid=%06x %8phC ", + fcport->d_id.b24, fcport->port_name); + return; + } + + if (vha->hw->flags.edif_enabled && DBELL_ACTIVE(vha)) { + /* + * On ipsec start by remote port, Target port + * may use RSCN to trigger initiator to + * relogin. If driver is already in the + * process of a relogin, then ignore the RSCN + * and allow the current relogin to continue. + * This reduces thrashing of the connection. + */ + if (atomic_read(&fcport->state) == FCS_ONLINE) { + /* + * If state = online, then set scan_needed=1 to do relogin. + * Otherwise we're already in the middle of a relogin + */ + fcport->scan_needed = 1; + fcport->rscn_gen++; + } + } else { + fcport->scan_needed = 1; + fcport->rscn_gen++; + } + } + break; + case RSCN_AREA_ADDR: + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->flags & FCF_FCP2_DEVICE) + continue; + + if ((ea->id.b24 & 0xffff00) == (fcport->d_id.b24 & 0xffff00)) { + fcport->scan_needed = 1; + fcport->rscn_gen++; + } + } + break; + case RSCN_DOM_ADDR: + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->flags & FCF_FCP2_DEVICE) + continue; + + if ((ea->id.b24 & 0xff0000) == (fcport->d_id.b24 & 0xff0000)) { + fcport->scan_needed = 1; + fcport->rscn_gen++; + } + } + break; + case RSCN_FAB_ADDR: + default: + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->flags & FCF_FCP2_DEVICE) + continue; + + fcport->scan_needed = 1; + fcport->rscn_gen++; } - fcport->scan_needed = 1; - fcport->rscn_gen++; + break; } spin_lock_irqsave(&vha->work_lock, flags); @@ -4187,7 +4240,7 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha) * fw shal not send PRLI after PLOGI Acc */ if (ha->flags.edif_enabled && - vha->e_dbell.db_flags & EDB_ACTIVE) { + DBELL_ACTIVE(vha)) { ha->fw_options[3] |= BIT_15; ha->flags.n2n_fw_acc_sec = 1; } else { @@ -4433,6 +4486,10 @@ qla2x00_init_rings(scsi_qla_host_t *vha) (ha->flags.fawwpn_enabled) ? "enabled" : "disabled"); } + /* ELS pass through payload is limit by frame size. */ + if (ha->flags.edif_enabled) + mid_init_cb->init_cb.frame_payload_size = cpu_to_le16(ELS_MAX_PAYLOAD); + rval = qla2x00_init_firmware(vha, ha->init_cb_size); next_check: if (rval) { @@ -5339,8 +5396,7 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) * use link up to wake up app to get ready for * authentication. */ - if (ha->flags.edif_enabled && - !(vha->e_dbell.db_flags & EDB_ACTIVE)) + if (ha->flags.edif_enabled && DBELL_INACTIVE(vha)) qla2x00_post_aen_work(vha, FCH_EVT_LINKUP, ha->link_data_rate); @@ -5833,6 +5889,10 @@ void qla_register_fcport_fn(struct work_struct *work) qla2x00_update_fcport(fcport->vha, fcport); + ql_dbg(ql_dbg_disc, fcport->vha, 0x911e, + "%s rscn gen %d/%d next DS %d\n", __func__, + rscn_gen, fcport->rscn_gen, fcport->next_disc_state); + if (rscn_gen != fcport->rscn_gen) { /* RSCN(s) came in while registration */ switch (fcport->next_disc_state) { diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 9d4ad1d2b00a..ed604f2185bf 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3034,8 +3034,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, elsio->u.els_plogi.els_cmd = els_opcode; elsio->u.els_plogi.els_plogi_pyld->opcode = els_opcode; - if (els_opcode == ELS_DCMD_PLOGI && vha->hw->flags.edif_enabled && - vha->e_dbell.db_flags & EDB_ACTIVE) { + if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) { struct fc_els_flogi *p = ptr; p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index b26f2699adb2..aaf6504570fd 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2233,6 +2233,10 @@ qla24xx_els_ct_entry(scsi_qla_host_t *v, struct req_que *req, } } else if (comp_status == CS_PORT_LOGGED_OUT) { + ql_dbg(ql_dbg_disc, vha, 0x911e, + "%s %d schedule session deletion\n", + __func__, __LINE__); + els->u.els_plogi.len = 0; res = DID_IMM_RETRY << 16; qlt_schedule_sess_for_deletion(sp->fcport); diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c index 6e920da64863..350b0c4346fb 100644 --- a/drivers/scsi/qla2xxx/qla_mr.c +++ b/drivers/scsi/qla2xxx/qla_mr.c @@ -739,29 +739,6 @@ qlafx00_lun_reset(fc_port_t *fcport, uint64_t l, int tag) } int -qlafx00_loop_reset(scsi_qla_host_t *vha) -{ - int ret; - struct fc_port *fcport; - struct qla_hw_data *ha = vha->hw; - - if (ql2xtargetreset) { - list_for_each_entry(fcport, &vha->vp_fcports, list) { - if (fcport->port_type != FCT_TARGET) - continue; - - ret = ha->isp_ops->target_reset(fcport, 0, 0); - if (ret != QLA_SUCCESS) { - ql_dbg(ql_dbg_taskm, vha, 0x803d, - "Bus Reset failed: Reset=%d " - "d_id=%x.\n", ret, fcport->d_id.b24); - } - } - } - return QLA_SUCCESS; -} - -int qlafx00_iospace_config(struct qla_hw_data *ha) { if (pci_request_selected_regions(ha->pdev, ha->bars, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index c3ff50ffe205..abcd30917263 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -202,12 +202,6 @@ MODULE_PARM_DESC(ql2xdbwr, " 0 -- Regular doorbell.\n" " 1 -- CAMRAM doorbell (faster).\n"); -int ql2xtargetreset = 1; -module_param(ql2xtargetreset, int, S_IRUGO); -MODULE_PARM_DESC(ql2xtargetreset, - "Enable target reset." - "Default is 1 - use hw defaults."); - int ql2xgffidenable; module_param(ql2xgffidenable, int, S_IRUGO); MODULE_PARM_DESC(ql2xgffidenable, @@ -1695,27 +1689,10 @@ int qla2x00_loop_reset(scsi_qla_host_t *vha) { int ret; - struct fc_port *fcport; struct qla_hw_data *ha = vha->hw; - if (IS_QLAFX00(ha)) { - return qlafx00_loop_reset(vha); - } - - if (ql2xtargetreset == 1 && ha->flags.enable_target_reset) { - list_for_each_entry(fcport, &vha->vp_fcports, list) { - if (fcport->port_type != FCT_TARGET) - continue; - - ret = ha->isp_ops->target_reset(fcport, 0, 0); - if (ret != QLA_SUCCESS) { - ql_dbg(ql_dbg_taskm, vha, 0x802c, - "Bus Reset failed: Reset=%d " - "d_id=%x.\n", ret, fcport->d_id.b24); - } - } - } - + if (IS_QLAFX00(ha)) + return QLA_SUCCESS; if (ha->flags.enable_lip_full_login && !IS_CNA_CAPABLE(ha)) { atomic_set(&vha->loop_state, LOOP_DOWN); @@ -3908,13 +3885,13 @@ qla2x00_remove_one(struct pci_dev *pdev) static inline void qla24xx_free_purex_list(struct purex_list *list) { - struct list_head *item, *next; + struct purex_item *item, *next; ulong flags; spin_lock_irqsave(&list->lock, flags); - list_for_each_safe(item, next, &list->head) { - list_del(item); - kfree(list_entry(item, struct purex_item, list)); + list_for_each_entry_safe(item, next, &list->head, list) { + list_del(&item->list); + kfree(item); } spin_unlock_irqrestore(&list->lock, flags); } @@ -4375,7 +4352,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, /* allocate the purex dma pool */ ha->purex_dma_pool = dma_pool_create(name, &ha->pdev->dev, - MAX_PAYLOAD, 8, 0); + ELS_MAX_PAYLOAD, 8, 0); if (!ha->purex_dma_pool) { ql_dbg_pci(ql_dbg_init, ha->pdev, 0x011b, diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 7d8242c120fc..8993d438e0b7 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1003,6 +1003,7 @@ void qlt_free_session_done(struct work_struct *work) "%s bypassing release_all_sadb\n", __func__); } + qla_edif_clear_appdata(vha, sess); qla_edif_sess_down(vha, sess); } qla2x00_mark_device_lost(vha, sess, 0); @@ -4812,7 +4813,7 @@ static int qlt_handle_login(struct scsi_qla_host *vha, } if (vha->hw->flags.edif_enabled) { - if (!(vha->e_dbell.db_flags & EDB_ACTIVE)) { + if (DBELL_INACTIVE(vha)) { ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d Term INOT due to app not started lid=%d, NportID %06X ", __func__, __LINE__, loop_id, port_id.b24); diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h index 4b117165bf8b..27e440f8a702 100644 --- a/drivers/scsi/qla2xxx/qla_version.h +++ b/drivers/scsi/qla2xxx/qla_version.h @@ -6,9 +6,9 @@ /* * Driver version */ -#define QLA2XXX_VERSION "10.02.07.100-k" +#define QLA2XXX_VERSION "10.02.07.200-k" #define QLA_DRIVER_MAJOR_VER 10 #define QLA_DRIVER_MINOR_VER 2 #define QLA_DRIVER_PATCH_VER 7 -#define QLA_DRIVER_BETA_VER 100 +#define QLA_DRIVER_BETA_VER 200 diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 06e7266018c7..1d0278da9041 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4259,6 +4259,8 @@ static int resp_verify(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) mk_sense_invalid_opcode(scp); return check_condition_result; } + if (vnum == 0) + return 0; /* not an error */ a_num = is_bytchk3 ? 1 : vnum; /* Treat following check like one for read (i.e. no write) access */ ret = check_device_access_params(scp, lba, a_num, false); @@ -4322,6 +4324,8 @@ static int resp_report_zones(struct scsi_cmnd *scp, } zs_lba = get_unaligned_be64(cmd + 2); alloc_len = get_unaligned_be32(cmd + 10); + if (alloc_len == 0) + return 0; /* not an error */ rep_opts = cmd[14] & 0x3f; partial = cmd[14] & 0x80; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index a531336f6a0a..2371edbc3af4 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -133,6 +133,23 @@ static bool scsi_eh_should_retry_cmd(struct scsi_cmnd *cmd) return true; } +static void scsi_eh_complete_abort(struct scsi_cmnd *scmd, struct Scsi_Host *shost) +{ + unsigned long flags; + + spin_lock_irqsave(shost->host_lock, flags); + list_del_init(&scmd->eh_entry); + /* + * If the abort succeeds, and there is no further + * EH action, clear the ->last_reset time. + */ + if (list_empty(&shost->eh_abort_list) && + list_empty(&shost->eh_cmd_q)) + if (shost->eh_deadline != -1) + shost->last_reset = 0; + spin_unlock_irqrestore(shost->host_lock, flags); +} + /** * scmd_eh_abort_handler - Handle command aborts * @work: command to be aborted. @@ -150,6 +167,7 @@ scmd_eh_abort_handler(struct work_struct *work) container_of(work, struct scsi_cmnd, abort_work.work); struct scsi_device *sdev = scmd->device; enum scsi_disposition rtn; + unsigned long flags; if (scsi_host_eh_past_deadline(sdev->host)) { SCSI_LOG_ERROR_RECOVERY(3, @@ -173,12 +191,14 @@ scmd_eh_abort_handler(struct work_struct *work) SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "retry aborted command\n")); + scsi_eh_complete_abort(scmd, sdev->host); scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY); return; } else { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "finish aborted command\n")); + scsi_eh_complete_abort(scmd, sdev->host); scsi_finish_command(scmd); return; } @@ -191,6 +211,9 @@ scmd_eh_abort_handler(struct work_struct *work) } } + spin_lock_irqsave(sdev->host->host_lock, flags); + list_del_init(&scmd->eh_entry); + spin_unlock_irqrestore(sdev->host->host_lock, flags); scsi_eh_scmd_add(scmd); } @@ -221,6 +244,8 @@ scsi_abort_command(struct scsi_cmnd *scmd) spin_lock_irqsave(shost->host_lock, flags); if (shost->eh_deadline != -1 && !shost->last_reset) shost->last_reset = jiffies; + BUG_ON(!list_empty(&scmd->eh_entry)); + list_add_tail(&scmd->eh_entry, &shost->eh_abort_list); spin_unlock_irqrestore(shost->host_lock, flags); scmd->eh_eflags |= SCSI_EH_ABORT_SCHEDULED; diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 34412eac4566..400df3354cd6 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -347,6 +347,8 @@ static int scsi_fill_sghdr_rq(struct scsi_device *sdev, struct request *rq, { struct scsi_request *req = scsi_req(rq); + if (hdr->cmd_len < 6) + return -EMSGSIZE; if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; if (!scsi_cmd_allowed(req->cmd, mode)) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b731c2983515..621d841d819a 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1153,6 +1153,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) cmd->sense_buffer = buf; cmd->prot_sdb = prot; cmd->flags = flags; + INIT_LIST_HEAD(&cmd->eh_entry); INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler); cmd->jiffies_at_alloc = jiffies_at_alloc; cmd->retries = retries; @@ -1184,8 +1185,6 @@ static blk_status_t scsi_setup_scsi_cmnd(struct scsi_device *sdev, } cmd->cmd_len = scsi_req(req)->cmd_len; - if (cmd->cmd_len == 0) - cmd->cmd_len = scsi_command_size(cmd->cmnd); cmd->cmnd = scsi_req(req)->cmd; cmd->transfersize = blk_rq_bytes(req); cmd->allowed = scsi_req(req)->retries; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index d3d362289ecc..55addd78fde4 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1383,6 +1383,7 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) * We're treating error on bsg register as non-fatal, so * pretend nothing went wrong. */ + error = PTR_ERR(sdev->bsg_dev); sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", error); @@ -1580,7 +1581,6 @@ static struct device_type scsi_dev_type = { void scsi_sysfs_device_initialize(struct scsi_device *sdev) { - int i, j = 0; unsigned long flags; struct Scsi_Host *shost = sdev->host; struct scsi_host_template *hostt = shost->hostt; @@ -1592,15 +1592,7 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev) scsi_enable_async_suspend(&sdev->sdev_gendev); dev_set_name(&sdev->sdev_gendev, "%d:%d:%d:%llu", sdev->host->host_no, sdev->channel, sdev->id, sdev->lun); - sdev->gendev_attr_groups[j++] = &scsi_sdev_attr_group; - if (hostt->sdev_groups) { - for (i = 0; hostt->sdev_groups[i] && - j < ARRAY_SIZE(sdev->gendev_attr_groups); - i++, j++) { - sdev->gendev_attr_groups[j] = hostt->sdev_groups[i]; - } - } - WARN_ON_ONCE(j >= ARRAY_SIZE(sdev->gendev_attr_groups)); + sdev->sdev_gendev.groups = hostt->sdev_groups; device_initialize(&sdev->sdev_dev); sdev->sdev_dev.parent = get_device(&sdev->sdev_gendev); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 50f8dc960ae2..8e4af111c078 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -693,7 +693,6 @@ static int sr_probe(struct device *dev) cd->device = sdev; cd->disk = disk; cd->driver = &sr_template; - cd->disk = disk; cd->capacity = 0x1fffff; cd->device->changed = 1; /* force recheck CD type */ cd->media_present = 1; diff --git a/drivers/scsi/ufs/ufs-debugfs.c b/drivers/scsi/ufs/ufs-debugfs.c index 4e1ff209b933..4a0bbcf1757a 100644 --- a/drivers/scsi/ufs/ufs-debugfs.c +++ b/drivers/scsi/ufs/ufs-debugfs.c @@ -8,6 +8,18 @@ static struct dentry *ufs_debugfs_root; +struct ufs_debugfs_attr { + const char *name; + mode_t mode; + const struct file_operations *fops; +}; + +/* @file corresponds to a debugfs attribute in directory hba->debugfs_root. */ +static inline struct ufs_hba *hba_from_file(const struct file *file) +{ + return d_inode(file->f_path.dentry->d_parent)->i_private; +} + void __init ufs_debugfs_init(void) { ufs_debugfs_root = debugfs_create_dir("ufshcd", NULL); @@ -20,7 +32,7 @@ void ufs_debugfs_exit(void) static int ufs_debugfs_stats_show(struct seq_file *s, void *data) { - struct ufs_hba *hba = s->private; + struct ufs_hba *hba = hba_from_file(s->file); struct ufs_event_hist *e = hba->ufs_stats.event; #define PRT(fmt, typ) \ @@ -126,13 +138,93 @@ static void ufs_debugfs_restart_ee(struct work_struct *work) ufs_debugfs_put_user_access(hba); } +static int ufs_saved_err_show(struct seq_file *s, void *data) +{ + struct ufs_debugfs_attr *attr = s->private; + struct ufs_hba *hba = hba_from_file(s->file); + const int *p; + + if (strcmp(attr->name, "saved_err") == 0) { + p = &hba->saved_err; + } else if (strcmp(attr->name, "saved_uic_err") == 0) { + p = &hba->saved_uic_err; + } else { + return -ENOENT; + } + + seq_printf(s, "%d\n", *p); + return 0; +} + +static ssize_t ufs_saved_err_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct ufs_debugfs_attr *attr = file->f_inode->i_private; + struct ufs_hba *hba = hba_from_file(file); + char val_str[16] = { }; + int val, ret; + + if (count > sizeof(val_str)) + return -EINVAL; + if (copy_from_user(val_str, buf, count)) + return -EFAULT; + ret = kstrtoint(val_str, 0, &val); + if (ret < 0) + return ret; + + spin_lock_irq(hba->host->host_lock); + if (strcmp(attr->name, "saved_err") == 0) { + hba->saved_err = val; + } else if (strcmp(attr->name, "saved_uic_err") == 0) { + hba->saved_uic_err = val; + } else { + ret = -ENOENT; + } + if (ret == 0) + ufshcd_schedule_eh_work(hba); + spin_unlock_irq(hba->host->host_lock); + + return ret < 0 ? ret : count; +} + +static int ufs_saved_err_open(struct inode *inode, struct file *file) +{ + return single_open(file, ufs_saved_err_show, inode->i_private); +} + +static const struct file_operations ufs_saved_err_fops = { + .owner = THIS_MODULE, + .open = ufs_saved_err_open, + .read = seq_read, + .write = ufs_saved_err_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct ufs_debugfs_attr ufs_attrs[] = { + { "stats", 0400, &ufs_debugfs_stats_fops }, + { "saved_err", 0600, &ufs_saved_err_fops }, + { "saved_uic_err", 0600, &ufs_saved_err_fops }, + { } +}; + void ufs_debugfs_hba_init(struct ufs_hba *hba) { + const struct ufs_debugfs_attr *attr; + struct dentry *root; + /* Set default exception event rate limit period to 20ms */ hba->debugfs_ee_rate_limit_ms = 20; INIT_DELAYED_WORK(&hba->debugfs_ee_work, ufs_debugfs_restart_ee); - hba->debugfs_root = debugfs_create_dir(dev_name(hba->dev), ufs_debugfs_root); - debugfs_create_file("stats", 0400, hba->debugfs_root, hba, &ufs_debugfs_stats_fops); + + root = debugfs_create_dir(dev_name(hba->dev), ufs_debugfs_root); + if (IS_ERR_OR_NULL(root)) + return; + hba->debugfs_root = root; + d_inode(root)->i_private = hba; + for (attr = ufs_attrs; attr->name; attr++) + debugfs_create_file(attr->name, attr->mode, root, (void *)attr, + attr->fops); debugfs_create_file("exception_event_mask", 0600, hba->debugfs_root, hba, &ee_usr_mask_fops); debugfs_create_u32("exception_event_rate_limit_ms", 0600, hba->debugfs_root, diff --git a/drivers/scsi/ufs/ufs-exynos.c b/drivers/scsi/ufs/ufs-exynos.c index 30d0c1aba0c7..cd26bc82462e 100644 --- a/drivers/scsi/ufs/ufs-exynos.c +++ b/drivers/scsi/ufs/ufs-exynos.c @@ -12,8 +12,10 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/mfd/syscon.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/regmap.h> #include "ufshcd.h" #include "ufshcd-pltfrm.h" @@ -48,10 +50,11 @@ #define HCI_ERR_EN_T_LAYER 0x84 #define HCI_ERR_EN_DME_LAYER 0x88 #define HCI_CLKSTOP_CTRL 0xB0 +#define REFCLKOUT_STOP BIT(4) #define REFCLK_STOP BIT(2) #define UNIPRO_MCLK_STOP BIT(1) #define UNIPRO_PCLK_STOP BIT(0) -#define CLK_STOP_MASK (REFCLK_STOP |\ +#define CLK_STOP_MASK (REFCLKOUT_STOP | REFCLK_STOP |\ UNIPRO_MCLK_STOP |\ UNIPRO_PCLK_STOP) #define HCI_MISC 0xB4 @@ -74,6 +77,52 @@ UIC_TRANSPORT_NO_CONNECTION_RX |\ UIC_TRANSPORT_BAD_TC) +/* FSYS UFS Shareability */ +#define UFS_WR_SHARABLE BIT(2) +#define UFS_RD_SHARABLE BIT(1) +#define UFS_SHARABLE (UFS_WR_SHARABLE | UFS_RD_SHARABLE) +#define UFS_SHAREABILITY_OFFSET 0x710 + +/* Multi-host registers */ +#define MHCTRL 0xC4 +#define MHCTRL_EN_VH_MASK (0xE) +#define MHCTRL_EN_VH(vh) (vh << 1) +#define PH2VH_MBOX 0xD8 + +#define MH_MSG_MASK (0xFF) + +#define MH_MSG(id, msg) ((id << 8) | (msg & 0xFF)) +#define MH_MSG_PH_READY 0x1 +#define MH_MSG_VH_READY 0x2 + +#define ALLOW_INQUIRY BIT(25) +#define ALLOW_MODE_SELECT BIT(24) +#define ALLOW_MODE_SENSE BIT(23) +#define ALLOW_PRE_FETCH GENMASK(22, 21) +#define ALLOW_READ_CMD_ALL GENMASK(20, 18) /* read_6/10/16 */ +#define ALLOW_READ_BUFFER BIT(17) +#define ALLOW_READ_CAPACITY GENMASK(16, 15) +#define ALLOW_REPORT_LUNS BIT(14) +#define ALLOW_REQUEST_SENSE BIT(13) +#define ALLOW_SYNCHRONIZE_CACHE GENMASK(8, 7) +#define ALLOW_TEST_UNIT_READY BIT(6) +#define ALLOW_UNMAP BIT(5) +#define ALLOW_VERIFY BIT(4) +#define ALLOW_WRITE_CMD_ALL GENMASK(3, 1) /* write_6/10/16 */ + +#define ALLOW_TRANS_VH_DEFAULT (ALLOW_INQUIRY | ALLOW_MODE_SELECT | \ + ALLOW_MODE_SENSE | ALLOW_PRE_FETCH | \ + ALLOW_READ_CMD_ALL | ALLOW_READ_BUFFER | \ + ALLOW_READ_CAPACITY | ALLOW_REPORT_LUNS | \ + ALLOW_REQUEST_SENSE | ALLOW_SYNCHRONIZE_CACHE | \ + ALLOW_TEST_UNIT_READY | ALLOW_UNMAP | \ + ALLOW_VERIFY | ALLOW_WRITE_CMD_ALL) + +#define HCI_MH_ALLOWABLE_TRAN_OF_VH 0x30C +#define HCI_MH_IID_IN_TASK_TAG 0X308 + +#define PH_READY_TIMEOUT_MS (5 * MSEC_PER_SEC) + enum { UNIPRO_L1_5 = 0,/* PHY Adapter */ UNIPRO_L2, /* Data Link */ @@ -149,6 +198,117 @@ static int exynos7_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs) return 0; } +static int exynosauto_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs) +{ + struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr; + + /* IO Coherency setting */ + if (ufs->sysreg) { + return regmap_update_bits(ufs->sysreg, + ufs->shareability_reg_offset, + UFS_SHARABLE, UFS_SHARABLE); + } + + attr->tx_dif_p_nsec = 3200000; + + return 0; +} + +static int exynosauto_ufs_post_hce_enable(struct exynos_ufs *ufs) +{ + struct ufs_hba *hba = ufs->hba; + + /* Enable Virtual Host #1 */ + ufshcd_rmwl(hba, MHCTRL_EN_VH_MASK, MHCTRL_EN_VH(1), MHCTRL); + /* Default VH Transfer permissions */ + hci_writel(ufs, ALLOW_TRANS_VH_DEFAULT, HCI_MH_ALLOWABLE_TRAN_OF_VH); + /* IID information is replaced in TASKTAG[7:5] instead of IID in UCD */ + hci_writel(ufs, 0x1, HCI_MH_IID_IN_TASK_TAG); + + return 0; +} + +static int exynosauto_ufs_pre_link(struct exynos_ufs *ufs) +{ + struct ufs_hba *hba = ufs->hba; + int i; + u32 tx_line_reset_period, rx_line_reset_period; + + rx_line_reset_period = (RX_LINE_RESET_TIME * ufs->mclk_rate) / NSEC_PER_MSEC; + tx_line_reset_period = (TX_LINE_RESET_TIME * ufs->mclk_rate) / NSEC_PER_MSEC; + + ufshcd_dme_set(hba, UIC_ARG_MIB(0x200), 0x40); + for_each_ufs_rx_lane(ufs, i) { + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_RX_CLK_PRD, i), + DIV_ROUND_UP(NSEC_PER_SEC, ufs->mclk_rate)); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_RX_CLK_PRD_EN, i), 0x0); + + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_RX_LINERESET_VALUE2, i), + (rx_line_reset_period >> 16) & 0xFF); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_RX_LINERESET_VALUE1, i), + (rx_line_reset_period >> 8) & 0xFF); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_RX_LINERESET_VALUE0, i), + (rx_line_reset_period) & 0xFF); + + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x2f, i), 0x79); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x84, i), 0x1); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x25, i), 0xf6); + } + + for_each_ufs_tx_lane(ufs, i) { + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_TX_CLK_PRD, i), + DIV_ROUND_UP(NSEC_PER_SEC, ufs->mclk_rate)); + /* Not to affect VND_TX_LINERESET_PVALUE to VND_TX_CLK_PRD */ + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_TX_CLK_PRD_EN, i), + 0x02); + + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_TX_LINERESET_PVALUE2, i), + (tx_line_reset_period >> 16) & 0xFF); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_TX_LINERESET_PVALUE1, i), + (tx_line_reset_period >> 8) & 0xFF); + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(VND_TX_LINERESET_PVALUE0, i), + (tx_line_reset_period) & 0xFF); + + /* TX PWM Gear Capability / PWM_G1_ONLY */ + ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x04, i), 0x1); + } + + ufshcd_dme_set(hba, UIC_ARG_MIB(0x200), 0x0); + + ufshcd_dme_set(hba, UIC_ARG_MIB(PA_LOCAL_TX_LCC_ENABLE), 0x0); + + ufshcd_dme_set(hba, UIC_ARG_MIB(0xa011), 0x8000); + + return 0; +} + +static int exynosauto_ufs_pre_pwr_change(struct exynos_ufs *ufs, + struct ufs_pa_layer_attr *pwr) +{ + struct ufs_hba *hba = ufs->hba; + + /* PACP_PWR_req and delivered to the remote DME */ + ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA0), 12000); + ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA1), 32000); + ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA2), 16000); + + return 0; +} + +static int exynosauto_ufs_post_pwr_change(struct exynos_ufs *ufs, + struct ufs_pa_layer_attr *pwr) +{ + struct ufs_hba *hba = ufs->hba; + u32 enabled_vh; + + enabled_vh = ufshcd_readl(hba, MHCTRL) & MHCTRL_EN_VH_MASK; + + /* Send physical host ready message to virtual hosts */ + ufshcd_writel(hba, MH_MSG(enabled_vh, MH_MSG_PH_READY), PH2VH_MBOX); + + return 0; +} + static int exynos7_ufs_pre_link(struct exynos_ufs *ufs) { struct ufs_hba *hba = ufs->hba; @@ -793,6 +953,27 @@ static void exynos_ufs_config_intr(struct exynos_ufs *ufs, u32 errs, u8 index) } } +static int exynos_ufs_setup_clocks(struct ufs_hba *hba, bool on, + enum ufs_notify_change_status status) +{ + struct exynos_ufs *ufs = ufshcd_get_variant(hba); + + if (!ufs) + return 0; + + if (on && status == PRE_CHANGE) { + if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL) + exynos_ufs_disable_auto_ctrl_hcc(ufs); + exynos_ufs_ungate_clks(ufs); + } else if (!on && status == POST_CHANGE) { + exynos_ufs_gate_clks(ufs); + if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL) + exynos_ufs_enable_auto_ctrl_hcc(ufs); + } + + return 0; +} + static int exynos_ufs_pre_link(struct ufs_hba *hba) { struct exynos_ufs *ufs = ufshcd_get_variant(hba); @@ -808,8 +989,12 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba) /* m-phy */ exynos_ufs_phy_init(ufs); - exynos_ufs_config_phy_time_attr(ufs); - exynos_ufs_config_phy_cap_attr(ufs); + if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR)) { + exynos_ufs_config_phy_time_attr(ufs); + exynos_ufs_config_phy_cap_attr(ufs); + } + + exynos_ufs_setup_clocks(hba, true, PRE_CHANGE); if (ufs->drv_data->pre_link) ufs->drv_data->pre_link(ufs); @@ -893,17 +1078,10 @@ static int exynos_ufs_post_link(struct ufs_hba *hba) static int exynos_ufs_parse_dt(struct device *dev, struct exynos_ufs *ufs) { struct device_node *np = dev->of_node; - struct exynos_ufs_drv_data *drv_data = &exynos_ufs_drvs; struct exynos_ufs_uic_attr *attr; int ret = 0; - while (drv_data->compatible) { - if (of_device_is_compatible(np, drv_data->compatible)) { - ufs->drv_data = drv_data; - break; - } - drv_data++; - } + ufs->drv_data = device_get_match_data(dev); if (ufs->drv_data && ufs->drv_data->uic_attr) { attr = ufs->drv_data->uic_attr; @@ -913,6 +1091,17 @@ static int exynos_ufs_parse_dt(struct device *dev, struct exynos_ufs *ufs) goto out; } + ufs->sysreg = syscon_regmap_lookup_by_phandle(np, "samsung,sysreg"); + if (IS_ERR(ufs->sysreg)) + ufs->sysreg = NULL; + else { + if (of_property_read_u32_index(np, "samsung,sysreg", 1, + &ufs->shareability_reg_offset)) { + dev_warn(dev, "can't get an offset from sysreg. Set to default value\n"); + ufs->shareability_reg_offset = UFS_SHAREABILITY_OFFSET; + } + } + ufs->pclk_avail_min = PCLK_AVAIL_MIN; ufs->pclk_avail_max = PCLK_AVAIL_MAX; @@ -927,6 +1116,18 @@ out: return ret; } +static inline void exynos_ufs_priv_init(struct ufs_hba *hba, + struct exynos_ufs *ufs) +{ + ufs->hba = hba; + ufs->opts = ufs->drv_data->opts; + ufs->rx_sel_idx = PA_MAXDATALANES; + if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX) + ufs->rx_sel_idx = 0; + hba->priv = (void *)ufs; + hba->quirks = ufs->drv_data->quirks; +} + static int exynos_ufs_init(struct ufs_hba *hba) { struct device *dev = hba->dev; @@ -976,13 +1177,8 @@ static int exynos_ufs_init(struct ufs_hba *hba) if (ret) goto phy_off; - ufs->hba = hba; - ufs->opts = ufs->drv_data->opts; - ufs->rx_sel_idx = PA_MAXDATALANES; - if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX) - ufs->rx_sel_idx = 0; - hba->priv = (void *)ufs; - hba->quirks = ufs->drv_data->quirks; + exynos_ufs_priv_init(hba, ufs); + if (ufs->drv_data->drv_init) { ret = ufs->drv_data->drv_init(dev, ufs); if (ret) { @@ -1110,6 +1306,12 @@ static int exynos_ufs_hce_enable_notify(struct ufs_hba *hba, switch (status) { case PRE_CHANGE: + if (ufs->drv_data->pre_hce_enable) { + ret = ufs->drv_data->pre_hce_enable(ufs); + if (ret) + return ret; + } + ret = exynos_ufs_host_reset(hba); if (ret) return ret; @@ -1119,6 +1321,10 @@ static int exynos_ufs_hce_enable_notify(struct ufs_hba *hba, exynos_ufs_calc_pwm_clk_div(ufs); if (!(ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL)) exynos_ufs_enable_auto_ctrl_hcc(ufs); + + if (ufs->drv_data->post_hce_enable) + ret = ufs->drv_data->post_hce_enable(ufs); + break; } @@ -1202,12 +1408,77 @@ static int exynos_ufs_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) return 0; } +static int exynosauto_ufs_vh_link_startup_notify(struct ufs_hba *hba, + enum ufs_notify_change_status status) +{ + if (status == POST_CHANGE) { + ufshcd_set_link_active(hba); + ufshcd_set_ufs_dev_active(hba); + } + + return 0; +} + +static int exynosauto_ufs_vh_wait_ph_ready(struct ufs_hba *hba) +{ + u32 mbox; + ktime_t start, stop; + + start = ktime_get(); + stop = ktime_add(start, ms_to_ktime(PH_READY_TIMEOUT_MS)); + + do { + mbox = ufshcd_readl(hba, PH2VH_MBOX); + /* TODO: Mailbox message protocols between the PH and VHs are + * not implemented yet. This will be supported later + */ + if ((mbox & MH_MSG_MASK) == MH_MSG_PH_READY) + return 0; + + usleep_range(40, 50); + } while (ktime_before(ktime_get(), stop)); + + return -ETIME; +} + +static int exynosauto_ufs_vh_init(struct ufs_hba *hba) +{ + struct device *dev = hba->dev; + struct platform_device *pdev = to_platform_device(dev); + struct exynos_ufs *ufs; + int ret; + + ufs = devm_kzalloc(dev, sizeof(*ufs), GFP_KERNEL); + if (!ufs) + return -ENOMEM; + + /* exynos-specific hci */ + ufs->reg_hci = devm_platform_ioremap_resource_byname(pdev, "vs_hci"); + if (IS_ERR(ufs->reg_hci)) { + dev_err(dev, "cannot ioremap for hci vendor register\n"); + return PTR_ERR(ufs->reg_hci); + } + + ret = exynosauto_ufs_vh_wait_ph_ready(hba); + if (ret) + return ret; + + ufs->drv_data = device_get_match_data(dev); + if (!ufs->drv_data) + return -ENODEV; + + exynos_ufs_priv_init(hba, ufs); + + return 0; +} + static struct ufs_hba_variant_ops ufs_hba_exynos_ops = { .name = "exynos_ufs", .init = exynos_ufs_init, .hce_enable_notify = exynos_ufs_hce_enable_notify, .link_startup_notify = exynos_ufs_link_startup_notify, .pwr_change_notify = exynos_ufs_pwr_change_notify, + .setup_clocks = exynos_ufs_setup_clocks, .setup_xfer_req = exynos_ufs_specify_nexus_t_xfer_req, .setup_task_mgmt = exynos_ufs_specify_nexus_t_tm_req, .hibern8_notify = exynos_ufs_hibern8_notify, @@ -1215,12 +1486,24 @@ static struct ufs_hba_variant_ops ufs_hba_exynos_ops = { .resume = exynos_ufs_resume, }; +static struct ufs_hba_variant_ops ufs_hba_exynosauto_vh_ops = { + .name = "exynosauto_ufs_vh", + .init = exynosauto_ufs_vh_init, + .link_startup_notify = exynosauto_ufs_vh_link_startup_notify, +}; + static int exynos_ufs_probe(struct platform_device *pdev) { int err; struct device *dev = &pdev->dev; + const struct ufs_hba_variant_ops *vops = &ufs_hba_exynos_ops; + const struct exynos_ufs_drv_data *drv_data = + device_get_match_data(dev); - err = ufshcd_pltfrm_init(pdev, &ufs_hba_exynos_ops); + if (drv_data && drv_data->vops) + vops = drv_data->vops; + + err = ufshcd_pltfrm_init(pdev, vops); if (err) dev_err(dev, "ufshcd_pltfrm_init() failed %d\n", err); @@ -1261,8 +1544,35 @@ static struct exynos_ufs_uic_attr exynos7_uic_attr = { .pa_dbg_option_suite = 0x30103, }; +static struct exynos_ufs_drv_data exynosauto_ufs_drvs = { + .uic_attr = &exynos7_uic_attr, + .quirks = UFSHCD_QUIRK_PRDT_BYTE_GRAN | + UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR | + UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR | + UFSHCD_QUIRK_SKIP_DEF_UNIPRO_TIMEOUT_SETTING, + .opts = EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL | + EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR | + EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX, + .drv_init = exynosauto_ufs_drv_init, + .post_hce_enable = exynosauto_ufs_post_hce_enable, + .pre_link = exynosauto_ufs_pre_link, + .pre_pwr_change = exynosauto_ufs_pre_pwr_change, + .post_pwr_change = exynosauto_ufs_post_pwr_change, +}; + +static struct exynos_ufs_drv_data exynosauto_ufs_vh_drvs = { + .vops = &ufs_hba_exynosauto_vh_ops, + .quirks = UFSHCD_QUIRK_PRDT_BYTE_GRAN | + UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR | + UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR | + UFSHCI_QUIRK_BROKEN_HCE | + UFSHCD_QUIRK_BROKEN_UIC_CMD | + UFSHCD_QUIRK_SKIP_PH_CONFIGURATION | + UFSHCD_QUIRK_SKIP_DEF_UNIPRO_TIMEOUT_SETTING, + .opts = EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX, +}; + static struct exynos_ufs_drv_data exynos_ufs_drvs = { - .compatible = "samsung,exynos7-ufs", .uic_attr = &exynos7_uic_attr, .quirks = UFSHCD_QUIRK_PRDT_BYTE_GRAN | UFSHCI_QUIRK_BROKEN_REQ_LIST_CLR | @@ -1287,6 +1597,10 @@ static struct exynos_ufs_drv_data exynos_ufs_drvs = { static const struct of_device_id exynos_ufs_of_match[] = { { .compatible = "samsung,exynos7-ufs", .data = &exynos_ufs_drvs }, + { .compatible = "samsung,exynosautov9-ufs", + .data = &exynosauto_ufs_drvs }, + { .compatible = "samsung,exynosautov9-ufs-vh", + .data = &exynosauto_ufs_vh_drvs }, {}, }; diff --git a/drivers/scsi/ufs/ufs-exynos.h b/drivers/scsi/ufs/ufs-exynos.h index dadf4fd10dd8..1c33e5466082 100644 --- a/drivers/scsi/ufs/ufs-exynos.h +++ b/drivers/scsi/ufs/ufs-exynos.h @@ -56,6 +56,22 @@ #define TX_GRAN_NVAL_10_08 0x0296 #define TX_GRAN_NVAL_H(v) (((v) >> 8) & 0x3) +#define VND_TX_CLK_PRD 0xAA +#define VND_TX_CLK_PRD_EN 0xA9 +#define VND_TX_LINERESET_PVALUE0 0xAD +#define VND_TX_LINERESET_PVALUE1 0xAC +#define VND_TX_LINERESET_PVALUE2 0xAB + +#define TX_LINE_RESET_TIME 3200 + +#define VND_RX_CLK_PRD 0x12 +#define VND_RX_CLK_PRD_EN 0x11 +#define VND_RX_LINERESET_VALUE0 0x1D +#define VND_RX_LINERESET_VALUE1 0x1C +#define VND_RX_LINERESET_VALUE2 0x1B + +#define RX_LINE_RESET_TIME 1000 + #define RX_FILLER_ENABLE 0x0316 #define RX_FILLER_EN (1 << 1) #define RX_LINERESET_VAL 0x0317 @@ -99,7 +115,7 @@ struct exynos_ufs; #define PA_HIBERN8TIME_VAL 0x20 #define PCLK_AVAIL_MIN 70000000 -#define PCLK_AVAIL_MAX 133000000 +#define PCLK_AVAIL_MAX 167000000 struct exynos_ufs_uic_attr { /* TX Attributes */ @@ -142,7 +158,7 @@ struct exynos_ufs_uic_attr { }; struct exynos_ufs_drv_data { - char *compatible; + const struct ufs_hba_variant_ops *vops; struct exynos_ufs_uic_attr *uic_attr; unsigned int quirks; unsigned int opts; @@ -154,6 +170,8 @@ struct exynos_ufs_drv_data { struct ufs_pa_layer_attr *pwr); int (*post_pwr_change)(struct exynos_ufs *ufs, struct ufs_pa_layer_attr *pwr); + int (*pre_hce_enable)(struct exynos_ufs *ufs); + int (*post_hce_enable)(struct exynos_ufs *ufs); }; struct ufs_phy_time_cfg { @@ -191,7 +209,9 @@ struct exynos_ufs { struct ufs_pa_layer_attr dev_req_params; struct ufs_phy_time_cfg t_cfg; ktime_t entry_hibern8_t; - struct exynos_ufs_drv_data *drv_data; + const struct exynos_ufs_drv_data *drv_data; + struct regmap *sysreg; + u32 shareability_reg_offset; u32 opts; #define EXYNOS_UFS_OPT_HAS_APB_CLK_CTRL BIT(0) @@ -199,6 +219,7 @@ struct exynos_ufs { #define EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL BIT(2) #define EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX BIT(3) #define EXYNOS_UFS_OPT_USE_SW_HIBERN8_TIMER BIT(4) +#define EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR BIT(5) }; #define for_each_ufs_rx_lane(ufs, i) \ diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 5c6a58a666d2..afd38142b1c0 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -132,6 +132,14 @@ enum { UFSHCD_CAN_QUEUE = 32, }; +static const char *const ufshcd_state_name[] = { + [UFSHCD_STATE_RESET] = "reset", + [UFSHCD_STATE_OPERATIONAL] = "operational", + [UFSHCD_STATE_ERROR] = "error", + [UFSHCD_STATE_EH_SCHEDULED_FATAL] = "eh_fatal", + [UFSHCD_STATE_EH_SCHEDULED_NON_FATAL] = "eh_non_fatal", +}; + /* UFSHCD error handling flags */ enum { UFSHCD_EH_IN_PROGRESS = (1 << 0), @@ -236,7 +244,6 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up); static irqreturn_t ufshcd_intr(int irq, void *__hba); static int ufshcd_change_power_mode(struct ufs_hba *hba, struct ufs_pa_layer_attr *pwr_mode); -static void ufshcd_schedule_eh_work(struct ufs_hba *hba); static int ufshcd_setup_hba_vreg(struct ufs_hba *hba, bool on); static int ufshcd_setup_vreg(struct ufs_hba *hba, bool on); static inline int ufshcd_config_vreg_hpm(struct ufs_hba *hba, @@ -711,7 +718,7 @@ static inline bool ufshcd_is_device_present(struct ufs_hba *hba) * This function is used to get the OCS field from UTRD * Returns the OCS field in the UTRD */ -static inline int ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp) +static enum utp_ocs ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp) { return le32_to_cpu(lrbp->utr_descriptor_ptr->header.dword_2) & MASK_OCS; } @@ -2323,6 +2330,9 @@ int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) int ret; unsigned long flags; + if (hba->quirks & UFSHCD_QUIRK_BROKEN_UIC_CMD) + return 0; + ufshcd_hold(hba, false); mutex_lock(&hba->uic_cmd_mutex); ufshcd_add_delay_before_dme_cmd(hba); @@ -2367,17 +2377,24 @@ static int ufshcd_map_sg(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) sizeof(struct ufshcd_sg_entry))); else lrbp->utr_descriptor_ptr->prd_table_length = - cpu_to_le16((u16) (sg_segments)); + cpu_to_le16(sg_segments); - prd_table = (struct ufshcd_sg_entry *)lrbp->ucd_prdt_ptr; + prd_table = lrbp->ucd_prdt_ptr; scsi_for_each_sg(cmd, sg, sg_segments, i) { - prd_table[i].size = - cpu_to_le32(((u32) sg_dma_len(sg))-1); - prd_table[i].base_addr = - cpu_to_le32(lower_32_bits(sg->dma_address)); - prd_table[i].upper_addr = - cpu_to_le32(upper_32_bits(sg->dma_address)); + const unsigned int len = sg_dma_len(sg); + + /* + * From the UFSHCI spec: "Data Byte Count (DBC): A '0' + * based value that indicates the length, in bytes, of + * the data block. A maximum of length of 256KB may + * exist for any entry. Bits 1:0 of this field shall be + * 11b to indicate Dword granularity. A value of '3' + * indicates 4 bytes, '7' indicates 8 bytes, etc." + */ + WARN_ONCE(len > 256 * 1024, "len = %#x\n", len); + prd_table[i].size = cpu_to_le32(len - 1); + prd_table[i].addr = cpu_to_le64(sg->dma_address); prd_table[i].reserved = 0; } } else { @@ -2661,7 +2678,7 @@ static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) lrb->ucd_req_dma_addr = cmd_desc_element_addr; lrb->ucd_rsp_ptr = (struct utp_upiu_rsp *)cmd_descp[i].response_upiu; lrb->ucd_rsp_dma_addr = cmd_desc_element_addr + response_offset; - lrb->ucd_prdt_ptr = (struct ufshcd_sg_entry *)cmd_descp[i].prd_table; + lrb->ucd_prdt_ptr = cmd_descp[i].prd_table; lrb->ucd_prdt_dma_addr = cmd_desc_element_addr + prdt_offset; } @@ -5084,7 +5101,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) { int result = 0; int scsi_status; - int ocs; + enum utp_ocs ocs; /* overall command status of utrd */ ocs = ufshcd_get_tr_ocs(lrbp); @@ -5243,11 +5260,9 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) * __ufshcd_transfer_req_compl - handle SCSI and query command completion * @hba: per adapter instance * @completed_reqs: bitmask that indicates which requests to complete - * @retry_requests: whether to ask the SCSI core to retry completed requests */ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba, - unsigned long completed_reqs, - bool retry_requests) + unsigned long completed_reqs) { struct ufshcd_lrb *lrbp; struct scsi_cmnd *cmd; @@ -5263,8 +5278,7 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba, if (unlikely(ufshcd_should_inform_monitor(hba, lrbp))) ufshcd_update_monitor(hba, lrbp); ufshcd_add_command_trace(hba, index, UFS_CMD_COMP); - result = retry_requests ? DID_BUS_BUSY << 16 : - ufshcd_transfer_rsp_status(hba, lrbp); + result = ufshcd_transfer_rsp_status(hba, lrbp); scsi_dma_unmap(cmd); cmd->result = result; /* Mark completed command as NULL in LRB */ @@ -5290,14 +5304,12 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba, /** * ufshcd_transfer_req_compl - handle SCSI and query command completion * @hba: per adapter instance - * @retry_requests: whether or not to ask to retry requests * * Returns * IRQ_HANDLED - If interrupt is valid * IRQ_NONE - If invalid interrupt */ -static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba, - bool retry_requests) +static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba) { unsigned long completed_reqs, flags; u32 tr_doorbell; @@ -5326,8 +5338,7 @@ static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba, spin_unlock_irqrestore(&hba->outstanding_lock, flags); if (completed_reqs) { - __ufshcd_transfer_req_compl(hba, completed_reqs, - retry_requests); + __ufshcd_transfer_req_compl(hba, completed_reqs); return IRQ_HANDLED; } else { return IRQ_NONE; @@ -5826,13 +5837,7 @@ out: /* Complete requests that have door-bell cleared */ static void ufshcd_complete_requests(struct ufs_hba *hba) { - ufshcd_transfer_req_compl(hba, /*retry_requests=*/false); - ufshcd_tmc_handler(hba); -} - -static void ufshcd_retry_aborted_requests(struct ufs_hba *hba) -{ - ufshcd_transfer_req_compl(hba, /*retry_requests=*/true); + ufshcd_transfer_req_compl(hba); ufshcd_tmc_handler(hba); } @@ -5914,9 +5919,10 @@ static inline bool ufshcd_is_saved_err_fatal(struct ufs_hba *hba) (hba->saved_err & (INT_FATAL_ERRORS | UFSHCD_UIC_HIBERN8_MASK)); } -/* host lock must be held before calling this func */ -static inline void ufshcd_schedule_eh_work(struct ufs_hba *hba) +void ufshcd_schedule_eh_work(struct ufs_hba *hba) { + lockdep_assert_held(hba->host->host_lock); + /* handle fatal errors only when link is not in error state */ if (hba->ufshcd_state != UFSHCD_STATE_ERROR) { if (hba->force_reset || ufshcd_is_link_broken(hba) || @@ -6076,6 +6082,13 @@ static void ufshcd_err_handler(struct work_struct *work) hba = container_of(work, struct ufs_hba, eh_work); + dev_info(hba->dev, + "%s started; HBA state %s; powered %d; shutting down %d; saved_err = %d; saved_uic_err = %d; force_reset = %d%s\n", + __func__, ufshcd_state_name[hba->ufshcd_state], + hba->is_powered, hba->shutting_down, hba->saved_err, + hba->saved_uic_err, hba->force_reset, + ufshcd_is_link_broken(hba) ? "; link is broken" : ""); + down(&hba->host_sem); spin_lock_irqsave(hba->host->host_lock, flags); if (ufshcd_err_handling_should_stop(hba)) { @@ -6170,6 +6183,8 @@ again: err_xfer = true; goto lock_skip_pending_xfer_clear; } + dev_err(hba->dev, "Aborted tag %d / CDB %#02x\n", tag, + hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1); } /* Clear pending task management requests */ @@ -6181,7 +6196,8 @@ again: } lock_skip_pending_xfer_clear: - ufshcd_retry_aborted_requests(hba); + /* Complete the requests that are cleared by s/w */ + ufshcd_complete_requests(hba); spin_lock_irqsave(hba->host->host_lock, flags); hba->silence_err_logs = false; @@ -6249,6 +6265,9 @@ skip_err_handling: spin_unlock_irqrestore(hba->host->host_lock, flags); ufshcd_err_handling_unprepare(hba); up(&hba->host_sem); + + dev_info(hba->dev, "%s finished; HBA state %s\n", __func__, + ufshcd_state_name[hba->ufshcd_state]); } /** @@ -6473,7 +6492,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status) retval |= ufshcd_tmc_handler(hba); if (intr_status & UTP_TRANSFER_REQ_COMPL) - retval |= ufshcd_transfer_req_compl(hba, /*retry_requests=*/false); + retval |= ufshcd_transfer_req_compl(hba); return retval; } @@ -6545,6 +6564,10 @@ static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag) err = ufshcd_wait_for_register(hba, REG_UTP_TASK_REQ_DOOR_BELL, mask, 0, 1000, 1000); + + dev_err(hba->dev, "Clearing task management function with tag %d %s\n", + tag, err ? "succeeded" : "failed"); + out: return err; } @@ -6637,7 +6660,8 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id, u8 tm_function, u8 *tm_response) { struct utp_task_req_desc treq = { { 0 }, }; - int ocs_value, err; + enum utp_ocs ocs_value; + int err; /* Configure task request descriptor */ treq.header.dword_0 = cpu_to_le32(UTP_REQ_DESC_INT_CMD); @@ -6815,7 +6839,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba, int err; enum dev_cmd_type cmd_type = DEV_CMD_TYPE_QUERY; struct utp_task_req_desc treq = { { 0 }, }; - int ocs_value; + enum utp_ocs ocs_value; u8 tm_f = be32_to_cpu(req_upiu->header.dword_1) >> 16 & MASK_TM_FUNC; switch (msgcode) { @@ -6893,7 +6917,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd) err = ufshcd_clear_cmd(hba, pos); if (err) break; - __ufshcd_transfer_req_compl(hba, 1U << pos, false); + __ufshcd_transfer_req_compl(hba, 1U << pos); } } @@ -7055,7 +7079,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) dev_err(hba->dev, "%s: cmd was completed, but without a notifying intr, tag = %d", __func__, tag); - __ufshcd_transfer_req_compl(hba, 1UL << tag, /*retry_requests=*/false); + __ufshcd_transfer_req_compl(hba, 1UL << tag); goto release; } @@ -7121,7 +7145,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) ufshpb_reset_host(hba); ufshcd_hba_stop(hba); hba->silence_err_logs = true; - ufshcd_retry_aborted_requests(hba); + ufshcd_complete_requests(hba); hba->silence_err_logs = false; /* scale up clocks to max frequency before full reinitialization */ @@ -8002,6 +8026,9 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) if (ret) goto out; + if (hba->quirks & UFSHCD_QUIRK_SKIP_PH_CONFIGURATION) + goto out; + /* Debug counters initialization */ ufshcd_clear_dbg_ufs_stats(hba); @@ -9772,6 +9799,11 @@ static int __init ufshcd_core_init(void) { int ret; + /* Verify that there are no gaps in struct utp_transfer_cmd_desc. */ + static_assert(sizeof(struct utp_transfer_cmd_desc) == + 2 * ALIGNED_UPIU_SIZE + + SG_ALL * sizeof(struct ufshcd_sg_entry)); + ufs_debugfs_init(); ret = scsi_register_driver(&ufs_dev_wlun_template.gendrv); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index dd765863b05f..54750d72c8fb 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -589,6 +589,18 @@ enum ufshcd_quirks { * This quirk allows only sg entries aligned with page size. */ UFSHCD_QUIRK_ALIGN_SG_WITH_PAGE_SIZE = 1 << 14, + + /* + * This quirk needs to be enabled if the host controller does not + * support UIC command + */ + UFSHCD_QUIRK_BROKEN_UIC_CMD = 1 << 15, + + /* + * This quirk needs to be enabled if the host controller cannot + * support physical host configuration. + */ + UFSHCD_QUIRK_SKIP_PH_CONFIGURATION = 1 << 16, }; enum ufshcd_caps { @@ -1023,6 +1035,7 @@ int ufshcd_wait_for_register(struct ufs_hba *hba, u32 reg, u32 mask, void ufshcd_parse_dev_ref_clk_freq(struct ufs_hba *hba, struct clk *refclk); void ufshcd_update_evt_hist(struct ufs_hba *hba, u32 id, u32 val); void ufshcd_hba_stop(struct ufs_hba *hba); +void ufshcd_schedule_eh_work(struct ufs_hba *hba); static inline void check_upiu_size(void) { diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h index de95be5d11d4..6a295c88d850 100644 --- a/drivers/scsi/ufs/ufshci.h +++ b/drivers/scsi/ufs/ufshci.h @@ -389,7 +389,7 @@ enum { }; /* Overall command status values */ -enum { +enum utp_ocs { OCS_SUCCESS = 0x0, OCS_INVALID_CMD_TABLE_ATTR = 0x1, OCS_INVALID_PRDT_ATTR = 0x2, @@ -402,6 +402,9 @@ enum { OCS_INVALID_CRYPTO_CONFIG = 0x9, OCS_GENERAL_CRYPTO_ERROR = 0xA, OCS_INVALID_COMMAND_STATUS = 0x0F, +}; + +enum { MASK_OCS = 0x0F, }; @@ -412,20 +415,18 @@ enum { /** * struct ufshcd_sg_entry - UFSHCI PRD Entry - * @base_addr: Lower 32bit physical address DW-0 - * @upper_addr: Upper 32bit physical address DW-1 + * @addr: Physical address; DW-0 and DW-1. * @reserved: Reserved for future use DW-2 * @size: size of physical segment DW-3 */ struct ufshcd_sg_entry { - __le32 base_addr; - __le32 upper_addr; + __le64 addr; __le32 reserved; __le32 size; }; /** - * struct utp_transfer_cmd_desc - UFS Command Descriptor structure + * struct utp_transfer_cmd_desc - UTP Command Descriptor (UCD) * @command_upiu: Command UPIU Frame address * @response_upiu: Response UPIU Frame address * @prd_table: Physical Region Descriptor @@ -451,7 +452,7 @@ struct request_desc_header { }; /** - * struct utp_transfer_req_desc - UTRD structure + * struct utp_transfer_req_desc - UTP Transfer Request Descriptor (UTRD) * @header: UTRD header DW-0 to DW-3 * @command_desc_base_addr_lo: UCD base address low DW-4 * @command_desc_base_addr_hi: UCD base address high DW-5 diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index f4eca441b433..2e31e1413826 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -394,8 +394,6 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) if (!ufshpb_is_supported_chunk(hpb, transfer_len)) return 0; - WARN_ON_ONCE(transfer_len > HPB_MULTI_CHUNK_HIGH); - if (hpb->is_hcm) { /* * in host control mode, reads are the main source for @@ -1572,7 +1570,7 @@ static void ufshpb_lu_parameter_init(struct ufs_hba *hba, if (ufshpb_is_legacy(hba)) hpb->pre_req_max_tr_len = HPB_LEGACY_CHUNK_HIGH; else - hpb->pre_req_max_tr_len = HPB_MULTI_CHUNK_HIGH; + hpb->pre_req_max_tr_len = hpb_dev_info->max_hpb_single_cmd; hpb->lu_pinned_start = hpb_lu_info->pinned_start; hpb->lu_pinned_end = hpb_lu_info->num_pinned ? @@ -2582,7 +2580,7 @@ void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) { struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev; int version, ret; - u32 max_hpb_single_cmd = HPB_MULTI_CHUNK_LOW; + int max_single_cmd; hpb_dev_info->control_mode = desc_buf[DEVICE_DESC_PARAM_HPB_CONTROL]; @@ -2598,18 +2596,22 @@ void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf) if (version == HPB_SUPPORT_LEGACY_VERSION) hpb_dev_info->is_legacy = true; - ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR, - QUERY_ATTR_IDN_MAX_HPB_SINGLE_CMD, 0, 0, &max_hpb_single_cmd); - if (ret) - dev_err(hba->dev, "%s: idn: read max size of single hpb cmd query request failed", - __func__); - hpb_dev_info->max_hpb_single_cmd = max_hpb_single_cmd; - /* * Get the number of user logical unit to check whether all * scsi_device finish initialization */ hpb_dev_info->num_lu = desc_buf[DEVICE_DESC_PARAM_NUM_LU]; + + if (hpb_dev_info->is_legacy) + return; + + ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR, + QUERY_ATTR_IDN_MAX_HPB_SINGLE_CMD, 0, 0, &max_single_cmd); + + if (ret) + hpb_dev_info->max_hpb_single_cmd = HPB_LEGACY_CHUNK_HIGH; + else + hpb_dev_info->max_hpb_single_cmd = min(max_single_cmd + 1, HPB_MULTI_CHUNK_HIGH); } void ufshpb_init(struct ufs_hba *hba) diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index f15d8fdbce2e..b475dbd78988 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -31,7 +31,6 @@ /* hpb support chunk size */ #define HPB_LEGACY_CHUNK_HIGH 1 -#define HPB_MULTI_CHUNK_LOW 7 #define HPB_MULTI_CHUNK_HIGH 255 /* hpb vender defined opcode */ diff --git a/drivers/soc/fsl/dpaa2-console.c b/drivers/soc/fsl/dpaa2-console.c index 27243f706f37..53917410f2bd 100644 --- a/drivers/soc/fsl/dpaa2-console.c +++ b/drivers/soc/fsl/dpaa2-console.c @@ -231,6 +231,7 @@ static ssize_t dpaa2_console_read(struct file *fp, char __user *buf, cd->cur_ptr += bytes; written += bytes; + kfree(kbuf); return written; err_free_buf: diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index db0d3910fee4..1d2b27e3ea63 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -68,7 +68,7 @@ static inline struct dpaa2_io *service_select_by_cpu(struct dpaa2_io *d, * potentially being migrated away. */ if (cpu < 0) - cpu = smp_processor_id(); + cpu = raw_smp_processor_id(); /* If a specific cpu was requested, pick it up immediately */ return dpio_by_cpu[cpu]; diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c index e46bcf78ed59..058b78fac5e3 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.c +++ b/drivers/soc/fsl/dpio/qbman-portal.c @@ -737,8 +737,7 @@ int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s, int i, num_enqueued = 0; unsigned long irq_flags; - spin_lock(&s->access_spinlock); - local_irq_save(irq_flags); + spin_lock_irqsave(&s->access_spinlock, irq_flags); half_mask = (s->eqcr.pi_ci_mask>>1); full_mask = s->eqcr.pi_ci_mask; @@ -749,8 +748,7 @@ int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s, s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size, eqcr_ci, s->eqcr.ci); if (!s->eqcr.available) { - local_irq_restore(irq_flags); - spin_unlock(&s->access_spinlock); + spin_unlock_irqrestore(&s->access_spinlock, irq_flags); return 0; } } @@ -789,8 +787,7 @@ int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s, dma_wmb(); qbman_write_register(s, QBMAN_CINH_SWP_EQCR_PI, (QB_RT_BIT)|(s->eqcr.pi)|s->eqcr.pi_vb); - local_irq_restore(irq_flags); - spin_unlock(&s->access_spinlock); + spin_unlock_irqrestore(&s->access_spinlock, irq_flags); return num_enqueued; } diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c index 09abd17065ba..72386bd393fe 100644 --- a/drivers/soc/ti/wkup_m3_ipc.c +++ b/drivers/soc/ti/wkup_m3_ipc.c @@ -413,8 +413,9 @@ void wkup_m3_ipc_put(struct wkup_m3_ipc *m3_ipc) } EXPORT_SYMBOL_GPL(wkup_m3_ipc_put); -static void wkup_m3_rproc_boot_thread(struct wkup_m3_ipc *m3_ipc) +static int wkup_m3_rproc_boot_thread(void *arg) { + struct wkup_m3_ipc *m3_ipc = arg; struct device *dev = m3_ipc->dev; int ret; @@ -426,7 +427,7 @@ static void wkup_m3_rproc_boot_thread(struct wkup_m3_ipc *m3_ipc) else m3_ipc_state = m3_ipc; - do_exit(0); + return 0; } static int wkup_m3_ipc_probe(struct platform_device *pdev) @@ -500,7 +501,7 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev) * can boot the wkup_m3 as soon as it's ready without holding * up kernel boot */ - task = kthread_run((void *)wkup_m3_rproc_boot_thread, m3_ipc, + task = kthread_run(wkup_m3_rproc_boot_thread, m3_ipc, "wkup_m3_rproc_loader"); if (IS_ERR(task)) { diff --git a/drivers/staging/r8188eu/core/rtw_cmd.c b/drivers/staging/r8188eu/core/rtw_cmd.c index 5d5f25364b2f..48869a7056fd 100644 --- a/drivers/staging/r8188eu/core/rtw_cmd.c +++ b/drivers/staging/r8188eu/core/rtw_cmd.c @@ -323,7 +323,7 @@ post_process: complete(&pcmdpriv->stop_cmd_thread); - thread_exit(); + return 0; } /* diff --git a/drivers/staging/r8188eu/include/osdep_service.h b/drivers/staging/r8188eu/include/osdep_service.h index efab3a97eb46..f6f5e4581212 100644 --- a/drivers/staging/r8188eu/include/osdep_service.h +++ b/drivers/staging/r8188eu/include/osdep_service.h @@ -49,8 +49,6 @@ struct __queue { spinlock_t lock; }; -#define thread_exit() complete_and_exit(NULL, 0) - static inline struct list_head *get_list_head(struct __queue *queue) { return (&(queue->queue)); diff --git a/drivers/staging/rtl8712/osdep_service.h b/drivers/staging/rtl8712/osdep_service.h index d33ddffb7ad9..0d9bb42cbc58 100644 --- a/drivers/staging/rtl8712/osdep_service.h +++ b/drivers/staging/rtl8712/osdep_service.h @@ -37,7 +37,6 @@ struct __queue { #define _pkt struct sk_buff #define _buffer unsigned char -#define thread_exit() complete_and_exit(NULL, 0) #define _init_queue(pqueue) \ do { \ diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c index e9294e1ed06e..2326aae6709e 100644 --- a/drivers/staging/rtl8712/rtl8712_cmd.c +++ b/drivers/staging/rtl8712/rtl8712_cmd.c @@ -393,7 +393,7 @@ _next: r8712_free_cmd_obj(pcmd); } while (1); complete(&pcmdpriv->terminate_cmdthread_comp); - thread_exit(); + return 0; } void r8712_event_handle(struct _adapter *padapter, __le32 *peventbuf) diff --git a/drivers/staging/rtl8723bs/core/rtw_cmd.c b/drivers/staging/rtl8723bs/core/rtw_cmd.c index 639459d52261..bd24d913b464 100644 --- a/drivers/staging/rtl8723bs/core/rtw_cmd.c +++ b/drivers/staging/rtl8723bs/core/rtw_cmd.c @@ -518,7 +518,7 @@ post_process: complete(&pcmdpriv->terminate_cmdthread_comp); atomic_set(&pcmdpriv->cmdthd_running, false); - thread_exit(); + return 0; } /* diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c index 46054d6a1fb5..13b8bd5ffabc 100644 --- a/drivers/staging/rtl8723bs/core/rtw_xmit.c +++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c @@ -2500,7 +2500,7 @@ int rtw_xmit_thread(void *context) complete(&padapter->xmitpriv.terminate_xmitthread_comp); - thread_exit(); + return 0; } void rtw_sctx_init(struct submit_ctx *sctx, int timeout_ms) diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c index 5f5c4719b586..7fe3df863fe1 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c @@ -435,7 +435,7 @@ int rtl8723bs_xmit_thread(void *context) complete(&pxmitpriv->SdioXmitTerminate); - thread_exit(); + return 0; } s32 rtl8723bs_mgnt_xmit( diff --git a/drivers/staging/rtl8723bs/include/osdep_service_linux.h b/drivers/staging/rtl8723bs/include/osdep_service_linux.h index 3492ec1efd1e..188ed7e26550 100644 --- a/drivers/staging/rtl8723bs/include/osdep_service_linux.h +++ b/drivers/staging/rtl8723bs/include/osdep_service_linux.h @@ -45,8 +45,6 @@ spinlock_t lock; }; - #define thread_exit() complete_and_exit(NULL, 0) - static inline struct list_head *get_next(struct list_head *list) { return list->next; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index e7fcbc09f9db..bac111456fa1 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -50,15 +50,6 @@ EXPORT_SYMBOL(core_tmr_alloc_req); void core_tmr_release_req(struct se_tmr_req *tmr) { - struct se_device *dev = tmr->tmr_dev; - unsigned long flags; - - if (dev) { - spin_lock_irqsave(&dev->se_tmr_lock, flags); - list_del_init(&tmr->tmr_list); - spin_unlock_irqrestore(&dev->se_tmr_lock, flags); - } - kfree(tmr); } @@ -156,13 +147,6 @@ void core_tmr_abort_task( se_cmd->state_active = false; spin_unlock_irqrestore(&dev->queues[i].lock, flags); - /* - * Ensure that this ABORT request is visible to the LU - * RESET code. - */ - if (!tmr->tmr_dev) - WARN_ON_ONCE(transport_lookup_tmr_lun(tmr->task_cmd) < 0); - if (dev->transport->tmr_notify) dev->transport->tmr_notify(dev, TMR_ABORT_TASK, &aborted_list); @@ -234,6 +218,7 @@ static void core_tmr_drain_tmr_list( } list_move_tail(&tmr_p->tmr_list, &drain_tmr_list); + tmr_p->tmr_dev = NULL; } spin_unlock_irqrestore(&dev->se_tmr_lock, flags); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 4a2e749eb182..7838dc20f713 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -676,6 +676,21 @@ static void target_remove_from_state_list(struct se_cmd *cmd) spin_unlock_irqrestore(&dev->queues[cmd->cpuid].lock, flags); } +static void target_remove_from_tmr_list(struct se_cmd *cmd) +{ + struct se_device *dev = NULL; + unsigned long flags; + + if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) + dev = cmd->se_tmr_req->tmr_dev; + + if (dev) { + spin_lock_irqsave(&dev->se_tmr_lock, flags); + if (cmd->se_tmr_req->tmr_dev) + list_del_init(&cmd->se_tmr_req->tmr_list); + spin_unlock_irqrestore(&dev->se_tmr_lock, flags); + } +} /* * This function is called by the target core after the target core has * finished processing a SCSI command or SCSI TMF. Both the regular command @@ -687,13 +702,6 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) { unsigned long flags; - target_remove_from_state_list(cmd); - - /* - * Clear struct se_cmd->se_lun before the handoff to FE. - */ - cmd->se_lun = NULL; - spin_lock_irqsave(&cmd->t_state_lock, flags); /* * Determine if frontend context caller is requesting the stopping of @@ -728,8 +736,16 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd) if (!lun) return; + target_remove_from_state_list(cmd); + target_remove_from_tmr_list(cmd); + if (cmpxchg(&cmd->lun_ref_active, true, false)) percpu_ref_put(&lun->lun_ref); + + /* + * Clear struct se_cmd->se_lun before the handoff to FE. + */ + cmd->se_lun = NULL; } static void target_complete_failure_work(struct work_struct *work) diff --git a/drivers/thermal/gov_user_space.c b/drivers/thermal/gov_user_space.c index f4fe050e1cbc..64a18e354a20 100644 --- a/drivers/thermal/gov_user_space.c +++ b/drivers/thermal/gov_user_space.c @@ -17,8 +17,8 @@ static int user_space_bind(struct thermal_zone_device *tz) { - pr_warn("Userspace governor deprecated: use thermal netlink " \ - "notification instead\n"); + pr_warn_once("Userspace governor deprecated: use thermal netlink " \ + "notification instead\n"); return 0; } diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h index c1d8de6dc3d1..be27f633e40a 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h @@ -80,7 +80,7 @@ void proc_thermal_rfim_remove(struct pci_dev *pdev); int proc_thermal_mbox_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv); void proc_thermal_mbox_remove(struct pci_dev *pdev); -int processor_thermal_send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u32 *cmd_resp); +int processor_thermal_send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u64 *cmd_resp); int proc_thermal_add(struct device *dev, struct proc_thermal_device *priv); void proc_thermal_remove(struct proc_thermal_device *proc_priv); int proc_thermal_suspend(struct device *dev); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_mbox.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_mbox.c index 59e93b04f0a9..01008ae00e7f 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_mbox.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_mbox.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include "processor_thermal_device.h" #define MBOX_CMD_WORKLOAD_TYPE_READ 0x0E @@ -23,7 +24,7 @@ static DEFINE_MUTEX(mbox_lock); -static int send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u32 *cmd_resp) +static int send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u64 *cmd_resp) { struct proc_thermal_device *proc_priv; u32 retries, data; @@ -68,12 +69,16 @@ static int send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u32 *cm goto unlock_mbox; } - if (cmd_id == MBOX_CMD_WORKLOAD_TYPE_READ) { - data = readl((void __iomem *) (proc_priv->mmio_base + MBOX_OFFSET_DATA)); - *cmd_resp = data & 0xff; - } - ret = 0; + + if (!cmd_resp) + break; + + if (cmd_id == MBOX_CMD_WORKLOAD_TYPE_READ) + *cmd_resp = readl((void __iomem *) (proc_priv->mmio_base + MBOX_OFFSET_DATA)); + else + *cmd_resp = readq((void __iomem *) (proc_priv->mmio_base + MBOX_OFFSET_DATA)); + break; } while (--retries); @@ -82,7 +87,7 @@ unlock_mbox: return ret; } -int processor_thermal_send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u32 *cmd_resp) +int processor_thermal_send_mbox_cmd(struct pci_dev *pdev, u16 cmd_id, u32 cmd_data, u64 *cmd_resp) { return send_mbox_cmd(pdev, cmd_id, cmd_data, cmd_resp); } @@ -153,7 +158,7 @@ static ssize_t workload_type_show(struct device *dev, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); - u32 cmd_resp; + u64 cmd_resp; int ret; ret = send_mbox_cmd(pdev, MBOX_CMD_WORKLOAD_TYPE_READ, 0, &cmd_resp); @@ -187,7 +192,7 @@ static bool workload_req_created; int proc_thermal_mbox_add(struct pci_dev *pdev, struct proc_thermal_device *proc_priv) { - u32 cmd_resp; + u64 cmd_resp; int ret; /* Check if there is a mailbox support, if fails return success */ diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c index 2b8a3235d518..b25b54d4bac1 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c @@ -195,7 +195,7 @@ static ssize_t rfi_restriction_store(struct device *dev, const char *buf, size_t count) { u16 cmd_id = 0x0008; - u32 cmd_resp; + u64 cmd_resp; u32 input; int ret; @@ -215,14 +215,14 @@ static ssize_t rfi_restriction_show(struct device *dev, char *buf) { u16 cmd_id = 0x0007; - u32 cmd_resp; + u64 cmd_resp; int ret; ret = processor_thermal_send_mbox_cmd(to_pci_dev(dev), cmd_id, 0, &cmd_resp); if (ret) return ret; - return sprintf(buf, "%u\n", cmd_resp); + return sprintf(buf, "%llu\n", cmd_resp); } static ssize_t ddr_data_rate_show(struct device *dev, @@ -230,14 +230,14 @@ static ssize_t ddr_data_rate_show(struct device *dev, char *buf) { u16 cmd_id = 0x0107; - u32 cmd_resp; + u64 cmd_resp; int ret; ret = processor_thermal_send_mbox_cmd(to_pci_dev(dev), cmd_id, 0, &cmd_resp); if (ret) return ret; - return sprintf(buf, "%u\n", cmd_resp); + return sprintf(buf, "%llu\n", cmd_resp); } static DEVICE_ATTR_RW(rfi_restriction); diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 6379f26a335f..9233f7e74454 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -89,7 +89,7 @@ static int of_thermal_get_temp(struct thermal_zone_device *tz, { struct __thermal_zone *data = tz->devdata; - if (!data->ops->get_temp) + if (!data->ops || !data->ops->get_temp) return -EINVAL; return data->ops->get_temp(data->sensor_data, temp); @@ -186,6 +186,9 @@ static int of_thermal_set_emul_temp(struct thermal_zone_device *tz, { struct __thermal_zone *data = tz->devdata; + if (!data->ops || !data->ops->set_emul_temp) + return -EINVAL; + return data->ops->set_emul_temp(data->sensor_data, temp); } @@ -194,7 +197,7 @@ static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip, { struct __thermal_zone *data = tz->devdata; - if (!data->ops->get_trend) + if (!data->ops || !data->ops->get_trend) return -EINVAL; return data->ops->get_trend(data->sensor_data, trip, trend); @@ -301,7 +304,7 @@ static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip, if (trip >= data->ntrips || trip < 0) return -EDOM; - if (data->ops->set_trip_temp) { + if (data->ops && data->ops->set_trip_temp) { int ret; ret = data->ops->set_trip_temp(data->sensor_data, trip, temp); diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index a3311e937847..4d326ee12c36 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2795,7 +2795,6 @@ int usb_add_hcd(struct usb_hcd *hcd, { int retval; struct usb_device *rhdev; - struct usb_hcd *shared_hcd; if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); @@ -2956,26 +2955,13 @@ int usb_add_hcd(struct usb_hcd *hcd, goto err_hcd_driver_start; } - /* starting here, usbcore will pay attention to the shared HCD roothub */ - shared_hcd = hcd->shared_hcd; - if (!usb_hcd_is_primary_hcd(hcd) && shared_hcd && HCD_DEFER_RH_REGISTER(shared_hcd)) { - retval = register_root_hub(shared_hcd); - if (retval != 0) - goto err_register_root_hub; - - if (shared_hcd->uses_new_polling && HCD_POLL_RH(shared_hcd)) - usb_hcd_poll_rh_status(shared_hcd); - } - /* starting here, usbcore will pay attention to this root hub */ - if (!HCD_DEFER_RH_REGISTER(hcd)) { - retval = register_root_hub(hcd); - if (retval != 0) - goto err_register_root_hub; + retval = register_root_hub(hcd); + if (retval != 0) + goto err_register_root_hub; - if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) - usb_hcd_poll_rh_status(hcd); - } + if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) + usb_hcd_poll_rh_status(hcd); return retval; @@ -3013,7 +2999,6 @@ EXPORT_SYMBOL_GPL(usb_add_hcd); void usb_remove_hcd(struct usb_hcd *hcd) { struct usb_device *rhdev = hcd->self.root_hub; - bool rh_registered; dev_info(hcd->self.controller, "remove, state %x\n", hcd->state); @@ -3024,7 +3009,6 @@ void usb_remove_hcd(struct usb_hcd *hcd) dev_dbg(hcd->self.controller, "roothub graceful disconnect\n"); spin_lock_irq (&hcd_root_hub_lock); - rh_registered = hcd->rh_registered; hcd->rh_registered = 0; spin_unlock_irq (&hcd_root_hub_lock); @@ -3034,8 +3018,7 @@ void usb_remove_hcd(struct usb_hcd *hcd) cancel_work_sync(&hcd->died_work); mutex_lock(&usb_bus_idr_lock); - if (rh_registered) - usb_disconnect(&rhdev); /* Sets rhdev to NULL */ + usb_disconnect(&rhdev); /* Sets rhdev to NULL */ mutex_unlock(&usb_bus_idr_lock); /* diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index a3f875eea751..af946c42b6f0 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -257,7 +257,6 @@ static void xhci_common_hub_descriptor(struct xhci_hcd *xhci, { u16 temp; - desc->bPwrOn2PwrGood = 10; /* xhci section 5.4.9 says 20ms max */ desc->bHubContrCurrent = 0; desc->bNbrPorts = ports; @@ -292,6 +291,7 @@ static void xhci_usb2_hub_descriptor(struct usb_hcd *hcd, struct xhci_hcd *xhci, desc->bDescriptorType = USB_DT_HUB; temp = 1 + (ports / 8); desc->bDescLength = USB_DT_HUB_NONVAR_SIZE + 2 * temp; + desc->bPwrOn2PwrGood = 10; /* xhci section 5.4.8 says 20ms */ /* The Device Removable bits are reported on a byte granularity. * If the port doesn't exist within that byte, the bit is set to 0. @@ -344,6 +344,7 @@ static void xhci_usb3_hub_descriptor(struct usb_hcd *hcd, struct xhci_hcd *xhci, xhci_common_hub_descriptor(xhci, desc, ports); desc->bDescriptorType = USB_DT_SS_HUB; desc->bDescLength = USB_DT_SS_HUB_SIZE; + desc->bPwrOn2PwrGood = 50; /* usb 3.1 may fail if less than 100ms */ /* header decode latency should be zero for roothubs, * see section 4.23.5.2. diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 541fe4dcc43a..902f410874e8 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -692,7 +692,6 @@ int xhci_run(struct usb_hcd *hcd) if (ret) xhci_free_command(xhci, command); } - set_bit(HCD_FLAG_DEFER_RH_REGISTER, &hcd->flags); xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Finished xhci_run for USB2 roothub"); diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index f98e8f298bc1..01fae2c96965 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -43,21 +43,6 @@ static void update_attr(u8 *dst, u8 *src, int attribute, } } -static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fb_copyarea area; - - area.sx = sx * vc->vc_font.width; - area.sy = sy * vc->vc_font.height; - area.dx = dx * vc->vc_font.width; - area.dy = dy * vc->vc_font.height; - area.height = height * vc->vc_font.height; - area.width = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -393,7 +378,6 @@ static int bit_update_start(struct fb_info *info) void fbcon_set_bitops(struct fbcon_ops *ops) { - ops->bmove = bit_bmove; ops->clear = bit_clear; ops->putcs = bit_putcs; ops->clear_margins = bit_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 22bb3892f6bd..99ecd9a6d844 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -173,8 +173,6 @@ static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, int count, int ypos, int xpos); static void fbcon_clear_margins(struct vc_data *vc, int bottom_only); static void fbcon_cursor(struct vc_data *vc, int mode); -static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, - int height, int width); static int fbcon_switch(struct vc_data *vc); static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); @@ -182,16 +180,8 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines */ -static __inline__ void ywrap_up(struct vc_data *vc, int count); -static __inline__ void ywrap_down(struct vc_data *vc, int count); -static __inline__ void ypan_up(struct vc_data *vc, int count); -static __inline__ void ypan_down(struct vc_data *vc, int count); -static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, - int dy, int dx, int height, int width, u_int y_break); static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit); -static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, - int line, int count, int dy); static void fbcon_modechanged(struct fb_info *info); static void fbcon_set_all_vcs(struct fb_info *info); static void fbcon_start(void); @@ -1136,14 +1126,6 @@ static void fbcon_init(struct vc_data *vc, int init) ops->graphics = 0; /* - * No more hw acceleration for fbcon. - * - * FIXME: Garbage collect all the now dead code after sufficient time - * has passed. - */ - p->scrollmode = SCROLL_REDRAW; - - /* * ++guenther: console.c:vc_allocate() relies on initializing * vc_{cols,rows}, but we must not set those if we are only * resizing the console. @@ -1229,14 +1211,13 @@ finished: * This system is now divided into two levels because of complications * caused by hardware scrolling. Top level functions: * - * fbcon_bmove(), fbcon_clear(), fbcon_putc(), fbcon_clear_margins() + * fbcon_clear(), fbcon_putc(), fbcon_clear_margins() * * handles y values in range [0, scr_height-1] that correspond to real * screen positions. y_wrap shift means that first line of bitmap may be * anywhere on this display. These functions convert lineoffsets to * bitmap offsets and deal with the wrap-around case by splitting blits. * - * fbcon_bmove_physical_8() -- These functions fast implementations * fbcon_clear_physical_8() -- of original fbcon_XXX fns. * fbcon_putc_physical_8() -- (font width != 8) may be added later * @@ -1409,224 +1390,6 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, } } -static __inline__ void ywrap_up(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll += count; - if (p->yscroll >= p->vrows) /* Deal with wrap */ - p->yscroll -= p->vrows; - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode |= FB_VMODE_YWRAP; - ops->update_start(info); - scrollback_max += count; - if (scrollback_max > scrollback_phys_max) - scrollback_max = scrollback_phys_max; - scrollback_current = 0; -} - -static __inline__ void ywrap_down(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll -= count; - if (p->yscroll < 0) /* Deal with wrap */ - p->yscroll += p->vrows; - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode |= FB_VMODE_YWRAP; - ops->update_start(info); - scrollback_max -= count; - if (scrollback_max < 0) - scrollback_max = 0; - scrollback_current = 0; -} - -static __inline__ void ypan_up(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; - - p->yscroll += count; - if (p->yscroll > p->vrows - vc->vc_rows) { - ops->bmove(vc, info, p->vrows - vc->vc_rows, - 0, 0, 0, vc->vc_rows, vc->vc_cols); - p->yscroll -= p->vrows - vc->vc_rows; - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max += count; - if (scrollback_max > scrollback_phys_max) - scrollback_max = scrollback_phys_max; - scrollback_current = 0; -} - -static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll += count; - - if (p->yscroll > p->vrows - vc->vc_rows) { - p->yscroll -= p->vrows - vc->vc_rows; - fbcon_redraw_move(vc, p, t + count, vc->vc_rows - count, t); - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max += count; - if (scrollback_max > scrollback_phys_max) - scrollback_max = scrollback_phys_max; - scrollback_current = 0; -} - -static __inline__ void ypan_down(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; - - p->yscroll -= count; - if (p->yscroll < 0) { - ops->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, - 0, vc->vc_rows, vc->vc_cols); - p->yscroll += p->vrows - vc->vc_rows; - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max -= count; - if (scrollback_max < 0) - scrollback_max = 0; - scrollback_current = 0; -} - -static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll -= count; - - if (p->yscroll < 0) { - p->yscroll += p->vrows - vc->vc_rows; - fbcon_redraw_move(vc, p, t, vc->vc_rows - count, t + count); - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max -= count; - if (scrollback_max < 0) - scrollback_max = 0; - scrollback_current = 0; -} - -static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, - int line, int count, int dy) -{ - unsigned short *s = (unsigned short *) - (vc->vc_origin + vc->vc_size_row * line); - - while (count--) { - unsigned short *start = s; - unsigned short *le = advance_row(s, 1); - unsigned short c; - int x = 0; - unsigned short attr = 1; - - do { - c = scr_readw(s); - if (attr != (c & 0xff00)) { - attr = c & 0xff00; - if (s > start) { - fbcon_putcs(vc, start, s - start, - dy, x); - x += s - start; - start = s; - } - } - console_conditional_schedule(); - s++; - } while (s < le); - if (s > start) - fbcon_putcs(vc, start, s - start, dy, x); - console_conditional_schedule(); - dy++; - } -} - -static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, - struct fbcon_display *p, int line, int count, int ycount) -{ - int offset = ycount * vc->vc_cols; - unsigned short *d = (unsigned short *) - (vc->vc_origin + vc->vc_size_row * line); - unsigned short *s = d + offset; - struct fbcon_ops *ops = info->fbcon_par; - - while (count--) { - unsigned short *start = s; - unsigned short *le = advance_row(s, 1); - unsigned short c; - int x = 0; - - do { - c = scr_readw(s); - - if (c == scr_readw(d)) { - if (s > start) { - ops->bmove(vc, info, line + ycount, x, - line, x, 1, s-start); - x += s - start + 1; - start = s + 1; - } else { - x++; - start++; - } - } - - scr_writew(c, d); - console_conditional_schedule(); - s++; - d++; - } while (s < le); - if (s > start) - ops->bmove(vc, info, line + ycount, x, line, x, 1, - s-start); - console_conditional_schedule(); - if (ycount > 0) - line++; - else { - line--; - /* NOTE: We subtract two lines from these pointers */ - s -= vc->vc_size_row; - d -= vc->vc_size_row; - } - } -} - static void fbcon_redraw(struct vc_data *vc, struct fbcon_display *p, int line, int count, int offset) { @@ -1687,7 +1450,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; struct fbcon_display *p = &fb_display[vc->vc_num]; - int scroll_partial = info->flags & FBINFO_PARTIAL_PAN_OK; if (fbcon_is_inactive(vc, info)) return true; @@ -1704,249 +1466,32 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, case SM_UP: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - if (logo_shown >= 0) - goto redraw_up; - switch (p->scrollmode) { - case SCROLL_MOVE: - fbcon_redraw_blit(vc, info, p, t, b - t - count, - count); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - (b - count)), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - - case SCROLL_WRAP_MOVE: - if (b - t - count > 3 * vc->vc_rows >> 2) { - if (t > 0) - fbcon_bmove(vc, 0, 0, count, 0, t, - vc->vc_cols); - ywrap_up(vc, count); - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b - count, 0, b, 0, - vc->vc_rows - b, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t + count, 0, t, 0, - b - t - count, vc->vc_cols); - else - goto redraw_up; - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_REDRAW: - if ((p->yscroll + count <= - 2 * (p->vrows - vc->vc_rows)) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (t > 0) - fbcon_redraw_move(vc, p, 0, t, count); - ypan_up_redraw(vc, t, count); - if (vc->vc_rows - b > 0) - fbcon_redraw_move(vc, p, b, - vc->vc_rows - b, b); - } else - fbcon_redraw_move(vc, p, t + count, b - t - count, t); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_MOVE: - if ((p->yscroll + count <= - 2 * (p->vrows - vc->vc_rows)) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (t > 0) - fbcon_bmove(vc, 0, 0, count, 0, t, - vc->vc_cols); - ypan_up(vc, count); - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b - count, 0, b, 0, - vc->vc_rows - b, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t + count, 0, t, 0, - b - t - count, vc->vc_cols); - else - goto redraw_up; - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - break; - - case SCROLL_REDRAW: - redraw_up: - fbcon_redraw(vc, p, t, b - t - count, - count * vc->vc_cols); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - (b - count)), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - } - break; + fbcon_redraw(vc, p, t, b - t - count, + count * vc->vc_cols); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + (b - count)), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; case SM_DOWN: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - if (logo_shown >= 0) - goto redraw_down; - switch (p->scrollmode) { - case SCROLL_MOVE: - fbcon_redraw_blit(vc, info, p, b - 1, b - t - count, - -count); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - t), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - - case SCROLL_WRAP_MOVE: - if (b - t - count > 3 * vc->vc_rows >> 2) { - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b, 0, b - count, 0, - vc->vc_rows - b, - vc->vc_cols); - ywrap_down(vc, count); - if (t > 0) - fbcon_bmove(vc, count, 0, 0, 0, t, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t, 0, t + count, 0, - b - t - count, vc->vc_cols); - else - goto redraw_down; - fbcon_clear(vc, t, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_MOVE: - if ((count - p->yscroll <= p->vrows - vc->vc_rows) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b, 0, b - count, 0, - vc->vc_rows - b, - vc->vc_cols); - ypan_down(vc, count); - if (t > 0) - fbcon_bmove(vc, count, 0, 0, 0, t, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t, 0, t + count, 0, - b - t - count, vc->vc_cols); - else - goto redraw_down; - fbcon_clear(vc, t, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_REDRAW: - if ((count - p->yscroll <= p->vrows - vc->vc_rows) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (vc->vc_rows - b > 0) - fbcon_redraw_move(vc, p, b, vc->vc_rows - b, - b - count); - ypan_down_redraw(vc, t, count); - if (t > 0) - fbcon_redraw_move(vc, p, count, t, 0); - } else - fbcon_redraw_move(vc, p, t, b - t - count, t + count); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - break; - - case SCROLL_REDRAW: - redraw_down: - fbcon_redraw(vc, p, b - 1, b - t - count, - -count * vc->vc_cols); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - t), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - } + fbcon_redraw(vc, p, b - 1, b - t - count, + -count * vc->vc_cols); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + t), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; } return false; } - -static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, - int height, int width) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - if (fbcon_is_inactive(vc, info)) - return; - - if (!width || !height) - return; - - /* Split blits that cross physical y_wrap case. - * Pathological case involves 4 blits, better to use recursive - * code rather than unrolled case - * - * Recursive invocations don't need to erase the cursor over and - * over again, so we use fbcon_bmove_rec() - */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, - p->vrows - p->yscroll); -} - -static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, - int dy, int dx, int height, int width, u_int y_break) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - u_int b; - - if (sy < y_break && sy + height > y_break) { - b = y_break - sy; - if (dy < sy) { /* Avoid trashing self */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - } else { - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - } - return; - } - - if (dy < y_break && dy + height > y_break) { - b = y_break - dy; - if (dy < sy) { /* Avoid trashing self */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - } else { - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - } - return; - } - ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, - height, width); -} - static void updatescrollmode(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) @@ -2119,21 +1664,7 @@ static int fbcon_switch(struct vc_data *vc) updatescrollmode(p, info, vc); - switch (p->scrollmode) { - case SCROLL_WRAP_MOVE: - scrollback_phys_max = p->vrows - vc->vc_rows; - break; - case SCROLL_PAN_MOVE: - case SCROLL_PAN_REDRAW: - scrollback_phys_max = p->vrows - 2 * vc->vc_rows; - if (scrollback_phys_max < 0) - scrollback_phys_max = 0; - break; - default: - scrollback_phys_max = 0; - break; - } - + scrollback_phys_max = 0; scrollback_max = 0; scrollback_current = 0; diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 9315b360c898..a00603b4451a 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -29,7 +29,6 @@ struct fbcon_display { /* Filled in by the low-level console driver */ const u_char *fontdata; int userfont; /* != 0 if fontdata kmalloc()ed */ - u_short scrollmode; /* Scroll Method */ u_short inverse; /* != 0 text black on white as default */ short yscroll; /* Hardware scrolling */ int vrows; /* number of virtual rows */ @@ -52,8 +51,6 @@ struct fbcon_display { }; struct fbcon_ops { - void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width); void (*clear)(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width); void (*putcs)(struct vc_data *vc, struct fb_info *info, @@ -152,62 +149,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) - /* - * Scroll Method - */ - -/* There are several methods fbcon can use to move text around the screen: - * - * Operation Pan Wrap - *--------------------------------------------- - * SCROLL_MOVE copyarea No No - * SCROLL_PAN_MOVE copyarea Yes No - * SCROLL_WRAP_MOVE copyarea No Yes - * SCROLL_REDRAW imageblit No No - * SCROLL_PAN_REDRAW imageblit Yes No - * SCROLL_WRAP_REDRAW imageblit No Yes - * - * (SCROLL_WRAP_REDRAW is not implemented yet) - * - * In general, fbcon will choose the best scrolling - * method based on the rule below: - * - * Pan/Wrap > accel imageblit > accel copyarea > - * soft imageblit > (soft copyarea) - * - * Exception to the rule: Pan + accel copyarea is - * preferred over Pan + accel imageblit. - * - * The above is typical for PCI/AGP cards. Unless - * overridden, fbcon will never use soft copyarea. - * - * If you need to override the above rule, set the - * appropriate flags in fb_info->flags. For example, - * to prefer copyarea over imageblit, set - * FBINFO_READS_FAST. - * - * Other notes: - * + use the hardware engine to move the text - * (hw-accelerated copyarea() and fillrect()) - * + use hardware-supported panning on a large virtual screen - * + amifb can not only pan, but also wrap the display by N lines - * (i.e. visible line i = physical line (i+N) % yres). - * + read what's already rendered on the screen and - * write it in a different place (this is cfb_copyarea()) - * + re-render the text to the screen - * - * Whether to use wrapping or panning can only be figured out at - * runtime (when we know whether our font height is a multiple - * of the pan/wrap step) - * - */ - -#define SCROLL_MOVE 0x001 -#define SCROLL_PAN_MOVE 0x002 -#define SCROLL_WRAP_MOVE 0x003 -#define SCROLL_REDRAW 0x004 -#define SCROLL_PAN_REDRAW 0x005 - #ifdef CONFIG_FB_TILEBLITTING extern void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info); #endif diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index 9cd2c4b05c32..ffa78936eaab 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -59,31 +59,12 @@ static void ccw_update_attr(u8 *dst, u8 *src, int attribute, } } - -static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fbcon_ops *ops = info->fbcon_par; - struct fb_copyarea area; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - - area.sx = sy * vc->vc_font.height; - area.sy = vyres - ((sx + width) * vc->vc_font.width); - area.dx = dy * vc->vc_font.height; - area.dy = vyres - ((dx + width) * vc->vc_font.width); - area.width = height * vc->vc_font.height; - area.height = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = sy * vc->vc_font.height; @@ -140,7 +121,7 @@ static void ccw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; if (!ops->fontbuffer) return; @@ -229,7 +210,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; if (!ops->fontbuffer) return; @@ -387,7 +368,7 @@ static int ccw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; u32 yoffset; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; int err; yoffset = (vyres - info->var.yres) - ops->var.xoffset; @@ -402,7 +383,6 @@ static int ccw_update_start(struct fb_info *info) void fbcon_rotate_ccw(struct fbcon_ops *ops) { - ops->bmove = ccw_bmove; ops->clear = ccw_clear; ops->putcs = ccw_putcs; ops->clear_margins = ccw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index 88d89fad3f05..92e5b7fb51ee 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -44,31 +44,12 @@ static void cw_update_attr(u8 *dst, u8 *src, int attribute, } } - -static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fbcon_ops *ops = info->fbcon_par; - struct fb_copyarea area; - u32 vxres = GETVXRES(ops->p->scrollmode, info); - - area.sx = vxres - ((sy + height) * vc->vc_font.height); - area.sy = sx * vc->vc_font.width; - area.dx = vxres - ((dy + height) * vc->vc_font.height); - area.dy = dx * vc->vc_font.width; - area.width = height * vc->vc_font.height; - area.height = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = vxres - ((sy + height) * vc->vc_font.height); @@ -125,7 +106,7 @@ static void cw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -212,7 +193,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -369,7 +350,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, static int cw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; u32 xoffset; int err; @@ -385,7 +366,6 @@ static int cw_update_start(struct fb_info *info) void fbcon_rotate_cw(struct fbcon_ops *ops) { - ops->bmove = cw_bmove; ops->clear = cw_clear; ops->putcs = cw_putcs; ops->clear_margins = cw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_rotate.h b/drivers/video/fbdev/core/fbcon_rotate.h index e233444cda66..b528b2e54283 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.h +++ b/drivers/video/fbdev/core/fbcon_rotate.h @@ -11,15 +11,6 @@ #ifndef _FBCON_ROTATE_H #define _FBCON_ROTATE_H -#define GETVYRES(s,i) ({ \ - (s == SCROLL_REDRAW || s == SCROLL_MOVE) ? \ - (i)->var.yres : (i)->var.yres_virtual; }) - -#define GETVXRES(s,i) ({ \ - (s == SCROLL_REDRAW || s == SCROLL_MOVE || !(i)->fix.xpanstep) ? \ - (i)->var.xres : (i)->var.xres_virtual; }) - - static inline int pattern_test_bit(u32 x, u32 y, u32 pitch, const char *pat) { u32 tmp = (y * pitch) + x, index = tmp / 8, bit = tmp % 8; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 8d5e66b1bdfb..09619bd8e021 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -44,33 +44,13 @@ static void ud_update_attr(u8 *dst, u8 *src, int attribute, } } - -static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fbcon_ops *ops = info->fbcon_par; - struct fb_copyarea area; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); - - area.sy = vyres - ((sy + height) * vc->vc_font.height); - area.sx = vxres - ((sx + width) * vc->vc_font.width); - area.dy = vyres - ((dy + height) * vc->vc_font.height); - area.dx = vxres - ((dx + width) * vc->vc_font.width); - area.height = height * vc->vc_font.height; - area.width = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; region.color = attr_bgcol_ec(bgshift,vc,info); region.dy = vyres - ((sy + height) * vc->vc_font.height); @@ -162,8 +142,8 @@ static void ud_putcs(struct vc_data *vc, struct fb_info *info, u32 mod = vc->vc_font.width % 8, cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -259,8 +239,8 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -410,8 +390,8 @@ static int ud_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; int xoffset, yoffset; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; int err; xoffset = vxres - info->var.xres - ops->var.xoffset; @@ -429,7 +409,6 @@ static int ud_update_start(struct fb_info *info) void fbcon_rotate_ud(struct fbcon_ops *ops) { - ops->bmove = ud_bmove; ops->clear = ud_clear; ops->putcs = ud_putcs; ops->clear_margins = ud_clear_margins; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 7420d2c16e47..826175ad88a2 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1702,8 +1702,11 @@ static void do_unregister_framebuffer(struct fb_info *fb_info) { unlink_framebuffer(fb_info); if (fb_info->pixmap.addr && - (fb_info->pixmap.flags & FB_PIXMAP_DEFAULT)) + (fb_info->pixmap.flags & FB_PIXMAP_DEFAULT)) { kfree(fb_info->pixmap.addr); + fb_info->pixmap.addr = NULL; + } + fb_destroy_modelist(&fb_info->modelist); registered_fb[fb_info->node] = NULL; num_registered_fb--; diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 2768eff247ba..72af95053bcb 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -16,21 +16,6 @@ #include <asm/types.h> #include "fbcon.h" -static void tile_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fb_tilearea area; - - area.sx = sx; - area.sy = sy; - area.dx = dx; - area.dy = dy; - area.height = height; - area.width = width; - - info->tileops->fb_tilecopy(info, &area); -} - static void tile_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -133,7 +118,6 @@ void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info) struct fb_tilemap map; struct fbcon_ops *ops = info->fbcon_par; - ops->bmove = tile_bmove; ops->clear = tile_clear; ops->putcs = tile_putcs; ops->clear_margins = tile_clear_margins; diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c index bcacfb6934fa..0fe922f726e9 100644 --- a/drivers/video/fbdev/skeletonfb.c +++ b/drivers/video/fbdev/skeletonfb.c @@ -505,15 +505,15 @@ void xxxfb_fillrect(struct fb_info *p, const struct fb_fillrect *region) } /** - * xxxfb_copyarea - REQUIRED function. Can use generic routines if - * non acclerated hardware and packed pixel based. + * xxxfb_copyarea - OBSOLETE function. * Copies one area of the screen to another area. + * Will be deleted in a future version * * @info: frame buffer structure that represents a single frame buffer * @area: Structure providing the data to copy the framebuffer contents * from one region to another. * - * This drawing operation copies a rectangular area from one area of the + * This drawing operation copied a rectangular area from one area of the * screen to another area. */ void xxxfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) @@ -645,9 +645,9 @@ static const struct fb_ops xxxfb_ops = { .fb_setcolreg = xxxfb_setcolreg, .fb_blank = xxxfb_blank, .fb_pan_display = xxxfb_pan_display, - .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ - .fb_copyarea = xxxfb_copyarea, /* Needed !!! */ - .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ + .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ + .fb_copyarea = xxxfb_copyarea, /* Obsolete */ + .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ .fb_cursor = xxxfb_cursor, /* Optional !!! */ .fb_sync = xxxfb_sync, .fb_ioctl = xxxfb_ioctl, diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index bf59faeb3de1..9d222ba17ec6 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -496,16 +496,18 @@ config S3C2410_WATCHDOG select WATCHDOG_CORE select MFD_SYSCON if ARCH_EXYNOS help - Watchdog timer block in the Samsung SoCs. This will reboot - the system when the timer expires with the watchdog enabled. + Watchdog timer block in the Samsung S3C24xx, S3C64xx, S5Pv210 and + Exynos SoCs. This will reboot the system when the timer expires with + the watchdog enabled. The driver is limited by the speed of the system's PCLK signal, so with reasonably fast systems (PCLK around 50-66MHz) then watchdog intervals of over approximately 20seconds are unavailable. + Choose Y/M here only if you build for such Samsung SoC. The driver can be built as a module by choosing M, and will - be called s3c2410_wdt + be called s3c2410_wdt. config SA1100_WATCHDOG tristate "SA1100/PXA2xx watchdog" @@ -561,22 +563,6 @@ config PNX4008_WATCHDOG Say N if you are unsure. -config IOP_WATCHDOG - tristate "IOP Watchdog" - depends on ARCH_IOP13XX - select WATCHDOG_NOWAYOUT if (ARCH_IOP32X || ARCH_IOP33X) - help - Say Y here if to include support for the watchdog timer - in the Intel IOP3XX & IOP13XX I/O Processors. This driver can - be built as a module by choosing M. The module will - be called iop_wdt. - - Note: The IOP13XX watchdog does an Internal Bus Reset which will - affect both cores and the peripherals of the IOP. The ATU-X - and/or ATUe configuration registers will remain intact, but if - operating as an Root Complex and/or Central Resource, the PCI-X - and/or PCIe busses will also be reset. THIS IS A VERY BIG HAMMER. - config DAVINCI_WATCHDOG tristate "DaVinci watchdog" depends on ARCH_DAVINCI || ARCH_KEYSTONE || COMPILE_TEST @@ -743,17 +729,17 @@ config IMX7ULP_WDT To compile this driver as a module, choose M here: the module will be called imx7ulp_wdt. -config UX500_WATCHDOG - tristate "ST-Ericsson Ux500 watchdog" +config DB500_WATCHDOG + tristate "ST-Ericsson DB800 watchdog" depends on MFD_DB8500_PRCMU select WATCHDOG_CORE default y help Say Y here to include Watchdog timer support for the watchdog - existing in the prcmu of ST-Ericsson Ux500 series platforms. + existing in the prcmu of ST-Ericsson DB8500 platform. To compile this driver as a module, choose M here: the - module will be called ux500_wdt. + module will be called db500_wdt. config RETU_WATCHDOG tristate "Retu watchdog" @@ -1052,6 +1038,7 @@ config EBC_C384_WDT config F71808E_WDT tristate "Fintek F718xx, F818xx Super I/O Watchdog" depends on X86 + select WATCHDOG_CORE help This is the driver for the hardware watchdog on the Fintek F71808E, F71862FG, F71868, F71869, F71882FG, F71889FG, F81803, F81865, and @@ -1679,7 +1666,7 @@ config SIBYTE_WDOG config AR7_WDT tristate "TI AR7 Watchdog Timer" - depends on AR7 || (MIPS && COMPILE_TEST) + depends on AR7 || (MIPS && 32BIT && COMPILE_TEST) help Hardware driver for the TI AR7 Watchdog Timer. diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index 1bd2d6f37c53..2ee97064145b 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -56,7 +56,6 @@ obj-$(CONFIG_SAMA5D4_WATCHDOG) += sama5d4_wdt.o obj-$(CONFIG_DW_WATCHDOG) += dw_wdt.o obj-$(CONFIG_EP93XX_WATCHDOG) += ep93xx_wdt.o obj-$(CONFIG_PNX4008_WATCHDOG) += pnx4008_wdt.o -obj-$(CONFIG_IOP_WATCHDOG) += iop_wdt.o obj-$(CONFIG_DAVINCI_WATCHDOG) += davinci_wdt.o obj-$(CONFIG_K3_RTI_WATCHDOG) += rti_wdt.o obj-$(CONFIG_ORION_WATCHDOG) += orion_wdt.o @@ -69,7 +68,7 @@ obj-$(CONFIG_TS72XX_WATCHDOG) += ts72xx_wdt.o obj-$(CONFIG_IMX2_WDT) += imx2_wdt.o obj-$(CONFIG_IMX_SC_WDT) += imx_sc_wdt.o obj-$(CONFIG_IMX7ULP_WDT) += imx7ulp_wdt.o -obj-$(CONFIG_UX500_WATCHDOG) += ux500_wdt.o +obj-$(CONFIG_DB500_WATCHDOG) += db8500_wdt.o obj-$(CONFIG_RETU_WATCHDOG) += retu_wdt.o obj-$(CONFIG_BCM2835_WDT) += bcm2835_wdt.o obj-$(CONFIG_MOXART_WDT) += moxart_wdt.o diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c index ff37dc91057d..743e171d97a3 100644 --- a/drivers/watchdog/ar7_wdt.c +++ b/drivers/watchdog/ar7_wdt.c @@ -63,8 +63,6 @@ static DEFINE_SPINLOCK(wdt_lock); /* XXX currently fixed, allows max margin ~68.72 secs */ #define prescale_value 0xffff -/* Resource of the WDT registers */ -static struct resource *ar7_regs_wdt; /* Pointer to the remapped WDT IO space */ static struct ar7_wdt *ar7_wdt; @@ -265,9 +263,7 @@ static int ar7_wdt_probe(struct platform_device *pdev) { int rc; - ar7_regs_wdt = - platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); - ar7_wdt = devm_ioremap_resource(&pdev->dev, ar7_regs_wdt); + ar7_wdt = devm_platform_ioremap_resource_byname(pdev, "regs"); if (IS_ERR(ar7_wdt)) return PTR_ERR(ar7_wdt); diff --git a/drivers/watchdog/bcm63xx_wdt.c b/drivers/watchdog/bcm63xx_wdt.c index 7cdb25363ea0..56cc262571a5 100644 --- a/drivers/watchdog/bcm63xx_wdt.c +++ b/drivers/watchdog/bcm63xx_wdt.c @@ -207,6 +207,8 @@ static long bcm63xx_wdt_ioctl(struct file *file, unsigned int cmd, bcm63xx_wdt_pet(); + fallthrough; + case WDIOC_GETTIMEOUT: return put_user(wdt_time, p); diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c index 706fb09c2f24..f02cbd530538 100644 --- a/drivers/watchdog/da9062_wdt.c +++ b/drivers/watchdog/da9062_wdt.c @@ -117,6 +117,13 @@ static int da9062_wdt_ping(struct watchdog_device *wdd) struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); int ret; + /* + * Prevent pings from occurring late in system poweroff/reboot sequence + * and possibly locking out restart handler from accessing i2c bus. + */ + if (system_state > SYSTEM_RUNNING) + return 0; + ret = da9062_reset_watchdog_timer(wdt); if (ret) dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n", diff --git a/drivers/watchdog/da9063_wdt.c b/drivers/watchdog/da9063_wdt.c index 423584252606..d79ce64e26a9 100644 --- a/drivers/watchdog/da9063_wdt.c +++ b/drivers/watchdog/da9063_wdt.c @@ -121,6 +121,13 @@ static int da9063_wdt_ping(struct watchdog_device *wdd) struct da9063 *da9063 = watchdog_get_drvdata(wdd); int ret; + /* + * Prevent pings from occurring late in system poweroff/reboot sequence + * and possibly locking out restart handler from accessing i2c bus. + */ + if (system_state > SYSTEM_RUNNING) + return 0; + ret = regmap_write(da9063->regmap, DA9063_REG_CONTROL_F, DA9063_WATCHDOG); if (ret) diff --git a/drivers/watchdog/ux500_wdt.c b/drivers/watchdog/db8500_wdt.c index 072758106865..6ed8b63d310d 100644 --- a/drivers/watchdog/ux500_wdt.c +++ b/drivers/watchdog/db8500_wdt.c @@ -15,7 +15,6 @@ #include <linux/uaccess.h> #include <linux/watchdog.h> #include <linux/platform_device.h> -#include <linux/platform_data/ux500_wdt.h> #include <linux/mfd/dbx500-prcmu.h> @@ -23,7 +22,6 @@ #define WATCHDOG_MIN 0 #define WATCHDOG_MAX28 268435 /* 28 bit resolution in ms == 268435.455 s */ -#define WATCHDOG_MAX32 4294967 /* 32 bit resolution in ms == 4294967.295 s */ static unsigned int timeout = WATCHDOG_TIMEOUT; module_param(timeout, uint, 0); @@ -37,67 +35,60 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -static int ux500_wdt_start(struct watchdog_device *wdd) +static int db8500_wdt_start(struct watchdog_device *wdd) { return prcmu_enable_a9wdog(PRCMU_WDOG_ALL); } -static int ux500_wdt_stop(struct watchdog_device *wdd) +static int db8500_wdt_stop(struct watchdog_device *wdd) { return prcmu_disable_a9wdog(PRCMU_WDOG_ALL); } -static int ux500_wdt_keepalive(struct watchdog_device *wdd) +static int db8500_wdt_keepalive(struct watchdog_device *wdd) { return prcmu_kick_a9wdog(PRCMU_WDOG_ALL); } -static int ux500_wdt_set_timeout(struct watchdog_device *wdd, +static int db8500_wdt_set_timeout(struct watchdog_device *wdd, unsigned int timeout) { - ux500_wdt_stop(wdd); + db8500_wdt_stop(wdd); prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); - ux500_wdt_start(wdd); + db8500_wdt_start(wdd); return 0; } -static const struct watchdog_info ux500_wdt_info = { +static const struct watchdog_info db8500_wdt_info = { .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, - .identity = "Ux500 WDT", + .identity = "DB8500 WDT", .firmware_version = 1, }; -static const struct watchdog_ops ux500_wdt_ops = { +static const struct watchdog_ops db8500_wdt_ops = { .owner = THIS_MODULE, - .start = ux500_wdt_start, - .stop = ux500_wdt_stop, - .ping = ux500_wdt_keepalive, - .set_timeout = ux500_wdt_set_timeout, + .start = db8500_wdt_start, + .stop = db8500_wdt_stop, + .ping = db8500_wdt_keepalive, + .set_timeout = db8500_wdt_set_timeout, }; -static struct watchdog_device ux500_wdt = { - .info = &ux500_wdt_info, - .ops = &ux500_wdt_ops, +static struct watchdog_device db8500_wdt = { + .info = &db8500_wdt_info, + .ops = &db8500_wdt_ops, .min_timeout = WATCHDOG_MIN, - .max_timeout = WATCHDOG_MAX32, + .max_timeout = WATCHDOG_MAX28, }; -static int ux500_wdt_probe(struct platform_device *pdev) +static int db8500_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; int ret; - struct ux500_wdt_data *pdata = dev_get_platdata(dev); - if (pdata) { - if (pdata->timeout > 0) - timeout = pdata->timeout; - if (pdata->has_28_bits_resolution) - ux500_wdt.max_timeout = WATCHDOG_MAX28; - } - - ux500_wdt.parent = dev; - watchdog_set_nowayout(&ux500_wdt, nowayout); + timeout = 600; /* Default to 10 minutes */ + db8500_wdt.parent = dev; + watchdog_set_nowayout(&db8500_wdt, nowayout); /* disable auto off on sleep */ prcmu_config_a9wdog(PRCMU_WDOG_CPU1, false); @@ -105,7 +96,7 @@ static int ux500_wdt_probe(struct platform_device *pdev) /* set HW initial value */ prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); - ret = devm_watchdog_register_device(dev, &ux500_wdt); + ret = devm_watchdog_register_device(dev, &db8500_wdt); if (ret) return ret; @@ -115,47 +106,47 @@ static int ux500_wdt_probe(struct platform_device *pdev) } #ifdef CONFIG_PM -static int ux500_wdt_suspend(struct platform_device *pdev, +static int db8500_wdt_suspend(struct platform_device *pdev, pm_message_t state) { - if (watchdog_active(&ux500_wdt)) { - ux500_wdt_stop(&ux500_wdt); + if (watchdog_active(&db8500_wdt)) { + db8500_wdt_stop(&db8500_wdt); prcmu_config_a9wdog(PRCMU_WDOG_CPU1, true); prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); - ux500_wdt_start(&ux500_wdt); + db8500_wdt_start(&db8500_wdt); } return 0; } -static int ux500_wdt_resume(struct platform_device *pdev) +static int db8500_wdt_resume(struct platform_device *pdev) { - if (watchdog_active(&ux500_wdt)) { - ux500_wdt_stop(&ux500_wdt); + if (watchdog_active(&db8500_wdt)) { + db8500_wdt_stop(&db8500_wdt); prcmu_config_a9wdog(PRCMU_WDOG_CPU1, false); prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); - ux500_wdt_start(&ux500_wdt); + db8500_wdt_start(&db8500_wdt); } return 0; } #else -#define ux500_wdt_suspend NULL -#define ux500_wdt_resume NULL +#define db8500_wdt_suspend NULL +#define db8500_wdt_resume NULL #endif -static struct platform_driver ux500_wdt_driver = { - .probe = ux500_wdt_probe, - .suspend = ux500_wdt_suspend, - .resume = ux500_wdt_resume, +static struct platform_driver db8500_wdt_driver = { + .probe = db8500_wdt_probe, + .suspend = db8500_wdt_suspend, + .resume = db8500_wdt_resume, .driver = { - .name = "ux500_wdt", + .name = "db8500_wdt", }, }; -module_platform_driver(ux500_wdt_driver); +module_platform_driver(db8500_wdt_driver); MODULE_AUTHOR("Jonas Aaberg <jonas.aberg@stericsson.com>"); -MODULE_DESCRIPTION("Ux500 Watchdog Driver"); +MODULE_DESCRIPTION("DB8500 Watchdog Driver"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:ux500_wdt"); +MODULE_ALIAS("platform:db8500_wdt"); diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index f60beec1bbae..ee90c5f943f9 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -9,16 +9,11 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/err.h> -#include <linux/fs.h> #include <linux/init.h> #include <linux/io.h> #include <linux/ioport.h> -#include <linux/miscdevice.h> #include <linux/module.h> -#include <linux/mutex.h> -#include <linux/notifier.h> -#include <linux/reboot.h> -#include <linux/uaccess.h> +#include <linux/platform_device.h> #include <linux/watchdog.h> #define DRVNAME "f71808e_wdt" @@ -81,7 +76,6 @@ static unsigned short force_id; module_param(force_id, ushort, 0); MODULE_PARM_DESC(force_id, "Override the detected device ID"); -static const int max_timeout = WATCHDOG_MAX_TIMEOUT; static int timeout = WATCHDOG_TIMEOUT; /* default timeout in seconds */ module_param(timeout, int, 0); MODULE_PARM_DESC(timeout, @@ -113,7 +107,7 @@ MODULE_PARM_DESC(start_withtimeout, "Start watchdog timer on module load with" enum chips { f71808fg, f71858fg, f71862fg, f71868, f71869, f71882fg, f71889fg, f81803, f81865, f81866}; -static const char *f71808e_names[] = { +static const char * const fintek_wdt_names[] = { "f71808fg", "f71858fg", "f71862fg", @@ -136,24 +130,20 @@ static inline int superio_enter(int base); static inline void superio_select(int base, int ld); static inline void superio_exit(int base); -struct watchdog_data { +struct fintek_wdt { + struct watchdog_device wdd; unsigned short sioaddr; enum chips type; - unsigned long opened; - struct mutex lock; - char expect_close; struct watchdog_info ident; - unsigned short timeout; u8 timer_val; /* content for the wd_time register */ char minutes_mode; u8 pulse_val; /* pulse width flag */ char pulse_mode; /* enable pulse output mode? */ - char caused_reboot; /* last reboot was by the watchdog */ }; -static struct watchdog_data watchdog = { - .lock = __MUTEX_INITIALIZER(watchdog.lock), +struct fintek_wdt_pdata { + enum chips type; }; /* Super I/O functions */ @@ -218,156 +208,142 @@ static inline void superio_exit(int base) release_region(base, 2); } -static int watchdog_set_timeout(int timeout) +static int fintek_wdt_set_timeout(struct watchdog_device *wdd, unsigned int timeout) { - if (timeout <= 0 - || timeout > max_timeout) { - pr_err("watchdog timeout out of range\n"); - return -EINVAL; - } - - mutex_lock(&watchdog.lock); + struct fintek_wdt *wd = watchdog_get_drvdata(wdd); - watchdog.timeout = timeout; if (timeout > 0xff) { - watchdog.timer_val = DIV_ROUND_UP(timeout, 60); - watchdog.minutes_mode = true; + wd->timer_val = DIV_ROUND_UP(timeout, 60); + wd->minutes_mode = true; + timeout = wd->timer_val * 60; } else { - watchdog.timer_val = timeout; - watchdog.minutes_mode = false; + wd->timer_val = timeout; + wd->minutes_mode = false; } - mutex_unlock(&watchdog.lock); + wdd->timeout = timeout; return 0; } -static int watchdog_set_pulse_width(unsigned int pw) +static int fintek_wdt_set_pulse_width(struct fintek_wdt *wd, unsigned int pw) { - int err = 0; unsigned int t1 = 25, t2 = 125, t3 = 5000; - if (watchdog.type == f71868) { + if (wd->type == f71868) { t1 = 30; t2 = 150; t3 = 6000; } - mutex_lock(&watchdog.lock); - if (pw <= 1) { - watchdog.pulse_val = 0; + wd->pulse_val = 0; } else if (pw <= t1) { - watchdog.pulse_val = 1; + wd->pulse_val = 1; } else if (pw <= t2) { - watchdog.pulse_val = 2; + wd->pulse_val = 2; } else if (pw <= t3) { - watchdog.pulse_val = 3; + wd->pulse_val = 3; } else { pr_err("pulse width out of range\n"); - err = -EINVAL; - goto exit_unlock; + return -EINVAL; } - watchdog.pulse_mode = pw; + wd->pulse_mode = pw; -exit_unlock: - mutex_unlock(&watchdog.lock); - return err; + return 0; } -static int watchdog_keepalive(void) +static int fintek_wdt_keepalive(struct watchdog_device *wdd) { - int err = 0; + struct fintek_wdt *wd = watchdog_get_drvdata(wdd); + int err; - mutex_lock(&watchdog.lock); - err = superio_enter(watchdog.sioaddr); + err = superio_enter(wd->sioaddr); if (err) - goto exit_unlock; - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); + return err; + superio_select(wd->sioaddr, SIO_F71808FG_LD_WDT); - if (watchdog.minutes_mode) + if (wd->minutes_mode) /* select minutes for timer units */ - superio_set_bit(watchdog.sioaddr, F71808FG_REG_WDT_CONF, + superio_set_bit(wd->sioaddr, F71808FG_REG_WDT_CONF, F71808FG_FLAG_WD_UNIT); else /* select seconds for timer units */ - superio_clear_bit(watchdog.sioaddr, F71808FG_REG_WDT_CONF, + superio_clear_bit(wd->sioaddr, F71808FG_REG_WDT_CONF, F71808FG_FLAG_WD_UNIT); /* Set timer value */ - superio_outb(watchdog.sioaddr, F71808FG_REG_WD_TIME, - watchdog.timer_val); + superio_outb(wd->sioaddr, F71808FG_REG_WD_TIME, + wd->timer_val); - superio_exit(watchdog.sioaddr); + superio_exit(wd->sioaddr); -exit_unlock: - mutex_unlock(&watchdog.lock); - return err; + return 0; } -static int watchdog_start(void) +static int fintek_wdt_start(struct watchdog_device *wdd) { + struct fintek_wdt *wd = watchdog_get_drvdata(wdd); int err; u8 tmp; /* Make sure we don't die as soon as the watchdog is enabled below */ - err = watchdog_keepalive(); + err = fintek_wdt_keepalive(wdd); if (err) return err; - mutex_lock(&watchdog.lock); - err = superio_enter(watchdog.sioaddr); + err = superio_enter(wd->sioaddr); if (err) - goto exit_unlock; - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); + return err; + superio_select(wd->sioaddr, SIO_F71808FG_LD_WDT); /* Watchdog pin configuration */ - switch (watchdog.type) { + switch (wd->type) { case f71808fg: /* Set pin 21 to GPIO23/WDTRST#, then to WDTRST# */ - superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT2, 3); - superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 3); + superio_clear_bit(wd->sioaddr, SIO_REG_MFUNCT2, 3); + superio_clear_bit(wd->sioaddr, SIO_REG_MFUNCT3, 3); break; case f71862fg: if (f71862fg_pin == 63) { /* SPI must be disabled first to use this pin! */ - superio_clear_bit(watchdog.sioaddr, SIO_REG_ROM_ADDR_SEL, 6); - superio_set_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 4); + superio_clear_bit(wd->sioaddr, SIO_REG_ROM_ADDR_SEL, 6); + superio_set_bit(wd->sioaddr, SIO_REG_MFUNCT3, 4); } else if (f71862fg_pin == 56) { - superio_set_bit(watchdog.sioaddr, SIO_REG_MFUNCT1, 1); + superio_set_bit(wd->sioaddr, SIO_REG_MFUNCT1, 1); } break; case f71868: case f71869: /* GPIO14 --> WDTRST# */ - superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT1, 4); + superio_clear_bit(wd->sioaddr, SIO_REG_MFUNCT1, 4); break; case f71882fg: /* Set pin 56 to WDTRST# */ - superio_set_bit(watchdog.sioaddr, SIO_REG_MFUNCT1, 1); + superio_set_bit(wd->sioaddr, SIO_REG_MFUNCT1, 1); break; case f71889fg: /* set pin 40 to WDTRST# */ - superio_outb(watchdog.sioaddr, SIO_REG_MFUNCT3, - superio_inb(watchdog.sioaddr, SIO_REG_MFUNCT3) & 0xcf); + superio_outb(wd->sioaddr, SIO_REG_MFUNCT3, + superio_inb(wd->sioaddr, SIO_REG_MFUNCT3) & 0xcf); break; case f81803: /* Enable TSI Level register bank */ - superio_clear_bit(watchdog.sioaddr, SIO_REG_CLOCK_SEL, 3); + superio_clear_bit(wd->sioaddr, SIO_REG_CLOCK_SEL, 3); /* Set pin 27 to WDTRST# */ - superio_outb(watchdog.sioaddr, SIO_REG_TSI_LEVEL_SEL, 0x5f & - superio_inb(watchdog.sioaddr, SIO_REG_TSI_LEVEL_SEL)); + superio_outb(wd->sioaddr, SIO_REG_TSI_LEVEL_SEL, 0x5f & + superio_inb(wd->sioaddr, SIO_REG_TSI_LEVEL_SEL)); break; case f81865: /* Set pin 70 to WDTRST# */ - superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 5); + superio_clear_bit(wd->sioaddr, SIO_REG_MFUNCT3, 5); break; case f81866: @@ -377,12 +353,12 @@ static int watchdog_start(void) * BIT5: 0 -> WDTRST# * 1 -> GPIO15 */ - tmp = superio_inb(watchdog.sioaddr, SIO_F81866_REG_PORT_SEL); + tmp = superio_inb(wd->sioaddr, SIO_F81866_REG_PORT_SEL); tmp &= ~(BIT(3) | BIT(0)); tmp |= BIT(2); - superio_outb(watchdog.sioaddr, SIO_F81866_REG_PORT_SEL, tmp); + superio_outb(wd->sioaddr, SIO_F81866_REG_PORT_SEL, tmp); - superio_clear_bit(watchdog.sioaddr, SIO_F81866_REG_GPIO1, 5); + superio_clear_bit(wd->sioaddr, SIO_F81866_REG_GPIO1, 5); break; default: @@ -394,300 +370,114 @@ static int watchdog_start(void) goto exit_superio; } - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); - superio_set_bit(watchdog.sioaddr, SIO_REG_ENABLE, 0); + superio_select(wd->sioaddr, SIO_F71808FG_LD_WDT); + superio_set_bit(wd->sioaddr, SIO_REG_ENABLE, 0); - if (watchdog.type == f81865 || watchdog.type == f81866) - superio_set_bit(watchdog.sioaddr, F81865_REG_WDO_CONF, + if (wd->type == f81865 || wd->type == f81866) + superio_set_bit(wd->sioaddr, F81865_REG_WDO_CONF, F81865_FLAG_WDOUT_EN); else - superio_set_bit(watchdog.sioaddr, F71808FG_REG_WDO_CONF, + superio_set_bit(wd->sioaddr, F71808FG_REG_WDO_CONF, F71808FG_FLAG_WDOUT_EN); - superio_set_bit(watchdog.sioaddr, F71808FG_REG_WDT_CONF, + superio_set_bit(wd->sioaddr, F71808FG_REG_WDT_CONF, F71808FG_FLAG_WD_EN); - if (watchdog.pulse_mode) { + if (wd->pulse_mode) { /* Select "pulse" output mode with given duration */ - u8 wdt_conf = superio_inb(watchdog.sioaddr, + u8 wdt_conf = superio_inb(wd->sioaddr, F71808FG_REG_WDT_CONF); /* Set WD_PSWIDTH bits (1:0) */ - wdt_conf = (wdt_conf & 0xfc) | (watchdog.pulse_val & 0x03); + wdt_conf = (wdt_conf & 0xfc) | (wd->pulse_val & 0x03); /* Set WD_PULSE to "pulse" mode */ wdt_conf |= BIT(F71808FG_FLAG_WD_PULSE); - superio_outb(watchdog.sioaddr, F71808FG_REG_WDT_CONF, + superio_outb(wd->sioaddr, F71808FG_REG_WDT_CONF, wdt_conf); } else { /* Select "level" output mode */ - superio_clear_bit(watchdog.sioaddr, F71808FG_REG_WDT_CONF, + superio_clear_bit(wd->sioaddr, F71808FG_REG_WDT_CONF, F71808FG_FLAG_WD_PULSE); } exit_superio: - superio_exit(watchdog.sioaddr); -exit_unlock: - mutex_unlock(&watchdog.lock); + superio_exit(wd->sioaddr); return err; } -static int watchdog_stop(void) -{ - int err = 0; - - mutex_lock(&watchdog.lock); - err = superio_enter(watchdog.sioaddr); - if (err) - goto exit_unlock; - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); - - superio_clear_bit(watchdog.sioaddr, F71808FG_REG_WDT_CONF, - F71808FG_FLAG_WD_EN); - - superio_exit(watchdog.sioaddr); - -exit_unlock: - mutex_unlock(&watchdog.lock); - - return err; -} - -static int watchdog_get_status(void) -{ - int status = 0; - - mutex_lock(&watchdog.lock); - status = (watchdog.caused_reboot) ? WDIOF_CARDRESET : 0; - mutex_unlock(&watchdog.lock); - - return status; -} - -static bool watchdog_is_running(void) -{ - /* - * if we fail to determine the watchdog's status assume it to be - * running to be on the safe side - */ - bool is_running = true; - - mutex_lock(&watchdog.lock); - if (superio_enter(watchdog.sioaddr)) - goto exit_unlock; - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); - - is_running = (superio_inb(watchdog.sioaddr, SIO_REG_ENABLE) & BIT(0)) - && (superio_inb(watchdog.sioaddr, F71808FG_REG_WDT_CONF) - & BIT(F71808FG_FLAG_WD_EN)); - - superio_exit(watchdog.sioaddr); - -exit_unlock: - mutex_unlock(&watchdog.lock); - return is_running; -} - -/* /dev/watchdog api */ - -static int watchdog_open(struct inode *inode, struct file *file) +static int fintek_wdt_stop(struct watchdog_device *wdd) { + struct fintek_wdt *wd = watchdog_get_drvdata(wdd); int err; - /* If the watchdog is alive we don't need to start it again */ - if (test_and_set_bit(0, &watchdog.opened)) - return -EBUSY; - - err = watchdog_start(); - if (err) { - clear_bit(0, &watchdog.opened); + err = superio_enter(wd->sioaddr); + if (err) return err; - } - - if (nowayout) - __module_get(THIS_MODULE); + superio_select(wd->sioaddr, SIO_F71808FG_LD_WDT); - watchdog.expect_close = 0; - return stream_open(inode, file); -} + superio_clear_bit(wd->sioaddr, F71808FG_REG_WDT_CONF, + F71808FG_FLAG_WD_EN); -static int watchdog_release(struct inode *inode, struct file *file) -{ - clear_bit(0, &watchdog.opened); + superio_exit(wd->sioaddr); - if (!watchdog.expect_close) { - watchdog_keepalive(); - pr_crit("Unexpected close, not stopping watchdog!\n"); - } else if (!nowayout) { - watchdog_stop(); - } return 0; } -/* - * watchdog_write: - * @file: file handle to the watchdog - * @buf: buffer to write - * @count: count of bytes - * @ppos: pointer to the position to write. No seeks allowed - * - * A write to a watchdog device is defined as a keepalive signal. Any - * write of data will do, as we we don't define content meaning. - */ - -static ssize_t watchdog_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static bool fintek_wdt_is_running(struct fintek_wdt *wd, u8 wdt_conf) { - if (count) { - if (!nowayout) { - size_t i; - - /* In case it was set long ago */ - bool expect_close = false; - - for (i = 0; i != count; i++) { - char c; - if (get_user(c, buf + i)) - return -EFAULT; - if (c == 'V') - expect_close = true; - } - - /* Properly order writes across fork()ed processes */ - mutex_lock(&watchdog.lock); - watchdog.expect_close = expect_close; - mutex_unlock(&watchdog.lock); - } - - /* someone wrote to us, we should restart timer */ - watchdog_keepalive(); - } - return count; + return (superio_inb(wd->sioaddr, SIO_REG_ENABLE) & BIT(0)) + && (wdt_conf & BIT(F71808FG_FLAG_WD_EN)); } -/* - * watchdog_ioctl: - * @inode: inode of the device - * @file: file handle to the device - * @cmd: watchdog command - * @arg: argument pointer - * - * The watchdog API defines a common set of functions for all watchdogs - * according to their available features. - */ -static long watchdog_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - int status; - int new_options; - int new_timeout; - union { - struct watchdog_info __user *ident; - int __user *i; - } uarg; - - uarg.i = (int __user *)arg; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(uarg.ident, &watchdog.ident, - sizeof(watchdog.ident)) ? -EFAULT : 0; - - case WDIOC_GETSTATUS: - status = watchdog_get_status(); - if (status < 0) - return status; - return put_user(status, uarg.i); - - case WDIOC_GETBOOTSTATUS: - return put_user(0, uarg.i); - - case WDIOC_SETOPTIONS: - if (get_user(new_options, uarg.i)) - return -EFAULT; - - if (new_options & WDIOS_DISABLECARD) - watchdog_stop(); - - if (new_options & WDIOS_ENABLECARD) - return watchdog_start(); - fallthrough; - - case WDIOC_KEEPALIVE: - watchdog_keepalive(); - return 0; - - case WDIOC_SETTIMEOUT: - if (get_user(new_timeout, uarg.i)) - return -EFAULT; - - if (watchdog_set_timeout(new_timeout)) - return -EINVAL; - - watchdog_keepalive(); - fallthrough; - - case WDIOC_GETTIMEOUT: - return put_user(watchdog.timeout, uarg.i); - - default: - return -ENOTTY; - - } -} +static const struct watchdog_ops fintek_wdt_ops = { + .owner = THIS_MODULE, + .start = fintek_wdt_start, + .stop = fintek_wdt_stop, + .ping = fintek_wdt_keepalive, + .set_timeout = fintek_wdt_set_timeout, +}; -static int watchdog_notify_sys(struct notifier_block *this, unsigned long code, - void *unused) +static int fintek_wdt_probe(struct platform_device *pdev) { - if (code == SYS_DOWN || code == SYS_HALT) - watchdog_stop(); - return NOTIFY_DONE; -} + struct device *dev = &pdev->dev; + struct fintek_wdt_pdata *pdata; + struct watchdog_device *wdd; + struct fintek_wdt *wd; + int wdt_conf, err = 0; + struct resource *res; + int sioaddr; -static const struct file_operations watchdog_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .open = watchdog_open, - .release = watchdog_release, - .write = watchdog_write, - .unlocked_ioctl = watchdog_ioctl, - .compat_ioctl = compat_ptr_ioctl, -}; + res = platform_get_resource(pdev, IORESOURCE_IO, 0); + if (!res) + return -ENXIO; -static struct miscdevice watchdog_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &watchdog_fops, -}; + sioaddr = res->start; -static struct notifier_block watchdog_notifier = { - .notifier_call = watchdog_notify_sys, -}; + wd = devm_kzalloc(dev, sizeof(*wd), GFP_KERNEL); + if (!wd) + return -ENOMEM; -static int __init watchdog_init(int sioaddr) -{ - int wdt_conf, err = 0; + pdata = dev->platform_data; - /* No need to lock watchdog.lock here because no entry points - * into the module have been registered yet. - */ - watchdog.sioaddr = sioaddr; - watchdog.ident.options = WDIOF_MAGICCLOSE - | WDIOF_KEEPALIVEPING - | WDIOF_CARDRESET; + wd->type = pdata->type; + wd->sioaddr = sioaddr; + wd->ident.options = WDIOF_SETTIMEOUT + | WDIOF_MAGICCLOSE + | WDIOF_KEEPALIVEPING + | WDIOF_CARDRESET; - snprintf(watchdog.ident.identity, - sizeof(watchdog.ident.identity), "%s watchdog", - f71808e_names[watchdog.type]); + snprintf(wd->ident.identity, + sizeof(wd->ident.identity), "%s watchdog", + fintek_wdt_names[wd->type]); err = superio_enter(sioaddr); if (err) return err; - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); + superio_select(wd->sioaddr, SIO_F71808FG_LD_WDT); wdt_conf = superio_inb(sioaddr, F71808FG_REG_WDT_CONF); - watchdog.caused_reboot = wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS); /* * We don't want WDTMOUT_STS to stick around till regular reboot. @@ -696,84 +486,54 @@ static int __init watchdog_init(int sioaddr) superio_outb(sioaddr, F71808FG_REG_WDT_CONF, wdt_conf | BIT(F71808FG_FLAG_WDTMOUT_STS)); - superio_exit(sioaddr); + wdd = &wd->wdd; - err = watchdog_set_timeout(timeout); - if (err) - return err; - err = watchdog_set_pulse_width(pulse_width); - if (err) - return err; + if (fintek_wdt_is_running(wd, wdt_conf)) + set_bit(WDOG_HW_RUNNING, &wdd->status); - err = register_reboot_notifier(&watchdog_notifier); - if (err) - return err; + superio_exit(sioaddr); - err = misc_register(&watchdog_miscdev); - if (err) { - pr_err("cannot register miscdev on minor=%d\n", - watchdog_miscdev.minor); - goto exit_reboot; - } + wdd->parent = dev; + wdd->info = &wd->ident; + wdd->ops = &fintek_wdt_ops; + wdd->min_timeout = 1; + wdd->max_timeout = WATCHDOG_MAX_TIMEOUT; - if (start_withtimeout) { - if (start_withtimeout <= 0 - || start_withtimeout > max_timeout) { - pr_err("starting timeout out of range\n"); - err = -EINVAL; - goto exit_miscdev; - } + watchdog_set_drvdata(wdd, wd); + watchdog_set_nowayout(wdd, nowayout); + watchdog_stop_on_unregister(wdd); + watchdog_stop_on_reboot(wdd); + watchdog_init_timeout(wdd, start_withtimeout ?: timeout, NULL); - err = watchdog_start(); - if (err) { - pr_err("cannot start watchdog timer\n"); - goto exit_miscdev; - } + if (wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS)) + wdd->bootstatus = WDIOF_CARDRESET; - mutex_lock(&watchdog.lock); - err = superio_enter(sioaddr); - if (err) - goto exit_unlock; - superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT); + /* + * WATCHDOG_HANDLE_BOOT_ENABLED can result in keepalive being directly + * called without a set_timeout before, so it needs to be done here + * unconditionally. + */ + fintek_wdt_set_timeout(wdd, wdd->timeout); + fintek_wdt_set_pulse_width(wd, pulse_width); - if (start_withtimeout > 0xff) { - /* select minutes for timer units */ - superio_set_bit(sioaddr, F71808FG_REG_WDT_CONF, - F71808FG_FLAG_WD_UNIT); - superio_outb(sioaddr, F71808FG_REG_WD_TIME, - DIV_ROUND_UP(start_withtimeout, 60)); - } else { - /* select seconds for timer units */ - superio_clear_bit(sioaddr, F71808FG_REG_WDT_CONF, - F71808FG_FLAG_WD_UNIT); - superio_outb(sioaddr, F71808FG_REG_WD_TIME, - start_withtimeout); + if (start_withtimeout) { + err = fintek_wdt_start(wdd); + if (err) { + dev_err(dev, "cannot start watchdog timer\n"); + return err; } - superio_exit(sioaddr); - mutex_unlock(&watchdog.lock); - - if (nowayout) - __module_get(THIS_MODULE); - - pr_info("watchdog started with initial timeout of %u sec\n", - start_withtimeout); + set_bit(WDOG_HW_RUNNING, &wdd->status); + dev_info(dev, "watchdog started with initial timeout of %u sec\n", + start_withtimeout); } - return 0; - -exit_unlock: - mutex_unlock(&watchdog.lock); -exit_miscdev: - misc_deregister(&watchdog_miscdev); -exit_reboot: - unregister_reboot_notifier(&watchdog_notifier); - - return err; + return devm_watchdog_register_device(dev, wdd); } -static int __init f71808e_find(int sioaddr) +static int __init fintek_wdt_find(int sioaddr) { + enum chips type; u16 devid; int err = superio_enter(sioaddr); if (err) @@ -789,36 +549,36 @@ static int __init f71808e_find(int sioaddr) devid = force_id ? force_id : superio_inw(sioaddr, SIO_REG_DEVID); switch (devid) { case SIO_F71808_ID: - watchdog.type = f71808fg; + type = f71808fg; break; case SIO_F71862_ID: - watchdog.type = f71862fg; + type = f71862fg; break; case SIO_F71868_ID: - watchdog.type = f71868; + type = f71868; break; case SIO_F71869_ID: case SIO_F71869A_ID: - watchdog.type = f71869; + type = f71869; break; case SIO_F71882_ID: - watchdog.type = f71882fg; + type = f71882fg; break; case SIO_F71889_ID: - watchdog.type = f71889fg; + type = f71889fg; break; case SIO_F71858_ID: /* Confirmed (by datasheet) not to have a watchdog. */ err = -ENODEV; goto exit; case SIO_F81803_ID: - watchdog.type = f81803; + type = f81803; break; case SIO_F81865_ID: - watchdog.type = f81865; + type = f81865; break; case SIO_F81866_ID: - watchdog.type = f81866; + type = f81866; break; default: pr_info("Unrecognized Fintek device: %04x\n", @@ -828,17 +588,29 @@ static int __init f71808e_find(int sioaddr) } pr_info("Found %s watchdog chip, revision %d\n", - f71808e_names[watchdog.type], + fintek_wdt_names[type], (int)superio_inb(sioaddr, SIO_REG_DEVREV)); + exit: superio_exit(sioaddr); - return err; + return err ? err : type; } -static int __init f71808e_init(void) +static struct platform_driver fintek_wdt_driver = { + .probe = fintek_wdt_probe, + .driver = { + .name = DRVNAME, + }, +}; + +static struct platform_device *fintek_wdt_pdev; + +static int __init fintek_wdt_init(void) { static const unsigned short addrs[] = { 0x2e, 0x4e }; - int err = -ENODEV; + struct fintek_wdt_pdata pdata; + struct resource wdt_res = {}; + int ret; int i; if (f71862fg_pin != 63 && f71862fg_pin != 56) { @@ -847,29 +619,42 @@ static int __init f71808e_init(void) } for (i = 0; i < ARRAY_SIZE(addrs); i++) { - err = f71808e_find(addrs[i]); - if (err == 0) + ret = fintek_wdt_find(addrs[i]); + if (ret >= 0) break; } if (i == ARRAY_SIZE(addrs)) - return err; + return ret; - return watchdog_init(addrs[i]); + pdata.type = ret; + + platform_driver_register(&fintek_wdt_driver); + + wdt_res.name = "superio port"; + wdt_res.flags = IORESOURCE_IO; + wdt_res.start = addrs[i]; + wdt_res.end = addrs[i] + 1; + + fintek_wdt_pdev = platform_device_register_resndata(NULL, DRVNAME, -1, + &wdt_res, 1, + &pdata, sizeof(pdata)); + if (IS_ERR(fintek_wdt_pdev)) { + platform_driver_unregister(&fintek_wdt_driver); + return PTR_ERR(fintek_wdt_pdev); + } + + return 0; } -static void __exit f71808e_exit(void) +static void __exit fintek_wdt_exit(void) { - if (watchdog_is_running()) { - pr_warn("Watchdog timer still running, stopping it\n"); - watchdog_stop(); - } - misc_deregister(&watchdog_miscdev); - unregister_reboot_notifier(&watchdog_notifier); + platform_device_unregister(fintek_wdt_pdev); + platform_driver_unregister(&fintek_wdt_driver); } MODULE_DESCRIPTION("F71808E Watchdog Driver"); MODULE_AUTHOR("Giel van Schijndel <me@mortis.eu>"); MODULE_LICENSE("GPL"); -module_init(f71808e_init); -module_exit(f71808e_exit); +module_init(fintek_wdt_init); +module_exit(fintek_wdt_exit); diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index ced2fc0deb8c..3f2f4343644f 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -94,7 +94,6 @@ struct iTCO_wdt_private { * NO_REBOOT flag is Memory-Mapped GCS register bit 5 (TCO version 2), * or memory-mapped PMC register bit 4 (TCO version 3). */ - struct resource *gcs_pmc_res; unsigned long __iomem *gcs_pmc; /* the lock for io operations */ spinlock_t io_lock; @@ -424,6 +423,16 @@ static unsigned int iTCO_wdt_get_timeleft(struct watchdog_device *wd_dev) return time_left; } +static void iTCO_wdt_set_running(struct iTCO_wdt_private *p) +{ + u16 val; + + /* Bit 11: TCO Timer Halt -> 0 = The TCO timer is * enabled */ + val = inw(TCO1_CNT(p)); + if (!(val & BIT(11))) + set_bit(WDOG_HW_RUNNING, &p->wddev.status); +} + /* * Kernel Interfaces */ @@ -497,10 +506,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev) */ if (p->iTCO_version >= 2 && p->iTCO_version < 6 && !pdata->no_reboot_use_pmc) { - p->gcs_pmc_res = platform_get_resource(pdev, - IORESOURCE_MEM, - ICH_RES_MEM_GCS_PMC); - p->gcs_pmc = devm_ioremap_resource(dev, p->gcs_pmc_res); + p->gcs_pmc = devm_platform_ioremap_resource(pdev, ICH_RES_MEM_GCS_PMC); if (IS_ERR(p->gcs_pmc)) return PTR_ERR(p->gcs_pmc); } @@ -566,8 +572,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev) watchdog_set_drvdata(&p->wddev, p); platform_set_drvdata(pdev, p); - /* Make sure the watchdog is not running */ - iTCO_wdt_stop(&p->wddev); + iTCO_wdt_set_running(p); /* Check that the heartbeat value is within it's range; if not reset to the default */ diff --git a/drivers/watchdog/iop_wdt.c b/drivers/watchdog/iop_wdt.c deleted file mode 100644 index 6bf68d4750de..000000000000 --- a/drivers/watchdog/iop_wdt.c +++ /dev/null @@ -1,250 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * drivers/char/watchdog/iop_wdt.c - * - * WDT driver for Intel I/O Processors - * Copyright (C) 2005, Intel Corporation. - * - * Based on ixp4xx driver, Copyright 2004 (c) MontaVista, Software, Inc. - * - * Curt E Bruns <curt.e.bruns@intel.com> - * Peter Milne <peter.milne@d-tacq.com> - * Dan Williams <dan.j.williams@intel.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/fs.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/miscdevice.h> -#include <linux/watchdog.h> -#include <linux/uaccess.h> -#include <mach/hardware.h> - -static bool nowayout = WATCHDOG_NOWAYOUT; -static unsigned long wdt_status; -static unsigned long boot_status; -static DEFINE_SPINLOCK(wdt_lock); - -#define WDT_IN_USE 0 -#define WDT_OK_TO_CLOSE 1 -#define WDT_ENABLED 2 - -static unsigned long iop_watchdog_timeout(void) -{ - return (0xffffffffUL / get_iop_tick_rate()); -} - -/** - * wdt_supports_disable - determine if we are accessing a iop13xx watchdog - * or iop3xx by whether it has a disable command - */ -static int wdt_supports_disable(void) -{ - int can_disable; - - if (IOP_WDTCR_EN_ARM != IOP_WDTCR_DIS_ARM) - can_disable = 1; - else - can_disable = 0; - - return can_disable; -} - -static void wdt_enable(void) -{ - /* Arm and enable the Timer to starting counting down from 0xFFFF.FFFF - * Takes approx. 10.7s to timeout - */ - spin_lock(&wdt_lock); - write_wdtcr(IOP_WDTCR_EN_ARM); - write_wdtcr(IOP_WDTCR_EN); - spin_unlock(&wdt_lock); -} - -/* returns 0 if the timer was successfully disabled */ -static int wdt_disable(void) -{ - /* Stop Counting */ - if (wdt_supports_disable()) { - spin_lock(&wdt_lock); - write_wdtcr(IOP_WDTCR_DIS_ARM); - write_wdtcr(IOP_WDTCR_DIS); - clear_bit(WDT_ENABLED, &wdt_status); - spin_unlock(&wdt_lock); - pr_info("Disabled\n"); - return 0; - } else - return 1; -} - -static int iop_wdt_open(struct inode *inode, struct file *file) -{ - if (test_and_set_bit(WDT_IN_USE, &wdt_status)) - return -EBUSY; - - clear_bit(WDT_OK_TO_CLOSE, &wdt_status); - wdt_enable(); - set_bit(WDT_ENABLED, &wdt_status); - return stream_open(inode, file); -} - -static ssize_t iop_wdt_write(struct file *file, const char *data, size_t len, - loff_t *ppos) -{ - if (len) { - if (!nowayout) { - size_t i; - - clear_bit(WDT_OK_TO_CLOSE, &wdt_status); - - for (i = 0; i != len; i++) { - char c; - - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') - set_bit(WDT_OK_TO_CLOSE, &wdt_status); - } - } - wdt_enable(); - } - return len; -} - -static const struct watchdog_info ident = { - .options = WDIOF_CARDRESET | WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING, - .identity = "iop watchdog", -}; - -static long iop_wdt_ioctl(struct file *file, - unsigned int cmd, unsigned long arg) -{ - int options; - int ret = -ENOTTY; - int __user *argp = (int __user *)arg; - - switch (cmd) { - case WDIOC_GETSUPPORT: - if (copy_to_user(argp, &ident, sizeof(ident))) - ret = -EFAULT; - else - ret = 0; - break; - - case WDIOC_GETSTATUS: - ret = put_user(0, argp); - break; - - case WDIOC_GETBOOTSTATUS: - ret = put_user(boot_status, argp); - break; - - case WDIOC_SETOPTIONS: - if (get_user(options, (int *)arg)) - return -EFAULT; - - if (options & WDIOS_DISABLECARD) { - if (!nowayout) { - if (wdt_disable() == 0) { - set_bit(WDT_OK_TO_CLOSE, &wdt_status); - ret = 0; - } else - ret = -ENXIO; - } else - ret = 0; - } - if (options & WDIOS_ENABLECARD) { - wdt_enable(); - ret = 0; - } - break; - - case WDIOC_KEEPALIVE: - wdt_enable(); - ret = 0; - break; - - case WDIOC_GETTIMEOUT: - ret = put_user(iop_watchdog_timeout(), argp); - break; - } - return ret; -} - -static int iop_wdt_release(struct inode *inode, struct file *file) -{ - int state = 1; - if (test_bit(WDT_OK_TO_CLOSE, &wdt_status)) - if (test_bit(WDT_ENABLED, &wdt_status)) - state = wdt_disable(); - - /* if the timer is not disabled reload and notify that we are still - * going down - */ - if (state != 0) { - wdt_enable(); - pr_crit("Device closed unexpectedly - reset in %lu seconds\n", - iop_watchdog_timeout()); - } - - clear_bit(WDT_IN_USE, &wdt_status); - clear_bit(WDT_OK_TO_CLOSE, &wdt_status); - - return 0; -} - -static const struct file_operations iop_wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .write = iop_wdt_write, - .unlocked_ioctl = iop_wdt_ioctl, - .compat_ioctl = compat_ptr_ioctl, - .open = iop_wdt_open, - .release = iop_wdt_release, -}; - -static struct miscdevice iop_wdt_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &iop_wdt_fops, -}; - -static int __init iop_wdt_init(void) -{ - int ret; - - /* check if the reset was caused by the watchdog timer */ - boot_status = (read_rcsr() & IOP_RCSR_WDT) ? WDIOF_CARDRESET : 0; - - /* Configure Watchdog Timeout to cause an Internal Bus (IB) Reset - * NOTE: An IB Reset will Reset both cores in the IOP342 - */ - write_wdtsr(IOP13XX_WDTCR_IB_RESET); - - /* Register after we have the device set up so we cannot race - with an open */ - ret = misc_register(&iop_wdt_miscdev); - if (ret == 0) - pr_info("timeout %lu sec\n", iop_watchdog_timeout()); - - return ret; -} - -static void __exit iop_wdt_exit(void) -{ - misc_deregister(&iop_wdt_miscdev); -} - -module_init(iop_wdt_init); -module_exit(iop_wdt_exit); - -module_param(nowayout, bool, 0); -MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started"); - -MODULE_AUTHOR("Curt E Bruns <curt.e.bruns@intel.com>"); -MODULE_DESCRIPTION("iop watchdog timer driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c index 5a9ca10fbcfa..945f5e65db57 100644 --- a/drivers/watchdog/meson_gxbb_wdt.c +++ b/drivers/watchdog/meson_gxbb_wdt.c @@ -29,6 +29,16 @@ #define GXBB_WDT_TCNT_SETUP_MASK (BIT(16) - 1) #define GXBB_WDT_TCNT_CNT_SHIFT 16 +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, 0); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +static unsigned int timeout; +module_param(timeout, uint, 0); +MODULE_PARM_DESC(timeout, "Watchdog heartbeat in seconds=" + __MODULE_STRING(DEFAULT_TIMEOUT) ")"); + struct meson_gxbb_wdt { void __iomem *reg_base; struct watchdog_device wdt_dev; @@ -175,6 +185,8 @@ static int meson_gxbb_wdt_probe(struct platform_device *pdev) data->wdt_dev.max_hw_heartbeat_ms = GXBB_WDT_TCNT_SETUP_MASK; data->wdt_dev.min_timeout = 1; data->wdt_dev.timeout = DEFAULT_TIMEOUT; + watchdog_init_timeout(&data->wdt_dev, timeout, dev); + watchdog_set_nowayout(&data->wdt_dev, nowayout); watchdog_set_drvdata(&data->wdt_dev, data); /* Setup with 1ms timebase */ diff --git a/drivers/watchdog/mlx_wdt.c b/drivers/watchdog/mlx_wdt.c index 54193369e85c..9c5b6616fc87 100644 --- a/drivers/watchdog/mlx_wdt.c +++ b/drivers/watchdog/mlx_wdt.c @@ -100,9 +100,8 @@ static int mlxreg_wdt_ping(struct watchdog_device *wdd) struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd); struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->ping_idx]; - return regmap_update_bits_base(wdt->regmap, reg_data->reg, - ~reg_data->mask, BIT(reg_data->bit), - NULL, false, true); + return regmap_write_bits(wdt->regmap, reg_data->reg, ~reg_data->mask, + BIT(reg_data->bit)); } static int mlxreg_wdt_set_timeout(struct watchdog_device *wdd, diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c index 3d208d627fb0..543cf38bd04e 100644 --- a/drivers/watchdog/mtk_wdt.c +++ b/drivers/watchdog/mtk_wdt.c @@ -65,6 +65,7 @@ struct mtk_wdt_dev { void __iomem *wdt_base; spinlock_t lock; /* protects WDT_SWSYSRST reg */ struct reset_controller_dev rcdev; + bool disable_wdt_extrst; }; struct mtk_wdt_data { @@ -256,6 +257,8 @@ static int mtk_wdt_start(struct watchdog_device *wdt_dev) reg |= (WDT_MODE_IRQ_EN | WDT_MODE_DUAL_EN); else reg &= ~(WDT_MODE_IRQ_EN | WDT_MODE_DUAL_EN); + if (mtk_wdt->disable_wdt_extrst) + reg &= ~WDT_MODE_EXRST_EN; reg |= (WDT_MODE_EN | WDT_MODE_KEY); iowrite32(reg, wdt_base + WDT_MODE); @@ -381,6 +384,10 @@ static int mtk_wdt_probe(struct platform_device *pdev) if (err) return err; } + + mtk_wdt->disable_wdt_extrst = + of_property_read_bool(dev->of_node, "mediatek,disable-extrst"); + return 0; } diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c index 359302f71f7e..117bc2a8eb0a 100644 --- a/drivers/watchdog/rti_wdt.c +++ b/drivers/watchdog/rti_wdt.c @@ -194,7 +194,6 @@ static int rti_wdt_probe(struct platform_device *pdev) { int ret = 0; struct device *dev = &pdev->dev; - struct resource *wdt_mem; struct watchdog_device *wdd; struct rti_wdt_device *wdt; struct clk *clk; @@ -246,8 +245,7 @@ static int rti_wdt_probe(struct platform_device *pdev) watchdog_set_nowayout(wdd, 1); watchdog_set_restart_priority(wdd, 128); - wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - wdt->base = devm_ioremap_resource(dev, wdt_mem); + wdt->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(wdt->base)) { ret = PTR_ERR(wdt->base); goto err_iomap; diff --git a/drivers/watchdog/rza_wdt.c b/drivers/watchdog/rza_wdt.c index 7b6c365f7cd3..fe6c2ed35e04 100644 --- a/drivers/watchdog/rza_wdt.c +++ b/drivers/watchdog/rza_wdt.c @@ -189,8 +189,8 @@ static int rza_wdt_probe(struct platform_device *pdev) return -ENOENT; } - priv->wdev.info = &rza_wdt_ident, - priv->wdev.ops = &rza_wdt_ops, + priv->wdev.info = &rza_wdt_ident; + priv->wdev.ops = &rza_wdt_ops; priv->wdev.parent = dev; priv->cks = (u8)(uintptr_t) of_device_get_match_data(dev); diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index a730ecbf78cd..dd9a744f82f8 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -10,6 +10,7 @@ * https://www.kernelconcepts.de * * See AMD Publication 43009 "AMD SB700/710/750 Register Reference Guide", + * AMD Publication 44413 "AMD SP5100 Register Reference Guide" * AMD Publication 45482 "AMD SB800-Series Southbridges Register * Reference Guide" * AMD Publication 48751 "BIOS and Kernel Developer’s Guide (BKDG) @@ -144,6 +145,13 @@ static int tco_timer_set_timeout(struct watchdog_device *wdd, return 0; } +static unsigned int tco_timer_get_timeleft(struct watchdog_device *wdd) +{ + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); + + return readl(SP5100_WDT_COUNT(tco->tcobase)); +} + static u8 sp5100_tco_read_pm_reg8(u8 index) { outb(index, SP5100_IO_PM_INDEX_REG); @@ -386,6 +394,7 @@ static const struct watchdog_ops sp5100_tco_wdt_ops = { .stop = tco_timer_stop, .ping = tco_timer_ping, .set_timeout = tco_timer_set_timeout, + .get_timeleft = tco_timer_get_timeleft, }; static int sp5100_tco_probe(struct platform_device *pdev) diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index a3436c296c97..570a71509d2a 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -237,10 +237,8 @@ static int stm32_iwdg_probe(struct platform_device *pdev) /* This is the timer base. */ wdt->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(wdt->regs)) { - dev_err(dev, "Could not get resource\n"); + if (IS_ERR(wdt->regs)) return PTR_ERR(wdt->regs); - } ret = stm32_iwdg_clk_init(pdev, wdt); if (ret) diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c index b50757882a98..6cf82922d3fb 100644 --- a/drivers/watchdog/sunxi_wdt.c +++ b/drivers/watchdog/sunxi_wdt.c @@ -48,6 +48,7 @@ struct sunxi_wdt_reg { u8 wdt_timeout_shift; u8 wdt_reset_mask; u8 wdt_reset_val; + u32 wdt_key_val; }; struct sunxi_wdt_dev { @@ -91,12 +92,14 @@ static int sunxi_wdt_restart(struct watchdog_device *wdt_dev, val = readl(wdt_base + regs->wdt_cfg); val &= ~(regs->wdt_reset_mask); val |= regs->wdt_reset_val; + val |= regs->wdt_key_val; writel(val, wdt_base + regs->wdt_cfg); /* Set lowest timeout and enable watchdog */ val = readl(wdt_base + regs->wdt_mode); val &= ~(WDT_TIMEOUT_MASK << regs->wdt_timeout_shift); val |= WDT_MODE_EN; + val |= regs->wdt_key_val; writel(val, wdt_base + regs->wdt_mode); /* @@ -109,6 +112,7 @@ static int sunxi_wdt_restart(struct watchdog_device *wdt_dev, mdelay(5); val = readl(wdt_base + regs->wdt_mode); val |= WDT_MODE_EN; + val |= regs->wdt_key_val; writel(val, wdt_base + regs->wdt_mode); } return 0; @@ -141,6 +145,7 @@ static int sunxi_wdt_set_timeout(struct watchdog_device *wdt_dev, reg = readl(wdt_base + regs->wdt_mode); reg &= ~(WDT_TIMEOUT_MASK << regs->wdt_timeout_shift); reg |= wdt_timeout_map[timeout] << regs->wdt_timeout_shift; + reg |= regs->wdt_key_val; writel(reg, wdt_base + regs->wdt_mode); sunxi_wdt_ping(wdt_dev); @@ -154,7 +159,7 @@ static int sunxi_wdt_stop(struct watchdog_device *wdt_dev) void __iomem *wdt_base = sunxi_wdt->wdt_base; const struct sunxi_wdt_reg *regs = sunxi_wdt->wdt_regs; - writel(0, wdt_base + regs->wdt_mode); + writel(regs->wdt_key_val, wdt_base + regs->wdt_mode); return 0; } @@ -176,11 +181,13 @@ static int sunxi_wdt_start(struct watchdog_device *wdt_dev) reg = readl(wdt_base + regs->wdt_cfg); reg &= ~(regs->wdt_reset_mask); reg |= regs->wdt_reset_val; + reg |= regs->wdt_key_val; writel(reg, wdt_base + regs->wdt_cfg); /* Enable watchdog */ reg = readl(wdt_base + regs->wdt_mode); reg |= WDT_MODE_EN; + reg |= regs->wdt_key_val; writel(reg, wdt_base + regs->wdt_mode); return 0; @@ -220,9 +227,20 @@ static const struct sunxi_wdt_reg sun6i_wdt_reg = { .wdt_reset_val = 0x01, }; +static const struct sunxi_wdt_reg sun20i_wdt_reg = { + .wdt_ctrl = 0x10, + .wdt_cfg = 0x14, + .wdt_mode = 0x18, + .wdt_timeout_shift = 4, + .wdt_reset_mask = 0x03, + .wdt_reset_val = 0x01, + .wdt_key_val = 0x16aa0000, +}; + static const struct of_device_id sunxi_wdt_dt_ids[] = { { .compatible = "allwinner,sun4i-a10-wdt", .data = &sun4i_wdt_reg }, { .compatible = "allwinner,sun6i-a31-wdt", .data = &sun6i_wdt_reg }, + { .compatible = "allwinner,sun20i-d1-wdt", .data = &sun20i_wdt_reg }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sunxi_wdt_dt_ids); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 1b2c3aca6887..a1b11c62da9e 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -181,10 +181,34 @@ config SWIOTLB_XEN select DMA_OPS select SWIOTLB +config XEN_PCI_STUB + bool + +config XEN_PCIDEV_STUB + tristate "Xen PCI-device stub driver" + depends on PCI && !X86 && XEN + depends on XEN_BACKEND + select XEN_PCI_STUB + default m + help + The PCI device stub driver provides limited version of the PCI + device backend driver without para-virtualized support for guests. + If you select this to be a module, you will need to make sure no + other driver has bound to the device(s) you want to make visible to + other guests. + + The "hide" parameter (only applicable if backend driver is compiled + into the kernel) allows you to bind the PCI devices to this module + from the default device drivers. The argument is the list of PCI BDFs: + xen-pciback.hide=(03:00.0)(04:00.0) + + If in doubt, say m. + config XEN_PCIDEV_BACKEND tristate "Xen PCI-device backend driver" depends on PCI && X86 && XEN depends on XEN_BACKEND + select XEN_PCI_STUB default m help The PCI device backend driver allows the kernel to export arbitrary diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 3434593455b2..5aae66e638a7 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -24,7 +24,7 @@ obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o obj-$(CONFIG_XEN_PVHVM_GUEST) += platform-pci.o obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o obj-$(CONFIG_XEN_MCE_LOG) += mcelog.o -obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/ +obj-$(CONFIG_XEN_PCI_STUB) += xen-pciback/ obj-$(CONFIG_XEN_PRIVCMD) += xen-privcmd.o obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 3a50f097ed3e..ba2ea11e0d3d 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -58,6 +58,7 @@ #include <linux/percpu-defs.h> #include <linux/slab.h> #include <linux/sysctl.h> +#include <linux/moduleparam.h> #include <asm/page.h> #include <asm/tlb.h> @@ -73,9 +74,14 @@ #include <xen/page.h> #include <xen/mem-reservation.h> -static int xen_hotplug_unpopulated; +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "xen." + +static uint __read_mostly balloon_boot_timeout = 180; +module_param(balloon_boot_timeout, uint, 0444); #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +static int xen_hotplug_unpopulated; static struct ctl_table balloon_table[] = { { @@ -108,6 +114,8 @@ static struct ctl_table xen_root[] = { { } }; +#else +#define xen_hotplug_unpopulated 0 #endif /* @@ -125,12 +133,12 @@ static struct ctl_table xen_root[] = { * BP_ECANCELED: error, balloon operation canceled. */ -enum bp_state { +static enum bp_state { BP_DONE, BP_WAIT, BP_EAGAIN, BP_ECANCELED -}; +} balloon_state = BP_DONE; /* Main waiting point for xen-balloon thread. */ static DECLARE_WAIT_QUEUE_HEAD(balloon_thread_wq); @@ -199,18 +207,15 @@ static struct page *balloon_next_page(struct page *page) return list_entry(next, struct page, lru); } -static enum bp_state update_schedule(enum bp_state state) +static void update_schedule(void) { - if (state == BP_WAIT) - return BP_WAIT; - - if (state == BP_ECANCELED) - return BP_ECANCELED; + if (balloon_state == BP_WAIT || balloon_state == BP_ECANCELED) + return; - if (state == BP_DONE) { + if (balloon_state == BP_DONE) { balloon_stats.schedule_delay = 1; balloon_stats.retry_count = 1; - return BP_DONE; + return; } ++balloon_stats.retry_count; @@ -219,7 +224,8 @@ static enum bp_state update_schedule(enum bp_state state) balloon_stats.retry_count > balloon_stats.max_retry_count) { balloon_stats.schedule_delay = 1; balloon_stats.retry_count = 1; - return BP_ECANCELED; + balloon_state = BP_ECANCELED; + return; } balloon_stats.schedule_delay <<= 1; @@ -227,7 +233,7 @@ static enum bp_state update_schedule(enum bp_state state) if (balloon_stats.schedule_delay > balloon_stats.max_schedule_delay) balloon_stats.schedule_delay = balloon_stats.max_schedule_delay; - return BP_EAGAIN; + balloon_state = BP_EAGAIN; } #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG @@ -494,9 +500,9 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) * Stop waiting if either state is BP_DONE and ballooning action is * needed, or if the credit has changed while state is not BP_DONE. */ -static bool balloon_thread_cond(enum bp_state state, long credit) +static bool balloon_thread_cond(long credit) { - if (state == BP_DONE) + if (balloon_state == BP_DONE) credit = 0; return current_credit() != credit || kthread_should_stop(); @@ -510,13 +516,12 @@ static bool balloon_thread_cond(enum bp_state state, long credit) */ static int balloon_thread(void *unused) { - enum bp_state state = BP_DONE; long credit; unsigned long timeout; set_freezable(); for (;;) { - switch (state) { + switch (balloon_state) { case BP_DONE: case BP_ECANCELED: timeout = 3600 * HZ; @@ -532,7 +537,7 @@ static int balloon_thread(void *unused) credit = current_credit(); wait_event_freezable_timeout(balloon_thread_wq, - balloon_thread_cond(state, credit), timeout); + balloon_thread_cond(credit), timeout); if (kthread_should_stop()) return 0; @@ -543,22 +548,23 @@ static int balloon_thread(void *unused) if (credit > 0) { if (balloon_is_inflated()) - state = increase_reservation(credit); + balloon_state = increase_reservation(credit); else - state = reserve_additional_memory(); + balloon_state = reserve_additional_memory(); } if (credit < 0) { long n_pages; n_pages = min(-credit, si_mem_available()); - state = decrease_reservation(n_pages, GFP_BALLOON); - if (state == BP_DONE && n_pages != -credit && + balloon_state = decrease_reservation(n_pages, + GFP_BALLOON); + if (balloon_state == BP_DONE && n_pages != -credit && n_pages < totalreserve_pages) - state = BP_EAGAIN; + balloon_state = BP_EAGAIN; } - state = update_schedule(state); + update_schedule(); mutex_unlock(&balloon_mutex); @@ -575,7 +581,8 @@ void balloon_set_new_target(unsigned long target) } EXPORT_SYMBOL_GPL(balloon_set_new_target); -static int add_ballooned_pages(int nr_pages) +#ifndef CONFIG_XEN_UNPOPULATED_ALLOC +static int add_ballooned_pages(unsigned int nr_pages) { enum bp_state st; @@ -603,14 +610,14 @@ static int add_ballooned_pages(int nr_pages) } /** - * alloc_xenballooned_pages - get pages that have been ballooned out + * xen_alloc_unpopulated_pages - get pages that have been ballooned out * @nr_pages: Number of pages to get * @pages: pages returned * @return 0 on success, error otherwise */ -int alloc_xenballooned_pages(int nr_pages, struct page **pages) +int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) { - int pgno = 0; + unsigned int pgno = 0; struct page *page; int ret; @@ -645,7 +652,7 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) return 0; out_undo: mutex_unlock(&balloon_mutex); - free_xenballooned_pages(pgno, pages); + xen_free_unpopulated_pages(pgno, pages); /* * NB: free_xenballooned_pages will only subtract pgno pages, but since * target_unpopulated is incremented with nr_pages at the start we need @@ -654,16 +661,16 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) balloon_stats.target_unpopulated -= nr_pages - pgno; return ret; } -EXPORT_SYMBOL(alloc_xenballooned_pages); +EXPORT_SYMBOL(xen_alloc_unpopulated_pages); /** - * free_xenballooned_pages - return pages retrieved with get_ballooned_pages + * xen_free_unpopulated_pages - return pages retrieved with get_ballooned_pages * @nr_pages: Number of pages * @pages: pages to return */ -void free_xenballooned_pages(int nr_pages, struct page **pages) +void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages) { - int i; + unsigned int i; mutex_lock(&balloon_mutex); @@ -680,9 +687,9 @@ void free_xenballooned_pages(int nr_pages, struct page **pages) mutex_unlock(&balloon_mutex); } -EXPORT_SYMBOL(free_xenballooned_pages); +EXPORT_SYMBOL(xen_free_unpopulated_pages); -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) +#if defined(CONFIG_XEN_PV) static void __init balloon_add_region(unsigned long start_pfn, unsigned long pages) { @@ -705,6 +712,7 @@ static void __init balloon_add_region(unsigned long start_pfn, balloon_stats.total_pages += extra_pfn_end - start_pfn; } #endif +#endif static int __init balloon_init(void) { @@ -765,3 +773,38 @@ static int __init balloon_init(void) return 0; } subsys_initcall(balloon_init); + +static int __init balloon_wait_finish(void) +{ + long credit, last_credit = 0; + unsigned long last_changed = 0; + + if (!xen_domain()) + return -ENODEV; + + /* PV guests don't need to wait. */ + if (xen_pv_domain() || !current_credit()) + return 0; + + pr_notice("Waiting for initial ballooning down having finished.\n"); + + while ((credit = current_credit()) < 0) { + if (credit != last_credit) { + last_changed = jiffies; + last_credit = credit; + } + if (balloon_state == BP_ECANCELED) { + pr_warn_once("Initial ballooning failed, %ld pages need to be freed.\n", + -credit); + if (jiffies - last_changed >= HZ * balloon_boot_timeout) + panic("Initial ballooning failed!\n"); + } + + schedule_timeout_interruptible(HZ / 10); + } + + pr_notice("Initial ballooning down finished.\n"); + + return 0; +} +late_initcall_sync(balloon_wait_finish); diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c index 3782cf070338..24648836e0d4 100644 --- a/drivers/xen/mem-reservation.c +++ b/drivers/xen/mem-reservation.c @@ -35,6 +35,7 @@ void __xenmem_reservation_va_mapping_update(unsigned long count, for (i = 0; i < count; i++) { struct page *page = pages[i]; unsigned long pfn = page_to_pfn(page); + int ret; BUG_ON(!page); @@ -46,16 +47,10 @@ void __xenmem_reservation_va_mapping_update(unsigned long count, set_phys_to_machine(pfn, frames[i]); - /* Link back into the page tables if not highmem. */ - if (!PageHighMem(page)) { - int ret; - - ret = HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - mfn_pte(frames[i], PAGE_KERNEL), - 0); - BUG_ON(ret); - } + ret = HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + mfn_pte(frames[i], PAGE_KERNEL), 0); + BUG_ON(ret); } } EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_update); @@ -68,6 +63,7 @@ void __xenmem_reservation_va_mapping_reset(unsigned long count, for (i = 0; i < count; i++) { struct page *page = pages[i]; unsigned long pfn = page_to_pfn(page); + int ret; /* * We don't support PV MMU when Linux and Xen are using @@ -75,14 +71,11 @@ void __xenmem_reservation_va_mapping_reset(unsigned long count, */ BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); - if (!PageHighMem(page)) { - int ret; + ret = HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + __pte_ma(0), 0); + BUG_ON(ret); - ret = HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - __pte_ma(0), 0); - BUG_ON(ret); - } __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } } diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 224df03ce42e..2c890f4f2cbc 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -8,6 +8,7 @@ #include <linux/pci.h> #include <linux/acpi.h> #include <linux/pci-acpi.h> +#include <xen/pci.h> #include <xen/xen.h> #include <xen/interface/physdev.h> #include <xen/interface/xen.h> @@ -254,3 +255,78 @@ static int xen_mcfg_late(void) return 0; } #endif + +#ifdef CONFIG_XEN_DOM0 +struct xen_device_domain_owner { + domid_t domain; + struct pci_dev *dev; + struct list_head list; +}; + +static DEFINE_SPINLOCK(dev_domain_list_spinlock); +static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list); + +static struct xen_device_domain_owner *find_device(struct pci_dev *dev) +{ + struct xen_device_domain_owner *owner; + + list_for_each_entry(owner, &dev_domain_list, list) { + if (owner->dev == dev) + return owner; + } + return NULL; +} + +int xen_find_device_domain_owner(struct pci_dev *dev) +{ + struct xen_device_domain_owner *owner; + int domain = -ENODEV; + + spin_lock(&dev_domain_list_spinlock); + owner = find_device(dev); + if (owner) + domain = owner->domain; + spin_unlock(&dev_domain_list_spinlock); + return domain; +} +EXPORT_SYMBOL_GPL(xen_find_device_domain_owner); + +int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain) +{ + struct xen_device_domain_owner *owner; + + owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL); + if (!owner) + return -ENODEV; + + spin_lock(&dev_domain_list_spinlock); + if (find_device(dev)) { + spin_unlock(&dev_domain_list_spinlock); + kfree(owner); + return -EEXIST; + } + owner->domain = domain; + owner->dev = dev; + list_add_tail(&owner->list, &dev_domain_list); + spin_unlock(&dev_domain_list_spinlock); + return 0; +} +EXPORT_SYMBOL_GPL(xen_register_device_domain_owner); + +int xen_unregister_device_domain_owner(struct pci_dev *dev) +{ + struct xen_device_domain_owner *owner; + + spin_lock(&dev_domain_list_spinlock); + owner = find_device(dev); + if (!owner) { + spin_unlock(&dev_domain_list_spinlock); + return -ENODEV; + } + list_del(&owner->list); + spin_unlock(&dev_domain_list_spinlock); + kfree(owner); + return 0; +} +EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner); +#endif diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index b47fd8435061..d6f945fd4147 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -465,7 +465,6 @@ static int pvcalls_back_release_passive(struct xenbus_device *dev, write_unlock_bh(&mappass->sock->sk->sk_callback_lock); } sock_release(mappass->sock); - flush_workqueue(mappass->wq); destroy_workqueue(mappass->wq); kfree(mappass); diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index df7cab870be5..9cb61db67efd 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -450,7 +450,7 @@ static struct acpi_processor_performance __percpu *acpi_perf_data; static void free_acpi_perf_data(void) { - unsigned int i; + int i; /* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */ for_each_possible_cpu(i) @@ -462,7 +462,7 @@ static void free_acpi_perf_data(void) static int xen_upload_processor_pm_data(void) { struct acpi_processor *pr_backup = NULL; - unsigned int i; + int i; int rc = 0; pr_info("Uploading Xen processor PM info\n"); @@ -518,7 +518,7 @@ static struct syscore_ops xap_syscore_ops = { static int __init xen_acpi_processor_init(void) { - unsigned int i; + int i; int rc; if (!xen_initial_domain()) diff --git a/drivers/xen/xen-pciback/Makefile b/drivers/xen/xen-pciback/Makefile index e8d981d43235..d63df09de81c 100644 --- a/drivers/xen/xen-pciback/Makefile +++ b/drivers/xen/xen-pciback/Makefile @@ -1,5 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 + +# N.B. The below cannot be expressed with a single line using +# CONFIG_XEN_PCI_STUB as it always remains in "y" state, +# thus preventing the driver to be built as a module. +# Please note, that CONFIG_XEN_PCIDEV_BACKEND and +# CONFIG_XEN_PCIDEV_STUB are mutually exclusive. obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback.o +obj-$(CONFIG_XEN_PCIDEV_STUB) += xen-pciback.o xen-pciback-y := pci_stub.o pciback_ops.o xenbus.o xen-pciback-y += conf_space.o conf_space_header.o \ diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index 22f13abbe913..5e53b4817f16 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -160,7 +160,7 @@ static void *pm_ctrl_init(struct pci_dev *dev, int offset) } out: - return ERR_PTR(err); + return err ? ERR_PTR(err) : NULL; } static const struct config_field caplist_pm[] = { diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index ac45cdc38e85..981435103af1 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -236,8 +236,12 @@ static void *bar_init(struct pci_dev *dev, int offset) else { pos = (offset - PCI_BASE_ADDRESS_0) / 4; if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64)) { - bar->val = res[pos - 1].start >> 32; - bar->len_val = -resource_size(&res[pos - 1]) >> 32; + /* + * Use ">> 16 >> 16" instead of direct ">> 32" shift + * to avoid warnings on 32-bit architectures. + */ + bar->val = res[pos - 1].start >> 16 >> 16; + bar->len_val = -resource_size(&res[pos - 1]) >> 16 >> 16; return bar; } } diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index f8e4faa96ad6..bba527620507 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -19,7 +19,8 @@ #include <linux/sched.h> #include <linux/atomic.h> #include <xen/events.h> -#include <asm/xen/pci.h> +#include <xen/pci.h> +#include <xen/xen.h> #include <asm/xen/hypervisor.h> #include <xen/interface/physdev.h> #include "pciback.h" diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index 95e28ee48d52..9a64196e831d 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -71,6 +71,11 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev); void pcistub_put_pci_dev(struct pci_dev *dev); +static inline bool xen_pcibk_pv_support(void) +{ + return IS_ENABLED(CONFIG_XEN_PCIDEV_BACKEND); +} + /* Ensure a device is turned off or reset */ void xen_pcibk_reset_device(struct pci_dev *pdev); diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index c09c7ebd6968..bde63ef677b8 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -14,7 +14,7 @@ #include <linux/workqueue.h> #include <xen/xenbus.h> #include <xen/events.h> -#include <asm/xen/pci.h> +#include <xen/pci.h> #include "pciback.h" #define INVALID_EVTCHN_IRQ (-1) @@ -743,6 +743,9 @@ const struct xen_pcibk_backend *__read_mostly xen_pcibk_backend; int __init xen_pcibk_xenbus_register(void) { + if (!xen_pcibk_pv_support()) + return 0; + xen_pcibk_backend = &xen_pcibk_vpci_backend; if (passthrough) xen_pcibk_backend = &xen_pcibk_passthrough_backend; @@ -752,5 +755,6 @@ int __init xen_pcibk_xenbus_register(void) void __exit xen_pcibk_xenbus_unregister(void) { - xenbus_unregister_driver(&xen_pcibk_driver); + if (xen_pcibk_pv_support()) + xenbus_unregister_driver(&xen_pcibk_driver); } diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index adafdf86f42f..fac918ccb305 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -108,7 +108,9 @@ static const struct netfs_read_request_ops v9fs_req_ops = { */ static int v9fs_vfs_readpage(struct file *file, struct page *page) { - return netfs_readpage(file, page, &v9fs_req_ops, NULL); + struct folio *folio = page_folio(page); + + return netfs_readpage(file, folio, &v9fs_req_ops, NULL); } /** @@ -130,13 +132,15 @@ static void v9fs_vfs_readahead(struct readahead_control *ractl) static int v9fs_release_page(struct page *page, gfp_t gfp) { - if (PagePrivate(page)) + struct folio *folio = page_folio(page); + + if (folio_test_private(folio)) return 0; #ifdef CONFIG_9P_FSCACHE - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) return 0; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } #endif return 1; @@ -152,55 +156,58 @@ static int v9fs_release_page(struct page *page, gfp_t gfp) static void v9fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length) { - wait_on_page_fscache(page); + struct folio *folio = page_folio(page); + + folio_wait_fscache(folio); } -static int v9fs_vfs_writepage_locked(struct page *page) +static int v9fs_vfs_write_folio_locked(struct folio *folio) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio_inode(folio); struct v9fs_inode *v9inode = V9FS_I(inode); - loff_t start = page_offset(page); - loff_t size = i_size_read(inode); + loff_t start = folio_pos(folio); + loff_t i_size = i_size_read(inode); struct iov_iter from; - int err, len; + size_t len = folio_size(folio); + int err; + + if (start >= i_size) + return 0; /* Simultaneous truncation occurred */ - if (page->index == size >> PAGE_SHIFT) - len = size & ~PAGE_MASK; - else - len = PAGE_SIZE; + len = min_t(loff_t, i_size - start, len); - iov_iter_xarray(&from, WRITE, &page->mapping->i_pages, start, len); + iov_iter_xarray(&from, WRITE, &folio_mapping(folio)->i_pages, start, len); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); - set_page_writeback(page); + folio_start_writeback(folio); p9_client_write(v9inode->writeback_fid, start, &from, &err); - end_page_writeback(page); + folio_end_writeback(folio); return err; } static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) { + struct folio *folio = page_folio(page); int retval; - p9_debug(P9_DEBUG_VFS, "page %p\n", page); + p9_debug(P9_DEBUG_VFS, "folio %p\n", folio); - retval = v9fs_vfs_writepage_locked(page); + retval = v9fs_vfs_write_folio_locked(folio); if (retval < 0) { if (retval == -EAGAIN) { - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); retval = 0; } else { - SetPageError(page); - mapping_set_error(page->mapping, retval); + mapping_set_error(folio_mapping(folio), retval); } } else retval = 0; - unlock_page(page); + folio_unlock(folio); return retval; } @@ -213,14 +220,15 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) static int v9fs_launder_page(struct page *page) { + struct folio *folio = page_folio(page); int retval; - if (clear_page_dirty_for_io(page)) { - retval = v9fs_vfs_writepage_locked(page); + if (folio_clear_dirty_for_io(folio)) { + retval = v9fs_vfs_write_folio_locked(folio); if (retval) return retval; } - wait_on_page_fscache(page); + folio_wait_fscache(folio); return 0; } @@ -265,10 +273,10 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static int v9fs_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int flags, - struct page **pagep, void **fsdata) + struct page **subpagep, void **fsdata) { int retval; - struct page *page; + struct folio *folio; struct v9fs_inode *v9inode = V9FS_I(mapping->host); p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); @@ -279,31 +287,32 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &page, fsdata, + retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata, &v9fs_req_ops, NULL); if (retval < 0) return retval; - *pagep = find_subpage(page, pos / PAGE_SIZE); + *subpagep = &folio->page; return retval; } static int v9fs_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { loff_t last_pos = pos + copied; - struct inode *inode = page->mapping->host; + struct folio *folio = page_folio(subpage); + struct inode *inode = mapping->host; p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (unlikely(copied < len)) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* @@ -314,10 +323,10 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, inode_add_bytes(inode, last_pos - inode->i_size); i_size_write(inode, last_pos); } - set_page_dirty(page); + folio_mark_dirty(folio); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 4244d48398ef..612e297f3763 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -528,13 +528,13 @@ static vm_fault_t v9fs_vm_page_mkwrite(struct vm_fault *vmf) { struct v9fs_inode *v9inode; - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct file *filp = vmf->vma->vm_file; struct inode *inode = file_inode(filp); - p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n", - page, (unsigned long)filp->private_data); + p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n", + folio, (unsigned long)filp->private_data); v9inode = V9FS_I(inode); @@ -542,24 +542,24 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) * be modified. We then assume the entire page will need writing back. */ #ifdef CONFIG_9P_FSCACHE - if (PageFsCache(page) && - wait_on_page_fscache_killable(page) < 0) - return VM_FAULT_RETRY; + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) + return VM_FAULT_NOPAGE; #endif /* Update file times before taking page lock */ file_update_time(filp); BUG_ON(!v9inode->writeback_fid); - if (lock_page_killable(page) < 0) + if (folio_lock_killable(folio) < 0) return VM_FAULT_RETRY; - if (page->mapping != inode->i_mapping) + if (folio_mapping(folio) != inode->i_mapping) goto out_unlock; - wait_for_stable_page(page); + folio_wait_stable(folio); return VM_FAULT_LOCKED; out_unlock: - unlock_page(page); + folio_unlock(folio); return VM_FAULT_NOPAGE; } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 4579bbda4634..da9b4f8577a1 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -103,13 +103,13 @@ struct afs_lookup_cookie { }; /* - * Drop the refs that we're holding on the pages we were reading into. We've + * Drop the refs that we're holding on the folios we were reading into. We've * got refs on the first nr_pages pages. */ static void afs_dir_read_cleanup(struct afs_read *req) { struct address_space *mapping = req->vnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t last = req->nr_pages - 1; XA_STATE(xas, &mapping->i_pages, 0); @@ -118,65 +118,56 @@ static void afs_dir_read_cleanup(struct afs_read *req) return; rcu_read_lock(); - xas_for_each(&xas, page, last) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, last) { + if (xas_retry(&xas, folio)) continue; - BUG_ON(xa_is_value(page)); - BUG_ON(PageCompound(page)); - ASSERTCMP(page->mapping, ==, mapping); + BUG_ON(xa_is_value(folio)); + ASSERTCMP(folio_file_mapping(folio), ==, mapping); - put_page(page); + folio_put(folio); } rcu_read_unlock(); } /* - * check that a directory page is valid + * check that a directory folio is valid */ -static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page, - loff_t i_size) +static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio, + loff_t i_size) { - struct afs_xdr_dir_page *dbuf; - loff_t latter, off; - int tmp, qty; + union afs_xdr_dir_block *block; + size_t offset, size; + loff_t pos; - /* Determine how many magic numbers there should be in this page, but + /* Determine how many magic numbers there should be in this folio, but * we must take care because the directory may change size under us. */ - off = page_offset(page); - if (i_size <= off) + pos = folio_pos(folio); + if (i_size <= pos) goto checked; - latter = i_size - off; - if (latter >= PAGE_SIZE) - qty = PAGE_SIZE; - else - qty = latter; - qty /= sizeof(union afs_xdr_dir_block); - - /* check them */ - dbuf = kmap_atomic(page); - for (tmp = 0; tmp < qty; tmp++) { - if (dbuf->blocks[tmp].hdr.magic != AFS_DIR_MAGIC) { - printk("kAFS: %s(%lx): bad magic %d/%d is %04hx\n", - __func__, dvnode->vfs_inode.i_ino, tmp, qty, - ntohs(dbuf->blocks[tmp].hdr.magic)); - trace_afs_dir_check_failed(dvnode, off, i_size); - kunmap(page); + size = min_t(loff_t, folio_size(folio), i_size - pos); + for (offset = 0; offset < size; offset += sizeof(*block)) { + block = kmap_local_folio(folio, offset); + if (block->hdr.magic != AFS_DIR_MAGIC) { + printk("kAFS: %s(%lx): [%llx] bad magic %zx/%zx is %04hx\n", + __func__, dvnode->vfs_inode.i_ino, + pos, offset, size, ntohs(block->hdr.magic)); + trace_afs_dir_check_failed(dvnode, pos + offset, i_size); + kunmap_local(block); trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic); goto error; } /* Make sure each block is NUL terminated so we can reasonably - * use string functions on it. The filenames in the page + * use string functions on it. The filenames in the folio * *should* be NUL-terminated anyway. */ - ((u8 *)&dbuf->blocks[tmp])[AFS_DIR_BLOCK_SIZE - 1] = 0; - } - - kunmap_atomic(dbuf); + ((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0; + kunmap_local(block); + } checked: afs_stat_v(dvnode, n_read_dir); return true; @@ -190,11 +181,11 @@ error: */ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) { - struct afs_xdr_dir_page *dbuf; + union afs_xdr_dir_block *block; struct address_space *mapping = dvnode->vfs_inode.i_mapping; - struct page *page; - unsigned int i, qty = PAGE_SIZE / sizeof(union afs_xdr_dir_block); + struct folio *folio; pgoff_t last = req->nr_pages - 1; + size_t offset, size; XA_STATE(xas, &mapping->i_pages, 0); @@ -205,30 +196,28 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) req->pos, req->nr_pages, req->iter->iov_offset, iov_iter_count(req->iter)); - xas_for_each(&xas, page, last) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, last) { + if (xas_retry(&xas, folio)) continue; - BUG_ON(PageCompound(page)); - BUG_ON(page->mapping != mapping); - - dbuf = kmap_atomic(page); - for (i = 0; i < qty; i++) { - union afs_xdr_dir_block *block = &dbuf->blocks[i]; + BUG_ON(folio_file_mapping(folio) != mapping); - pr_warn("[%02lx] %32phN\n", page->index * qty + i, block); + size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio)); + for (offset = 0; offset < size; offset += sizeof(*block)) { + block = kmap_local_folio(folio, offset); + pr_warn("[%02lx] %32phN\n", folio_index(folio) + offset, block); + kunmap_local(block); } - kunmap_atomic(dbuf); } } /* - * Check all the pages in a directory. All the pages are held pinned. + * Check all the blocks in a directory. All the folios are held pinned. */ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) { struct address_space *mapping = dvnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t last = req->nr_pages - 1; int ret = 0; @@ -238,14 +227,13 @@ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) return 0; rcu_read_lock(); - xas_for_each(&xas, page, last) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, last) { + if (xas_retry(&xas, folio)) continue; - BUG_ON(PageCompound(page)); - BUG_ON(page->mapping != mapping); + BUG_ON(folio_file_mapping(folio) != mapping); - if (!afs_dir_check_page(dvnode, page, req->file_size)) { + if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) { afs_dir_dump(dvnode, req); ret = -EIO; break; @@ -274,15 +262,16 @@ static int afs_dir_open(struct inode *inode, struct file *file) /* * Read the directory into the pagecache in one go, scrubbing the previous - * contents. The list of pages is returned, pinning them so that they don't + * contents. The list of folios is returned, pinning them so that they don't * get reclaimed during the iteration. */ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) __acquires(&dvnode->validate_lock) { + struct address_space *mapping = dvnode->vfs_inode.i_mapping; struct afs_read *req; loff_t i_size; - int nr_pages, i, n; + int nr_pages, i; int ret; _enter(""); @@ -320,43 +309,30 @@ expand: req->iter = &req->def_iter; /* Fill in any gaps that we might find where the memory reclaimer has - * been at work and pin all the pages. If there are any gaps, we will + * been at work and pin all the folios. If there are any gaps, we will * need to reread the entire directory contents. */ i = req->nr_pages; while (i < nr_pages) { - struct page *pages[8], *page; - - n = find_get_pages_contig(dvnode->vfs_inode.i_mapping, i, - min_t(unsigned int, nr_pages - i, - ARRAY_SIZE(pages)), - pages); - _debug("find %u at %u/%u", n, i, nr_pages); - - if (n == 0) { - gfp_t gfp = dvnode->vfs_inode.i_mapping->gfp_mask; + struct folio *folio; + folio = filemap_get_folio(mapping, i); + if (!folio) { if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_stat_v(dvnode, n_inval); ret = -ENOMEM; - page = __page_cache_alloc(gfp); - if (!page) + folio = __filemap_get_folio(mapping, + i, FGP_LOCK | FGP_CREAT, + mapping->gfp_mask); + if (!folio) goto error; - ret = add_to_page_cache_lru(page, - dvnode->vfs_inode.i_mapping, - i, gfp); - if (ret < 0) - goto error; - - attach_page_private(page, (void *)1); - unlock_page(page); - req->nr_pages++; - i++; - } else { - req->nr_pages += n; - i += n; + folio_attach_private(folio, (void *)1); + folio_unlock(folio); } + + req->nr_pages += folio_nr_pages(folio); + i += folio_nr_pages(folio); } /* If we're going to reload, we need to lock all the pages to prevent @@ -424,7 +400,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, size_t nlen; int tmp; - _enter("%u,%x,%p,,",(unsigned)ctx->pos,blkoff,block); + _enter("%llx,%x", ctx->pos, blkoff); curr = (ctx->pos - blkoff) / sizeof(union afs_xdr_dirent); @@ -513,12 +489,10 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, struct key *key, afs_dataversion_t *_dir_version) { struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_xdr_dir_page *dbuf; union afs_xdr_dir_block *dblock; struct afs_read *req; - struct page *page; - unsigned blkoff, limit; - void __rcu **slot; + struct folio *folio; + unsigned offset, size; int ret; _enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos); @@ -540,43 +514,30 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, /* walk through the blocks in sequence */ ret = 0; while (ctx->pos < req->actual_len) { - blkoff = ctx->pos & ~(sizeof(union afs_xdr_dir_block) - 1); - - /* Fetch the appropriate page from the directory and re-add it + /* Fetch the appropriate folio from the directory and re-add it * to the LRU. We have all the pages pinned with an extra ref. */ - rcu_read_lock(); - page = NULL; - slot = radix_tree_lookup_slot(&dvnode->vfs_inode.i_mapping->i_pages, - blkoff / PAGE_SIZE); - if (slot) - page = radix_tree_deref_slot(slot); - rcu_read_unlock(); - if (!page) { + folio = __filemap_get_folio(dir->i_mapping, ctx->pos / PAGE_SIZE, + FGP_ACCESSED, 0); + if (!folio) { ret = afs_bad(dvnode, afs_file_error_dir_missing_page); break; } - mark_page_accessed(page); - limit = blkoff & ~(PAGE_SIZE - 1); + offset = round_down(ctx->pos, sizeof(*dblock)) - folio_file_pos(folio); + size = min_t(loff_t, folio_size(folio), + req->actual_len - folio_file_pos(folio)); - dbuf = kmap(page); - - /* deal with the individual blocks stashed on this page */ do { - dblock = &dbuf->blocks[(blkoff % PAGE_SIZE) / - sizeof(union afs_xdr_dir_block)]; - ret = afs_dir_iterate_block(dvnode, ctx, dblock, blkoff); - if (ret != 1) { - kunmap(page); + dblock = kmap_local_folio(folio, offset); + ret = afs_dir_iterate_block(dvnode, ctx, dblock, + folio_file_pos(folio) + offset); + kunmap_local(dblock); + if (ret != 1) goto out; - } - blkoff += sizeof(union afs_xdr_dir_block); + } while (offset += sizeof(*dblock), offset < size); - } while (ctx->pos < dir->i_size && blkoff < limit); - - kunmap(page); ret = 0; } @@ -2037,42 +1998,42 @@ error: } /* - * Release a directory page and clean up its private state if it's not busy - * - return true if the page can now be released, false if not + * Release a directory folio and clean up its private state if it's not busy + * - return true if the folio can now be released, false if not */ -static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags) +static int afs_dir_releasepage(struct page *subpage, gfp_t gfp_flags) { - struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index); + _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio)); - detach_page_private(page); + folio_detach_private(folio); /* The directory will need reloading. */ if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_stat_v(dvnode, n_relpg); - return 1; + return true; } /* - * invalidate part or all of a page - * - release a page and clean up its private data if offset is 0 (indicating - * the entire page) + * Invalidate part or all of a folio. */ -static void afs_dir_invalidatepage(struct page *page, unsigned int offset, +static void afs_dir_invalidatepage(struct page *subpage, unsigned int offset, unsigned int length) { - struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - _enter("{%lu},%u,%u", page->index, offset, length); + _enter("{%lu},%u,%u", folio_index(folio), offset, length); - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); /* The directory will need reloading. */ if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_stat_v(dvnode, n_inval); - /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == thp_size(page)) - detach_page_private(page); + /* we clean up only if the entire folio is being invalidated */ + if (offset == 0 && length == folio_size(folio)) + folio_detach_private(folio); } diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 540b9fc96824..d98e109ecee9 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -105,6 +105,25 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block, } /* + * Get a new directory folio. + */ +static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) +{ + struct address_space *mapping = vnode->vfs_inode.i_mapping; + struct folio *folio; + + folio = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping->gfp_mask); + if (!folio) + clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + else if (folio && !folio_test_private(folio)) + folio_attach_private(folio, (void *)1); + + return folio; +} + +/* * Scan a directory block looking for a dirent of the right name. */ static int afs_dir_scan_block(union afs_xdr_dir_block *block, struct qstr *name, @@ -188,13 +207,11 @@ void afs_edit_dir_add(struct afs_vnode *vnode, enum afs_edit_dir_reason why) { union afs_xdr_dir_block *meta, *block; - struct afs_xdr_dir_page *meta_page, *dir_page; union afs_xdr_dirent *de; - struct page *page0, *page; + struct folio *folio0, *folio; unsigned int need_slots, nr_blocks, b; pgoff_t index; loff_t i_size; - gfp_t gfp; int slot; _enter(",,{%d,%s},", name->len, name->name); @@ -206,10 +223,8 @@ void afs_edit_dir_add(struct afs_vnode *vnode, return; } - gfp = vnode->vfs_inode.i_mapping->gfp_mask; - page0 = find_or_create_page(vnode->vfs_inode.i_mapping, 0, gfp); - if (!page0) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + folio0 = afs_dir_get_folio(vnode, 0); + if (!folio0) { _leave(" [fgp]"); return; } @@ -217,42 +232,35 @@ void afs_edit_dir_add(struct afs_vnode *vnode, /* Work out how many slots we're going to need. */ need_slots = afs_dir_calc_slots(name->len); - meta_page = kmap(page0); - meta = &meta_page->blocks[0]; + meta = kmap_local_folio(folio0, 0); if (i_size == 0) goto new_directory; nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; - /* Find a block that has sufficient slots available. Each VM page + /* Find a block that has sufficient slots available. Each folio * contains two or more directory blocks. */ for (b = 0; b < nr_blocks + 1; b++) { - /* If the directory extended into a new page, then we need to - * tack a new page on the end. + /* If the directory extended into a new folio, then we need to + * tack a new folio on the end. */ index = b / AFS_DIR_BLOCKS_PER_PAGE; - if (index == 0) { - page = page0; - dir_page = meta_page; - } else { - if (nr_blocks >= AFS_DIR_MAX_BLOCKS) - goto error; - gfp = vnode->vfs_inode.i_mapping->gfp_mask; - page = find_or_create_page(vnode->vfs_inode.i_mapping, - index, gfp); - if (!page) + if (nr_blocks >= AFS_DIR_MAX_BLOCKS) + goto error; + if (index >= folio_nr_pages(folio0)) { + folio = afs_dir_get_folio(vnode, index); + if (!folio) goto error; - if (!PagePrivate(page)) - attach_page_private(page, (void *)1); - dir_page = kmap(page); + } else { + folio = folio0; } + block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_file_pos(folio)); + /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) goto invalidated; - block = &dir_page->blocks[b % AFS_DIR_BLOCKS_PER_PAGE]; - _debug("block %u: %2u %3u %u", b, (b < AFS_DIR_BLOCKS_WITH_CTR) ? meta->meta.alloc_ctrs[b] : 99, @@ -266,7 +274,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode, afs_set_i_size(vnode, (b + 1) * AFS_DIR_BLOCK_SIZE); } - /* Only lower dir pages have a counter in the header. */ + /* Only lower dir blocks have a counter in the header. */ if (b >= AFS_DIR_BLOCKS_WITH_CTR || meta->meta.alloc_ctrs[b] >= need_slots) { /* We need to try and find one or more consecutive @@ -279,10 +287,10 @@ void afs_edit_dir_add(struct afs_vnode *vnode, } } - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } } @@ -298,8 +306,8 @@ new_directory: i_size = AFS_DIR_BLOCK_SIZE; afs_set_i_size(vnode, i_size); slot = AFS_DIR_RESV_BLOCKS0; - page = page0; - block = meta; + folio = folio0; + block = kmap_local_folio(folio, 0); nr_blocks = 1; b = 0; @@ -318,10 +326,10 @@ found_space: /* Adjust the bitmap. */ afs_set_contig_bits(block, slot, need_slots); - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } /* Adjust the allocation counter. */ @@ -333,18 +341,19 @@ found_space: _debug("Insert %s in %u[%u]", name->name, b, slot); out_unmap: - unlock_page(page0); - kunmap(page0); - put_page(page0); + kunmap_local(meta); + folio_unlock(folio0); + folio_put(folio0); _leave(""); return; invalidated: trace_afs_edit_dir(vnode, why, afs_edit_dir_create_inval, 0, 0, 0, 0, name->name); clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - if (page != page0) { - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } goto out_unmap; @@ -364,10 +373,9 @@ error: void afs_edit_dir_remove(struct afs_vnode *vnode, struct qstr *name, enum afs_edit_dir_reason why) { - struct afs_xdr_dir_page *meta_page, *dir_page; union afs_xdr_dir_block *meta, *block; union afs_xdr_dirent *de; - struct page *page0, *page; + struct folio *folio0, *folio; unsigned int need_slots, nr_blocks, b; pgoff_t index; loff_t i_size; @@ -384,9 +392,8 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, } nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; - page0 = find_lock_page(vnode->vfs_inode.i_mapping, 0); - if (!page0) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + folio0 = afs_dir_get_folio(vnode, 0); + if (!folio0) { _leave(" [fgp]"); return; } @@ -394,30 +401,27 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Work out how many slots we're going to discard. */ need_slots = afs_dir_calc_slots(name->len); - meta_page = kmap(page0); - meta = &meta_page->blocks[0]; + meta = kmap_local_folio(folio0, 0); - /* Find a page that has sufficient slots available. Each VM page + /* Find a block that has sufficient slots available. Each folio * contains two or more directory blocks. */ for (b = 0; b < nr_blocks; b++) { index = b / AFS_DIR_BLOCKS_PER_PAGE; - if (index != 0) { - page = find_lock_page(vnode->vfs_inode.i_mapping, index); - if (!page) + if (index >= folio_nr_pages(folio0)) { + folio = afs_dir_get_folio(vnode, index); + if (!folio) goto error; - dir_page = kmap(page); } else { - page = page0; - dir_page = meta_page; + folio = folio0; } + block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_file_pos(folio)); + /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) goto invalidated; - block = &dir_page->blocks[b % AFS_DIR_BLOCKS_PER_PAGE]; - if (b > AFS_DIR_BLOCKS_WITH_CTR || meta->meta.alloc_ctrs[b] <= AFS_DIR_SLOTS_PER_BLOCK - 1 - need_slots) { slot = afs_dir_scan_block(block, name, b); @@ -425,10 +429,10 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, goto found_dirent; } - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } } @@ -449,10 +453,10 @@ found_dirent: /* Adjust the bitmap. */ afs_clear_contig_bits(block, slot, need_slots); - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } /* Adjust the allocation counter. */ @@ -464,9 +468,9 @@ found_dirent: _debug("Remove %s from %u[%u]", name->name, b, slot); out_unmap: - unlock_page(page0); - kunmap(page0); - put_page(page0); + kunmap_local(meta); + folio_unlock(folio0); + folio_put(folio0); _leave(""); return; @@ -474,10 +478,10 @@ invalidated: trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval, 0, 0, 0, 0, name->name); clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } goto out_unmap; diff --git a/fs/afs/file.c b/fs/afs/file.c index eb11d047c0ae..cb6ad61eec3b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -324,21 +324,24 @@ static int afs_symlink_readpage(struct file *file, struct page *page) { struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); struct afs_read *fsreq; + struct folio *folio = page_folio(page); int ret; fsreq = afs_alloc_read(GFP_NOFS); if (!fsreq) return -ENOMEM; - fsreq->pos = page->index * PAGE_SIZE; - fsreq->len = PAGE_SIZE; + fsreq->pos = folio_pos(folio); + fsreq->len = folio_size(folio); fsreq->vnode = vnode; fsreq->iter = &fsreq->def_iter; iov_iter_xarray(&fsreq->def_iter, READ, &page->mapping->i_pages, fsreq->pos, fsreq->len); ret = afs_fetch_data(fsreq->vnode, fsreq); - page_endio(page, false, ret); + if (ret == 0) + SetPageUptodate(page); + unlock_page(page); return ret; } @@ -362,7 +365,7 @@ static int afs_begin_cache_operation(struct netfs_read_request *rreq) } static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata) + struct folio *folio, void **_fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); @@ -385,7 +388,9 @@ const struct netfs_read_request_ops afs_req_ops = { static int afs_readpage(struct file *file, struct page *page) { - return netfs_readpage(file, page, &afs_req_ops, NULL); + struct folio *folio = page_folio(page); + + return netfs_readpage(file, folio, &afs_req_ops, NULL); } static void afs_readahead(struct readahead_control *ractl) @@ -397,29 +402,29 @@ static void afs_readahead(struct readahead_control *ractl) * Adjust the dirty region of the page on truncation or full invalidation, * getting rid of the markers altogether if the region is entirely invalidated. */ -static void afs_invalidate_dirty(struct page *page, unsigned int offset, +static void afs_invalidate_dirty(struct folio *folio, unsigned int offset, unsigned int length) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); unsigned long priv; unsigned int f, t, end = offset + length; - priv = page_private(page); + priv = (unsigned long)folio_get_private(folio); /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == thp_size(page)) + if (offset == 0 && length == folio_size(folio)) goto full_invalidate; /* If the page was dirtied by page_mkwrite(), the PTE stays writable * and we don't get another notification to tell us to expand it * again. */ - if (afs_is_page_dirty_mmapped(priv)) + if (afs_is_folio_dirty_mmapped(priv)) return; /* We may need to shorten the dirty region */ - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (t <= offset || f >= end) return; /* Doesn't overlap */ @@ -437,17 +442,17 @@ static void afs_invalidate_dirty(struct page *page, unsigned int offset, if (f == t) goto undirty; - priv = afs_page_dirty(page, f, t); - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page); + priv = afs_folio_dirty(folio, f, t); + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio); return; undirty: - trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page); - clear_page_dirty_for_io(page); + trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio); + folio_clear_dirty_for_io(folio); full_invalidate: - trace_afs_page_dirty(vnode, tracepoint_string("inval"), page); - detach_page_private(page); + trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio); + folio_detach_private(folio); } /* @@ -458,14 +463,16 @@ full_invalidate: static void afs_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - _enter("{%lu},%u,%u", page->index, offset, length); + struct folio *folio = page_folio(page); + + _enter("{%lu},%u,%u", folio_index(folio), offset, length); BUG_ON(!PageLocked(page)); if (PagePrivate(page)) - afs_invalidate_dirty(page, offset, length); + afs_invalidate_dirty(folio, offset, length); - wait_on_page_fscache(page); + folio_wait_fscache(folio); _leave(""); } @@ -475,30 +482,31 @@ static void afs_invalidatepage(struct page *page, unsigned int offset, */ static int afs_releasepage(struct page *page, gfp_t gfp_flags) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(page); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); _enter("{{%llx:%llu}[%lu],%lx},%x", - vnode->fid.vid, vnode->fid.vnode, page->index, page->flags, + vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags, gfp_flags); /* deny if page is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (!(gfp_flags & __GFP_DIRECT_RECLAIM) || !(gfp_flags & __GFP_FS)) return false; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } #endif - if (PagePrivate(page)) { - trace_afs_page_dirty(vnode, tracepoint_string("rel"), page); - detach_page_private(page); + if (folio_test_private(folio)) { + trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio); + folio_detach_private(folio); } - /* indicate that the page can be released */ + /* Indicate that the folio can be released */ _leave(" = T"); - return 1; + return true; } static void afs_add_open_mmap(struct afs_vnode *vnode) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 9357c53faa69..aa4c0d6c9780 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -876,59 +876,59 @@ struct afs_vnode_cache_aux { } __packed; /* - * We use page->private to hold the amount of the page that we've written to, + * We use folio->private to hold the amount of the folio that we've written to, * splitting the field into two parts. However, we need to represent a range - * 0...PAGE_SIZE, so we reduce the resolution if the size of the page + * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio * exceeds what we can encode. */ #ifdef CONFIG_64BIT -#define __AFS_PAGE_PRIV_MASK 0x7fffffffUL -#define __AFS_PAGE_PRIV_SHIFT 32 -#define __AFS_PAGE_PRIV_MMAPPED 0x80000000UL +#define __AFS_FOLIO_PRIV_MASK 0x7fffffffUL +#define __AFS_FOLIO_PRIV_SHIFT 32 +#define __AFS_FOLIO_PRIV_MMAPPED 0x80000000UL #else -#define __AFS_PAGE_PRIV_MASK 0x7fffUL -#define __AFS_PAGE_PRIV_SHIFT 16 -#define __AFS_PAGE_PRIV_MMAPPED 0x8000UL +#define __AFS_FOLIO_PRIV_MASK 0x7fffUL +#define __AFS_FOLIO_PRIV_SHIFT 16 +#define __AFS_FOLIO_PRIV_MMAPPED 0x8000UL #endif -static inline unsigned int afs_page_dirty_resolution(struct page *page) +static inline unsigned int afs_folio_dirty_resolution(struct folio *folio) { - int shift = thp_order(page) + PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1); + int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1); return (shift > 0) ? shift : 0; } -static inline size_t afs_page_dirty_from(struct page *page, unsigned long priv) +static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv) { - unsigned long x = priv & __AFS_PAGE_PRIV_MASK; + unsigned long x = priv & __AFS_FOLIO_PRIV_MASK; /* The lower bound is inclusive */ - return x << afs_page_dirty_resolution(page); + return x << afs_folio_dirty_resolution(folio); } -static inline size_t afs_page_dirty_to(struct page *page, unsigned long priv) +static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv) { - unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK; + unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK; /* The upper bound is immediately beyond the region */ - return (x + 1) << afs_page_dirty_resolution(page); + return (x + 1) << afs_folio_dirty_resolution(folio); } -static inline unsigned long afs_page_dirty(struct page *page, size_t from, size_t to) +static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to) { - unsigned int res = afs_page_dirty_resolution(page); + unsigned int res = afs_folio_dirty_resolution(folio); from >>= res; to = (to - 1) >> res; - return (to << __AFS_PAGE_PRIV_SHIFT) | from; + return (to << __AFS_FOLIO_PRIV_SHIFT) | from; } -static inline unsigned long afs_page_dirty_mmapped(unsigned long priv) +static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv) { - return priv | __AFS_PAGE_PRIV_MMAPPED; + return priv | __AFS_FOLIO_PRIV_MMAPPED; } -static inline bool afs_is_page_dirty_mmapped(unsigned long priv) +static inline bool afs_is_folio_dirty_mmapped(unsigned long priv) { - return priv & __AFS_PAGE_PRIV_MMAPPED; + return priv & __AFS_FOLIO_PRIV_MMAPPED; } #include <trace/events/afs.h> diff --git a/fs/afs/write.c b/fs/afs/write.c index 8b1d9c2f6bec..ca4909baf5e6 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -32,7 +32,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, struct page **_page, void **fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); - struct page *page; + struct folio *folio; unsigned long priv; unsigned f, from; unsigned t, to; @@ -46,12 +46,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &page, fsdata, + ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata, &afs_req_ops, NULL); if (ret < 0) return ret; - index = page->index; + index = folio_index(folio); from = pos - index * PAGE_SIZE; to = from + len; @@ -59,14 +59,14 @@ try_again: /* See if this page is already partially written in a way that we can * merge the new write with. */ - if (PagePrivate(page)) { - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + if (folio_test_private(folio)) { + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); ASSERTCMP(f, <=, t); - if (PageWriteback(page)) { - trace_afs_page_dirty(vnode, tracepoint_string("alrdy"), page); + if (folio_test_writeback(folio)) { + trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio); goto flush_conflicting_write; } /* If the file is being filled locally, allow inter-write @@ -78,7 +78,7 @@ try_again: goto flush_conflicting_write; } - *_page = page; + *_page = &folio->page; _leave(" = 0"); return 0; @@ -87,17 +87,17 @@ try_again: */ flush_conflicting_write: _debug("flush conflict"); - ret = write_one_page(page); + ret = folio_write_one(folio); if (ret < 0) goto error; - ret = lock_page_killable(page); + ret = folio_lock_killable(folio); if (ret < 0) goto error; goto try_again; error: - put_page(page); + folio_put(folio); _leave(" = %d", ret); return ret; } @@ -107,24 +107,25 @@ error: */ int afs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { + struct folio *folio = page_folio(subpage); struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); unsigned long priv; - unsigned int f, from = pos & (thp_size(page) - 1); + unsigned int f, from = offset_in_folio(folio, pos); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; _enter("{%llx:%llu},{%lx}", - vnode->fid.vid, vnode->fid.vnode, page->index); + vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (copied < len) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } if (copied == 0) @@ -141,29 +142,29 @@ int afs_write_end(struct file *file, struct address_space *mapping, write_sequnlock(&vnode->cb_lock); } - if (PagePrivate(page)) { - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + if (folio_test_private(folio)) { + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (from < f) f = from; if (to > t) t = to; - priv = afs_page_dirty(page, f, t); - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("dirty+"), page); + priv = afs_folio_dirty(folio, f, t); + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio); } else { - priv = afs_page_dirty(page, from, to); - attach_page_private(page, (void *)priv); - trace_afs_page_dirty(vnode, tracepoint_string("dirty"), page); + priv = afs_folio_dirty(folio, from, to); + folio_attach_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio); } - if (set_page_dirty(page)) - _debug("dirtied %lx", page->index); + if (folio_mark_dirty(folio)) + _debug("dirtied %lx", folio_index(folio)); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } @@ -174,40 +175,32 @@ static void afs_kill_pages(struct address_space *mapping, loff_t start, loff_t len) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct pagevec pv; - unsigned int loop, psize; + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; _enter("{%llx:%llu},%llx @%llx", vnode->fid.vid, vnode->fid.vnode, len, start); - pagevec_init(&pv); - do { - _debug("kill %llx @%llx", len, start); - - pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE, - PAGEVEC_SIZE, pv.pages); - if (pv.nr == 0) - break; + _debug("kill %lx (to %lx)", index, last); - for (loop = 0; loop < pv.nr; loop++) { - struct page *page = pv.pages[loop]; + folio = filemap_get_folio(mapping, index); + if (!folio) { + next = index + 1; + continue; + } - if (page->index * PAGE_SIZE >= start + len) - break; + next = folio_next_index(folio); - psize = thp_size(page); - start += psize; - len -= psize; - ClearPageUptodate(page); - end_page_writeback(page); - lock_page(page); - generic_error_remove_page(mapping, page); - unlock_page(page); - } + folio_clear_uptodate(folio); + folio_end_writeback(folio); + folio_lock(folio); + generic_error_remove_page(mapping, &folio->page); + folio_unlock(folio); + folio_put(folio); - __pagevec_release(&pv); - } while (len > 0); + } while (index = next, index <= last); _leave(""); } @@ -220,37 +213,27 @@ static void afs_redirty_pages(struct writeback_control *wbc, loff_t start, loff_t len) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct pagevec pv; - unsigned int loop, psize; + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; _enter("{%llx:%llu},%llx @%llx", vnode->fid.vid, vnode->fid.vnode, len, start); - pagevec_init(&pv); - do { _debug("redirty %llx @%llx", len, start); - pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE, - PAGEVEC_SIZE, pv.pages); - if (pv.nr == 0) - break; - - for (loop = 0; loop < pv.nr; loop++) { - struct page *page = pv.pages[loop]; - - if (page->index * PAGE_SIZE >= start + len) - break; - - psize = thp_size(page); - start += psize; - len -= psize; - redirty_page_for_writepage(wbc, page); - end_page_writeback(page); + folio = filemap_get_folio(mapping, index); + if (!folio) { + next = index + 1; + continue; } - __pagevec_release(&pv); - } while (len > 0); + next = index + folio_nr_pages(folio); + folio_redirty_for_writepage(wbc, folio); + folio_end_writeback(folio); + folio_put(folio); + } while (index = next, index <= last); _leave(""); } @@ -261,7 +244,7 @@ static void afs_redirty_pages(struct writeback_control *wbc, static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len) { struct address_space *mapping = vnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t end; XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); @@ -272,15 +255,16 @@ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsign rcu_read_lock(); end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, page, end) { - if (!PageWriteback(page)) { - kdebug("bad %x @%llx page %lx %lx", len, start, page->index, end); - ASSERT(PageWriteback(page)); + xas_for_each(&xas, folio, end) { + if (!folio_test_writeback(folio)) { + kdebug("bad %x @%llx page %lx %lx", + len, start, folio_index(folio), end); + ASSERT(folio_test_writeback(folio)); } - trace_afs_page_dirty(vnode, tracepoint_string("clear"), page); - detach_page_private(page); - page_endio(page, true, 0); + trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio); + folio_detach_private(folio); + folio_end_writeback(folio); } rcu_read_unlock(); @@ -437,7 +421,7 @@ static void afs_extend_writeback(struct address_space *mapping, unsigned int *_len) { struct pagevec pvec; - struct page *page; + struct folio *folio; unsigned long priv; unsigned int psize, filler = 0; unsigned int f, t; @@ -456,43 +440,43 @@ static void afs_extend_writeback(struct address_space *mapping, */ rcu_read_lock(); - xas_for_each(&xas, page, ULONG_MAX) { + xas_for_each(&xas, folio, ULONG_MAX) { stop = true; - if (xas_retry(&xas, page)) + if (xas_retry(&xas, folio)) continue; - if (xa_is_value(page)) + if (xa_is_value(folio)) break; - if (page->index != index) + if (folio_index(folio) != index) break; - if (!page_cache_get_speculative(page)) { + if (!folio_try_get_rcu(folio)) { xas_reset(&xas); continue; } /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) { - put_page(page); + if (unlikely(folio != xas_reload(&xas))) { + folio_put(folio); break; } - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); break; } - if (!PageDirty(page) || PageWriteback(page)) { - unlock_page(page); - put_page(page); + if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { + folio_unlock(folio); + folio_put(folio); break; } - psize = thp_size(page); - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + psize = folio_size(folio); + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (f != 0 && !new_content) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); break; } @@ -503,8 +487,8 @@ static void afs_extend_writeback(struct address_space *mapping, else if (t == psize || new_content) stop = false; - index += thp_nr_pages(page); - if (!pagevec_add(&pvec, page)) + index += folio_nr_pages(folio); + if (!pagevec_add(&pvec, &folio->page)) break; if (stop) break; @@ -521,16 +505,16 @@ static void afs_extend_writeback(struct address_space *mapping, break; for (i = 0; i < pagevec_count(&pvec); i++) { - page = pvec.pages[i]; - trace_afs_page_dirty(vnode, tracepoint_string("store+"), page); + folio = page_folio(pvec.pages[i]); + trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio); - if (!clear_page_dirty_for_io(page)) + if (!folio_clear_dirty_for_io(folio)) BUG(); - if (test_set_page_writeback(page)) + if (folio_start_writeback(folio)) BUG(); - *_count -= thp_nr_pages(page); - unlock_page(page); + *_count -= folio_nr_pages(folio); + folio_unlock(folio); } pagevec_release(&pvec); @@ -544,10 +528,10 @@ static void afs_extend_writeback(struct address_space *mapping, * Synchronously write back the locked page and any subsequent non-locked dirty * pages. */ -static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, - struct writeback_control *wbc, - struct page *page, - loff_t start, loff_t end) +static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, + struct writeback_control *wbc, + struct folio *folio, + loff_t start, loff_t end) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); struct iov_iter iter; @@ -558,22 +542,22 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, long count = wbc->nr_to_write; int ret; - _enter(",%lx,%llx-%llx", page->index, start, end); + _enter(",%lx,%llx-%llx", folio_index(folio), start, end); - if (test_set_page_writeback(page)) + if (folio_start_writeback(folio)) BUG(); - count -= thp_nr_pages(page); + count -= folio_nr_pages(folio); /* Find all consecutive lockable dirty pages that have contiguous * written regions, stopping when we find a page that is not * immediately lockable, is not dirty or is missing, or we reach the * end of the range. */ - priv = page_private(page); - offset = afs_page_dirty_from(page, priv); - to = afs_page_dirty_to(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("store"), page); + priv = (unsigned long)folio_get_private(folio); + offset = afs_folio_dirty_from(folio, priv); + to = afs_folio_dirty_to(folio, priv); + trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio); len = to - offset; start += offset; @@ -586,7 +570,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, max_len = min_t(unsigned long long, max_len, i_size - start); if (len < max_len && - (to == thp_size(page) || new_content)) + (to == folio_size(folio) || new_content)) afs_extend_writeback(mapping, vnode, &count, start, max_len, new_content, &len); len = min_t(loff_t, len, max_len); @@ -596,7 +580,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, * set; the first page is still locked at this point, but all the rest * have been unlocked. */ - unlock_page(page); + folio_unlock(folio); if (start < i_size) { _debug("write back %x @%llx [%llx]", len, start, i_size); @@ -657,16 +641,17 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, * write a page back to the server * - the caller locked the page for us */ -int afs_writepage(struct page *page, struct writeback_control *wbc) +int afs_writepage(struct page *subpage, struct writeback_control *wbc) { + struct folio *folio = page_folio(subpage); ssize_t ret; loff_t start; - _enter("{%lx},", page->index); + _enter("{%lx},", folio_index(folio)); - start = page->index * PAGE_SIZE; - ret = afs_write_back_from_locked_page(page->mapping, wbc, page, - start, LLONG_MAX - start); + start = folio_index(folio) * PAGE_SIZE; + ret = afs_write_back_from_locked_folio(folio_mapping(folio), wbc, + folio, start, LLONG_MAX - start); if (ret < 0) { _leave(" = %zd", ret); return ret; @@ -683,7 +668,8 @@ static int afs_writepages_region(struct address_space *mapping, struct writeback_control *wbc, loff_t start, loff_t end, loff_t *_next) { - struct page *page; + struct folio *folio; + struct page *head_page; ssize_t ret; int n; @@ -693,13 +679,14 @@ static int afs_writepages_region(struct address_space *mapping, pgoff_t index = start / PAGE_SIZE; n = find_get_pages_range_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, 1, &page); + PAGECACHE_TAG_DIRTY, 1, &head_page); if (!n) break; - start = (loff_t)page->index * PAGE_SIZE; /* May regress with THPs */ + folio = page_folio(head_page); + start = folio_pos(folio); /* May regress with THPs */ - _debug("wback %lx", page->index); + _debug("wback %lx", folio_index(folio)); /* At this point we hold neither the i_pages lock nor the * page lock: the page may be truncated or invalidated @@ -707,37 +694,38 @@ static int afs_writepages_region(struct address_space *mapping, * back from swapper_space to tmpfs file mapping */ if (wbc->sync_mode != WB_SYNC_NONE) { - ret = lock_page_killable(page); + ret = folio_lock_killable(folio); if (ret < 0) { - put_page(page); + folio_put(folio); return ret; } } else { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return 0; } } - if (page->mapping != mapping || !PageDirty(page)) { - start += thp_size(page); - unlock_page(page); - put_page(page); + if (folio_mapping(folio) != mapping || + !folio_test_dirty(folio)) { + start += folio_size(folio); + folio_unlock(folio); + folio_put(folio); continue; } - if (PageWriteback(page)) { - unlock_page(page); + if (folio_test_writeback(folio)) { + folio_unlock(folio); if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - put_page(page); + folio_wait_writeback(folio); + folio_put(folio); continue; } - if (!clear_page_dirty_for_io(page)) + if (!folio_clear_dirty_for_io(folio)) BUG(); - ret = afs_write_back_from_locked_page(mapping, wbc, page, start, end); - put_page(page); + ret = afs_write_back_from_locked_folio(mapping, wbc, folio, start, end); + folio_put(folio); if (ret < 0) { _leave(" = %zd", ret); return ret; @@ -862,7 +850,6 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { struct folio *folio = page_folio(vmf->page); - struct page *page = &folio->page; struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); @@ -870,7 +857,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) unsigned long priv; vm_fault_t ret = VM_FAULT_RETRY; - _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); afs_validate(vnode, af->key); @@ -880,18 +867,18 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) * be modified. We then assume the entire page will need writing back. */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page) && - wait_on_page_fscache_killable(page) < 0) + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) goto out; #endif if (folio_wait_writeback_killable(folio)) goto out; - if (lock_page_killable(page) < 0) + if (folio_lock_killable(folio) < 0) goto out; - /* We mustn't change page->private until writeback is complete as that + /* We mustn't change folio->private until writeback is complete as that * details the portion of the page we need to write back and we might * need to redirty the page if there's a problem. */ @@ -900,14 +887,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) goto out; } - priv = afs_page_dirty(page, 0, thp_size(page)); - priv = afs_page_dirty_mmapped(priv); - if (PagePrivate(page)) { - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("mkwrite+"), page); + priv = afs_folio_dirty(folio, 0, folio_size(folio)); + priv = afs_folio_dirty_mmapped(priv); + if (folio_test_private(folio)) { + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio); } else { - attach_page_private(page, (void *)priv); - trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"), page); + folio_attach_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio); } file_update_time(file); @@ -948,38 +935,38 @@ void afs_prune_wb_keys(struct afs_vnode *vnode) /* * Clean up a page during invalidation. */ -int afs_launder_page(struct page *page) +int afs_launder_page(struct page *subpage) { - struct address_space *mapping = page->mapping; - struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); struct iov_iter iter; struct bio_vec bv[1]; unsigned long priv; unsigned int f, t; int ret = 0; - _enter("{%lx}", page->index); + _enter("{%lx}", folio_index(folio)); - priv = page_private(page); - if (clear_page_dirty_for_io(page)) { + priv = (unsigned long)folio_get_private(folio); + if (folio_clear_dirty_for_io(folio)) { f = 0; - t = thp_size(page); - if (PagePrivate(page)) { - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + t = folio_size(folio); + if (folio_test_private(folio)) { + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); } - bv[0].bv_page = page; + bv[0].bv_page = &folio->page; bv[0].bv_offset = f; bv[0].bv_len = t - f; iov_iter_bvec(&iter, WRITE, bv, 1, bv[0].bv_len); - trace_afs_page_dirty(vnode, tracepoint_string("launder"), page); - ret = afs_store_data(vnode, &iter, page_offset(page) + f, true); + trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio); + ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true); } - trace_afs_page_dirty(vnode, tracepoint_string("laundered"), page); - detach_page_private(page); - wait_on_page_fscache(page); + trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio); + folio_detach_private(folio); + folio_wait_fscache(folio); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 581662d16b72..11204dbbe053 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1912,16 +1912,17 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { + const bool is_sync_write = (iocb->ki_flags & IOCB_DSYNC); struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); loff_t pos; ssize_t written = 0; ssize_t written_buffered; + size_t prev_left = 0; loff_t endbyte; ssize_t err; unsigned int ilock_flags = 0; - struct iomap_dio *dio = NULL; if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; @@ -1964,23 +1965,80 @@ relock: goto buffered; } - dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - 0, 0); + /* + * We remove IOCB_DSYNC so that we don't deadlock when iomap_dio_rw() + * calls generic_write_sync() (through iomap_dio_complete()), because + * that results in calling fsync (btrfs_sync_file()) which will try to + * lock the inode in exclusive/write mode. + */ + if (is_sync_write) + iocb->ki_flags &= ~IOCB_DSYNC; - btrfs_inode_unlock(inode, ilock_flags); + /* + * The iov_iter can be mapped to the same file range we are writing to. + * If that's the case, then we will deadlock in the iomap code, because + * it first calls our callback btrfs_dio_iomap_begin(), which will create + * an ordered extent, and after that it will fault in the pages that the + * iov_iter refers to. During the fault in we end up in the readahead + * pages code (starting at btrfs_readahead()), which will lock the range, + * find that ordered extent and then wait for it to complete (at + * btrfs_lock_and_flush_ordered_range()), resulting in a deadlock since + * obviously the ordered extent can never complete as we didn't submit + * yet the respective bio(s). This always happens when the buffer is + * memory mapped to the same file range, since the iomap DIO code always + * invalidates pages in the target file range (after starting and waiting + * for any writeback). + * + * So here we disable page faults in the iov_iter and then retry if we + * got -EFAULT, faulting in the pages before the retry. + */ +again: + from->nofault = true; + err = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + IOMAP_DIO_PARTIAL, written); + from->nofault = false; - if (IS_ERR_OR_NULL(dio)) { - err = PTR_ERR_OR_ZERO(dio); - if (err < 0 && err != -ENOTBLK) - goto out; - } else { - written = iomap_dio_complete(dio); + /* No increment (+=) because iomap returns a cumulative value. */ + if (err > 0) + written = err; + + if (iov_iter_count(from) > 0 && (err == -EFAULT || err > 0)) { + const size_t left = iov_iter_count(from); + /* + * We have more data left to write. Try to fault in as many as + * possible of the remainder pages and retry. We do this without + * releasing and locking again the inode, to prevent races with + * truncate. + * + * Also, in case the iov refers to pages in the file range of the + * file we want to write to (due to a mmap), we could enter an + * infinite loop if we retry after faulting the pages in, since + * iomap will invalidate any pages in the range early on, before + * it tries to fault in the pages of the iov. So we keep track of + * how much was left of iov in the previous EFAULT and fallback + * to buffered IO in case we haven't made any progress. + */ + if (left == prev_left) { + err = -ENOTBLK; + } else { + fault_in_iov_iter_readable(from, left); + prev_left = left; + goto again; + } } - if (written < 0 || !iov_iter_count(from)) { - err = written; + btrfs_inode_unlock(inode, ilock_flags); + + /* + * Add back IOCB_DSYNC. Our caller, btrfs_file_write_iter(), will do + * the fsync (call generic_write_sync()). + */ + if (is_sync_write) + iocb->ki_flags |= IOCB_DSYNC; + + /* If 'err' is -ENOTBLK then it means we must fallback to buffered IO. */ + if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from)) goto out; - } buffered: pos = iocb->ki_pos; @@ -2005,7 +2063,7 @@ buffered: invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); out: - return written ? written : err; + return err < 0 ? err : written; } static ssize_t btrfs_file_write_iter(struct kiocb *iocb, @@ -3659,6 +3717,8 @@ static int check_direct_read(struct btrfs_fs_info *fs_info, static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); + size_t prev_left = 0; + ssize_t read = 0; ssize_t ret; if (fsverity_active(inode)) @@ -3668,10 +3728,57 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) return 0; btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); +again: + /* + * This is similar to what we do for direct IO writes, see the comment + * at btrfs_direct_write(), but we also disable page faults in addition + * to disabling them only at the iov_iter level. This is because when + * reading from a hole or prealloc extent, iomap calls iov_iter_zero(), + * which can still trigger page fault ins despite having set ->nofault + * to true of our 'to' iov_iter. + * + * The difference to direct IO writes is that we deadlock when trying + * to lock the extent range in the inode's tree during he page reads + * triggered by the fault in (while for writes it is due to waiting for + * our own ordered extent). This is because for direct IO reads, + * btrfs_dio_iomap_begin() returns with the extent range locked, which + * is only unlocked in the endio callback (end_bio_extent_readpage()). + */ + pagefault_disable(); + to->nofault = true; ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - 0, 0); + IOMAP_DIO_PARTIAL, read); + to->nofault = false; + pagefault_enable(); + + /* No increment (+=) because iomap returns a cumulative value. */ + if (ret > 0) + read = ret; + + if (iov_iter_count(to) > 0 && (ret == -EFAULT || ret > 0)) { + const size_t left = iov_iter_count(to); + + if (left == prev_left) { + /* + * We didn't make any progress since the last attempt, + * fallback to a buffered read for the remainder of the + * range. This is just to avoid any possibility of looping + * for too long. + */ + ret = read; + } else { + /* + * We made some progress since the last retry or this is + * the first time we are retrying. Fault in as many pages + * as possible and retry. + */ + fault_in_iov_iter_writeable(to, left); + prev_left = left; + goto again; + } + } btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); - return ret; + return ret < 0 ? ret : read; } static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 99b80b5c7a93..e53c8541f5b2 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -63,7 +63,7 @@ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); static inline struct ceph_snap_context *page_snap_context(struct page *page) { @@ -317,13 +317,14 @@ static const struct netfs_read_request_ops ceph_netfs_read_ops = { }; /* read a single page, without unlocking it. */ -static int ceph_readpage(struct file *file, struct page *page) +static int ceph_readpage(struct file *file, struct page *subpage) { + struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_vino vino = ceph_vino(inode); - u64 off = page_offset(page); - u64 len = thp_size(page); + size_t len = folio_size(folio); + u64 off = folio_file_pos(folio); if (ci->i_inline_version != CEPH_INLINE_NONE) { /* @@ -331,19 +332,19 @@ static int ceph_readpage(struct file *file, struct page *page) * into page cache while getting Fcr caps. */ if (off == 0) { - unlock_page(page); + folio_unlock(folio); return -EINVAL; } - zero_user_segment(page, 0, thp_size(page)); - SetPageUptodate(page); - unlock_page(page); + zero_user_segment(&folio->page, 0, folio_size(folio)); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; } - dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n", - vino.ino, vino.snap, file, off, len, page, page->index); + dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n", + vino.ino, vino.snap, file, off, len, folio, folio_index(folio)); - return netfs_readpage(file, page, &ceph_netfs_read_ops, NULL); + return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL); } static void ceph_readahead(struct readahead_control *ractl) @@ -724,7 +725,7 @@ static int ceph_writepages_start(struct address_space *mapping, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD")); - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { + if (ceph_inode_is_shutdown(inode)) { if (ci->i_wrbuffer_ref > 0) { pr_warn_ratelimited( "writepage_start %p %lld forced umount\n", @@ -1145,12 +1146,12 @@ static struct ceph_snap_context * ceph_find_incompatible(struct page *page) { struct inode *inode = page->mapping->host; - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - dout(" page %p forced umount\n", page); - return ERR_PTR(-EIO); + if (ceph_inode_is_shutdown(inode)) { + dout(" page %p %llx:%llx is shutdown\n", page, + ceph_vinop(inode)); + return ERR_PTR(-ESTALE); } for (;;) { @@ -1187,18 +1188,18 @@ ceph_find_incompatible(struct page *page) } static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct page *page, void **_fsdata) + struct folio *folio, void **_fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc; - snapc = ceph_find_incompatible(page); + snapc = ceph_find_incompatible(folio_page(folio, 0)); if (snapc) { int r; - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (IS_ERR(snapc)) return PTR_ERR(snapc); @@ -1216,12 +1217,12 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned * clean, or already dirty within the same snap context. */ static int ceph_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, unsigned aop_flags, struct page **pagep, void **fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct page *page = NULL; + struct folio *folio = NULL; pgoff_t index = pos >> PAGE_SHIFT; int r; @@ -1230,39 +1231,43 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, * for inline_version sent to the MDS. */ if (ci->i_inline_version != CEPH_INLINE_NONE) { - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) + unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) return -ENOMEM; /* * The inline_version on a new inode is set to 1. If that's the - * case, then the page is brand new and isn't yet Uptodate. + * case, then the folio is brand new and isn't yet Uptodate. */ r = 0; if (index == 0 && ci->i_inline_version != 1) { - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n", ci->i_inline_version); r = -EINVAL; } goto out; } - zero_user_segment(page, 0, thp_size(page)); - SetPageUptodate(page); + zero_user_segment(&folio->page, 0, folio_size(folio)); + folio_mark_uptodate(folio); goto out; } - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL, + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL, &ceph_netfs_read_ops, NULL); out: if (r == 0) - wait_on_page_fscache(page); + folio_wait_fscache(folio); if (r < 0) { - if (page) - put_page(page); + if (folio) + folio_put(folio); } else { - WARN_ON_ONCE(!PageLocked(page)); - *pagep = page; + WARN_ON_ONCE(!folio_test_locked(folio)); + *pagep = &folio->page; } return r; } @@ -1273,32 +1278,33 @@ out: */ static int ceph_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { + struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); bool check_cap = false; - dout("write_end file %p inode %p page %p %d~%d (%d)\n", file, - inode, page, (int)pos, (int)copied, (int)len); + dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file, + inode, folio, (int)pos, (int)copied, (int)len); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { /* just return that nothing was copied on a short copy */ if (copied < len) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* did file size increase? */ if (pos+copied > i_size_read(inode)) check_cap = ceph_inode_set_size(inode, pos+copied); - set_page_dirty(page); + folio_mark_dirty(folio); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (check_cap) ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL); @@ -1306,17 +1312,6 @@ out: return copied; } -/* - * we set .direct_IO to indicate direct io is supported, but since we - * intercept O_DIRECT reads and writes early, this function should - * never get called. - */ -static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter) -{ - WARN_ON(1); - return -EINVAL; -} - const struct address_space_operations ceph_aops = { .readpage = ceph_readpage, .readahead = ceph_readahead, @@ -1327,7 +1322,7 @@ const struct address_space_operations ceph_aops = { .set_page_dirty = ceph_set_page_dirty, .invalidatepage = ceph_invalidatepage, .releasepage = ceph_releasepage, - .direct_IO = ceph_direct_io, + .direct_IO = noop_direct_IO, }; static void ceph_block_sigs(sigset_t *oldset) @@ -1356,6 +1351,9 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) sigset_t oldset; vm_fault_t ret = VM_FAULT_SIGBUS; + if (ceph_inode_is_shutdown(inode)) + return ret; + ceph_block_sigs(&oldset); dout("filemap_fault %p %llx.%llx %llu trying to get caps\n", @@ -1447,6 +1445,9 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf) sigset_t oldset; vm_fault_t ret = VM_FAULT_SIGBUS; + if (ceph_inode_is_shutdown(inode)) + return ret; + prealloc_cf = ceph_alloc_cap_flush(); if (!prealloc_cf) return VM_FAULT_OOM; diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 9cfadbb86568..457afda5498a 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -12,12 +12,6 @@ #include "super.h" #include "cache.h" -struct ceph_aux_inode { - u64 version; - u64 mtime_sec; - u64 mtime_nsec; -}; - struct fscache_netfs ceph_cache_netfs = { .name = "ceph", .version = 0, @@ -109,20 +103,14 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux( void *cookie_netfs_data, const void *data, uint16_t dlen, loff_t object_size) { - struct ceph_aux_inode aux; struct ceph_inode_info* ci = cookie_netfs_data; struct inode* inode = &ci->vfs_inode; - if (dlen != sizeof(aux) || + if (dlen != sizeof(ci->i_version) || i_size_read(inode) != object_size) return FSCACHE_CHECKAUX_OBSOLETE; - memset(&aux, 0, sizeof(aux)); - aux.version = ci->i_version; - aux.mtime_sec = inode->i_mtime.tv_sec; - aux.mtime_nsec = inode->i_mtime.tv_nsec; - - if (memcmp(data, &aux, sizeof(aux)) != 0) + if (*(u64 *)data != ci->i_version) return FSCACHE_CHECKAUX_OBSOLETE; dout("ceph inode 0x%p cached okay\n", ci); @@ -139,7 +127,6 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - struct ceph_aux_inode aux; /* No caching for filesystem */ if (!fsc->fscache) @@ -151,14 +138,10 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) inode_lock_nested(inode, I_MUTEX_CHILD); if (!ci->fscache) { - memset(&aux, 0, sizeof(aux)); - aux.version = ci->i_version; - aux.mtime_sec = inode->i_mtime.tv_sec; - aux.mtime_nsec = inode->i_mtime.tv_nsec; ci->fscache = fscache_acquire_cookie(fsc->fscache, &ceph_fscache_inode_object_def, &ci->i_vino, sizeof(ci->i_vino), - &aux, sizeof(aux), + &ci->i_version, sizeof(ci->i_version), ci, i_size_read(inode), false); } inode_unlock(inode); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 8f537f1d9d1d..b9460b6fb76f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1188,11 +1188,11 @@ void ceph_remove_cap(struct ceph_cap *cap, bool queue_release) lockdep_assert_held(&ci->i_ceph_lock); - fsc = ceph_sb_to_client(ci->vfs_inode.i_sb); + fsc = ceph_inode_to_client(&ci->vfs_inode); WARN_ON_ONCE(ci->i_auth_cap == cap && !list_empty(&ci->i_dirty_item) && !fsc->blocklisted && - READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN); + !ceph_inode_is_shutdown(&ci->vfs_inode)); __ceph_remove_cap(cap, queue_release); } @@ -1968,8 +1968,8 @@ retry: } } - dout("check_caps %p file_want %s used %s dirty %s flushing %s" - " issued %s revoking %s retain %s %s%s\n", inode, + dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s" + " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode), ceph_cap_string(file_wanted), ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps), ceph_cap_string(ci->i_flushing_caps), @@ -1990,7 +1990,8 @@ retry: (revoking & (CEPH_CAP_FILE_CACHE| CEPH_CAP_FILE_LAZYIO)) && /* or revoking cache */ !tried_invalidate) { - dout("check_caps trying to invalidate on %p\n", inode); + dout("check_caps trying to invalidate on %llx.%llx\n", + ceph_vinop(inode)); if (try_nonblocking_invalidate(inode) < 0) { dout("check_caps queuing invalidate\n"); queue_invalidate = true; @@ -2629,9 +2630,9 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got, * * Returns 0 if caps were not able to be acquired (yet), 1 if succeed, * or a negative error code. There are 3 speical error codes: - * -EAGAIN: need to sleep but non-blocking is specified - * -EFBIG: ask caller to call check_max_size() and try again. - * -ESTALE: ask caller to call ceph_renew_caps() and try again. + * -EAGAIN: need to sleep but non-blocking is specified + * -EFBIG: ask caller to call check_max_size() and try again. + * -EUCLEAN: ask caller to call ceph_renew_caps() and try again. */ enum { /* first 8 bits are reserved for CEPH_FILE_MODE_FOO */ @@ -2679,7 +2680,7 @@ again: dout("get_cap_refs %p endoff %llu > maxsize %llu\n", inode, endoff, ci->i_max_size); if (endoff > ci->i_requested_max_size) - ret = ci->i_auth_cap ? -EFBIG : -ESTALE; + ret = ci->i_auth_cap ? -EFBIG : -EUCLEAN; goto out_unlock; } /* @@ -2749,9 +2750,9 @@ again: goto out_unlock; } - if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - dout("get_cap_refs %p forced umount\n", inode); - ret = -EIO; + if (ceph_inode_is_shutdown(inode)) { + dout("get_cap_refs %p inode is shutdown\n", inode); + ret = -ESTALE; goto out_unlock; } mds_wanted = __ceph_caps_mds_wanted(ci, false); @@ -2759,7 +2760,7 @@ again: dout("get_cap_refs %p need %s > mds_wanted %s\n", inode, ceph_cap_string(need), ceph_cap_string(mds_wanted)); - ret = -ESTALE; + ret = -EUCLEAN; goto out_unlock; } @@ -2843,7 +2844,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, ret = try_get_cap_refs(inode, need, want, 0, flags, got); /* three special error codes */ - if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE) + if (ret == -EAGAIN || ret == -EFBIG || ret == -EUCLEAN) ret = 0; return ret; } @@ -2926,7 +2927,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got } if (ret < 0) { - if (ret == -EFBIG || ret == -ESTALE) { + if (ret == -EFBIG || ret == -EUCLEAN) { int ret2 = ceph_wait_on_async_create(inode); if (ret2 < 0) return ret2; @@ -2935,7 +2936,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got check_max_size(inode, endoff); continue; } - if (ret == -ESTALE) { + if (ret == -EUCLEAN) { /* session was killed, try renew caps */ ret = ceph_renew_caps(inode, flags); if (ret == 0) @@ -4315,7 +4316,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s) i_dirty_item); inode = &ci->vfs_inode; ihold(inode); - dout("flush_dirty_caps %p\n", inode); + dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode)); spin_unlock(&mdsc->cap_dirty_lock); ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL); iput(inode); @@ -4560,3 +4561,119 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_unlock(&dentry->d_lock); return ret; } + +static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_cap_snap *capsnap; + int capsnap_release = 0; + + lockdep_assert_held(&ci->i_ceph_lock); + + dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode); + + while (!list_empty(&ci->i_cap_snaps)) { + capsnap = list_first_entry(&ci->i_cap_snaps, + struct ceph_cap_snap, ci_item); + __ceph_remove_capsnap(inode, capsnap, NULL, NULL); + ceph_put_snap_context(capsnap->context); + ceph_put_cap_snap(capsnap); + capsnap_release++; + } + wake_up_all(&ci->i_cap_wq); + wake_up_all(&mdsc->cap_flushing_wq); + return capsnap_release; +} + +int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate) +{ + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_mds_client *mdsc = fsc->mdsc; + struct ceph_inode_info *ci = ceph_inode(inode); + bool is_auth; + bool dirty_dropped = false; + int iputs = 0; + + lockdep_assert_held(&ci->i_ceph_lock); + + dout("removing cap %p, ci is %p, inode is %p\n", + cap, ci, &ci->vfs_inode); + + is_auth = (cap == ci->i_auth_cap); + __ceph_remove_cap(cap, false); + if (is_auth) { + struct ceph_cap_flush *cf; + + if (ceph_inode_is_shutdown(inode)) { + if (inode->i_data.nrpages > 0) + *invalidate = true; + if (ci->i_wrbuffer_ref > 0) + mapping_set_error(&inode->i_data, -EIO); + } + + spin_lock(&mdsc->cap_dirty_lock); + + /* trash all of the cap flushes for this inode */ + while (!list_empty(&ci->i_cap_flush_list)) { + cf = list_first_entry(&ci->i_cap_flush_list, + struct ceph_cap_flush, i_list); + list_del_init(&cf->g_list); + list_del_init(&cf->i_list); + if (!cf->is_capsnap) + ceph_free_cap_flush(cf); + } + + if (!list_empty(&ci->i_dirty_item)) { + pr_warn_ratelimited( + " dropping dirty %s state for %p %lld\n", + ceph_cap_string(ci->i_dirty_caps), + inode, ceph_ino(inode)); + ci->i_dirty_caps = 0; + list_del_init(&ci->i_dirty_item); + dirty_dropped = true; + } + if (!list_empty(&ci->i_flushing_item)) { + pr_warn_ratelimited( + " dropping dirty+flushing %s state for %p %lld\n", + ceph_cap_string(ci->i_flushing_caps), + inode, ceph_ino(inode)); + ci->i_flushing_caps = 0; + list_del_init(&ci->i_flushing_item); + mdsc->num_cap_flushing--; + dirty_dropped = true; + } + spin_unlock(&mdsc->cap_dirty_lock); + + if (dirty_dropped) { + mapping_set_error(inode->i_mapping, -EIO); + + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } + } + + if (atomic_read(&ci->i_filelock_ref) > 0) { + /* make further file lock syscall return -EIO */ + ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK; + pr_warn_ratelimited(" dropping file locks for %p %lld\n", + inode, ceph_ino(inode)); + } + + if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) { + cf = ci->i_prealloc_cap_flush; + ci->i_prealloc_cap_flush = NULL; + if (!cf->is_capsnap) + ceph_free_cap_flush(cf); + } + + if (!list_empty(&ci->i_cap_snaps)) + iputs = remove_capsnaps(mdsc, inode); + } + if (dirty_dropped) + ++iputs; + return iputs; +} diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 38b78b45811f..3cf7c9c1085b 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -146,82 +146,93 @@ static int mdsc_show(struct seq_file *s, void *p) name, total, avg, _min, max, sum); \ } -static int metric_show(struct seq_file *s, void *p) +static int metrics_file_show(struct seq_file *s, void *p) { struct ceph_fs_client *fsc = s->private; - struct ceph_mds_client *mdsc = fsc->mdsc; - struct ceph_client_metric *m = &mdsc->metric; - int nr_caps = 0; - s64 total, sum, avg, min, max, sq; - u64 sum_sz, avg_sz, min_sz, max_sz; + struct ceph_client_metric *m = &fsc->mdsc->metric; - sum = percpu_counter_sum(&m->total_inodes); seq_printf(s, "item total\n"); seq_printf(s, "------------------------------------------\n"); - seq_printf(s, "%-35s%lld / %lld\n", "opened files / total inodes", - atomic64_read(&m->opened_files), sum); - seq_printf(s, "%-35s%lld / %lld\n", "pinned i_caps / total inodes", - atomic64_read(&m->total_caps), sum); - seq_printf(s, "%-35s%lld / %lld\n", "opened inodes / total inodes", - percpu_counter_sum(&m->opened_inodes), sum); - - seq_printf(s, "\n"); + seq_printf(s, "%-35s%lld\n", "total inodes", + percpu_counter_sum(&m->total_inodes)); + seq_printf(s, "%-35s%lld\n", "opened files", + atomic64_read(&m->opened_files)); + seq_printf(s, "%-35s%lld\n", "pinned i_caps", + atomic64_read(&m->total_caps)); + seq_printf(s, "%-35s%lld\n", "opened inodes", + percpu_counter_sum(&m->opened_inodes)); + return 0; +} + +static const char * const metric_str[] = { + "read", + "write", + "metadata", + "copyfrom" +}; +static int metrics_latency_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_client_metric *cm = &fsc->mdsc->metric; + struct ceph_metric *m; + s64 total, sum, avg, min, max, sq; + int i; + seq_printf(s, "item total avg_lat(us) min_lat(us) max_lat(us) stdev(us)\n"); seq_printf(s, "-----------------------------------------------------------------------------------\n"); - spin_lock(&m->read_metric_lock); - total = m->total_reads; - sum = m->read_latency_sum; - avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; - min = m->read_latency_min; - max = m->read_latency_max; - sq = m->read_latency_sq_sum; - spin_unlock(&m->read_metric_lock); - CEPH_LAT_METRIC_SHOW("read", total, avg, min, max, sq); - - spin_lock(&m->write_metric_lock); - total = m->total_writes; - sum = m->write_latency_sum; - avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; - min = m->write_latency_min; - max = m->write_latency_max; - sq = m->write_latency_sq_sum; - spin_unlock(&m->write_metric_lock); - CEPH_LAT_METRIC_SHOW("write", total, avg, min, max, sq); - - spin_lock(&m->metadata_metric_lock); - total = m->total_metadatas; - sum = m->metadata_latency_sum; - avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; - min = m->metadata_latency_min; - max = m->metadata_latency_max; - sq = m->metadata_latency_sq_sum; - spin_unlock(&m->metadata_metric_lock); - CEPH_LAT_METRIC_SHOW("metadata", total, avg, min, max, sq); - - seq_printf(s, "\n"); + for (i = 0; i < METRIC_MAX; i++) { + m = &cm->metric[i]; + spin_lock(&m->lock); + total = m->total; + sum = m->latency_sum; + avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; + min = m->latency_min; + max = m->latency_max; + sq = m->latency_sq_sum; + spin_unlock(&m->lock); + CEPH_LAT_METRIC_SHOW(metric_str[i], total, avg, min, max, sq); + } + + return 0; +} + +static int metrics_size_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_client_metric *cm = &fsc->mdsc->metric; + struct ceph_metric *m; + s64 total; + u64 sum, avg, min, max; + int i; + seq_printf(s, "item total avg_sz(bytes) min_sz(bytes) max_sz(bytes) total_sz(bytes)\n"); seq_printf(s, "----------------------------------------------------------------------------------------\n"); - spin_lock(&m->read_metric_lock); - total = m->total_reads; - sum_sz = m->read_size_sum; - avg_sz = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum_sz, total) : 0; - min_sz = m->read_size_min; - max_sz = m->read_size_max; - spin_unlock(&m->read_metric_lock); - CEPH_SZ_METRIC_SHOW("read", total, avg_sz, min_sz, max_sz, sum_sz); - - spin_lock(&m->write_metric_lock); - total = m->total_writes; - sum_sz = m->write_size_sum; - avg_sz = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum_sz, total) : 0; - min_sz = m->write_size_min; - max_sz = m->write_size_max; - spin_unlock(&m->write_metric_lock); - CEPH_SZ_METRIC_SHOW("write", total, avg_sz, min_sz, max_sz, sum_sz); - - seq_printf(s, "\n"); + for (i = 0; i < METRIC_MAX; i++) { + /* skip 'metadata' as it doesn't use the size metric */ + if (i == METRIC_METADATA) + continue; + m = &cm->metric[i]; + spin_lock(&m->lock); + total = m->total; + sum = m->size_sum; + avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; + min = m->size_min; + max = m->size_max; + spin_unlock(&m->lock); + CEPH_SZ_METRIC_SHOW(metric_str[i], total, avg, min, max, sum); + } + + return 0; +} + +static int metrics_caps_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_client_metric *m = &fsc->mdsc->metric; + int nr_caps = 0; + seq_printf(s, "item total miss hit\n"); seq_printf(s, "-------------------------------------------------\n"); @@ -350,8 +361,11 @@ DEFINE_SHOW_ATTRIBUTE(mdsmap); DEFINE_SHOW_ATTRIBUTE(mdsc); DEFINE_SHOW_ATTRIBUTE(caps); DEFINE_SHOW_ATTRIBUTE(mds_sessions); -DEFINE_SHOW_ATTRIBUTE(metric); DEFINE_SHOW_ATTRIBUTE(status); +DEFINE_SHOW_ATTRIBUTE(metrics_file); +DEFINE_SHOW_ATTRIBUTE(metrics_latency); +DEFINE_SHOW_ATTRIBUTE(metrics_size); +DEFINE_SHOW_ATTRIBUTE(metrics_caps); /* @@ -385,8 +399,9 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) debugfs_remove(fsc->debugfs_mdsmap); debugfs_remove(fsc->debugfs_mds_sessions); debugfs_remove(fsc->debugfs_caps); - debugfs_remove(fsc->debugfs_metric); + debugfs_remove(fsc->debugfs_status); debugfs_remove(fsc->debugfs_mdsc); + debugfs_remove_recursive(fsc->debugfs_metrics_dir); } void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) @@ -426,12 +441,6 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) fsc, &mdsc_fops); - fsc->debugfs_metric = debugfs_create_file("metrics", - 0400, - fsc->client->debugfs_dir, - fsc, - &metric_fops); - fsc->debugfs_caps = debugfs_create_file("caps", 0400, fsc->client->debugfs_dir, @@ -443,6 +452,18 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) fsc->client->debugfs_dir, fsc, &status_fops); + + fsc->debugfs_metrics_dir = debugfs_create_dir("metrics", + fsc->client->debugfs_dir); + + debugfs_create_file("file", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_file_fops); + debugfs_create_file("latency", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_latency_fops); + debugfs_create_file("size", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_size_fops); + debugfs_create_file("caps", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_caps_fops); } diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 1d65934c1262..e0fa66ac8b9f 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -157,6 +157,11 @@ static struct inode *__lookup_inode(struct super_block *sb, u64 ino) ceph_mdsc_put_request(req); if (!inode) return err < 0 ? ERR_PTR(err) : ERR_PTR(-ESTALE); + } else { + if (ceph_inode_is_shutdown(inode)) { + iput(inode); + return ERR_PTR(-ESTALE); + } } return inode; } @@ -223,8 +228,13 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb, return ERR_PTR(-ESTALE); inode = ceph_find_inode(sb, vino); - if (inode) + if (inode) { + if (ceph_inode_is_shutdown(inode)) { + iput(inode); + return ERR_PTR(-ESTALE); + } return d_obtain_alias(inode); + } req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO, USE_ANY_MDS); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b129ea551378..02a0a0fd9ccd 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -525,6 +525,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, if (result) { struct dentry *dentry = req->r_dentry; + struct inode *inode = d_inode(dentry); int pathlen = 0; u64 base = 0; char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, @@ -534,7 +535,8 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, if (!d_unhashed(dentry)) d_drop(dentry); - /* FIXME: start returning I/O errors on all accesses? */ + ceph_inode_shutdown(inode); + pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n", base, IS_ERR(path) ? "<<bad>>" : path, result); ceph_mdsc_free_path(path, pathlen); @@ -556,7 +558,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, } ceph_kick_flushing_inode_caps(req->r_session, ci); spin_unlock(&ci->i_ceph_lock); - } else { + } else if (!result) { pr_warn("%s: no req->r_target_inode for 0x%llx\n", __func__, req->r_deleg_ino); } @@ -845,6 +847,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ssize_t ret; u64 off = iocb->ki_pos; u64 len = iov_iter_count(to); + u64 i_size; dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); @@ -868,7 +871,6 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, struct page **pages; int num_pages; size_t page_off; - u64 i_size; bool more; int idx; size_t left; @@ -951,11 +953,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, } if (off > iocb->ki_pos) { - if (ret >= 0 && - iov_iter_count(to) > 0 && off >= i_size_read(inode)) + if (off >= i_size) { *retry_op = CHECK_EOF; - ret = off - iocb->ki_pos; - iocb->ki_pos = off; + ret = i_size - iocb->ki_pos; + iocb->ki_pos = i_size; + } else { + ret = off - iocb->ki_pos; + iocb->ki_pos = off; + } } dout("sync_read result %zd retry_op %d\n", ret, *retry_op); @@ -1526,6 +1531,9 @@ again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode); + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + if (direct_lock) ceph_start_io_direct(inode); else @@ -1678,6 +1686,9 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) loff_t pos; loff_t limit = max(i_size_read(inode), fsc->max_file_size); + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; @@ -2200,6 +2211,54 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode, return 0; } +static struct ceph_osd_request * +ceph_alloc_copyfrom_request(struct ceph_osd_client *osdc, + u64 src_snapid, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 truncate_seq, u64 truncate_size) +{ + struct ceph_osd_request *req; + int ret; + u32 src_fadvise_flags = + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE; + u32 dst_fadvise_flags = + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED; + + req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); + if (!req) + return ERR_PTR(-ENOMEM); + + req->r_flags = CEPH_OSD_FLAG_WRITE; + + ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); + ceph_oid_copy(&req->r_t.base_oid, dst_oid); + + ret = osd_req_op_copy_from_init(req, src_snapid, 0, + src_oid, src_oloc, + src_fadvise_flags, + dst_fadvise_flags, + truncate_seq, + truncate_size, + CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + if (ret) + goto out; + + ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); + if (ret) + goto out; + + return req; + +out: + ceph_osdc_put_request(req); + return ERR_PTR(ret); +} + static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off, struct ceph_inode_info *dst_ci, u64 *dst_off, struct ceph_fs_client *fsc, @@ -2207,6 +2266,8 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off { struct ceph_object_locator src_oloc, dst_oloc; struct ceph_object_id src_oid, dst_oid; + struct ceph_osd_client *osdc; + struct ceph_osd_request *req; size_t bytes = 0; u64 src_objnum, src_objoff, dst_objnum, dst_objoff; u32 src_objlen, dst_objlen; @@ -2217,6 +2278,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns); dst_oloc.pool = dst_ci->i_layout.pool_id; dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns); + osdc = &fsc->client->osdc; while (len >= object_size) { ceph_calc_file_object_mapping(&src_ci->i_layout, *src_off, @@ -2232,17 +2294,22 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off ceph_oid_printf(&dst_oid, "%llx.%08llx", dst_ci->i_vino.ino, dst_objnum); /* Do an object remote copy */ - ret = ceph_osdc_copy_from(&fsc->client->osdc, - src_ci->i_vino.snap, 0, - &src_oid, &src_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_NOCACHE, - &dst_oid, &dst_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, - dst_ci->i_truncate_seq, - dst_ci->i_truncate_size, - CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + req = ceph_alloc_copyfrom_request(osdc, src_ci->i_vino.snap, + &src_oid, &src_oloc, + &dst_oid, &dst_oloc, + dst_ci->i_truncate_seq, + dst_ci->i_truncate_size); + if (IS_ERR(req)) + ret = PTR_ERR(req); + else { + ceph_osdc_start_request(osdc, req, false); + ret = ceph_osdc_wait_request(osdc, req); + ceph_update_copyfrom_metrics(&fsc->mdsc->metric, + req->r_start_latency, + req->r_end_latency, + object_size, ret); + ceph_osdc_put_request(req); + } if (ret) { if (ret == -EOPNOTSUPP) { fsc->have_copy_from2 = false; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 1c7574105478..e3322fcb2e8d 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1841,15 +1841,14 @@ void ceph_queue_inode_work(struct inode *inode, int work_bit) static void ceph_do_invalidate_pages(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); u32 orig_gen; int check = 0; mutex_lock(&ci->i_truncate_mutex); - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n", - inode, ceph_ino(inode)); + if (ceph_inode_is_shutdown(inode)) { + pr_warn_ratelimited("%s: inode %llx.%llx is shut down\n", + __func__, ceph_vinop(inode)); mapping_set_error(inode->i_mapping, -EIO); truncate_pagecache(inode, 0); mutex_unlock(&ci->i_truncate_mutex); @@ -1871,7 +1870,8 @@ static void ceph_do_invalidate_pages(struct inode *inode) ceph_fscache_invalidate(inode); if (invalidate_inode_pages2(inode->i_mapping) < 0) { - pr_err("invalidate_pages %p fails\n", inode); + pr_err("invalidate_inode_pages2 %llx.%llx failed\n", + ceph_vinop(inode)); } spin_lock(&ci->i_ceph_lock); @@ -2103,12 +2103,14 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) loff_t isize = i_size_read(inode); dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size); - if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size > isize) { - i_size_write(inode, attr->ia_size); - inode->i_blocks = calc_inode_blocks(attr->ia_size); - ci->i_reported_size = attr->ia_size; - dirtied |= CEPH_CAP_FILE_EXCL; - ia_valid |= ATTR_MTIME; + if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) { + if (attr->ia_size > isize) { + i_size_write(inode, attr->ia_size); + inode->i_blocks = calc_inode_blocks(attr->ia_size); + ci->i_reported_size = attr->ia_size; + dirtied |= CEPH_CAP_FILE_EXCL; + ia_valid |= ATTR_MTIME; + } } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || attr->ia_size != isize) { req->r_args.setattr.size = cpu_to_le64(attr->ia_size); @@ -2217,6 +2219,9 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + err = setattr_prepare(&init_user_ns, dentry, attr); if (err != 0) return err; @@ -2347,6 +2352,9 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, u32 valid_mask = STATX_BASIC_STATS; int err = 0; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + /* Skip the getattr altogether if we're asked not to sync */ if (!(flags & AT_STATX_DONT_SYNC)) { err = ceph_do_getattr(inode, @@ -2394,3 +2402,27 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->result_mask = request_mask & valid_mask; return err; } + +void ceph_inode_shutdown(struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct rb_node *p; + int iputs = 0; + bool invalidate = false; + + spin_lock(&ci->i_ceph_lock); + ci->i_ceph_flags |= CEPH_I_SHUTDOWN; + p = rb_first(&ci->i_caps); + while (p) { + struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); + + p = rb_next(p); + iputs += ceph_purge_inode_cap(inode, cap, &invalidate); + } + spin_unlock(&ci->i_ceph_lock); + + if (invalidate) + ceph_queue_invalidate(inode); + while (iputs--) + iput(inode); +} diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index d8c31069fbf2..d1f154aec249 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -241,6 +241,9 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + dout("ceph_lock, fl_owner: %p\n", fl->fl_owner); /* set wait bit as appropriate, then make command as Ceph expects it*/ @@ -303,6 +306,9 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + dout("ceph_flock, fl_file: %p\n", fl->fl_file); spin_lock(&ci->i_ceph_lock); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d64413adc0fd..250aad330a10 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1590,129 +1590,23 @@ out: return ret; } -static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode) -{ - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_cap_snap *capsnap; - int capsnap_release = 0; - - lockdep_assert_held(&ci->i_ceph_lock); - - dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode); - - while (!list_empty(&ci->i_cap_snaps)) { - capsnap = list_first_entry(&ci->i_cap_snaps, - struct ceph_cap_snap, ci_item); - __ceph_remove_capsnap(inode, capsnap, NULL, NULL); - ceph_put_snap_context(capsnap->context); - ceph_put_cap_snap(capsnap); - capsnap_release++; - } - wake_up_all(&ci->i_cap_wq); - wake_up_all(&mdsc->cap_flushing_wq); - return capsnap_release; -} - static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) { - struct ceph_fs_client *fsc = (struct ceph_fs_client *)arg; - struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); - LIST_HEAD(to_remove); - bool dirty_dropped = false; bool invalidate = false; - int capsnap_release = 0; + int iputs; dout("removing cap %p, ci is %p, inode is %p\n", cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); - __ceph_remove_cap(cap, false); - if (!ci->i_auth_cap) { - struct ceph_cap_flush *cf; - - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - if (inode->i_data.nrpages > 0) - invalidate = true; - if (ci->i_wrbuffer_ref > 0) - mapping_set_error(&inode->i_data, -EIO); - } - - while (!list_empty(&ci->i_cap_flush_list)) { - cf = list_first_entry(&ci->i_cap_flush_list, - struct ceph_cap_flush, i_list); - list_move(&cf->i_list, &to_remove); - } - - spin_lock(&mdsc->cap_dirty_lock); - - list_for_each_entry(cf, &to_remove, i_list) - list_del_init(&cf->g_list); - - if (!list_empty(&ci->i_dirty_item)) { - pr_warn_ratelimited( - " dropping dirty %s state for %p %lld\n", - ceph_cap_string(ci->i_dirty_caps), - inode, ceph_ino(inode)); - ci->i_dirty_caps = 0; - list_del_init(&ci->i_dirty_item); - dirty_dropped = true; - } - if (!list_empty(&ci->i_flushing_item)) { - pr_warn_ratelimited( - " dropping dirty+flushing %s state for %p %lld\n", - ceph_cap_string(ci->i_flushing_caps), - inode, ceph_ino(inode)); - ci->i_flushing_caps = 0; - list_del_init(&ci->i_flushing_item); - mdsc->num_cap_flushing--; - dirty_dropped = true; - } - spin_unlock(&mdsc->cap_dirty_lock); - - if (dirty_dropped) { - mapping_set_error(inode->i_mapping, -EIO); - - if (ci->i_wrbuffer_ref_head == 0 && - ci->i_wr_ref == 0 && - ci->i_dirty_caps == 0 && - ci->i_flushing_caps == 0) { - ceph_put_snap_context(ci->i_head_snapc); - ci->i_head_snapc = NULL; - } - } - - if (atomic_read(&ci->i_filelock_ref) > 0) { - /* make further file lock syscall return -EIO */ - ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK; - pr_warn_ratelimited(" dropping file locks for %p %lld\n", - inode, ceph_ino(inode)); - } - - if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) { - list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); - ci->i_prealloc_cap_flush = NULL; - } - - if (!list_empty(&ci->i_cap_snaps)) - capsnap_release = remove_capsnaps(mdsc, inode); - } + iputs = ceph_purge_inode_cap(inode, cap, &invalidate); spin_unlock(&ci->i_ceph_lock); - while (!list_empty(&to_remove)) { - struct ceph_cap_flush *cf; - cf = list_first_entry(&to_remove, - struct ceph_cap_flush, i_list); - list_del_init(&cf->i_list); - if (!cf->is_capsnap) - ceph_free_cap_flush(cf); - } wake_up_all(&ci->i_cap_wq); if (invalidate) ceph_queue_invalidate(inode); - if (dirty_dropped) - iput(inode); - while (capsnap_release--) + while (iputs--) iput(inode); return 0; } @@ -3467,9 +3361,14 @@ static void handle_session(struct ceph_mds_session *session, if (msg_version >= 3) { u32 len; - /* version >= 2, metadata */ - if (__decode_session_metadata(&p, end, &blocklisted) < 0) + /* version >= 2 and < 5, decode metadata, skip otherwise + * as it's handled via flags. + */ + if (msg_version >= 5) + ceph_decode_skip_map(&p, end, string, string, bad); + else if (__decode_session_metadata(&p, end, &blocklisted) < 0) goto bad; + /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); if (len) { @@ -3478,6 +3377,18 @@ static void handle_session(struct ceph_mds_session *session, } } + if (msg_version >= 5) { + u32 flags; + /* version >= 4, struct_v, struct_cv, len, metric_spec */ + ceph_decode_skip_n(&p, end, 2 + sizeof(u32) * 2, bad); + /* version >= 5, flags */ + ceph_decode_32_safe(&p, end, flags, bad); + if (flags & CEPH_SESSION_BLOCKLISTED) { + pr_warn("mds%d session blocklisted\n", session->s_mds); + blocklisted = true; + } + } + mutex_lock(&mdsc->mutex); if (op == CEPH_SESSION_CLOSE) { ceph_get_mds_session(session); @@ -5072,7 +4983,8 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) return; bad: - pr_err("error decoding fsmap\n"); + pr_err("error decoding fsmap %d. Shutting down mount.\n", err); + ceph_umount_begin(mdsc->fsc->sb); err_out: mutex_lock(&mdsc->mutex); mdsc->mdsmap_err = err; @@ -5139,7 +5051,8 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) bad_unlock: mutex_unlock(&mdsc->mutex); bad: - pr_err("error decoding mdsmap %d\n", err); + pr_err("error decoding mdsmap %d. Shutting down mount.\n", err); + ceph_umount_begin(mdsc->fsc->sb); return; } diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 61d67cbcb367..30387733765d 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -263,10 +263,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2) goto nomem; for (j = 0; j < num_export_targets; j++) { target = ceph_decode_32(&pexport_targets); - if (target >= m->possible_max_rank) { - err = -EIO; - goto corrupt; - } info->export_targets[j] = target; } } else { diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index 04d5df29bbbf..c57699d8408d 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -62,7 +62,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, read->header.ver = 1; read->header.compat = 1; read->header.data_len = cpu_to_le32(sizeof(*read) - header_len); - sum = m->read_latency_sum; + sum = m->metric[METRIC_READ].latency_sum; jiffies_to_timespec64(sum, &ts); read->sec = cpu_to_le32(ts.tv_sec); read->nsec = cpu_to_le32(ts.tv_nsec); @@ -74,7 +74,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, write->header.ver = 1; write->header.compat = 1; write->header.data_len = cpu_to_le32(sizeof(*write) - header_len); - sum = m->write_latency_sum; + sum = m->metric[METRIC_WRITE].latency_sum; jiffies_to_timespec64(sum, &ts); write->sec = cpu_to_le32(ts.tv_sec); write->nsec = cpu_to_le32(ts.tv_nsec); @@ -86,7 +86,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, meta->header.ver = 1; meta->header.compat = 1; meta->header.data_len = cpu_to_le32(sizeof(*meta) - header_len); - sum = m->metadata_latency_sum; + sum = m->metric[METRIC_METADATA].latency_sum; jiffies_to_timespec64(sum, &ts); meta->sec = cpu_to_le32(ts.tv_sec); meta->nsec = cpu_to_le32(ts.tv_nsec); @@ -141,8 +141,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, rsize->header.ver = 1; rsize->header.compat = 1; rsize->header.data_len = cpu_to_le32(sizeof(*rsize) - header_len); - rsize->total_ops = cpu_to_le64(m->total_reads); - rsize->total_size = cpu_to_le64(m->read_size_sum); + rsize->total_ops = cpu_to_le64(m->metric[METRIC_READ].total); + rsize->total_size = cpu_to_le64(m->metric[METRIC_READ].size_sum); items++; /* encode the write io size metric */ @@ -151,8 +151,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, wsize->header.ver = 1; wsize->header.compat = 1; wsize->header.data_len = cpu_to_le32(sizeof(*wsize) - header_len); - wsize->total_ops = cpu_to_le64(m->total_writes); - wsize->total_size = cpu_to_le64(m->write_size_sum); + wsize->total_ops = cpu_to_le64(m->metric[METRIC_WRITE].total); + wsize->total_size = cpu_to_le64(m->metric[METRIC_WRITE].size_sum); items++; put_unaligned_le32(items, &head->num); @@ -220,7 +220,8 @@ static void metric_delayed_work(struct work_struct *work) int ceph_metric_init(struct ceph_client_metric *m) { - int ret; + struct ceph_metric *metric; + int ret, i; if (!m) return -EINVAL; @@ -243,32 +244,18 @@ int ceph_metric_init(struct ceph_client_metric *m) if (ret) goto err_i_caps_mis; - spin_lock_init(&m->read_metric_lock); - m->read_latency_sq_sum = 0; - m->read_latency_min = KTIME_MAX; - m->read_latency_max = 0; - m->total_reads = 0; - m->read_latency_sum = 0; - m->read_size_min = U64_MAX; - m->read_size_max = 0; - m->read_size_sum = 0; - - spin_lock_init(&m->write_metric_lock); - m->write_latency_sq_sum = 0; - m->write_latency_min = KTIME_MAX; - m->write_latency_max = 0; - m->total_writes = 0; - m->write_latency_sum = 0; - m->write_size_min = U64_MAX; - m->write_size_max = 0; - m->write_size_sum = 0; - - spin_lock_init(&m->metadata_metric_lock); - m->metadata_latency_sq_sum = 0; - m->metadata_latency_min = KTIME_MAX; - m->metadata_latency_max = 0; - m->total_metadatas = 0; - m->metadata_latency_sum = 0; + for (i = 0; i < METRIC_MAX; i++) { + metric = &m->metric[i]; + spin_lock_init(&metric->lock); + metric->size_sum = 0; + metric->size_min = U64_MAX; + metric->size_max = 0; + metric->total = 0; + metric->latency_sum = 0; + metric->latency_sq_sum = 0; + metric->latency_min = KTIME_MAX; + metric->latency_max = 0; + } atomic64_set(&m->opened_files, 0); ret = percpu_counter_init(&m->opened_inodes, 0, GFP_KERNEL); @@ -338,9 +325,9 @@ static inline void __update_stdev(ktime_t total, ktime_t lsum, *sq_sump += sq; } -void ceph_update_read_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc) +void ceph_update_metrics(struct ceph_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) { ktime_t lat = ktime_sub(r_end, r_start); ktime_t total; @@ -348,63 +335,12 @@ void ceph_update_read_metrics(struct ceph_client_metric *m, if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT)) return; - spin_lock(&m->read_metric_lock); - total = ++m->total_reads; - m->read_size_sum += size; - m->read_latency_sum += lat; - METRIC_UPDATE_MIN_MAX(m->read_size_min, - m->read_size_max, - size); - METRIC_UPDATE_MIN_MAX(m->read_latency_min, - m->read_latency_max, - lat); - __update_stdev(total, m->read_latency_sum, - &m->read_latency_sq_sum, lat); - spin_unlock(&m->read_metric_lock); -} - -void ceph_update_write_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc) -{ - ktime_t lat = ktime_sub(r_end, r_start); - ktime_t total; - - if (unlikely(rc && rc != -ETIMEDOUT)) - return; - - spin_lock(&m->write_metric_lock); - total = ++m->total_writes; - m->write_size_sum += size; - m->write_latency_sum += lat; - METRIC_UPDATE_MIN_MAX(m->write_size_min, - m->write_size_max, - size); - METRIC_UPDATE_MIN_MAX(m->write_latency_min, - m->write_latency_max, - lat); - __update_stdev(total, m->write_latency_sum, - &m->write_latency_sq_sum, lat); - spin_unlock(&m->write_metric_lock); -} - -void ceph_update_metadata_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - int rc) -{ - ktime_t lat = ktime_sub(r_end, r_start); - ktime_t total; - - if (unlikely(rc && rc != -ENOENT)) - return; - - spin_lock(&m->metadata_metric_lock); - total = ++m->total_metadatas; - m->metadata_latency_sum += lat; - METRIC_UPDATE_MIN_MAX(m->metadata_latency_min, - m->metadata_latency_max, - lat); - __update_stdev(total, m->metadata_latency_sum, - &m->metadata_latency_sq_sum, lat); - spin_unlock(&m->metadata_metric_lock); + spin_lock(&m->lock); + total = ++m->total; + m->size_sum += size; + METRIC_UPDATE_MIN_MAX(m->size_min, m->size_max, size); + m->latency_sum += lat; + METRIC_UPDATE_MIN_MAX(m->latency_min, m->latency_max, lat); + __update_stdev(total, m->latency_sum, &m->latency_sq_sum, lat); + spin_unlock(&m->lock); } diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h index 0133955a3c6a..bb45608181e7 100644 --- a/fs/ceph/metric.h +++ b/fs/ceph/metric.h @@ -125,6 +125,26 @@ struct ceph_metric_head { __le32 num; /* the number of metrics that will be sent */ } __packed; +enum metric_type { + METRIC_READ, + METRIC_WRITE, + METRIC_METADATA, + METRIC_COPYFROM, + METRIC_MAX +}; + +struct ceph_metric { + spinlock_t lock; + u64 total; + u64 size_sum; + u64 size_min; + u64 size_max; + ktime_t latency_sum; + ktime_t latency_sq_sum; + ktime_t latency_min; + ktime_t latency_max; +}; + /* This is the global metrics */ struct ceph_client_metric { atomic64_t total_dentries; @@ -135,32 +155,7 @@ struct ceph_client_metric { struct percpu_counter i_caps_hit; struct percpu_counter i_caps_mis; - spinlock_t read_metric_lock; - u64 total_reads; - u64 read_size_sum; - u64 read_size_min; - u64 read_size_max; - ktime_t read_latency_sum; - ktime_t read_latency_sq_sum; - ktime_t read_latency_min; - ktime_t read_latency_max; - - spinlock_t write_metric_lock; - u64 total_writes; - u64 write_size_sum; - u64 write_size_min; - u64 write_size_max; - ktime_t write_latency_sum; - ktime_t write_latency_sq_sum; - ktime_t write_latency_min; - ktime_t write_latency_max; - - spinlock_t metadata_metric_lock; - u64 total_metadatas; - ktime_t metadata_latency_sum; - ktime_t metadata_latency_sq_sum; - ktime_t metadata_latency_min; - ktime_t metadata_latency_max; + struct ceph_metric metric[METRIC_MAX]; /* The total number of directories and files that are opened */ atomic64_t opened_files; @@ -195,13 +190,36 @@ static inline void ceph_update_cap_mis(struct ceph_client_metric *m) percpu_counter_inc(&m->i_caps_mis); } -extern void ceph_update_read_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc); -extern void ceph_update_write_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc); -extern void ceph_update_metadata_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - int rc); +extern void ceph_update_metrics(struct ceph_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc); + +static inline void ceph_update_read_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) +{ + ceph_update_metrics(&m->metric[METRIC_READ], + r_start, r_end, size, rc); +} +static inline void ceph_update_write_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) +{ + ceph_update_metrics(&m->metric[METRIC_WRITE], + r_start, r_end, size, rc); +} +static inline void ceph_update_metadata_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + int rc) +{ + ceph_update_metrics(&m->metric[METRIC_METADATA], + r_start, r_end, 0, rc); +} +static inline void ceph_update_copyfrom_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) +{ + ceph_update_metrics(&m->metric[METRIC_COPYFROM], + r_start, r_end, size, rc); +} #endif /* _FS_CEPH_MDS_METRIC_H */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index fd8742bae847..bab61232dc5a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -52,8 +52,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry)); struct ceph_mon_client *monc = &fsc->client->monc; struct ceph_statfs st; - u64 fsid; - int err; + int i, err; u64 data_pool; if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) { @@ -99,12 +98,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_namelen = NAME_MAX; /* Must convert the fsid, for consistent values across arches */ + buf->f_fsid.val[0] = 0; mutex_lock(&monc->mutex); - fsid = le64_to_cpu(*(__le64 *)(&monc->monmap->fsid)) ^ - le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1)); + for (i = 0 ; i < sizeof(monc->monmap->fsid) / sizeof(__le32) ; ++i) + buf->f_fsid.val[0] ^= le32_to_cpu(((__le32 *)&monc->monmap->fsid)[i]); mutex_unlock(&monc->mutex); - buf->f_fsid = u64_to_fsid(fsid); + /* fold the fs_cluster_id into the upper bits */ + buf->f_fsid.val[1] = monc->fs_cluster_id; return 0; } @@ -577,8 +578,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER) seq_show_option(m, "recover_session", "clean"); - if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) - seq_puts(m, ",nowsync"); + if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)) + seq_puts(m, ",wsync"); if (fsopt->wsize != CEPH_MAX_WRITE_SIZE) seq_printf(m, ",wsize=%u", fsopt->wsize); @@ -842,7 +843,7 @@ static void __ceph_umount_begin(struct ceph_fs_client *fsc) * ceph_umount_begin - initiate forced umount. Tear down the * mount, skipping steps that may hang while waiting for server(s). */ -static void ceph_umount_begin(struct super_block *sb) +void ceph_umount_begin(struct super_block *sb) { struct ceph_fs_client *fsc = ceph_sb_to_client(sb); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 14f951cd5b61..ac331aa07cfa 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -48,7 +48,8 @@ #define CEPH_MOUNT_OPT_DEFAULT \ (CEPH_MOUNT_OPT_DCACHE | \ - CEPH_MOUNT_OPT_NOCOPYFROM) + CEPH_MOUNT_OPT_NOCOPYFROM | \ + CEPH_MOUNT_OPT_ASYNC_DIROPS) #define ceph_set_mount_opt(fsc, opt) \ (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt @@ -128,9 +129,9 @@ struct ceph_fs_client { struct dentry *debugfs_congestion_kb; struct dentry *debugfs_bdi; struct dentry *debugfs_mdsc, *debugfs_mdsmap; - struct dentry *debugfs_metric; struct dentry *debugfs_status; struct dentry *debugfs_mds_sessions; + struct dentry *debugfs_metrics_dir; #endif #ifdef CONFIG_CEPH_FSCACHE @@ -580,6 +581,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ #define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) +#define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ /* * Masks of ceph inode work. @@ -939,6 +941,7 @@ extern void ceph_put_snapid_map(struct ceph_mds_client* mdsc, struct ceph_snapid_map *sm); extern void ceph_trim_snapid_map(struct ceph_mds_client *mdsc); extern void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc); +void ceph_umount_begin(struct super_block *sb); /* @@ -1027,6 +1030,16 @@ extern int ceph_setattr(struct user_namespace *mnt_userns, extern int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); +void ceph_inode_shutdown(struct inode *inode); + +static inline bool ceph_inode_is_shutdown(struct inode *inode) +{ + unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + int state = READ_ONCE(fsc->mount_state); + + return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN; +} /* xattr.c */ int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int); @@ -1198,6 +1211,7 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); extern int ceph_uninline_data(struct file *filp, struct page *locked_page); extern int ceph_pool_perm_check(struct inode *inode, int need); extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); +int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate); /* file.c */ extern const struct file_operations ceph_file_fops; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index de2c12bcfa4b..d282caf9f037 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -271,7 +271,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) c = 0; spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - if (server->is_channel) + /* channel info will be printed as a part of sessions below */ + if (CIFS_SERVER_IS_CHAN(server)) continue; c++; @@ -358,6 +359,8 @@ skip_rdma: seq_printf(m, " signed"); if (server->posix_ext_supported) seq_printf(m, " posix"); + if (server->nosharesock) + seq_printf(m, " nosharesock"); if (server->rdma) seq_printf(m, "\nRDMA "); @@ -412,12 +415,14 @@ skip_rdma: from_kuid(&init_user_ns, ses->linux_uid), from_kuid(&init_user_ns, ses->cred_uid)); + spin_lock(&ses->chan_lock); if (ses->chan_count > 1) { seq_printf(m, "\n\n\tExtra Channels: %zu ", ses->chan_count-1); for (j = 1; j < ses->chan_count; j++) cifs_dump_channel(m, j, &ses->chans[j]); } + spin_unlock(&ses->chan_lock); seq_puts(m, "\n\n\tShares: "); j = 0; diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 007427ba75e5..b0864da9ef43 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -307,12 +307,8 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt, static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) { struct cifs_sb_info *cifs_sb; - struct cifs_ses *ses; - struct cifs_tcon *tcon; void *page; - char *full_path, *root_path; - unsigned int xid; - int rc; + char *full_path; struct vfsmount *mnt; cifs_dbg(FYI, "in %s\n", __func__); @@ -324,8 +320,6 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) * the double backslashes usually used in the UNC. This function * gives us the latter, so we must adjust the result. */ - mnt = ERR_PTR(-ENOMEM); - cifs_sb = CIFS_SB(mntpt->d_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) { mnt = ERR_PTR(-EREMOTE); @@ -341,60 +335,11 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) } convert_delimiter(full_path, '\\'); - cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); - if (!cifs_sb_master_tlink(cifs_sb)) { - cifs_dbg(FYI, "%s: master tlink is NULL\n", __func__); - goto free_full_path; - } - - tcon = cifs_sb_master_tcon(cifs_sb); - if (!tcon) { - cifs_dbg(FYI, "%s: master tcon is NULL\n", __func__); - goto free_full_path; - } - - root_path = kstrdup(tcon->treeName, GFP_KERNEL); - if (!root_path) { - mnt = ERR_PTR(-ENOMEM); - goto free_full_path; - } - cifs_dbg(FYI, "%s: root path: %s\n", __func__, root_path); - - ses = tcon->ses; - xid = get_xid(); - - /* - * If DFS root has been expired, then unconditionally fetch it again to - * refresh DFS referral cache. - */ - rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), - root_path + 1, NULL, NULL); - if (!rc) { - rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, - cifs_remap(cifs_sb), full_path + 1, - NULL, NULL); - } - - free_xid(xid); - - if (rc) { - mnt = ERR_PTR(rc); - goto free_root_path; - } - /* - * OK - we were able to get and cache a referral for @full_path. - * - * Now, pass it down to cifs_mount() and it will retry every available - * node server in case of failures - no need to do it here. - */ mnt = cifs_dfs_do_mount(mntpt, cifs_sb, full_path); - cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__, - full_path + 1, mnt); + cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__, full_path + 1, mnt); -free_root_path: - kfree(root_path); free_full_path: free_dentry_path(page); cdda_exit: diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index f97407520ea1..013a4bd65280 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -61,11 +61,6 @@ struct cifs_sb_info { /* only used when CIFS_MOUNT_USE_PREFIX_PATH is set */ char *prepath; - /* - * Canonical DFS path initially provided by the mount call. We might connect to something - * different via DFS but we want to keep it to do failover properly. - */ - char *origin_fullpath; /* \\HOST\SHARE\[OPTIONAL PATH] */ /* randomly generated 128-bit number for indexing dfs mount groups in referral cache */ uuid_t dfs_mount_id; /* diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index abff31dcd005..be74606724c7 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/mempool.h> #include <linux/workqueue.h> +#include <linux/utsname.h> #include "cifs_fs_sb.h" #include "cifsacl.h" #include <crypto/internal/hash.h> @@ -75,7 +76,8 @@ #define SMB_ECHO_INTERVAL_MAX 600 #define SMB_ECHO_INTERVAL_DEFAULT 60 -/* dns resolution interval in seconds */ +/* dns resolution intervals in seconds */ +#define SMB_DNS_RESOLVE_INTERVAL_MIN 120 #define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600 /* maximum number of PDUs in one compound */ @@ -99,6 +101,8 @@ #define XATTR_DOS_ATTRIB "user.DOSATTRIB" #endif +#define CIFS_MAX_WORKSTATION_LEN (__NEW_UTS_LEN + 1) /* reasonable max for client */ + /* * CIFS vfs client Status information (based on what we know.) */ @@ -592,6 +596,7 @@ struct TCP_Server_Info { struct list_head pending_mid_q; bool noblocksnd; /* use blocking sendmsg */ bool noautotune; /* do not autotune send buf sizes */ + bool nosharesock; bool tcp_nodelay; unsigned int credits; /* send no more requests at once */ unsigned int max_credits; /* can override large 32000 default at mnt */ @@ -685,13 +690,34 @@ struct TCP_Server_Info { */ int nr_targets; bool noblockcnt; /* use non-blocking connect() */ - bool is_channel; /* if a session channel */ + + /* + * If this is a session channel, + * primary_server holds the ref-counted + * pointer to primary channel connection for the session. + */ +#define CIFS_SERVER_IS_CHAN(server) (!!(server)->primary_server) + struct TCP_Server_Info *primary_server; + #ifdef CONFIG_CIFS_SWN_UPCALL bool use_swn_dstaddr; struct sockaddr_storage swn_dstaddr; #endif #ifdef CONFIG_CIFS_DFS_UPCALL bool is_dfs_conn; /* if a dfs connection */ + struct mutex refpath_lock; /* protects leaf_fullpath */ + /* + * Canonical DFS full paths that were used to chase referrals in mount and reconnect. + * + * origin_fullpath: first or original referral path + * leaf_fullpath: last referral path (might be changed due to nested links in reconnect) + * + * current_fullpath: pointer to either origin_fullpath or leaf_fullpath + * NOTE: cannot be accessed outside cifs_reconnect() and smb2_reconnect() + * + * format: \\HOST\SHARE\[OPTIONAL PATH] + */ + char *origin_fullpath, *leaf_fullpath, *current_fullpath; #endif }; @@ -908,6 +934,7 @@ struct cifs_ses { and after mount option parsing we fill it */ char *domainName; char *password; + char *workstation_name; struct session_key auth_key; struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ enum securityEnum sectype; /* what security flavor was specified? */ @@ -933,16 +960,21 @@ struct cifs_ses { * iface_lock should be taken when accessing any of these fields */ spinlock_t iface_lock; + /* ========= begin: protected by iface_lock ======== */ struct cifs_server_iface *iface_list; size_t iface_count; unsigned long iface_last_update; /* jiffies */ + /* ========= end: protected by iface_lock ======== */ + spinlock_t chan_lock; + /* ========= begin: protected by chan_lock ======== */ #define CIFS_MAX_CHANNELS 16 struct cifs_chan chans[CIFS_MAX_CHANNELS]; struct cifs_chan *binding_chan; size_t chan_count; size_t chan_max; atomic_t chan_seq; /* round robin state */ + /* ========= end: protected by chan_lock ======== */ }; /* @@ -1091,7 +1123,6 @@ struct cifs_tcon { struct cached_fid crfid; /* Cached root fid */ /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - char *dfs_path; /* canonical DFS path */ struct list_head ulist; /* cache update list */ #endif }; @@ -1942,4 +1973,14 @@ static inline bool is_tcon_dfs(struct cifs_tcon *tcon) tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT); } +static inline bool cifs_is_referral_server(struct cifs_tcon *tcon, + const struct dfs_info3_param *ref) +{ + /* + * Check if all targets are capable of handling DFS referrals as per + * MS-DFSC 2.2.4 RESP_GET_DFS_REFERRAL. + */ + return is_tcon_dfs(tcon) || (ref && (ref->flags & DFSREF_REFERRAL_SERVER)); +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index d0f85b666662..f3073a62ce57 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -269,8 +269,9 @@ extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon); extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, const char *path); - -extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb3_fs_context *ctx); +extern struct TCP_Server_Info * +cifs_get_tcp_session(struct smb3_fs_context *ctx, + struct TCP_Server_Info *primary_server); extern void cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect); extern void cifs_put_tcon(struct cifs_tcon *tcon); @@ -607,7 +608,7 @@ int smb2_parse_query_directory(struct cifs_tcon *tcon, struct kvec *rsp_iov, struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server); void cifs_put_tcp_super(struct super_block *sb); -int update_super_prepath(struct cifs_tcon *tcon, char *prefix); +int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix); char *extract_hostname(const char *unc); char *extract_sharename(const char *unc); @@ -634,4 +635,7 @@ static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options) return options; } +struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); +void cifs_put_tcon_super(struct super_block *sb); + #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0abbff4e4135..82577a7a5bb1 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -61,6 +61,20 @@ extern bool disable_legacy_dialects; /* Drop the connection to not overload the server */ #define NUM_STATUS_IO_TIMEOUT 5 +struct mount_ctx { + struct cifs_sb_info *cifs_sb; + struct smb3_fs_context *fs_ctx; + unsigned int xid; + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct cifs_tcon *tcon; +#ifdef CONFIG_CIFS_DFS_UPCALL + struct cifs_ses *root_ses; + uuid_t mount_id; + char *origin_fullpath, *leaf_fullpath; +#endif +}; + static int ip_connect(struct TCP_Server_Info *server); static int generic_ip_connect(struct TCP_Server_Info *server); static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); @@ -115,7 +129,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) * To make sure we don't use the cached entry, retry 1s * after expiry. */ - ttl = (expiry - now + 1); + ttl = max_t(unsigned long, expiry - now, SMB_DNS_RESOLVE_INTERVAL_MIN) + 1; } rc = !rc ? -1 : 0; @@ -148,139 +162,38 @@ static void cifs_resolve_server(struct work_struct *work) mutex_unlock(&server->srv_mutex); } -#ifdef CONFIG_CIFS_DFS_UPCALL -/* These functions must be called with server->srv_mutex held */ -static void reconn_set_next_dfs_target(struct TCP_Server_Info *server, - struct cifs_sb_info *cifs_sb, - struct dfs_cache_tgt_list *tgt_list, - struct dfs_cache_tgt_iterator **tgt_it) -{ - const char *name; - int rc; - - if (!cifs_sb || !cifs_sb->origin_fullpath) - return; - - if (!*tgt_it) { - *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); - } else { - *tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it); - if (!*tgt_it) - *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); - } - - cifs_dbg(FYI, "%s: UNC: %s\n", __func__, cifs_sb->origin_fullpath); - - name = dfs_cache_get_tgt_name(*tgt_it); - - kfree(server->hostname); - - server->hostname = extract_hostname(name); - if (IS_ERR(server->hostname)) { - cifs_dbg(FYI, - "%s: failed to extract hostname from target: %ld\n", - __func__, PTR_ERR(server->hostname)); - return; - } - - rc = reconn_set_ipaddr_from_hostname(server); - if (rc) { - cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", - __func__, rc); - } -} - -static inline int reconn_setup_dfs_targets(struct cifs_sb_info *cifs_sb, - struct dfs_cache_tgt_list *tl) -{ - if (!cifs_sb->origin_fullpath) - return -EOPNOTSUPP; - return dfs_cache_noreq_find(cifs_sb->origin_fullpath + 1, NULL, tl); -} -#endif - -/* - * cifs tcp session reconnection +/** + * Mark all sessions and tcons for reconnect. * - * mark tcp session as reconnecting so temporarily locked - * mark all smb sessions as reconnecting for tcp session - * reconnect tcp session - * wake up waiters on reconnection? - (not needed currently) + * @server needs to be previously set to CifsNeedReconnect. */ -int -cifs_reconnect(struct TCP_Server_Info *server) +static void cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server) { - int rc = 0; - struct list_head *tmp, *tmp2; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct mid_q_entry *mid_entry; + struct mid_q_entry *mid, *nmid; struct list_head retry_list; -#ifdef CONFIG_CIFS_DFS_UPCALL - struct super_block *sb = NULL; - struct cifs_sb_info *cifs_sb = NULL; - struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list); - struct dfs_cache_tgt_iterator *tgt_it = NULL; -#endif + struct TCP_Server_Info *pserver; - spin_lock(&GlobalMid_Lock); - server->nr_targets = 1; -#ifdef CONFIG_CIFS_DFS_UPCALL - spin_unlock(&GlobalMid_Lock); - sb = cifs_get_tcp_super(server); - if (IS_ERR(sb)) { - rc = PTR_ERR(sb); - cifs_dbg(FYI, "%s: will not do DFS failover: rc = %d\n", - __func__, rc); - sb = NULL; - } else { - cifs_sb = CIFS_SB(sb); - rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list); - if (rc) { - cifs_sb = NULL; - if (rc != -EOPNOTSUPP) { - cifs_server_dbg(VFS, "%s: no target servers for DFS failover\n", - __func__); - } - } else { - server->nr_targets = dfs_cache_get_nr_tgts(&tgt_list); - } - } - cifs_dbg(FYI, "%s: will retry %d target(s)\n", __func__, - server->nr_targets); - spin_lock(&GlobalMid_Lock); -#endif - if (server->tcpStatus == CifsExiting) { - /* the demux thread will exit normally - next time through the loop */ - spin_unlock(&GlobalMid_Lock); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_cache_free_tgts(&tgt_list); - cifs_put_tcp_super(sb); -#endif - wake_up(&server->response_q); - return rc; - } else - server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); server->maxBuf = 0; server->max_read = 0; cifs_dbg(FYI, "Mark tcp session as need reconnect\n"); trace_smb3_reconnect(server->CurrentMid, server->conn_id, server->hostname); + /* + * before reconnecting the tcp session, mark the smb session (uid) and the tid bad so they + * are not used until reconnected. + */ + cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect\n", __func__); + + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; - /* before reconnecting the tcp session, mark the smb session (uid) - and the tid bad so they are not used until reconnected */ - cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect\n", - __func__); spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { ses->need_reconnect = true; - list_for_each(tmp2, &ses->tcon_list) { - tcon = list_entry(tmp2, struct cifs_tcon, tcon_list); + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) tcon->need_reconnect = true; - } if (ses->tcon_ipc) ses->tcon_ipc->need_reconnect = true; } @@ -290,11 +203,11 @@ cifs_reconnect(struct TCP_Server_Info *server) cifs_dbg(FYI, "%s: tearing down socket\n", __func__); mutex_lock(&server->srv_mutex); if (server->ssocket) { - cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", - server->ssocket->state, server->ssocket->flags); + cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", server->ssocket->state, + server->ssocket->flags); kernel_sock_shutdown(server->ssocket, SHUT_WR); - cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", - server->ssocket->state, server->ssocket->flags); + cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", server->ssocket->state, + server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; } @@ -309,23 +222,21 @@ cifs_reconnect(struct TCP_Server_Info *server) INIT_LIST_HEAD(&retry_list); cifs_dbg(FYI, "%s: moving mids to private list\n", __func__); spin_lock(&GlobalMid_Lock); - list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - kref_get(&mid_entry->refcount); - if (mid_entry->mid_state == MID_REQUEST_SUBMITTED) - mid_entry->mid_state = MID_RETRY_NEEDED; - list_move(&mid_entry->qhead, &retry_list); - mid_entry->mid_flags |= MID_DELETED; + list_for_each_entry_safe(mid, nmid, &server->pending_mid_q, qhead) { + kref_get(&mid->refcount); + if (mid->mid_state == MID_REQUEST_SUBMITTED) + mid->mid_state = MID_RETRY_NEEDED; + list_move(&mid->qhead, &retry_list); + mid->mid_flags |= MID_DELETED; } spin_unlock(&GlobalMid_Lock); mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); - list_for_each_safe(tmp, tmp2, &retry_list) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - list_del_init(&mid_entry->qhead); - mid_entry->callback(mid_entry); - cifs_mid_q_entry_release(mid_entry); + list_for_each_entry_safe(mid, nmid, &retry_list, qhead) { + list_del_init(&mid->qhead); + mid->callback(mid); + cifs_mid_q_entry_release(mid); } if (cifs_rdma_enabled(server)) { @@ -333,38 +244,48 @@ cifs_reconnect(struct TCP_Server_Info *server) smbd_destroy(server); mutex_unlock(&server->srv_mutex); } +} + +static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets) +{ + spin_lock(&GlobalMid_Lock); + server->nr_targets = num_targets; + if (server->tcpStatus == CifsExiting) { + /* the demux thread will exit normally next time through the loop */ + spin_unlock(&GlobalMid_Lock); + wake_up(&server->response_q); + return false; + } + server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + return true; +} + +/* + * cifs tcp session reconnection + * + * mark tcp session as reconnecting so temporarily locked + * mark all smb sessions as reconnecting for tcp session + * reconnect tcp session + * wake up waiters on reconnection? - (not needed currently) + */ +static int __cifs_reconnect(struct TCP_Server_Info *server) +{ + int rc = 0; + + if (!cifs_tcp_ses_needs_reconnect(server, 1)) + return 0; + + cifs_mark_tcp_ses_conns_for_reconnect(server); do { try_to_freeze(); - mutex_lock(&server->srv_mutex); - if (!cifs_swn_set_server_dstaddr(server)) { -#ifdef CONFIG_CIFS_DFS_UPCALL - if (cifs_sb && cifs_sb->origin_fullpath) - /* - * Set up next DFS target server (if any) for reconnect. If DFS - * feature is disabled, then we will retry last server we - * connected to before. - */ - reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it); - else { -#endif - /* - * Resolve the hostname again to make sure that IP address is up-to-date. - */ + /* resolve the hostname again to make sure that IP address is up-to-date */ rc = reconn_set_ipaddr_from_hostname(server); - if (rc) { - cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", - __func__, rc); - } - -#ifdef CONFIG_CIFS_DFS_UPCALL - } -#endif - - + cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc); } if (cifs_rdma_enabled(server)) @@ -372,8 +293,8 @@ cifs_reconnect(struct TCP_Server_Info *server) else rc = generic_ip_connect(server); if (rc) { - cifs_dbg(FYI, "reconnect error %d\n", rc); mutex_unlock(&server->srv_mutex); + cifs_dbg(FYI, "%s: reconnect error %d\n", __func__, rc); msleep(3000); } else { atomic_inc(&tcpSesReconnectCount); @@ -387,19 +308,128 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); + if (server->tcpStatus == CifsNeedNegotiate) + mod_delayed_work(cifsiod_wq, &server->echo, 0); + + wake_up(&server->response_q); + return rc; +} + #ifdef CONFIG_CIFS_DFS_UPCALL - if (tgt_it) { - rc = dfs_cache_noreq_update_tgthint(cifs_sb->origin_fullpath + 1, - tgt_it); - if (rc) { - cifs_server_dbg(VFS, "%s: failed to update DFS target hint: rc = %d\n", - __func__, rc); +static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const char *target) +{ + int rc; + char *hostname; + + if (!cifs_swn_set_server_dstaddr(server)) { + if (server->hostname != target) { + hostname = extract_hostname(target); + if (!IS_ERR(hostname)) { + kfree(server->hostname); + server->hostname = hostname; + } else { + cifs_dbg(FYI, "%s: couldn't extract hostname or address from dfs target: %ld\n", + __func__, PTR_ERR(hostname)); + cifs_dbg(FYI, "%s: default to last target server: %s\n", __func__, + server->hostname); + } } - dfs_cache_free_tgts(&tgt_list); + /* resolve the hostname again to make sure that IP address is up-to-date. */ + rc = reconn_set_ipaddr_from_hostname(server); + cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc); } + /* Reconnect the socket */ + if (cifs_rdma_enabled(server)) + rc = smbd_reconnect(server); + else + rc = generic_ip_connect(server); - cifs_put_tcp_super(sb); -#endif + return rc; +} + +static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_cache_tgt_list *tl, + struct dfs_cache_tgt_iterator **target_hint) +{ + int rc; + struct dfs_cache_tgt_iterator *tit; + + *target_hint = NULL; + + /* If dfs target list is empty, then reconnect to last server */ + tit = dfs_cache_get_tgt_iterator(tl); + if (!tit) + return __reconnect_target_unlocked(server, server->hostname); + + /* Otherwise, try every dfs target in @tl */ + for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) { + rc = __reconnect_target_unlocked(server, dfs_cache_get_tgt_name(tit)); + if (!rc) { + *target_hint = tit; + break; + } + } + return rc; +} + +static int reconnect_dfs_server(struct TCP_Server_Info *server) +{ + int rc = 0; + const char *refpath = server->current_fullpath + 1; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + struct dfs_cache_tgt_iterator *target_hint = NULL; + int num_targets = 0; + + /* + * Determine the number of dfs targets the referral path in @cifs_sb resolves to. + * + * smb2_reconnect() needs to know how long it should wait based upon the number of dfs + * targets (server->nr_targets). It's also possible that the cached referral was cleared + * through /proc/fs/cifs/dfscache or the target list is empty due to server settings after + * refreshing the referral, so, in this case, default it to 1. + */ + if (!dfs_cache_noreq_find(refpath, NULL, &tl)) + num_targets = dfs_cache_get_nr_tgts(&tl); + if (!num_targets) + num_targets = 1; + + if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) + return 0; + + cifs_mark_tcp_ses_conns_for_reconnect(server); + + do { + try_to_freeze(); + mutex_lock(&server->srv_mutex); + + rc = reconnect_target_unlocked(server, &tl, &target_hint); + if (rc) { + /* Failed to reconnect socket */ + mutex_unlock(&server->srv_mutex); + cifs_dbg(FYI, "%s: reconnect error %d\n", __func__, rc); + msleep(3000); + continue; + } + /* + * Socket was created. Update tcp session status to CifsNeedNegotiate so that a + * process waiting for reconnect will know it needs to re-establish session and tcon + * through the reconnected target server. + */ + atomic_inc(&tcpSesReconnectCount); + set_credits(server, 1); + spin_lock(&GlobalMid_Lock); + if (server->tcpStatus != CifsExiting) + server->tcpStatus = CifsNeedNegotiate; + spin_unlock(&GlobalMid_Lock); + cifs_swn_reset_server_dstaddr(server); + mutex_unlock(&server->srv_mutex); + } while (server->tcpStatus == CifsNeedReconnect); + + if (target_hint) + dfs_cache_noreq_update_tgthint(refpath, target_hint); + + dfs_cache_free_tgts(&tl); + + /* Need to set up echo worker again once connection has been established */ if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); @@ -407,6 +437,25 @@ cifs_reconnect(struct TCP_Server_Info *server) return rc; } +int cifs_reconnect(struct TCP_Server_Info *server) +{ + /* If tcp session is not an dfs connection, then reconnect to last target server */ + spin_lock(&cifs_tcp_ses_lock); + if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { + spin_unlock(&cifs_tcp_ses_lock); + return __cifs_reconnect(server); + } + spin_unlock(&cifs_tcp_ses_lock); + + return reconnect_dfs_server(server); +} +#else +int cifs_reconnect(struct TCP_Server_Info *server) +{ + return __cifs_reconnect(server); +} +#endif + static void cifs_echo_request(struct work_struct *work) { @@ -665,13 +714,14 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) * Trying to handle/dequeue a mid after the send_recv() * function has finished processing it is a bug. */ - if (mid->mid_flags & MID_DELETED) + if (mid->mid_flags & MID_DELETED) { + spin_unlock(&GlobalMid_Lock); pr_warn_once("trying to dequeue a deleted mid\n"); - else { + } else { list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; + spin_unlock(&GlobalMid_Lock); } - spin_unlock(&GlobalMid_Lock); } static unsigned int @@ -794,6 +844,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) */ } +#ifdef CONFIG_CIFS_DFS_UPCALL + kfree(server->origin_fullpath); + kfree(server->leaf_fullpath); +#endif kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -1217,7 +1271,13 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context * { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; - if (ctx->nosharesock) + if (ctx->nosharesock) { + server->nosharesock = true; + return 0; + } + + /* this server does not share socket */ + if (server->nosharesock) return 0; /* If multidialect negotiation see if existing sessions match one */ @@ -1283,7 +1343,7 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) * Skip ses channels since they're only handled in lower layers * (e.g. cifs_send_recv). */ - if (server->is_channel || !match_server(server, ctx)) + if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx)) continue; ++server->srv_count; @@ -1314,6 +1374,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); + /* For secondary channels, we pick up ref-count on the primary server */ + if (CIFS_SERVER_IS_CHAN(server)) + cifs_put_tcp_session(server->primary_server, from_reconnect); + cancel_delayed_work_sync(&server->echo); cancel_delayed_work_sync(&server->resolve); @@ -1333,7 +1397,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) spin_unlock(&GlobalMid_Lock); cifs_crypto_secmech_release(server); - cifs_fscache_release_client_cookie(server); + + /* fscache server cookies are based on primary channel only */ + if (!CIFS_SERVER_IS_CHAN(server)) + cifs_fscache_release_client_cookie(server); kfree(server->session_key.response); server->session_key.response = NULL; @@ -1346,7 +1413,8 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) } struct TCP_Server_Info * -cifs_get_tcp_session(struct smb3_fs_context *ctx) +cifs_get_tcp_session(struct smb3_fs_context *ctx, + struct TCP_Server_Info *primary_server) { struct TCP_Server_Info *tcp_ses = NULL; int rc; @@ -1383,6 +1451,10 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx) tcp_ses->in_flight = 0; tcp_ses->max_in_flight = 0; tcp_ses->credits = 1; + if (primary_server) { + ++primary_server->srv_count; + tcp_ses->primary_server = primary_server; + } init_waitqueue_head(&tcp_ses->response_q); init_waitqueue_head(&tcp_ses->request_q); INIT_LIST_HEAD(&tcp_ses->pending_mid_q); @@ -1403,6 +1475,9 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx) INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server); INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); +#ifdef CONFIG_CIFS_DFS_UPCALL + mutex_init(&tcp_ses->refpath_lock); +#endif memcpy(&tcp_ses->srcaddr, &ctx->srcaddr, sizeof(tcp_ses->srcaddr)); memcpy(&tcp_ses->dstaddr, &ctx->dstaddr, @@ -1481,7 +1556,9 @@ smbd_connected: list_add(&tcp_ses->tcp_ses_list, &cifs_tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); - cifs_fscache_get_client_cookie(tcp_ses); + /* fscache server cookies are based on primary channel only */ + if (!CIFS_SERVER_IS_CHAN(tcp_ses)) + cifs_fscache_get_client_cookie(tcp_ses); /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); @@ -1501,6 +1578,8 @@ out_err_crypto_release: out_err: if (tcp_ses) { + if (CIFS_SERVER_IS_CHAN(tcp_ses)) + cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); if (tcp_ses->ssocket) sock_release(tcp_ses->ssocket); @@ -1519,8 +1598,12 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) * If an existing session is limited to less channels than * requested, it should not be reused */ - if (ses->chan_max < ctx->max_channels) + spin_lock(&ses->chan_lock); + if (ses->chan_max < ctx->max_channels) { + spin_unlock(&ses->chan_lock); return 0; + } + spin_unlock(&ses->chan_lock); switch (ses->sectype) { case Kerberos: @@ -1655,6 +1738,7 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) void cifs_put_smb_ses(struct cifs_ses *ses) { unsigned int rc, xid; + unsigned int chan_count; struct TCP_Server_Info *server = ses->server; cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); @@ -1696,12 +1780,24 @@ void cifs_put_smb_ses(struct cifs_ses *ses) list_del_init(&ses->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); + spin_lock(&ses->chan_lock); + chan_count = ses->chan_count; + spin_unlock(&ses->chan_lock); + /* close any extra channels */ - if (ses->chan_count > 1) { + if (chan_count > 1) { int i; - for (i = 1; i < ses->chan_count; i++) + for (i = 1; i < chan_count; i++) { + /* + * note: for now, we're okay accessing ses->chans + * without chan_lock. But when chans can go away, we'll + * need to introduce ref counting to make sure that chan + * is not freed from under us. + */ cifs_put_tcp_session(ses->chans[i].server, 0); + ses->chans[i].server = NULL; + } } sesInfoFree(ses); @@ -1885,16 +1981,18 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) ses->status); mutex_lock(&ses->session_mutex); - rc = cifs_negotiate_protocol(xid, ses); - if (rc) { - mutex_unlock(&ses->session_mutex); - /* problem -- put our ses reference */ - cifs_put_smb_ses(ses); - free_xid(xid); - return ERR_PTR(rc); - } if (ses->need_reconnect) { cifs_dbg(FYI, "Session needs reconnect\n"); + + rc = cifs_negotiate_protocol(xid, ses); + if (rc) { + mutex_unlock(&ses->session_mutex); + /* problem -- put our ses reference */ + cifs_put_smb_ses(ses); + free_xid(xid); + return ERR_PTR(rc); + } + rc = cifs_setup_session(xid, ses, ctx->local_nls); if (rc) { @@ -1942,6 +2040,12 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) if (!ses->domainName) goto get_ses_fail; } + if (ctx->workstation_name) { + ses->workstation_name = kstrdup(ctx->workstation_name, + GFP_KERNEL); + if (!ses->workstation_name) + goto get_ses_fail; + } if (ctx->domainauto) ses->domainAuto = ctx->domainauto; ses->cred_uid = ctx->cred_uid; @@ -1952,9 +2056,11 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) mutex_lock(&ses->session_mutex); /* add server as first channel */ + spin_lock(&ses->chan_lock); ses->chans[0].server = server; ses->chan_count = 1; ses->chan_max = ctx->multichannel ? ctx->max_channels:1; + spin_unlock(&ses->chan_lock); rc = cifs_negotiate_protocol(xid, ses); if (!rc) @@ -2286,8 +2392,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) list_add(&tcon->tcon_list, &ses->tcon_list); spin_unlock(&cifs_tcp_ses_lock); - cifs_fscache_get_super_cookie(tcon); - return tcon; out_fail: @@ -2849,73 +2953,64 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) } /* Release all succeed connections */ -static inline void mount_put_conns(struct cifs_sb_info *cifs_sb, - unsigned int xid, - struct TCP_Server_Info *server, - struct cifs_ses *ses, struct cifs_tcon *tcon) +static inline void mount_put_conns(struct mount_ctx *mnt_ctx) { int rc = 0; - if (tcon) - cifs_put_tcon(tcon); - else if (ses) - cifs_put_smb_ses(ses); - else if (server) - cifs_put_tcp_session(server, 0); - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; - free_xid(xid); + if (mnt_ctx->tcon) + cifs_put_tcon(mnt_ctx->tcon); + else if (mnt_ctx->ses) + cifs_put_smb_ses(mnt_ctx->ses); + else if (mnt_ctx->server) + cifs_put_tcp_session(mnt_ctx->server, 0); + mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; + free_xid(mnt_ctx->xid); } /* Get connections for tcp, ses and tcon */ -static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, - unsigned int *xid, - struct TCP_Server_Info **nserver, - struct cifs_ses **nses, struct cifs_tcon **ntcon) +static int mount_get_conns(struct mount_ctx *mnt_ctx) { int rc = 0; - struct TCP_Server_Info *server; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - - *nserver = NULL; - *nses = NULL; - *ntcon = NULL; + struct TCP_Server_Info *server = NULL; + struct cifs_ses *ses = NULL; + struct cifs_tcon *tcon = NULL; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + unsigned int xid; - *xid = get_xid(); + xid = get_xid(); /* get a reference to a tcp session */ - server = cifs_get_tcp_session(ctx); + server = cifs_get_tcp_session(ctx, NULL); if (IS_ERR(server)) { rc = PTR_ERR(server); - return rc; + server = NULL; + goto out; } - *nserver = server; - /* get a reference to a SMB session */ ses = cifs_get_smb_ses(server, ctx); if (IS_ERR(ses)) { rc = PTR_ERR(ses); - return rc; + ses = NULL; + goto out; } - *nses = ses; - if ((ctx->persistent == true) && (!(ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES))) { cifs_server_dbg(VFS, "persistent handles not supported by server\n"); - return -EOPNOTSUPP; + rc = -EOPNOTSUPP; + goto out; } /* search for existing tcon to this server share */ tcon = cifs_get_tcon(ses, ctx); if (IS_ERR(tcon)) { rc = PTR_ERR(tcon); - return rc; + tcon = NULL; + goto out; } - *ntcon = tcon; - /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */ if (tcon->posix_extensions) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; @@ -2926,17 +3021,19 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif * reset of caps checks mount to see if unix extensions disabled * for just this mount. */ - reset_cifs_unix_caps(*xid, tcon, cifs_sb, ctx); + reset_cifs_unix_caps(xid, tcon, cifs_sb, ctx); if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && (le64_to_cpu(tcon->fsUnixInfo.Capability) & - CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) - return -EACCES; + CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { + rc = -EACCES; + goto out; + } } else tcon->unix_ext = 0; /* server does not support them */ /* do not care if a following call succeed - informational */ if (!tcon->pipe && server->ops->qfs_tcon) { - server->ops->qfs_tcon(*xid, tcon, cifs_sb); + server->ops->qfs_tcon(xid, tcon, cifs_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) { if (tcon->fsDevInfo.DeviceCharacteristics & cpu_to_le32(FILE_READ_ONLY_DEVICE)) @@ -2946,6 +3043,12 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif cifs_dbg(VFS, "read only mount of RW share\n"); /* no need to log a RW mount of a typical RW share */ } + /* + * The cookie is initialized from volume info returned above. + * Inside cifs_fscache_get_super_cookie it checks + * that we do not get super cookie twice. + */ + cifs_fscache_get_super_cookie(tcon); } /* @@ -2960,7 +3063,13 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx))) cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx); - return 0; +out: + mnt_ctx->server = server; + mnt_ctx->ses = ses; + mnt_ctx->tcon = tcon; + mnt_ctx->xid = xid; + + return rc; } static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, @@ -2990,18 +3099,17 @@ static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, } #ifdef CONFIG_CIFS_DFS_UPCALL -static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, - unsigned int *xid, struct TCP_Server_Info **nserver, - struct cifs_ses **nses, struct cifs_tcon **ntcon) +/* Get unique dfs connections */ +static int mount_get_dfs_conns(struct mount_ctx *mnt_ctx) { int rc; - ctx->nosharesock = true; - rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon); - if (*nserver) { + mnt_ctx->fs_ctx->nosharesock = true; + rc = mount_get_conns(mnt_ctx); + if (mnt_ctx->server) { cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__); spin_lock(&cifs_tcp_ses_lock); - (*nserver)->is_dfs_conn = true; + mnt_ctx->server->is_dfs_conn = true; spin_unlock(&cifs_tcp_ses_lock); } return rc; @@ -3043,190 +3151,38 @@ build_unc_path_to_root(const struct smb3_fs_context *ctx, } /* - * expand_dfs_referral - Perform a dfs referral query and update the cifs_sb + * expand_dfs_referral - Update cifs_sb from dfs referral path * - * If a referral is found, cifs_sb->ctx->mount_options will be (re-)allocated - * to a string containing updated options for the submount. Otherwise it - * will be left untouched. - * - * Returns the rc from get_dfs_path to the caller, which can be used to - * determine whether there were referrals. + * cifs_sb->ctx->mount_options will be (re-)allocated to a string containing updated options for the + * submount. Otherwise it will be left untouched. */ -static int -expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, - struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, - char *ref_path) -{ - int rc; - struct dfs_info3_param referral = {0}; - char *full_path = NULL, *mdata = NULL; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) - return -EREMOTE; - - full_path = build_unc_path_to_root(ctx, cifs_sb, true); - if (IS_ERR(full_path)) - return PTR_ERR(full_path); - - rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), - ref_path, &referral, NULL); - if (!rc) { - char *fake_devname = NULL; - - mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &referral, - &fake_devname); - free_dfs_info_param(&referral); - - if (IS_ERR(mdata)) { - rc = PTR_ERR(mdata); - mdata = NULL; - } else { - /* - * We can not clear out the whole structure since we - * no longer have an explicit function to parse - * a mount-string. Instead we need to clear out the - * individual fields that are no longer valid. - */ - kfree(ctx->prepath); - ctx->prepath = NULL; - rc = cifs_setup_volume_info(ctx, mdata, fake_devname); - } - kfree(fake_devname); - kfree(cifs_sb->ctx->mount_options); - cifs_sb->ctx->mount_options = mdata; - } - kfree(full_path); - return rc; -} - -static int get_next_dfs_tgt(struct dfs_cache_tgt_list *tgt_list, - struct dfs_cache_tgt_iterator **tgt_it) -{ - if (!*tgt_it) - *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); - else - *tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it); - return !*tgt_it ? -EHOSTDOWN : 0; -} - -static int update_vol_info(const struct dfs_cache_tgt_iterator *tgt_it, - struct smb3_fs_context *fake_ctx, struct smb3_fs_context *ctx) -{ - const char *tgt = dfs_cache_get_tgt_name(tgt_it); - int len = strlen(tgt) + 2; - char *new_unc; - - new_unc = kmalloc(len, GFP_KERNEL); - if (!new_unc) - return -ENOMEM; - scnprintf(new_unc, len, "\\%s", tgt); - - kfree(ctx->UNC); - ctx->UNC = new_unc; - - if (fake_ctx->prepath) { - kfree(ctx->prepath); - ctx->prepath = fake_ctx->prepath; - fake_ctx->prepath = NULL; - } - memcpy(&ctx->dstaddr, &fake_ctx->dstaddr, sizeof(ctx->dstaddr)); - - return 0; -} - -static int do_dfs_failover(const char *path, const char *full_path, struct cifs_sb_info *cifs_sb, - struct smb3_fs_context *ctx, struct cifs_ses *root_ses, - unsigned int *xid, struct TCP_Server_Info **server, - struct cifs_ses **ses, struct cifs_tcon **tcon) +static int expand_dfs_referral(struct mount_ctx *mnt_ctx, const char *full_path, + struct dfs_info3_param *referral) { int rc; - char *npath = NULL; - struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list); - struct dfs_cache_tgt_iterator *tgt_it = NULL; - struct smb3_fs_context tmp_ctx = {NULL}; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) - return -EOPNOTSUPP; - - npath = dfs_cache_canonical_path(path, cifs_sb->local_nls, cifs_remap(cifs_sb)); - if (IS_ERR(npath)) - return PTR_ERR(npath); - - cifs_dbg(FYI, "%s: path=%s full_path=%s\n", __func__, npath, full_path); - - rc = dfs_cache_noreq_find(npath, NULL, &tgt_list); - if (rc) - goto out; - /* - * We use a 'tmp_ctx' here because we need pass it down to the mount_{get,put} functions to - * test connection against new DFS targets. - */ - rc = smb3_fs_context_dup(&tmp_ctx, ctx); - if (rc) - goto out; - - for (;;) { - struct dfs_info3_param ref = {0}; - char *fake_devname = NULL, *mdata = NULL; - - /* Get next DFS target server - if any */ - rc = get_next_dfs_tgt(&tgt_list, &tgt_it); - if (rc) - break; - - rc = dfs_cache_get_tgt_referral(npath, tgt_it, &ref); - if (rc) - break; - - cifs_dbg(FYI, "%s: old ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC, - tmp_ctx.prepath); - - mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, full_path + 1, &ref, - &fake_devname); - free_dfs_info_param(&ref); - - if (IS_ERR(mdata)) { - rc = PTR_ERR(mdata); - mdata = NULL; - } else - rc = cifs_setup_volume_info(&tmp_ctx, mdata, fake_devname); - - kfree(mdata); - kfree(fake_devname); - - if (rc) - break; - - cifs_dbg(FYI, "%s: new ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC, - tmp_ctx.prepath); - - mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon); - rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon); - if (!rc || (*server && *ses)) { - /* - * We were able to connect to new target server. Update current context with - * new target server. - */ - rc = update_vol_info(tgt_it, &tmp_ctx, ctx); - break; - } - } - if (!rc) { - cifs_dbg(FYI, "%s: final ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC, - tmp_ctx.prepath); + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + char *fake_devname = NULL, *mdata = NULL; + + mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, full_path + 1, referral, + &fake_devname); + if (IS_ERR(mdata)) { + rc = PTR_ERR(mdata); + mdata = NULL; + } else { /* - * Update DFS target hint in DFS referral cache with the target server we - * successfully reconnected to. + * We can not clear out the whole structure since we no longer have an explicit + * function to parse a mount-string. Instead we need to clear out the individual + * fields that are no longer valid. */ - rc = dfs_cache_update_tgthint(*xid, root_ses ? root_ses : *ses, cifs_sb->local_nls, - cifs_remap(cifs_sb), path, tgt_it); + kfree(ctx->prepath); + ctx->prepath = NULL; + rc = cifs_setup_volume_info(ctx, mdata, fake_devname); } + kfree(fake_devname); + kfree(cifs_sb->ctx->mount_options); + cifs_sb->ctx->mount_options = mdata; -out: - kfree(npath); - smb3_cleanup_fs_context_contents(&tmp_ctx); - dfs_cache_free_tgts(&tgt_list); return rc; } #endif @@ -3333,12 +3289,14 @@ cifs_are_all_path_components_accessible(struct TCP_Server_Info *server, * Check if path is remote (e.g. a DFS share). Return -EREMOTE if it is, * otherwise 0. */ -static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx, - const unsigned int xid, - struct TCP_Server_Info *server, - struct cifs_tcon *tcon) +static int is_path_remote(struct mount_ctx *mnt_ctx) { int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct TCP_Server_Info *server = mnt_ctx->server; + unsigned int xid = mnt_ctx->xid; + struct cifs_tcon *tcon = mnt_ctx->tcon; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; char *full_path; if (!server->ops->is_path_accessible) @@ -3376,280 +3334,289 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context * } #ifdef CONFIG_CIFS_DFS_UPCALL -static void set_root_ses(struct cifs_sb_info *cifs_sb, const uuid_t *mount_id, struct cifs_ses *ses, - struct cifs_ses **root_ses) +static void set_root_ses(struct mount_ctx *mnt_ctx) { - if (ses) { + if (mnt_ctx->ses) { spin_lock(&cifs_tcp_ses_lock); - ses->ses_count++; + mnt_ctx->ses->ses_count++; spin_unlock(&cifs_tcp_ses_lock); - dfs_cache_add_refsrv_session(mount_id, ses); + dfs_cache_add_refsrv_session(&mnt_ctx->mount_id, mnt_ctx->ses); } - *root_ses = ses; + mnt_ctx->root_ses = mnt_ctx->ses; } -/* Set up next dfs prefix path in @dfs_path */ -static int next_dfs_prepath(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx, - const unsigned int xid, struct TCP_Server_Info *server, - struct cifs_tcon *tcon, char **dfs_path) +static int is_dfs_mount(struct mount_ctx *mnt_ctx, bool *isdfs, struct dfs_cache_tgt_list *root_tl) { - char *path, *npath; - int added_treename = is_tcon_dfs(tcon); int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - path = cifs_build_path_to_root(ctx, cifs_sb, tcon, added_treename); - if (!path) - return -ENOMEM; + *isdfs = true; - rc = is_path_remote(cifs_sb, ctx, xid, server, tcon); - if (rc == -EREMOTE) { - struct smb3_fs_context v = {NULL}; - /* if @path contains a tree name, skip it in the prefix path */ - if (added_treename) { - rc = smb3_parse_devname(path, &v); - if (rc) - goto out; - npath = build_unc_path_to_root(&v, cifs_sb, true); - smb3_cleanup_fs_context_contents(&v); - } else { - v.UNC = ctx->UNC; - v.prepath = path + 1; - npath = build_unc_path_to_root(&v, cifs_sb, true); - } + rc = mount_get_conns(mnt_ctx); + /* + * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally + * try to get an DFS referral (even cached) to determine whether it is an DFS mount. + * + * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem + * to respond with PATH_NOT_COVERED to requests that include the prefix. + */ + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) || + dfs_cache_find(mnt_ctx->xid, mnt_ctx->ses, cifs_sb->local_nls, cifs_remap(cifs_sb), + ctx->UNC + 1, NULL, root_tl)) { + if (rc) + return rc; + /* Check if it is fully accessible and then mount it */ + rc = is_path_remote(mnt_ctx); + if (!rc) + *isdfs = false; + else if (rc != -EREMOTE) + return rc; + } + return 0; +} - if (IS_ERR(npath)) { - rc = PTR_ERR(npath); - goto out; - } +static int connect_dfs_target(struct mount_ctx *mnt_ctx, const char *full_path, + const char *ref_path, struct dfs_cache_tgt_iterator *tit) +{ + int rc; + struct dfs_info3_param ref = {}; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + char *oldmnt = cifs_sb->ctx->mount_options; - kfree(*dfs_path); - *dfs_path = npath; - rc = -EREMOTE; + rc = dfs_cache_get_tgt_referral(ref_path, tit, &ref); + if (rc) + goto out; + + rc = expand_dfs_referral(mnt_ctx, full_path, &ref); + if (rc) + goto out; + + /* Connect to new target only if we were redirected (e.g. mount options changed) */ + if (oldmnt != cifs_sb->ctx->mount_options) { + mount_put_conns(mnt_ctx); + rc = mount_get_dfs_conns(mnt_ctx); + } + if (!rc) { + if (cifs_is_referral_server(mnt_ctx->tcon, &ref)) + set_root_ses(mnt_ctx); + rc = dfs_cache_update_tgthint(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls, + cifs_remap(cifs_sb), ref_path, tit); } out: - kfree(path); + free_dfs_info_param(&ref); return rc; } -/* Check if resolved targets can handle any DFS referrals */ -static int is_referral_server(const char *ref_path, struct cifs_sb_info *cifs_sb, - struct cifs_tcon *tcon, bool *ref_server) +static int connect_dfs_root(struct mount_ctx *mnt_ctx, struct dfs_cache_tgt_list *root_tl) { int rc; - struct dfs_info3_param ref = {0}; + char *full_path; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct dfs_cache_tgt_iterator *tit; - cifs_dbg(FYI, "%s: ref_path=%s\n", __func__, ref_path); + /* Put initial connections as they might be shared with other mounts. We need unique dfs + * connections per mount to properly failover, so mount_get_dfs_conns() must be used from + * now on. + */ + mount_put_conns(mnt_ctx); + mount_get_dfs_conns(mnt_ctx); - if (is_tcon_dfs(tcon)) { - *ref_server = true; - } else { - char *npath; + full_path = build_unc_path_to_root(ctx, cifs_sb, true); + if (IS_ERR(full_path)) + return PTR_ERR(full_path); - npath = dfs_cache_canonical_path(ref_path, cifs_sb->local_nls, cifs_remap(cifs_sb)); - if (IS_ERR(npath)) - return PTR_ERR(npath); + mnt_ctx->origin_fullpath = dfs_cache_canonical_path(ctx->UNC, cifs_sb->local_nls, + cifs_remap(cifs_sb)); + if (IS_ERR(mnt_ctx->origin_fullpath)) { + rc = PTR_ERR(mnt_ctx->origin_fullpath); + mnt_ctx->origin_fullpath = NULL; + goto out; + } - rc = dfs_cache_noreq_find(npath, &ref, NULL); - kfree(npath); - if (rc) { - cifs_dbg(VFS, "%s: dfs_cache_noreq_find: failed (rc=%d)\n", __func__, rc); - return rc; + /* Try all dfs root targets */ + for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(root_tl); + tit; tit = dfs_cache_get_next_tgt(root_tl, tit)) { + rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->origin_fullpath + 1, tit); + if (!rc) { + mnt_ctx->leaf_fullpath = kstrdup(mnt_ctx->origin_fullpath, GFP_KERNEL); + if (!mnt_ctx->leaf_fullpath) + rc = -ENOMEM; + break; } - cifs_dbg(FYI, "%s: ref.flags=0x%x\n", __func__, ref.flags); - /* - * Check if all targets are capable of handling DFS referrals as per - * MS-DFSC 2.2.4 RESP_GET_DFS_REFERRAL. - */ - *ref_server = !!(ref.flags & DFSREF_REFERRAL_SERVER); - free_dfs_info_param(&ref); } - return 0; + +out: + kfree(full_path); + return rc; } -int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) +static int __follow_dfs_link(struct mount_ctx *mnt_ctx) { - int rc = 0; - unsigned int xid; - struct TCP_Server_Info *server = NULL; - struct cifs_ses *ses = NULL, *root_ses = NULL; - struct cifs_tcon *tcon = NULL; - int count = 0; - uuid_t mount_id = {0}; - char *ref_path = NULL, *full_path = NULL; - char *oldmnt = NULL; - bool ref_server = false; + int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + char *full_path; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + struct dfs_cache_tgt_iterator *tit; - rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); - /* - * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally - * try to get an DFS referral (even cached) to determine whether it is an DFS mount. - * - * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem - * to respond with PATH_NOT_COVERED to requests that include the prefix. - */ - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) || - dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), ctx->UNC + 1, NULL, - NULL)) { - if (rc) - goto error; - /* Check if it is fully accessible and then mount it */ - rc = is_path_remote(cifs_sb, ctx, xid, server, tcon); - if (!rc) - goto out; - if (rc != -EREMOTE) - goto error; + full_path = build_unc_path_to_root(ctx, cifs_sb, true); + if (IS_ERR(full_path)) + return PTR_ERR(full_path); + + kfree(mnt_ctx->leaf_fullpath); + mnt_ctx->leaf_fullpath = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, + cifs_remap(cifs_sb)); + if (IS_ERR(mnt_ctx->leaf_fullpath)) { + rc = PTR_ERR(mnt_ctx->leaf_fullpath); + mnt_ctx->leaf_fullpath = NULL; + goto out; } - mount_put_conns(cifs_sb, xid, server, ses, tcon); - /* - * Ignore error check here because we may failover to other targets from cached a - * referral. - */ - (void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); + /* Get referral from dfs link */ + rc = dfs_cache_find(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls, + cifs_remap(cifs_sb), mnt_ctx->leaf_fullpath + 1, NULL, &tl); + if (rc) + goto out; - /* Get path of DFS root */ - ref_path = build_unc_path_to_root(ctx, cifs_sb, false); - if (IS_ERR(ref_path)) { - rc = PTR_ERR(ref_path); - ref_path = NULL; - goto error; + /* Try all dfs link targets */ + for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(&tl); + tit; tit = dfs_cache_get_next_tgt(&tl, tit)) { + rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->leaf_fullpath + 1, tit); + if (!rc) { + rc = is_path_remote(mnt_ctx); + break; + } + } + +out: + kfree(full_path); + dfs_cache_free_tgts(&tl); + return rc; +} + +static int follow_dfs_link(struct mount_ctx *mnt_ctx) +{ + int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + char *full_path; + int num_links = 0; + + full_path = build_unc_path_to_root(ctx, cifs_sb, true); + if (IS_ERR(full_path)) + return PTR_ERR(full_path); + + kfree(mnt_ctx->origin_fullpath); + mnt_ctx->origin_fullpath = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, + cifs_remap(cifs_sb)); + kfree(full_path); + + if (IS_ERR(mnt_ctx->origin_fullpath)) { + rc = PTR_ERR(mnt_ctx->origin_fullpath); + mnt_ctx->origin_fullpath = NULL; + return rc; } - uuid_gen(&mount_id); - set_root_ses(cifs_sb, &mount_id, ses, &root_ses); do { - /* Save full path of last DFS path we used to resolve final target server */ - kfree(full_path); - full_path = build_unc_path_to_root(ctx, cifs_sb, !!count); - if (IS_ERR(full_path)) { - rc = PTR_ERR(full_path); - full_path = NULL; - break; - } - /* Chase referral */ - oldmnt = cifs_sb->ctx->mount_options; - rc = expand_dfs_referral(xid, root_ses, ctx, cifs_sb, ref_path + 1); - if (rc) - break; - /* Connect to new DFS target only if we were redirected */ - if (oldmnt != cifs_sb->ctx->mount_options) { - mount_put_conns(cifs_sb, xid, server, ses, tcon); - rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); - } - if (rc && !server && !ses) { - /* Failed to connect. Try to connect to other targets in the referral. */ - rc = do_dfs_failover(ref_path + 1, full_path, cifs_sb, ctx, root_ses, &xid, - &server, &ses, &tcon); - } - if (rc == -EACCES || rc == -EOPNOTSUPP || !server || !ses) + rc = __follow_dfs_link(mnt_ctx); + if (!rc || rc != -EREMOTE) break; - if (!tcon) - continue; + } while (rc = -ELOOP, ++num_links < MAX_NESTED_LINKS); - /* Make sure that requests go through new root servers */ - rc = is_referral_server(ref_path + 1, cifs_sb, tcon, &ref_server); - if (rc) - break; - if (ref_server) - set_root_ses(cifs_sb, &mount_id, ses, &root_ses); + return rc; +} - /* Get next dfs path and then continue chasing them if -EREMOTE */ - rc = next_dfs_prepath(cifs_sb, ctx, xid, server, tcon, &ref_path); - /* Prevent recursion on broken link referrals */ - if (rc == -EREMOTE && ++count > MAX_NESTED_LINKS) - rc = -ELOOP; - } while (rc == -EREMOTE); +/* Set up DFS referral paths for failover */ +static void setup_server_referral_paths(struct mount_ctx *mnt_ctx) +{ + struct TCP_Server_Info *server = mnt_ctx->server; + + server->origin_fullpath = mnt_ctx->origin_fullpath; + server->leaf_fullpath = mnt_ctx->leaf_fullpath; + server->current_fullpath = mnt_ctx->leaf_fullpath; + mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL; +} - if (rc || !tcon || !ses) +int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) +{ + int rc; + struct mount_ctx mnt_ctx = { .cifs_sb = cifs_sb, .fs_ctx = ctx, }; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + bool isdfs; + + rc = is_dfs_mount(&mnt_ctx, &isdfs, &tl); + if (rc) goto error; + if (!isdfs) + goto out; - kfree(ref_path); - /* - * Store DFS full path in both superblock and tree connect structures. - * - * For DFS root mounts, the prefix path (cifs_sb->prepath) is preserved during reconnect so - * only the root path is set in cifs_sb->origin_fullpath and tcon->dfs_path. And for DFS - * links, the prefix path is included in both and may be changed during reconnect. See - * cifs_tree_connect(). - */ - ref_path = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, cifs_remap(cifs_sb)); - kfree(full_path); - full_path = NULL; + uuid_gen(&mnt_ctx.mount_id); + rc = connect_dfs_root(&mnt_ctx, &tl); + dfs_cache_free_tgts(&tl); - if (IS_ERR(ref_path)) { - rc = PTR_ERR(ref_path); - ref_path = NULL; + if (rc) goto error; - } - cifs_sb->origin_fullpath = ref_path; - ref_path = kstrdup(cifs_sb->origin_fullpath, GFP_KERNEL); - if (!ref_path) { - rc = -ENOMEM; + rc = is_path_remote(&mnt_ctx); + if (rc == -EREMOTE) + rc = follow_dfs_link(&mnt_ctx); + if (rc) goto error; - } - spin_lock(&cifs_tcp_ses_lock); - tcon->dfs_path = ref_path; - ref_path = NULL; - spin_unlock(&cifs_tcp_ses_lock); + setup_server_referral_paths(&mnt_ctx); /* - * After reconnecting to a different server, unique ids won't - * match anymore, so we disable serverino. This prevents - * dentry revalidation to think the dentry are stale (ESTALE). + * After reconnecting to a different server, unique ids won't match anymore, so we disable + * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). */ cifs_autodisable_serverino(cifs_sb); /* - * Force the use of prefix path to support failover on DFS paths that - * resolve to targets that have different prefix paths. + * Force the use of prefix path to support failover on DFS paths that resolve to targets + * that have different prefix paths. */ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; kfree(cifs_sb->prepath); cifs_sb->prepath = ctx->prepath; ctx->prepath = NULL; - uuid_copy(&cifs_sb->dfs_mount_id, &mount_id); + uuid_copy(&cifs_sb->dfs_mount_id, &mnt_ctx.mount_id); out: - free_xid(xid); - cifs_try_adding_channels(cifs_sb, ses); - return mount_setup_tlink(cifs_sb, ses, tcon); + free_xid(mnt_ctx.xid); + cifs_try_adding_channels(cifs_sb, mnt_ctx.ses); + return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); error: - kfree(ref_path); - kfree(full_path); - kfree(cifs_sb->origin_fullpath); - dfs_cache_put_refsrv_sessions(&mount_id); - mount_put_conns(cifs_sb, xid, server, ses, tcon); + dfs_cache_put_refsrv_sessions(&mnt_ctx.mount_id); + kfree(mnt_ctx.origin_fullpath); + kfree(mnt_ctx.leaf_fullpath); + mount_put_conns(&mnt_ctx); return rc; } #else int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) { int rc = 0; - unsigned int xid; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; + struct mount_ctx mnt_ctx = { .cifs_sb = cifs_sb, .fs_ctx = ctx, }; - rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); + rc = mount_get_conns(&mnt_ctx); if (rc) goto error; - if (tcon) { - rc = is_path_remote(cifs_sb, ctx, xid, server, tcon); + if (mnt_ctx.tcon) { + rc = is_path_remote(&mnt_ctx); if (rc == -EREMOTE) rc = -EOPNOTSUPP; if (rc) goto error; } - free_xid(xid); - - return mount_setup_tlink(cifs_sb, ses, tcon); + free_xid(mnt_ctx.xid); + return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); error: - mount_put_conns(cifs_sb, xid, server, ses, tcon); + mount_put_conns(&mnt_ctx); return rc; } #endif @@ -3818,7 +3785,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb) kfree(cifs_sb->prepath); #ifdef CONFIG_CIFS_DFS_UPCALL dfs_cache_put_refsrv_sessions(&cifs_sb->dfs_mount_id); - kfree(cifs_sb->origin_fullpath); #endif call_rcu(&cifs_sb->rcu, delayed_free); } @@ -4145,104 +4111,246 @@ cifs_prune_tlinks(struct work_struct *work) } #ifdef CONFIG_CIFS_DFS_UPCALL -int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc) +static void mark_tcon_tcp_ses_for_reconnect(struct cifs_tcon *tcon) +{ + int i; + + for (i = 0; i < tcon->ses->chan_count; i++) { + spin_lock(&GlobalMid_Lock); + if (tcon->ses->chans[i].server->tcpStatus != CifsExiting) + tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + } +} + +/* Update dfs referral path of superblock */ +static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb_info *cifs_sb, + const char *target) +{ + int rc = 0; + size_t len = strlen(target); + char *refpath, *npath; + + if (unlikely(len < 2 || *target != '\\')) + return -EINVAL; + + if (target[1] == '\\') { + len += 1; + refpath = kmalloc(len, GFP_KERNEL); + if (!refpath) + return -ENOMEM; + + scnprintf(refpath, len, "%s", target); + } else { + len += sizeof("\\"); + refpath = kmalloc(len, GFP_KERNEL); + if (!refpath) + return -ENOMEM; + + scnprintf(refpath, len, "\\%s", target); + } + + npath = dfs_cache_canonical_path(refpath, cifs_sb->local_nls, cifs_remap(cifs_sb)); + kfree(refpath); + + if (IS_ERR(npath)) { + rc = PTR_ERR(npath); + } else { + mutex_lock(&server->refpath_lock); + kfree(server->leaf_fullpath); + server->leaf_fullpath = npath; + mutex_unlock(&server->refpath_lock); + server->current_fullpath = server->leaf_fullpath; + } + return rc; +} + +static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host, + size_t tcp_host_len, char *share, bool *target_match) +{ + int rc = 0; + const char *dfs_host; + size_t dfs_host_len; + + *target_match = true; + extract_unc_hostname(share, &dfs_host, &dfs_host_len); + + /* Check if hostnames or addresses match */ + if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { + cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, + dfs_host, (int)tcp_host_len, tcp_host); + rc = match_target_ip(server, dfs_host, dfs_host_len, target_match); + if (rc) + cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc); + } + return rc; +} + +static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, char *tree, bool islink, + struct dfs_cache_tgt_list *tl) { int rc; struct TCP_Server_Info *server = tcon->ses->server; const struct smb_version_operations *ops = server->ops; - struct dfs_cache_tgt_list tl; - struct dfs_cache_tgt_iterator *it = NULL; - char *tree; + struct cifs_tcon *ipc = tcon->ses->tcon_ipc; + char *share = NULL, *prefix = NULL; const char *tcp_host; size_t tcp_host_len; - const char *dfs_host; - size_t dfs_host_len; - char *share = NULL, *prefix = NULL; - struct dfs_info3_param ref = {0}; - bool isroot; + struct dfs_cache_tgt_iterator *tit; + bool target_match; - tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); - if (!tree) - return -ENOMEM; + extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); - /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ - if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) { - if (tcon->ipc) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); - rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); - } else { - rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, nlsc); - } + tit = dfs_cache_get_tgt_iterator(tl); + if (!tit) { + rc = -ENOENT; goto out; } - isroot = ref.server_type == DFS_TYPE_ROOT; - free_dfs_info_param(&ref); - - extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); - - for (it = dfs_cache_get_tgt_iterator(&tl); it; it = dfs_cache_get_next_tgt(&tl, it)) { - bool target_match; + /* Try to tree connect to all dfs targets */ + for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) { + const char *target = dfs_cache_get_tgt_name(tit); + struct dfs_cache_tgt_list ntl = DFS_CACHE_TGT_LIST_INIT(ntl); kfree(share); kfree(prefix); - share = NULL; - prefix = NULL; + share = prefix = NULL; - rc = dfs_cache_get_tgt_share(tcon->dfs_path + 1, it, &share, &prefix); + /* Check if share matches with tcp ses */ + rc = dfs_cache_get_tgt_share(server->current_fullpath + 1, tit, &share, &prefix); if (rc) { - cifs_dbg(VFS, "%s: failed to parse target share %d\n", - __func__, rc); - continue; + cifs_dbg(VFS, "%s: failed to parse target share: %d\n", __func__, rc); + break; } - extract_unc_hostname(share, &dfs_host, &dfs_host_len); - - if (dfs_host_len != tcp_host_len - || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { - cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, - dfs_host, (int)tcp_host_len, tcp_host); + rc = target_share_matches_server(server, tcp_host, tcp_host_len, share, + &target_match); + if (rc) + break; + if (!target_match) { + rc = -EHOSTUNREACH; + continue; + } - rc = match_target_ip(server, dfs_host, dfs_host_len, &target_match); - if (rc) { - cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc); + if (ipc->need_reconnect) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); + rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls); + if (rc) break; - } - - if (!target_match) { - cifs_dbg(FYI, "%s: skipping target\n", __func__); - continue; - } } - if (tcon->ipc) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", share); - rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); + scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); + if (!islink) { + rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls); + break; + } + /* + * If no dfs referrals were returned from link target, then just do a TREE_CONNECT + * to it. Otherwise, cache the dfs referral and then mark current tcp ses for + * reconnect so either the demultiplex thread or the echo worker will reconnect to + * newly resolved target. + */ + if (dfs_cache_find(xid, tcon->ses, cifs_sb->local_nls, cifs_remap(cifs_sb), target, + NULL, &ntl)) { + rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls); + if (rc) + continue; + rc = dfs_cache_noreq_update_tgthint(server->current_fullpath + 1, tit); + if (!rc) + rc = cifs_update_super_prepath(cifs_sb, prefix); } else { - scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); - rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); - /* Only handle prefix paths of DFS link targets */ - if (!rc && !isroot) { - rc = update_super_prepath(tcon, prefix); - break; - } + /* Target is another dfs share */ + rc = update_server_fullpath(server, cifs_sb, target); + dfs_cache_free_tgts(tl); + + if (!rc) { + rc = -EREMOTE; + list_replace_init(&ntl.tl_list, &tl->tl_list); + } else + dfs_cache_free_tgts(&ntl); } - if (rc == -EREMOTE) - break; + break; } +out: kfree(share); kfree(prefix); - if (!rc) { - if (it) - rc = dfs_cache_noreq_update_tgthint(tcon->dfs_path + 1, it); - else - rc = -ENOENT; + return rc; +} + +static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, char *tree, bool islink, + struct dfs_cache_tgt_list *tl) +{ + int rc; + int num_links = 0; + struct TCP_Server_Info *server = tcon->ses->server; + + do { + rc = __tree_connect_dfs_target(xid, tcon, cifs_sb, tree, islink, tl); + if (!rc || rc != -EREMOTE) + break; + } while (rc = -ELOOP, ++num_links < MAX_NESTED_LINKS); + /* + * If we couldn't tree connect to any targets from last referral path, then retry from + * original referral path. + */ + if (rc && server->current_fullpath != server->origin_fullpath) { + server->current_fullpath = server->origin_fullpath; + mark_tcon_tcp_ses_for_reconnect(tcon); } - dfs_cache_free_tgts(&tl); + + dfs_cache_free_tgts(tl); + return rc; +} + +int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc) +{ + int rc; + struct TCP_Server_Info *server = tcon->ses->server; + const struct smb_version_operations *ops = server->ops; + struct super_block *sb = NULL; + struct cifs_sb_info *cifs_sb; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + char *tree; + struct dfs_info3_param ref = {0}; + + tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); + if (!tree) + return -ENOMEM; + + if (tcon->ipc) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); + rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); + goto out; + } + + sb = cifs_get_tcp_super(server); + if (IS_ERR(sb)) { + rc = PTR_ERR(sb); + cifs_dbg(VFS, "%s: could not find superblock: %d\n", __func__, rc); + goto out; + } + + cifs_sb = CIFS_SB(sb); + + /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ + if (!server->current_fullpath || + dfs_cache_noreq_find(server->current_fullpath + 1, &ref, &tl)) { + rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, cifs_sb->local_nls); + goto out; + } + + rc = tree_connect_dfs_target(xid, tcon, cifs_sb, tree, ref.server_type == DFS_TYPE_LINK, + &tl); + free_dfs_info_param(&ref); + out: kfree(tree); + cifs_put_tcp_super(sb); + return rc; } #else diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 283745592844..5c1259d2eeac 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -283,7 +283,7 @@ static int dfscache_proc_show(struct seq_file *m, void *v) seq_printf(m, "cache entry: path=%s,type=%s,ttl=%d,etime=%ld,hdr_flags=0x%x,ref_flags=0x%x,interlink=%s,path_consumed=%d,expired=%s\n", ce->path, ce->srvtype == DFS_TYPE_ROOT ? "root" : "link", - ce->ttl, ce->etime.tv_nsec, ce->ref_flags, ce->hdr_flags, + ce->ttl, ce->etime.tv_nsec, ce->hdr_flags, ce->ref_flags, IS_DFS_INTERLINK(ce->hdr_flags) ? "yes" : "no", ce->path_consumed, cache_entry_expired(ce) ? "yes" : "no"); @@ -1364,9 +1364,9 @@ static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cach } /* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh) +static int __refresh_tcon(const char *path, struct cifs_ses **sessions, struct cifs_tcon *tcon, + bool force_refresh) { - const char *path = tcon->dfs_path + 1; struct cifs_ses *ses; struct cache_entry *ce; struct dfs_info3_param *refs = NULL; @@ -1422,6 +1422,20 @@ out: return rc; } +static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh) +{ + struct TCP_Server_Info *server = tcon->ses->server; + + mutex_lock(&server->refpath_lock); + if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + mutex_unlock(&server->refpath_lock); + + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); + + return 0; +} + /** * dfs_cache_remount_fs - remount a DFS share * @@ -1435,6 +1449,7 @@ out: int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) { struct cifs_tcon *tcon; + struct TCP_Server_Info *server; struct mount_group *mg; struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL}; int rc; @@ -1443,13 +1458,15 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) return -EINVAL; tcon = cifs_sb_master_tcon(cifs_sb); - if (!tcon->dfs_path) { - cifs_dbg(FYI, "%s: not a dfs tcon\n", __func__); + server = tcon->ses->server; + + if (!server->origin_fullpath) { + cifs_dbg(FYI, "%s: not a dfs mount\n", __func__); return 0; } if (uuid_is_null(&cifs_sb->dfs_mount_id)) { - cifs_dbg(FYI, "%s: tcon has no dfs mount group id\n", __func__); + cifs_dbg(FYI, "%s: no dfs mount group id\n", __func__); return -EINVAL; } @@ -1457,7 +1474,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) mg = find_mount_group_locked(&cifs_sb->dfs_mount_id); if (IS_ERR(mg)) { mutex_unlock(&mount_group_list_lock); - cifs_dbg(FYI, "%s: tcon has ipc session to refresh referral\n", __func__); + cifs_dbg(FYI, "%s: no ipc session for refreshing referral\n", __func__); return PTR_ERR(mg); } kref_get(&mg->refcount); @@ -1498,9 +1515,12 @@ static void refresh_mounts(struct cifs_ses **sessions) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { + if (!server->is_dfs_conn) + continue; + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { - if (tcon->dfs_path) { + if (!tcon->ipc && !tcon->need_reconnect) { tcon->tc_count++; list_add_tail(&tcon->ulist, &tcons); } @@ -1510,8 +1530,16 @@ static void refresh_mounts(struct cifs_ses **sessions) spin_unlock(&cifs_tcp_ses_lock); list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) { + struct TCP_Server_Info *server = tcon->ses->server; + list_del_init(&tcon->ulist); - refresh_tcon(sessions, tcon, false); + + mutex_lock(&server->refpath_lock); + if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + mutex_unlock(&server->refpath_lock); + + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 1b855fcb179e..9fee3af83a73 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2692,12 +2692,23 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, tcon = tlink_tcon(smbfile->tlink); if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { server = tcon->ses->server; - if (server->ops->flush) - rc = server->ops->flush(xid, tcon, &smbfile->fid); - else + if (server->ops->flush == NULL) { rc = -ENOSYS; + goto strict_fsync_exit; + } + + if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { + smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); + if (smbfile) { + rc = server->ops->flush(xid, tcon, &smbfile->fid); + cifsFileInfo_put(smbfile); + } else + cifs_dbg(FYI, "ignore fsync for file not open for write\n"); + } else + rc = server->ops->flush(xid, tcon, &smbfile->fid); } +strict_fsync_exit: free_xid(xid); return rc; } @@ -2709,6 +2720,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct cifs_tcon *tcon; struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; + struct inode *inode = file_inode(file); struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); rc = file_write_and_wait_range(file, start, end); @@ -2725,12 +2737,23 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) tcon = tlink_tcon(smbfile->tlink); if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { server = tcon->ses->server; - if (server->ops->flush) - rc = server->ops->flush(xid, tcon, &smbfile->fid); - else + if (server->ops->flush == NULL) { rc = -ENOSYS; + goto fsync_exit; + } + + if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { + smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); + if (smbfile) { + rc = server->ops->flush(xid, tcon, &smbfile->fid); + cifsFileInfo_put(smbfile); + } else + cifs_dbg(FYI, "ignore fsync for file not open for write\n"); + } else + rc = server->ops->flush(xid, tcon, &smbfile->fid); } +fsync_exit: free_xid(xid); return rc; } diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 38d96a480745..6a179ae753c1 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -308,7 +308,9 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->nodename = NULL; new_ctx->username = NULL; new_ctx->password = NULL; + new_ctx->server_hostname = NULL; new_ctx->domainname = NULL; + new_ctx->workstation_name = NULL; new_ctx->UNC = NULL; new_ctx->source = NULL; new_ctx->iocharset = NULL; @@ -323,6 +325,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(UNC); DUP_CTX_STR(source); DUP_CTX_STR(domainname); + DUP_CTX_STR(workstation_name); DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); @@ -459,6 +462,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) return -EINVAL; /* record the server hostname */ + kfree(ctx->server_hostname); ctx->server_hostname = kstrndup(devname + 2, pos - devname - 2, GFP_KERNEL); if (!ctx->server_hostname) return -ENOMEM; @@ -720,6 +724,11 @@ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, cifs_errorf(fc, "can not change domainname during remount\n"); return -EINVAL; } + if (new_ctx->workstation_name && + (!old_ctx->workstation_name || strcmp(new_ctx->workstation_name, old_ctx->workstation_name))) { + cifs_errorf(fc, "can not change workstation_name during remount\n"); + return -EINVAL; + } if (new_ctx->nodename && (!old_ctx->nodename || strcmp(new_ctx->nodename, old_ctx->nodename))) { cifs_errorf(fc, "can not change nodename during remount\n"); @@ -753,7 +762,8 @@ static int smb3_reconfigure(struct fs_context *fc) return rc; /* - * We can not change UNC/username/password/domainname/nodename/iocharset + * We can not change UNC/username/password/domainname/ + * workstation_name/nodename/iocharset * during reconnect so ignore what we have in the new context and * just use what we already have in cifs_sb->ctx. */ @@ -762,6 +772,7 @@ static int smb3_reconfigure(struct fs_context *fc) STEAL_STRING(cifs_sb, ctx, username); STEAL_STRING(cifs_sb, ctx, password); STEAL_STRING(cifs_sb, ctx, domainname); + STEAL_STRING(cifs_sb, ctx, workstation_name); STEAL_STRING(cifs_sb, ctx, nodename); STEAL_STRING(cifs_sb, ctx, iocharset); @@ -1414,13 +1425,22 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, int smb3_init_fs_context(struct fs_context *fc) { + int rc; struct smb3_fs_context *ctx; char *nodename = utsname()->nodename; int i; ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL); - if (unlikely(!ctx)) - return -ENOMEM; + if (unlikely(!ctx)) { + rc = -ENOMEM; + goto err_exit; + } + + ctx->workstation_name = kstrdup(nodename, GFP_KERNEL); + if (unlikely(!ctx->workstation_name)) { + rc = -ENOMEM; + goto err_exit; + } /* * does not have to be perfect mapping since field is @@ -1493,6 +1513,14 @@ int smb3_init_fs_context(struct fs_context *fc) fc->fs_private = ctx; fc->ops = &smb3_fs_context_ops; return 0; + +err_exit: + if (ctx) { + kfree(ctx->workstation_name); + kfree(ctx); + } + + return rc; } void @@ -1518,6 +1546,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->source = NULL; kfree(ctx->domainname); ctx->domainname = NULL; + kfree(ctx->workstation_name); + ctx->workstation_name = NULL; kfree(ctx->nodename); ctx->nodename = NULL; kfree(ctx->iocharset); diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index b2d22cf9cb18..e54090d9ef36 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -170,6 +170,7 @@ struct smb3_fs_context { char *server_hostname; char *UNC; char *nodename; + char *workstation_name; char *iocharset; /* local code page for mapping to and from Unicode */ char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */ char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */ diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 8eedd20c44ab..7e409a38a2d7 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -87,6 +87,14 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) char *sharename; struct cifs_fscache_super_auxdata auxdata; + /* + * Check if cookie was already initialized so don't reinitialize it. + * In the future, as we integrate with newer fscache features, + * we may want to instead add a check if cookie has changed + */ + if (tcon->fscache == NULL) + return; + sharename = extract_sharename(tcon->treeName); if (IS_ERR(sharename)) { cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index ba2c3e897b29..5148d48d6a35 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -75,6 +75,7 @@ sesInfoAlloc(void) INIT_LIST_HEAD(&ret_buf->tcon_list); mutex_init(&ret_buf->session_mutex); spin_lock_init(&ret_buf->iface_lock); + spin_lock_init(&ret_buf->chan_lock); } return ret_buf; } @@ -94,6 +95,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree_sensitive(buf_to_free->password); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); + kfree(buf_to_free->workstation_name); kfree_sensitive(buf_to_free->auth_key.response); kfree(buf_to_free->iface_list); kfree_sensitive(buf_to_free); @@ -138,9 +140,6 @@ tconInfoFree(struct cifs_tcon *buf_to_free) kfree(buf_to_free->nativeFileSystem); kfree_sensitive(buf_to_free->password); kfree(buf_to_free->crfid.fid); -#ifdef CONFIG_CIFS_DFS_UPCALL - kfree(buf_to_free->dfs_path); -#endif kfree(buf_to_free); } @@ -1287,69 +1286,20 @@ out: return rc; } -static void tcon_super_cb(struct super_block *sb, void *arg) +int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) { - struct super_cb_data *sd = arg; - struct cifs_tcon *tcon = sd->data; - struct cifs_sb_info *cifs_sb; - - if (sd->sb) - return; - - cifs_sb = CIFS_SB(sb); - if (tcon->dfs_path && cifs_sb->origin_fullpath && - !strcasecmp(tcon->dfs_path, cifs_sb->origin_fullpath)) - sd->sb = sb; -} - -static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon) -{ - return __cifs_get_super(tcon_super_cb, tcon); -} - -static inline void cifs_put_tcon_super(struct super_block *sb) -{ - __cifs_put_super(sb); -} -#else -static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void cifs_put_tcon_super(struct super_block *sb) -{ -} -#endif - -int update_super_prepath(struct cifs_tcon *tcon, char *prefix) -{ - struct super_block *sb; - struct cifs_sb_info *cifs_sb; - int rc = 0; - - sb = cifs_get_tcon_super(tcon); - if (IS_ERR(sb)) - return PTR_ERR(sb); - - cifs_sb = CIFS_SB(sb); - kfree(cifs_sb->prepath); if (prefix && *prefix) { cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC); - if (!cifs_sb->prepath) { - rc = -ENOMEM; - goto out; - } + if (!cifs_sb->prepath) + return -ENOMEM; convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb)); } else cifs_sb->prepath = NULL; cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - -out: - cifs_put_tcon_super(sb); - return rc; + return 0; } +#endif diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 25a2b8ef88b9..fe707f45da89 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -119,7 +119,9 @@ typedef struct _AUTHENTICATE_MESSAGE { */ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses); -void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses); +int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, u16 *buflen, + struct cifs_ses *ses, + const struct nls_table *nls_cp); int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, const struct nls_table *nls_cp); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 23e02db7923f..2c10b186ed6e 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -54,41 +54,53 @@ bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) { int i; + spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { - if (is_server_using_iface(ses->chans[i].server, iface)) + if (is_server_using_iface(ses->chans[i].server, iface)) { + spin_unlock(&ses->chan_lock); return true; + } } + spin_unlock(&ses->chan_lock); return false; } /* returns number of channels added */ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) { - int old_chan_count = ses->chan_count; - int left = ses->chan_max - ses->chan_count; + int old_chan_count, new_chan_count; + int left; int i = 0; int rc = 0; int tries = 0; struct cifs_server_iface *ifaces = NULL; size_t iface_count; + if (ses->server->dialect < SMB30_PROT_ID) { + cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n"); + return 0; + } + + spin_lock(&ses->chan_lock); + + new_chan_count = old_chan_count = ses->chan_count; + left = ses->chan_max - ses->chan_count; + if (left <= 0) { cifs_dbg(FYI, "ses already at max_channels (%zu), nothing to open\n", ses->chan_max); - return 0; - } - - if (ses->server->dialect < SMB30_PROT_ID) { - cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n"); + spin_unlock(&ses->chan_lock); return 0; } if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname); ses->chan_max = 1; + spin_unlock(&ses->chan_lock); return 0; } + spin_unlock(&ses->chan_lock); /* * Make a copy of the iface list at the time and use that @@ -142,10 +154,11 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) cifs_dbg(FYI, "successfully opened new channel on iface#%d\n", i); left--; + new_chan_count++; } kfree(ifaces); - return ses->chan_count - old_chan_count; + return new_chan_count - old_chan_count; } /* @@ -157,10 +170,14 @@ cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server) { int i; + spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { - if (ses->chans[i].server == server) + if (ses->chans[i].server == server) { + spin_unlock(&ses->chan_lock); return &ses->chans[i]; + } } + spin_unlock(&ses->chan_lock); return NULL; } @@ -168,6 +185,7 @@ static int cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, struct cifs_server_iface *iface) { + struct TCP_Server_Info *chan_server; struct cifs_chan *chan; struct smb3_fs_context ctx = {NULL}; static const char unc_fmt[] = "\\%s\\foo"; @@ -240,18 +258,19 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, SMB2_CLIENT_GUID_SIZE); ctx.use_client_guid = true; - mutex_lock(&ses->session_mutex); + chan_server = cifs_get_tcp_session(&ctx, ses->server); + mutex_lock(&ses->session_mutex); + spin_lock(&ses->chan_lock); chan = ses->binding_chan = &ses->chans[ses->chan_count]; - chan->server = cifs_get_tcp_session(&ctx); + chan->server = chan_server; if (IS_ERR(chan->server)) { rc = PTR_ERR(chan->server); chan->server = NULL; + spin_unlock(&ses->chan_lock); goto out; } - spin_lock(&cifs_tcp_ses_lock); - chan->server->is_channel = true; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->chan_lock); /* * We need to allocate the server crypto now as we will need @@ -283,8 +302,11 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, * ses to the new server. */ + spin_lock(&ses->chan_lock); ses->chan_count++; atomic_set(&ses->chan_seq, 0); + spin_unlock(&ses->chan_lock); + out: ses->binding = false; ses->binding_chan = NULL; @@ -599,18 +621,85 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return 0; } +static int size_of_ntlmssp_blob(struct cifs_ses *ses, int base_size) +{ + int sz = base_size + ses->auth_key.len + - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2; + + if (ses->domainName) + sz += sizeof(__le16) * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); + else + sz += sizeof(__le16); + + if (ses->user_name) + sz += sizeof(__le16) * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); + else + sz += sizeof(__le16); + + sz += sizeof(__le16) * strnlen(ses->workstation_name, CIFS_MAX_WORKSTATION_LEN); + + return sz; +} + +static inline void cifs_security_buffer_from_str(SECURITY_BUFFER *pbuf, + char *str_value, + int str_length, + unsigned char *pstart, + unsigned char **pcur, + const struct nls_table *nls_cp) +{ + unsigned char *tmp = pstart; + int len; + + if (!pbuf) + return; + + if (!pcur) + pcur = &tmp; + + if (!str_value) { + pbuf->BufferOffset = cpu_to_le32(*pcur - pstart); + pbuf->Length = 0; + pbuf->MaximumLength = 0; + *pcur += sizeof(__le16); + } else { + len = cifs_strtoUTF16((__le16 *)*pcur, + str_value, + str_length, + nls_cp); + len *= sizeof(__le16); + pbuf->BufferOffset = cpu_to_le32(*pcur - pstart); + pbuf->Length = cpu_to_le16(len); + pbuf->MaximumLength = cpu_to_le16(len); + *pcur += len; + } +} + /* BB Move to ntlmssp.c eventually */ -/* We do not malloc the blob, it is passed in pbuffer, because - it is fixed size, and small, making this approach cleaner */ -void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, - struct cifs_ses *ses) +int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, + u16 *buflen, + struct cifs_ses *ses, + const struct nls_table *nls_cp) { + int rc = 0; struct TCP_Server_Info *server = cifs_ses_server(ses); - NEGOTIATE_MESSAGE *sec_blob = (NEGOTIATE_MESSAGE *)pbuffer; + NEGOTIATE_MESSAGE *sec_blob; __u32 flags; + unsigned char *tmp; + int len; + + len = size_of_ntlmssp_blob(ses, sizeof(NEGOTIATE_MESSAGE)); + *pbuffer = kmalloc(len, GFP_KERNEL); + if (!*pbuffer) { + rc = -ENOMEM; + cifs_dbg(VFS, "Error %d during NTLMSSP allocation\n", rc); + *buflen = 0; + goto setup_ntlm_neg_ret; + } + sec_blob = (NEGOTIATE_MESSAGE *)*pbuffer; - memset(pbuffer, 0, sizeof(NEGOTIATE_MESSAGE)); + memset(*pbuffer, 0, sizeof(NEGOTIATE_MESSAGE)); memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmNegotiate; @@ -624,34 +713,25 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess) flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + tmp = *pbuffer + sizeof(NEGOTIATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); - sec_blob->WorkstationName.BufferOffset = 0; - sec_blob->WorkstationName.Length = 0; - sec_blob->WorkstationName.MaximumLength = 0; + /* these fields should be null in negotiate phase MS-NLMP 3.1.5.1.1 */ + cifs_security_buffer_from_str(&sec_blob->DomainName, + NULL, + CIFS_MAX_DOMAINNAME_LEN, + *pbuffer, &tmp, + nls_cp); - /* Domain name is sent on the Challenge not Negotiate NTLMSSP request */ - sec_blob->DomainName.BufferOffset = 0; - sec_blob->DomainName.Length = 0; - sec_blob->DomainName.MaximumLength = 0; -} - -static int size_of_ntlmssp_blob(struct cifs_ses *ses) -{ - int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len - - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2; - - if (ses->domainName) - sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); - else - sz += 2; - - if (ses->user_name) - sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); - else - sz += 2; + cifs_security_buffer_from_str(&sec_blob->WorkstationName, + NULL, + CIFS_MAX_WORKSTATION_LEN, + *pbuffer, &tmp, + nls_cp); - return sz; + *buflen = tmp - *pbuffer; +setup_ntlm_neg_ret: + return rc; } int build_ntlmssp_auth_blob(unsigned char **pbuffer, @@ -663,6 +743,7 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, AUTHENTICATE_MESSAGE *sec_blob; __u32 flags; unsigned char *tmp; + int len; rc = setup_ntlmv2_rsp(ses, nls_cp); if (rc) { @@ -670,7 +751,9 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, *buflen = 0; goto setup_ntlmv2_ret; } - *pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL); + + len = size_of_ntlmssp_blob(ses, sizeof(AUTHENTICATE_MESSAGE)); + *pbuffer = kmalloc(len, GFP_KERNEL); if (!*pbuffer) { rc = -ENOMEM; cifs_dbg(VFS, "Error %d during NTLMSSP allocation\n", rc); @@ -686,7 +769,7 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC | - NTLMSSP_NEGOTIATE_SEAL; + NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED; if (ses->server->sign) flags |= NTLMSSP_NEGOTIATE_SIGN; if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) @@ -719,42 +802,23 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, sec_blob->NtChallengeResponse.MaximumLength = 0; } - if (ses->domainName == NULL) { - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->DomainName.Length = 0; - sec_blob->DomainName.MaximumLength = 0; - tmp += 2; - } else { - int len; - len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName, - CIFS_MAX_DOMAINNAME_LEN, nls_cp); - len *= 2; /* unicode is 2 bytes each */ - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->DomainName.Length = cpu_to_le16(len); - sec_blob->DomainName.MaximumLength = cpu_to_le16(len); - tmp += len; - } + cifs_security_buffer_from_str(&sec_blob->DomainName, + ses->domainName, + CIFS_MAX_DOMAINNAME_LEN, + *pbuffer, &tmp, + nls_cp); - if (ses->user_name == NULL) { - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->UserName.Length = 0; - sec_blob->UserName.MaximumLength = 0; - tmp += 2; - } else { - int len; - len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name, - CIFS_MAX_USERNAME_LEN, nls_cp); - len *= 2; /* unicode is 2 bytes each */ - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->UserName.Length = cpu_to_le16(len); - sec_blob->UserName.MaximumLength = cpu_to_le16(len); - tmp += len; - } + cifs_security_buffer_from_str(&sec_blob->UserName, + ses->user_name, + CIFS_MAX_USERNAME_LEN, + *pbuffer, &tmp, + nls_cp); - sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->WorkstationName.Length = 0; - sec_blob->WorkstationName.MaximumLength = 0; - tmp += 2; + cifs_security_buffer_from_str(&sec_blob->WorkstationName, + ses->workstation_name, + CIFS_MAX_WORKSTATION_LEN, + *pbuffer, &tmp, + nls_cp); if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) || (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) @@ -1230,6 +1294,7 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data) struct cifs_ses *ses = sess_data->ses; __u16 bytes_remaining; char *bcc_ptr; + unsigned char *ntlmsspblob = NULL; u16 blob_len; cifs_dbg(FYI, "rawntlmssp session setup negotiate phase\n"); @@ -1253,10 +1318,15 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data) pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; /* Build security blob before we assemble the request */ - build_ntlmssp_negotiate_blob(pSMB->req.SecurityBlob, ses); - sess_data->iov[1].iov_len = sizeof(NEGOTIATE_MESSAGE); - sess_data->iov[1].iov_base = pSMB->req.SecurityBlob; - pSMB->req.SecurityBlobLength = cpu_to_le16(sizeof(NEGOTIATE_MESSAGE)); + rc = build_ntlmssp_negotiate_blob(&ntlmsspblob, + &blob_len, ses, + sess_data->nls_cp); + if (rc) + goto out; + + sess_data->iov[1].iov_len = blob_len; + sess_data->iov[1].iov_base = ntlmsspblob; + pSMB->req.SecurityBlobLength = cpu_to_le16(blob_len); rc = _sess_auth_rawntlmssp_assemble_req(sess_data); if (rc) diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 8297703492ee..fe5bfa245fa7 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -46,6 +46,10 @@ struct cop_vars { struct smb2_file_link_info link_info; }; +/* + * note: If cfile is passed, the reference to it is dropped here. + * So make sure that you do not reuse cfile after return from this func. + */ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, @@ -536,10 +540,11 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ + cifs_get_readable_path(tcon, full_path, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_QUERY_INFO, NULL); + smb2_data, SMB2_OP_QUERY_INFO, cfile); } if (rc) goto out; @@ -587,10 +592,11 @@ smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ + cifs_get_readable_path(tcon, full_path, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_POSIX_QUERY_INFO, NULL); + smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile); } if (rc) goto out; @@ -707,10 +713,12 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, bool set_alloc) { __le64 eof = cpu_to_le64(size); + struct cifsFileInfo *cfile; + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); return smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE, - &eof, SMB2_OP_SET_EOF, NULL); + &eof, SMB2_OP_SET_EOF, cfile); } int @@ -719,6 +727,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path, { struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink; + struct cifs_tcon *tcon; + struct cifsFileInfo *cfile; int rc; if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && @@ -729,10 +739,12 @@ smb2_set_file_info(struct inode *inode, const char *full_path, tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); - rc = smb2_compound_op(xid, tlink_tcon(tlink), cifs_sb, full_path, + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, - 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, NULL); + 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile); cifs_put_tlink(tlink); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7acf71defea7..c5b1dea54ebc 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2844,6 +2844,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, struct fsctl_get_dfs_referral_req *dfs_req = NULL; struct get_dfs_referral_rsp *dfs_rsp = NULL; u32 dfs_req_size = 0, dfs_rsp_size = 0; + int retry_count = 0; cifs_dbg(FYI, "%s: path: %s\n", __func__, search_name); @@ -2895,11 +2896,14 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, true /* is_fsctl */, (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); - } while (rc == -EAGAIN); + if (!is_retryable_error(rc)) + break; + usleep_range(512, 2048); + } while (++retry_count < 5); if (rc) { - if ((rc != -ENOENT) && (rc != -EOPNOTSUPP)) - cifs_tcon_dbg(VFS, "ioctl error in %s rc=%d\n", __func__, rc); + if (!is_retryable_error(rc) && rc != -ENOENT && rc != -EOPNOTSUPP) + cifs_tcon_dbg(VFS, "%s: ioctl error: rc=%d\n", __func__, rc); goto out; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index d2ecb2ea37c0..2f5f2c4c6183 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -155,7 +155,11 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if (tcon == NULL) return 0; - if (smb2_command == SMB2_TREE_CONNECT) + /* + * Need to also skip SMB2_IOCTL because it is used for checking nested dfs links in + * cifs_tree_connect(). + */ + if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) return 0; if (tcon->tidStatus == CifsExiting) { @@ -253,7 +257,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, /* * If we are reconnecting an extra channel, bind */ - if (server->is_channel) { + if (CIFS_SERVER_IS_CHAN(server)) { ses->binding = true; ses->binding_chan = cifs_ses_find_chan(ses, server); } @@ -1456,7 +1460,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) int rc; struct cifs_ses *ses = sess_data->ses; struct smb2_sess_setup_rsp *rsp = NULL; - char *ntlmssp_blob = NULL; + unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ u16 blob_length = 0; @@ -1475,22 +1479,17 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) if (rc) goto out_err; - ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE), - GFP_KERNEL); - if (ntlmssp_blob == NULL) { - rc = -ENOMEM; - goto out; - } + rc = build_ntlmssp_negotiate_blob(&ntlmssp_blob, + &blob_length, ses, + sess_data->nls_cp); + if (rc) + goto out_err; - build_ntlmssp_negotiate_blob(ntlmssp_blob, ses); if (use_spnego) { /* BB eventually need to add this */ cifs_dbg(VFS, "spnego not supported for SMB2 yet\n"); rc = -EOPNOTSUPP; goto out; - } else { - blob_length = sizeof(struct _NEGOTIATE_MESSAGE); - /* with raw NTLMSSP we don't encapsulate in SPNEGO */ } sess_data->iov[1].iov_base = ntlmssp_blob; sess_data->iov[1].iov_len = blob_length; @@ -1841,7 +1840,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, cifs_small_buf_release(req); rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base; trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc); - if (rc != 0) { + if ((rc != 0) || (rsp == NULL)) { cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE); tcon->need_reconnect = true; goto tcon_error_exit; @@ -2669,7 +2668,18 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, goto err_free_rsp_buf; } + /* + * Although unlikely to be possible for rsp to be null and rc not set, + * adding check below is slightly safer long term (and quiets Coverity + * warning) + */ rsp = (struct smb2_create_rsp *)rsp_iov.iov_base; + if (rsp == NULL) { + rc = -EIO; + kfree(pc_buf); + goto err_free_req; + } + trace_smb3_posix_mkdir_done(xid, le64_to_cpu(rsp->PersistentFileId), tcon->tid, ses->Suid, CREATE_NOT_FILE, @@ -2942,7 +2952,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, tcon->need_reconnect = true; } goto creat_exit; - } else + } else if (rsp == NULL) /* unlikely to happen, but safer to check */ + goto creat_exit; + else trace_smb3_open_done(xid, le64_to_cpu(rsp->PersistentFileId), tcon->tid, ses->Suid, oparms->create_options, @@ -3163,6 +3175,16 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, if ((plen == NULL) || (out_data == NULL)) goto ioctl_exit; + /* + * Although unlikely to be possible for rsp to be null and rc not set, + * adding check below is slightly safer long term (and quiets Coverity + * warning) + */ + if (rsp == NULL) { + rc = -EIO; + goto ioctl_exit; + } + *plen = le32_to_cpu(rsp->OutputCount); /* We check for obvious errors in the output buffer length and offset */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b7379329b741..61ea3d3f95b4 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1044,14 +1044,17 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) if (!ses) return NULL; + spin_lock(&ses->chan_lock); if (!ses->binding) { /* round robin */ if (ses->chan_count > 1) { index = (uint)atomic_inc_return(&ses->chan_seq); index %= ses->chan_count; } + spin_unlock(&ses->chan_lock); return ses->chans[index].server; } else { + spin_unlock(&ses->chan_lock); return cifs_ses_server(ses); } } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index bcb1b91b234f..9a249bfc2770 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -96,16 +96,9 @@ static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl) DBG_BUGON(1); } -/* - * a compressed_pages[] placeholder in order to avoid - * being filled with file pages for in-place decompression. - */ -#define PAGE_UNALLOCATED ((void *)0x5F0E4B1D) - /* how to allocate cached pages for a pcluster */ enum z_erofs_cache_alloctype { DONTALLOC, /* don't allocate any cached pages */ - DELAYEDALLOC, /* delayed allocation (at the time of submitting io) */ /* * try to use cached I/O if page allocation succeeds or fallback * to in-place I/O instead to avoid any direct reclaim. @@ -267,10 +260,6 @@ static void preload_compressed_pages(struct z_erofs_collector *clt, /* I/O is needed, no possible to decompress directly */ standalone = false; switch (type) { - case DELAYEDALLOC: - t = tagptr_init(compressed_page_t, - PAGE_UNALLOCATED); - break; case TRYALLOC: newpage = erofs_allocpage(pagepool, gfp); if (!newpage) @@ -371,8 +360,8 @@ static bool z_erofs_try_inplace_io(struct z_erofs_collector *clt, /* callers must be with collection lock held */ static int z_erofs_attach_page(struct z_erofs_collector *clt, - struct page *page, - enum z_erofs_page_type type) + struct page *page, enum z_erofs_page_type type, + bool pvec_safereuse) { int ret; @@ -382,9 +371,9 @@ static int z_erofs_attach_page(struct z_erofs_collector *clt, z_erofs_try_inplace_io(clt, page)) return 0; - ret = z_erofs_pagevec_enqueue(&clt->vector, page, type); + ret = z_erofs_pagevec_enqueue(&clt->vector, page, type, + pvec_safereuse); clt->cl->vcnt += (unsigned int)ret; - return ret ? 0 : -EAGAIN; } @@ -727,7 +716,8 @@ hitted: tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED); retry: - err = z_erofs_attach_page(clt, page, page_type); + err = z_erofs_attach_page(clt, page, page_type, + clt->mode >= COLLECT_PRIMARY_FOLLOWED); /* should allocate an additional short-lived page for pagevec */ if (err == -EAGAIN) { struct page *const newpage = @@ -735,7 +725,7 @@ retry: set_page_private(newpage, Z_EROFS_SHORTLIVED_PAGE); err = z_erofs_attach_page(clt, newpage, - Z_EROFS_PAGE_TYPE_EXCLUSIVE); + Z_EROFS_PAGE_TYPE_EXCLUSIVE, true); if (!err) goto retry; } @@ -1089,15 +1079,6 @@ repeat: if (!page) goto out_allocpage; - /* - * the cached page has not been allocated and - * an placeholder is out there, prepare it now. - */ - if (page == PAGE_UNALLOCATED) { - tocache = true; - goto out_allocpage; - } - /* process the target tagged pointer */ t = tagptr_init(compressed_page_t, page); justfound = tagptr_unfold_tags(t); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index 879df5362777..4a69515dea75 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -179,4 +179,3 @@ static inline void z_erofs_onlinepage_endio(struct page *page) #define Z_EROFS_VMAP_GLOBAL_PAGES 2048 #endif - diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h index dfd7fe0503bb..b05464f4a808 100644 --- a/fs/erofs/zpvec.h +++ b/fs/erofs/zpvec.h @@ -106,11 +106,18 @@ static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor, static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor, struct page *page, - enum z_erofs_page_type type) + enum z_erofs_page_type type, + bool pvec_safereuse) { - if (!ctor->next && type) - if (ctor->index + 1 == ctor->nr) + if (!ctor->next) { + /* some pages cannot be reused as pvec safely without I/O */ + if (type == Z_EROFS_PAGE_TYPE_EXCLUSIVE && !pvec_safereuse) + type = Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED; + + if (type != Z_EROFS_PAGE_TYPE_EXCLUSIVE && + ctor->index + 1 == ctor->nr) return false; + } if (ctor->index >= ctor->nr) z_erofs_pagevec_ctor_pagedown(ctor, false); diff --git a/fs/exec.c b/fs/exec.c index b6079f1a098e..537d92c41105 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1850,7 +1850,7 @@ out: * SIGSEGV. */ if (bprm->point_of_no_return && !fatal_signal_pending(current)) - force_sigsegv(SIGSEGV); + force_fatal_sig(SIGSEGV); out_unmark: current->fs->in_exec = 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3825195539d7..404dd50856e5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -17,6 +17,7 @@ #ifndef _EXT4_H #define _EXT4_H +#include <linux/refcount.h> #include <linux/types.h> #include <linux/blkdev.h> #include <linux/magic.h> @@ -241,7 +242,7 @@ typedef struct ext4_io_end { struct bio *bio; /* Linked list of completed * bios covering the extent */ unsigned int flag; /* unwritten or not */ - atomic_t count; /* reference counter */ + refcount_t count; /* reference counter */ struct list_head list_vec; /* list of ext4_io_end_vec */ } ext4_io_end_t; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0e02571f2f82..0ecf819bf189 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -136,15 +136,25 @@ int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, static int ext4_ext_get_access(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { + int err = 0; + if (path->p_bh) { /* path points to block */ BUFFER_TRACE(path->p_bh, "get_write_access"); - return ext4_journal_get_write_access(handle, inode->i_sb, - path->p_bh, EXT4_JTR_NONE); + err = ext4_journal_get_write_access(handle, inode->i_sb, + path->p_bh, EXT4_JTR_NONE); + /* + * The extent buffer's verified bit will be set again in + * __ext4_ext_dirty(). We could leave an inconsistent + * buffer if the extents updating procudure break off du + * to some error happens, force to check it again. + */ + if (!err) + clear_buffer_verified(path->p_bh); } /* path points to leaf/index in inode body */ /* we use in-core data, no need to protect them */ - return 0; + return err; } /* @@ -165,6 +175,9 @@ static int __ext4_ext_dirty(const char *where, unsigned int line, /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); + /* Extents updating done, re-set verified flag */ + if (!err) + set_buffer_verified(path->p_bh); } else { /* path points to leaf/index in inode body */ err = ext4_mark_inode_dirty(handle, inode); @@ -354,9 +367,13 @@ static int ext4_valid_extent_idx(struct inode *inode, static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent_header *eh, - ext4_fsblk_t *pblk, int depth) + ext4_lblk_t lblk, ext4_fsblk_t *pblk, + int depth) { unsigned short entries; + ext4_lblk_t lblock = 0; + ext4_lblk_t prev = 0; + if (eh->eh_entries == 0) return 1; @@ -365,31 +382,51 @@ static int ext4_valid_extent_entries(struct inode *inode, if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); - ext4_lblk_t lblock = 0; - ext4_lblk_t prev = 0; - int len = 0; + + /* + * The logical block in the first entry should equal to + * the number in the index block. + */ + if (depth != ext_depth(inode) && + lblk != le32_to_cpu(ext->ee_block)) + return 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); - len = ext4_ext_get_actual_len(ext); if ((lblock <= prev) && prev) { *pblk = ext4_ext_pblock(ext); return 0; } + prev = lblock + ext4_ext_get_actual_len(ext) - 1; ext++; entries--; - prev = lblock + len - 1; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); + + /* + * The logical block in the first entry should equal to + * the number in the parent index block. + */ + if (depth != ext_depth(inode) && + lblk != le32_to_cpu(ext_idx->ei_block)) + return 0; while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; + + /* Check for overlapping index extents */ + lblock = le32_to_cpu(ext_idx->ei_block); + if ((lblock <= prev) && prev) { + *pblk = ext4_idx_pblock(ext_idx); + return 0; + } ext_idx++; entries--; + prev = lblock; } } return 1; @@ -397,7 +434,7 @@ static int ext4_valid_extent_entries(struct inode *inode, static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, - int depth, ext4_fsblk_t pblk) + int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk) { const char *error_msg; int max = 0, err = -EFSCORRUPTED; @@ -423,7 +460,7 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } - if (!ext4_valid_extent_entries(inode, eh, &pblk, depth)) { + if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } @@ -453,7 +490,7 @@ corrupted: } #define ext4_ext_check(inode, eh, depth, pblk) \ - __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk)) + __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0) int ext4_ext_check_inode(struct inode *inode) { @@ -486,16 +523,18 @@ static void ext4_cache_extents(struct inode *inode, static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, - struct inode *inode, ext4_fsblk_t pblk, int depth, - int flags) + struct inode *inode, struct ext4_extent_idx *idx, + int depth, int flags) { struct buffer_head *bh; int err; gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; + ext4_fsblk_t pblk; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; + pblk = ext4_idx_pblock(idx); bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); @@ -508,8 +547,8 @@ __read_extent_tree_block(const char *function, unsigned int line, } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); + err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh), + depth, pblk, le32_to_cpu(idx->ei_block)); if (err) goto errout; set_buffer_verified(bh); @@ -527,8 +566,8 @@ errout: } -#define read_extent_tree_block(inode, pblk, depth, flags) \ - __read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \ +#define read_extent_tree_block(inode, idx, depth, flags) \ + __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \ (depth), (flags)) /* @@ -578,8 +617,7 @@ int ext4_ext_precache(struct inode *inode) i--; continue; } - bh = read_extent_tree_block(inode, - ext4_idx_pblock(path[i].p_idx++), + bh = read_extent_tree_block(inode, path[i].p_idx++, depth - i - 1, EXT4_EX_FORCE_CACHE); if (IS_ERR(bh)) { @@ -714,13 +752,14 @@ ext4_ext_binsearch_idx(struct inode *inode, r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; + ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, + le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), + r, le32_to_cpu(r->ei_block)); + if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; - ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, - le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), - r, le32_to_cpu(r->ei_block)); } path->p_idx = l - 1; @@ -782,13 +821,14 @@ ext4_ext_binsearch(struct inode *inode, while (l <= r) { m = l + (r - l) / 2; + ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, + le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), + r, le32_to_cpu(r->ee_block)); + if (block < le32_to_cpu(m->ee_block)) r = m - 1; else l = m + 1; - ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, - le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), - r, le32_to_cpu(r->ee_block)); } path->p_ext = l - 1; @@ -884,8 +924,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, path[ppos].p_depth = i; path[ppos].p_ext = NULL; - bh = read_extent_tree_block(inode, path[ppos].p_block, --i, - flags); + bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags); if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; @@ -1494,7 +1533,6 @@ static int ext4_ext_search_right(struct inode *inode, struct ext4_extent_header *eh; struct ext4_extent_idx *ix; struct ext4_extent *ex; - ext4_fsblk_t block; int depth; /* Note, NOT eh_depth; depth from top of tree */ int ee_len; @@ -1561,20 +1599,17 @@ got_index: * follow it and find the closest allocated * block to the right */ ix++; - block = ext4_idx_pblock(ix); while (++depth < path->p_depth) { /* subtract from p_depth to get proper eh_depth */ - bh = read_extent_tree_block(inode, block, - path->p_depth - depth, 0); + bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); - block = ext4_idx_pblock(ix); put_bh(bh); } - bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0); + bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); @@ -2953,9 +2988,9 @@ again: ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); - bh = read_extent_tree_block(inode, - ext4_idx_pblock(path[i].p_idx), depth - i - 1, - EXT4_EX_NOCACHE); + bh = read_extent_tree_block(inode, path[i].p_idx, + depth - i - 1, + EXT4_EX_NOCACHE); if (IS_ERR(bh)) { /* should we reset i_size? */ err = PTR_ERR(bh); @@ -4978,36 +5013,6 @@ int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, } /* - * ext4_access_path: - * Function to access the path buffer for marking it dirty. - * It also checks if there are sufficient credits left in the journal handle - * to update path. - */ -static int -ext4_access_path(handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) -{ - int credits, err; - - if (!ext4_handle_valid(handle)) - return 0; - - /* - * Check if need to extend journal credits - * 3 for leaf, sb, and inode plus 2 (bmap and group - * descriptor) for each block group; assume two block - * groups - */ - credits = ext4_writepage_trans_blocks(inode); - err = ext4_datasem_ensure_credits(handle, inode, 7, credits, 0); - if (err < 0) - return err; - - err = ext4_ext_get_access(handle, inode, path); - return err; -} - -/* * ext4_ext_shift_path_extents: * Shift the extents of a path structure lying between path[depth].p_ext * and EXT_LAST_EXTENT(path[depth].p_hdr), by @shift blocks. @SHIFT tells @@ -5021,6 +5026,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, int depth, err = 0; struct ext4_extent *ex_start, *ex_last; bool update = false; + int credits, restart_credits; depth = path->p_depth; while (depth >= 0) { @@ -5030,13 +5036,26 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); + /* leaf + sb + inode */ + credits = 3; + if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) { + update = true; + /* extent tree + sb + inode */ + credits = depth + 2; + } - err = ext4_access_path(handle, inode, path + depth); - if (err) + restart_credits = ext4_writepage_trans_blocks(inode); + err = ext4_datasem_ensure_credits(handle, inode, credits, + restart_credits, 0); + if (err) { + if (err > 0) + err = -EAGAIN; goto out; + } - if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) - update = true; + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { @@ -5067,7 +5086,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, } /* Update index too */ - err = ext4_access_path(handle, inode, path + depth); + err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; @@ -5106,6 +5125,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, int ret = 0, depth; struct ext4_extent *extent; ext4_lblk_t stop, *iterator, ex_start, ex_end; + ext4_lblk_t tmp = EXT_MAX_BLOCKS; /* Let path point to the last extent */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, @@ -5159,11 +5179,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, * till we reach stop. In case of right shift, iterator points to stop * and it is decreased till we reach start. */ +again: if (SHIFT == SHIFT_LEFT) iterator = &start; else iterator = &stop; + if (tmp != EXT_MAX_BLOCKS) + *iterator = tmp; + /* * Its safe to start updating extents. Start and stop are unsigned, so * in case of right shift if extent with 0 block is reached, iterator @@ -5192,6 +5216,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, } } + tmp = *iterator; if (SHIFT == SHIFT_LEFT) { extent = EXT_LAST_EXTENT(path[depth].p_hdr); *iterator = le32_to_cpu(extent->ee_block) + @@ -5210,6 +5235,9 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, } ret = ext4_ext_shift_path_extents(path, shift, inode, handle, SHIFT); + /* iterator can be NULL which means we should break */ + if (ret == -EAGAIN) + goto again; if (ret) break; } @@ -6043,6 +6071,9 @@ int ext4_ext_clear_bb(struct inode *inode) int j, ret = 0; struct ext4_map_blocks map; + if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) + return 0; + /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8ea5a81e6554..0f32b445582a 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -819,7 +819,9 @@ static int ext4_fc_write_inode(struct inode *inode, u32 *crc) if (ret) return ret; - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) + if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) + inode_len = EXT4_INODE_SIZE(inode->i_sb); + else if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) inode_len += ei->i_extra_isize; fc_inode.fc_ino = cpu_to_le32(inode->i_ino); @@ -1524,7 +1526,8 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, * crashing. This should be fixed but until then, we calculate * the number of blocks the inode. */ - ext4_ext_replay_set_iblocks(inode); + if (!ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) + ext4_ext_replay_set_iblocks(inode); inode->i_generation = le32_to_cpu(ext4_raw_inode(&iloc)->i_generation); ext4_reset_inode_seed(inode); @@ -1842,6 +1845,10 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) } cur = 0; end = EXT_MAX_BLOCKS; + if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) { + iput(inode); + continue; + } while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f06305167d5..bfd3545f1e5d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1711,16 +1711,13 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, } /* - * the buffer head associated with a delayed and not unwritten - * block found in the extent status cache must contain an - * invalid block number and have its BH_New and BH_Delay bits - * set, reflecting the state assigned when the block was - * initially delayed allocated + * Delayed extent could be allocated by fallocate. + * So we need to check it. */ - if (ext4_es_is_delonly(&es)) { - BUG_ON(bh->b_blocknr != invalid_block); - BUG_ON(!buffer_new(bh)); - BUG_ON(!buffer_delay(bh)); + if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); return 0; } @@ -4234,14 +4231,161 @@ out_trace: return err; } +static inline u64 ext4_inode_peek_iversion(const struct inode *inode) +{ + if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return inode_peek_iversion_raw(inode); + else + return inode_peek_iversion(inode); +} + +static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, + struct ext4_inode_info *ei) +{ + struct inode *inode = &(ei->vfs_inode); + u64 i_blocks = READ_ONCE(inode->i_blocks); + struct super_block *sb = inode->i_sb; + + if (i_blocks <= ~0U) { + /* + * i_blocks can be represented in a 32 bit variable + * as multiple of 512 bytes + */ + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = 0; + ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); + return 0; + } + + /* + * This should never happen since sb->s_maxbytes should not have + * allowed this, sb->s_maxbytes was set according to the huge_file + * feature in ext4_fill_super(). + */ + if (!ext4_has_feature_huge_file(sb)) + return -EFSCORRUPTED; + + if (i_blocks <= 0xffffffffffffULL) { + /* + * i_blocks can be represented in a 48 bit variable + * as multiple of 512 bytes + */ + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); + ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); + } else { + ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); + /* i_block is stored in file system block size */ + i_blocks = i_blocks >> (inode->i_blkbits - 9); + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); + } + return 0; +} + +static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + uid_t i_uid; + gid_t i_gid; + projid_t i_projid; + int block; + int err; + + err = ext4_inode_blocks_set(raw_inode, ei); + + raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); + i_projid = from_kprojid(&init_user_ns, ei->i_projid); + if (!(test_opt(inode->i_sb, NO_UID32))) { + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); + /* + * Fix up interoperability with old kernels. Otherwise, + * old inodes get re-used with the upper 16 bits of the + * uid/gid intact. + */ + if (ei->i_dtime && list_empty(&ei->i_orphan)) { + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } else { + raw_inode->i_uid_high = + cpu_to_le16(high_16_bits(i_uid)); + raw_inode->i_gid_high = + cpu_to_le16(high_16_bits(i_gid)); + } + } else { + raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); + + EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); + EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); + EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); + + raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); + raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) + raw_inode->i_file_acl_high = + cpu_to_le16(ei->i_file_acl >> 32); + raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); + ext4_isize_set(raw_inode, ei->i_disksize); + + raw_inode->i_generation = cpu_to_le32(inode->i_generation); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { + if (old_valid_dev(inode->i_rdev)) { + raw_inode->i_block[0] = + cpu_to_le32(old_encode_dev(inode->i_rdev)); + raw_inode->i_block[1] = 0; + } else { + raw_inode->i_block[0] = 0; + raw_inode->i_block[1] = + cpu_to_le32(new_encode_dev(inode->i_rdev)); + raw_inode->i_block[2] = 0; + } + } else if (!ext4_has_inline_data(inode)) { + for (block = 0; block < EXT4_N_BLOCKS; block++) + raw_inode->i_block[block] = ei->i_data[block]; + } + + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { + u64 ivers = ext4_inode_peek_iversion(inode); + + raw_inode->i_disk_version = cpu_to_le32(ivers); + if (ei->i_extra_isize) { + if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) + raw_inode->i_version_hi = + cpu_to_le32(ivers >> 32); + raw_inode->i_extra_isize = + cpu_to_le16(ei->i_extra_isize); + } + } + + if (i_projid != EXT4_DEF_PROJID && + !ext4_has_feature_project(inode->i_sb)) + err = err ?: -EFSCORRUPTED; + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + raw_inode->i_projid = cpu_to_le32(i_projid); + + ext4_inode_csum_set(inode, raw_inode, ei); + return err; +} + /* * ext4_get_inode_loc returns with an extra refcount against the inode's - * underlying buffer_head on success. If 'in_mem' is true, we have all - * data in memory that is needed to recreate the on-disk version of this - * inode. + * underlying buffer_head on success. If we pass 'inode' and it does not + * have in-inode xattr, we have all inode data in memory that is needed + * to recreate the on-disk version of this inode. */ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, - struct ext4_iloc *iloc, int in_mem, + struct inode *inode, struct ext4_iloc *iloc, ext4_fsblk_t *ret_block) { struct ext4_group_desc *gdp; @@ -4287,7 +4431,7 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, * is the only valid inode in the block, we need not read the * block. */ - if (in_mem) { + if (inode && !ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { struct buffer_head *bitmap_bh; int i, start; @@ -4315,8 +4459,13 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, } brelse(bitmap_bh); if (i == start + inodes_per_block) { + struct ext4_inode *raw_inode = + (struct ext4_inode *) (bh->b_data + iloc->offset); + /* all other inodes are free, so skip I/O */ memset(bh->b_data, 0, bh->b_size); + if (!ext4_test_inode_state(inode, EXT4_STATE_NEW)) + ext4_fill_raw_inode(inode, raw_inode); set_buffer_uptodate(bh); unlock_buffer(bh); goto has_buffer; @@ -4377,7 +4526,7 @@ static int __ext4_get_inode_loc_noinmem(struct inode *inode, ext4_fsblk_t err_blk; int ret; - ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, 0, + ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, NULL, iloc, &err_blk); if (ret == -EIO) @@ -4392,9 +4541,8 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) ext4_fsblk_t err_blk; int ret; - /* We have all inode data except xattrs in memory here. */ - ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, - !ext4_test_inode_state(inode, EXT4_STATE_XATTR), &err_blk); + ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, inode, iloc, + &err_blk); if (ret == -EIO) ext4_error_inode_block(inode, err_blk, EIO, @@ -4407,7 +4555,7 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino, struct ext4_iloc *iloc) { - return __ext4_get_inode_loc(sb, ino, iloc, 0, NULL); + return __ext4_get_inode_loc(sb, ino, NULL, iloc, NULL); } static bool ext4_should_enable_dax(struct inode *inode) @@ -4528,13 +4676,6 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) else inode_set_iversion_queried(inode, val); } -static inline u64 ext4_inode_peek_iversion(const struct inode *inode) -{ - if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) - return inode_peek_iversion_raw(inode); - else - return inode_peek_iversion(inode); -} struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, @@ -4855,51 +4996,6 @@ bad_inode: return ERR_PTR(ret); } -static int ext4_inode_blocks_set(handle_t *handle, - struct ext4_inode *raw_inode, - struct ext4_inode_info *ei) -{ - struct inode *inode = &(ei->vfs_inode); - u64 i_blocks = READ_ONCE(inode->i_blocks); - struct super_block *sb = inode->i_sb; - - if (i_blocks <= ~0U) { - /* - * i_blocks can be represented in a 32 bit variable - * as multiple of 512 bytes - */ - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = 0; - ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); - return 0; - } - - /* - * This should never happen since sb->s_maxbytes should not have - * allowed this, sb->s_maxbytes was set according to the huge_file - * feature in ext4_fill_super(). - */ - if (!ext4_has_feature_huge_file(sb)) - return -EFSCORRUPTED; - - if (i_blocks <= 0xffffffffffffULL) { - /* - * i_blocks can be represented in a 48 bit variable - * as multiple of 512 bytes - */ - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); - ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); - } else { - ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); - /* i_block is stored in file system block size */ - i_blocks = i_blocks >> (inode->i_blkbits - 9); - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); - } - return 0; -} - static void __ext4_update_other_inode_time(struct super_block *sb, unsigned long orig_ino, unsigned long ino, @@ -4975,11 +5071,8 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; struct super_block *sb = inode->i_sb; - int err = 0, block; + int err; int need_datasync = 0, set_large_file = 0; - uid_t i_uid; - gid_t i_gid; - projid_t i_projid; spin_lock(&ei->i_raw_lock); @@ -4990,97 +5083,15 @@ static int ext4_do_update_inode(handle_t *handle, if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); - err = ext4_inode_blocks_set(handle, raw_inode, ei); - - raw_inode->i_mode = cpu_to_le16(inode->i_mode); - i_uid = i_uid_read(inode); - i_gid = i_gid_read(inode); - i_projid = from_kprojid(&init_user_ns, ei->i_projid); - if (!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); - /* - * Fix up interoperability with old kernels. Otherwise, - * old inodes get re-used with the upper 16 bits of the - * uid/gid intact. - */ - if (ei->i_dtime && list_empty(&ei->i_orphan)) { - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; - } else { - raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(i_uid)); - raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(i_gid)); - } - } else { - raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); - raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; - } - raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); - - EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); - EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); - - raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); - raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); - if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) - raw_inode->i_file_acl_high = - cpu_to_le16(ei->i_file_acl >> 32); - raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) { - ext4_isize_set(raw_inode, ei->i_disksize); + if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) need_datasync = 1; - } if (ei->i_disksize > 0x7fffffffULL) { if (!ext4_has_feature_large_file(sb) || - EXT4_SB(sb)->s_es->s_rev_level == - cpu_to_le32(EXT4_GOOD_OLD_REV)) + EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV)) set_large_file = 1; } - raw_inode->i_generation = cpu_to_le32(inode->i_generation); - if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { - if (old_valid_dev(inode->i_rdev)) { - raw_inode->i_block[0] = - cpu_to_le32(old_encode_dev(inode->i_rdev)); - raw_inode->i_block[1] = 0; - } else { - raw_inode->i_block[0] = 0; - raw_inode->i_block[1] = - cpu_to_le32(new_encode_dev(inode->i_rdev)); - raw_inode->i_block[2] = 0; - } - } else if (!ext4_has_inline_data(inode)) { - for (block = 0; block < EXT4_N_BLOCKS; block++) - raw_inode->i_block[block] = ei->i_data[block]; - } - - if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { - u64 ivers = ext4_inode_peek_iversion(inode); - - raw_inode->i_disk_version = cpu_to_le32(ivers); - if (ei->i_extra_isize) { - if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) - raw_inode->i_version_hi = - cpu_to_le32(ivers >> 32); - raw_inode->i_extra_isize = - cpu_to_le16(ei->i_extra_isize); - } - } - if (i_projid != EXT4_DEF_PROJID && - !ext4_has_feature_project(inode->i_sb)) - err = err ?: -EFSCORRUPTED; - - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && - EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) - raw_inode->i_projid = cpu_to_le32(i_projid); - - ext4_inode_csum_set(inode, raw_inode, ei); + err = ext4_fill_raw_inode(inode, raw_inode); spin_unlock(&ei->i_raw_lock); if (err) { EXT4_ERROR_INODE(inode, "corrupted inode contents"); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 72bfac2d6dce..215b7068f548 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -6299,7 +6299,6 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { ext4_grpblk_t next, count, free_count; void *bitmap; - int ret = 0; bitmap = e4b->bd_bitmap; start = (e4b->bd_info->bb_first_free > start) ? @@ -6314,10 +6313,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, next - start, e4b); + int ret = ext4_trim_extent(sb, start, next - start, e4b); + if (ret && ret != -EOPNOTSUPP) break; - ret = 0; count += next - start; } free_count += next - start; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index da7698341d7d..52c9bd154122 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1439,7 +1439,7 @@ static bool ext4_match(struct inode *parent, fname->hinfo.minor_hash != EXT4_DIRENT_MINOR_HASH(de)) { - return 0; + return false; } } return !ext4_ci_compare(parent, &cf, de->name, diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index f038d578d8d8..9cb261714991 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -279,14 +279,14 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) io_end->inode = inode; INIT_LIST_HEAD(&io_end->list); INIT_LIST_HEAD(&io_end->list_vec); - atomic_set(&io_end->count, 1); + refcount_set(&io_end->count, 1); } return io_end; } void ext4_put_io_end_defer(ext4_io_end_t *io_end) { - if (atomic_dec_and_test(&io_end->count)) { + if (refcount_dec_and_test(&io_end->count)) { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || list_empty(&io_end->list_vec)) { ext4_release_io_end(io_end); @@ -300,7 +300,7 @@ int ext4_put_io_end(ext4_io_end_t *io_end) { int err = 0; - if (atomic_dec_and_test(&io_end->count)) { + if (refcount_dec_and_test(&io_end->count)) { if (io_end->flag & EXT4_IO_END_UNWRITTEN) { err = ext4_convert_unwritten_io_end_vec(io_end->handle, io_end); @@ -314,7 +314,7 @@ int ext4_put_io_end(ext4_io_end_t *io_end) ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) { - atomic_inc(&io_end->count); + refcount_inc(&io_end->count); return io_end; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a320c54202d9..4e33b5eca694 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3270,9 +3270,9 @@ static int ext4_run_li_request(struct ext4_li_request *elr) struct super_block *sb = elr->lr_super; ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; ext4_group_t group = elr->lr_next_group; - unsigned long timeout = 0; unsigned int prefetch_ios = 0; int ret = 0; + u64 start_time; if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { elr->lr_next_group = ext4_mb_prefetch(sb, group, @@ -3309,14 +3309,13 @@ static int ext4_run_li_request(struct ext4_li_request *elr) ret = 1; if (!ret) { - timeout = jiffies; + start_time = ktime_get_real_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { - timeout = (jiffies - timeout) * - EXT4_SB(elr->lr_super)->s_li_wait_mult; - elr->lr_timeout = timeout; + elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) * + EXT4_SB(elr->lr_super)->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; @@ -5734,10 +5733,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long old_sb_flags, vfs_flags; struct ext4_mount_options old_opts; - int enable_quota = 0; ext4_group_t g; int err = 0; #ifdef CONFIG_QUOTA + int enable_quota = 0; int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif @@ -5828,7 +5827,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) - ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); + ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); @@ -5942,7 +5941,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) err = -EROFS; goto restore_opts; } +#ifdef CONFIG_QUOTA enable_quota = 1; +#endif } } diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 83e9bc0f91ff..f1693d45bb78 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -653,7 +653,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) return PTR_ERR(inode); } - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) { iput(inode); goto err_out; @@ -705,9 +705,6 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) } #ifdef CONFIG_QUOTA - /* Needed for iput() to work correctly and not trash data */ - sbi->sb->s_flags |= SB_ACTIVE; - /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. @@ -1162,7 +1159,8 @@ static bool __need_flush_quota(struct f2fs_sb_info *sbi) if (!is_journalled_quota(sbi)) return false; - down_write(&sbi->quota_sem); + if (!down_write_trylock(&sbi->quota_sem)) + return true; if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) { ret = false; } else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) { diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 20a083dc9042..a0d5cfab75e4 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -882,6 +882,25 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index) return is_page_in_cluster(cc, index); } +bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec, + int index, int nr_pages) +{ + unsigned long pgidx; + int i; + + if (nr_pages - index < cc->cluster_size) + return false; + + pgidx = pvec->pages[index]->index; + + for (i = 1; i < cc->cluster_size; i++) { + if (pvec->pages[index + i]->index != pgidx + i) + return false; + } + + return true; +} + static bool cluster_has_invalid_data(struct compress_ctx *cc) { loff_t i_size = i_size_read(cc->inode); @@ -1531,6 +1550,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc, if (cluster_may_compress(cc)) { err = f2fs_compress_pages(cc); if (err == -EAGAIN) { + add_compr_block_stat(cc->inode, cc->cluster_size); goto write; } else if (err) { f2fs_put_rpages_wbc(cc, wbc, true, 1); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f4fd6c246c9a..9f754aaef558 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1465,10 +1465,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, struct extent_info ei = {0, }; block_t blkaddr; unsigned int start_pgofs; + int bidx = 0; if (!maxblocks) return 0; + map->m_bdev = inode->i_sb->s_bdev; + map->m_multidev_dio = + f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag); + map->m_len = 0; map->m_flags = 0; @@ -1491,6 +1496,21 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, if (flag == F2FS_GET_BLOCK_DIO) f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); + + if (map->m_multidev_dio) { + block_t blk_addr = map->m_pblk; + + bidx = f2fs_target_device_index(sbi, map->m_pblk); + + map->m_bdev = FDEV(bidx).bdev; + map->m_pblk -= FDEV(bidx).start_blk; + map->m_len = min(map->m_len, + FDEV(bidx).end_blk + 1 - map->m_pblk); + + if (map->m_may_create) + f2fs_update_device_state(sbi, inode->i_ino, + blk_addr, map->m_len); + } goto out; } @@ -1609,6 +1629,9 @@ next_block: if (flag == F2FS_GET_BLOCK_PRE_AIO) goto skip; + if (map->m_multidev_dio) + bidx = f2fs_target_device_index(sbi, blkaddr); + if (map->m_len == 0) { /* preallocated unwritten block should be mapped for fiemap. */ if (blkaddr == NEW_ADDR) @@ -1617,10 +1640,15 @@ next_block: map->m_pblk = blkaddr; map->m_len = 1; + + if (map->m_multidev_dio) + map->m_bdev = FDEV(bidx).bdev; } else if ((map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs)) || (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) || flag == F2FS_GET_BLOCK_PRE_DIO) { + if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev) + goto sync_out; ofs++; map->m_len++; } else { @@ -1673,10 +1701,32 @@ skip: sync_out: - /* for hardware encryption, but to avoid potential issue in future */ - if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) + if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) { + /* + * for hardware encryption, but to avoid potential issue + * in future + */ f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); + invalidate_mapping_pages(META_MAPPING(sbi), + map->m_pblk, map->m_pblk); + + if (map->m_multidev_dio) { + block_t blk_addr = map->m_pblk; + + bidx = f2fs_target_device_index(sbi, map->m_pblk); + + map->m_bdev = FDEV(bidx).bdev; + map->m_pblk -= FDEV(bidx).start_blk; + + if (map->m_may_create) + f2fs_update_device_state(sbi, inode->i_ino, + blk_addr, map->m_len); + + f2fs_bug_on(sbi, blk_addr + map->m_len > + FDEV(bidx).end_blk + 1); + } + } if (flag == F2FS_GET_BLOCK_PRECACHE) { if (map->m_flags & F2FS_MAP_MAPPED) { @@ -1696,7 +1746,7 @@ unlock_out: f2fs_balance_fs(sbi, dn.node_changed); } out: - trace_f2fs_map_blocks(inode, map, err); + trace_f2fs_map_blocks(inode, map, create, flag, err); return err; } @@ -1755,6 +1805,9 @@ static int __get_data_block(struct inode *inode, sector_t iblock, map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags; bh->b_size = blks_to_bytes(inode, map.m_len); + + if (map.m_multidev_dio) + bh->b_bdev = map.m_bdev; } return err; } @@ -2989,6 +3042,10 @@ readd: need_readd = false; #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { + void *fsdata = NULL; + struct page *pagep; + int ret2; + ret = f2fs_init_compress_ctx(&cc); if (ret) { done = 1; @@ -3007,27 +3064,23 @@ readd: if (unlikely(f2fs_cp_error(sbi))) goto lock_page; - if (f2fs_cluster_is_empty(&cc)) { - void *fsdata = NULL; - struct page *pagep; - int ret2; + if (!f2fs_cluster_is_empty(&cc)) + goto lock_page; - ret2 = f2fs_prepare_compress_overwrite( + ret2 = f2fs_prepare_compress_overwrite( inode, &pagep, page->index, &fsdata); - if (ret2 < 0) { - ret = ret2; - done = 1; - break; - } else if (ret2 && - !f2fs_compress_write_end(inode, - fsdata, page->index, - 1)) { - retry = 1; - break; - } - } else { - goto lock_page; + if (ret2 < 0) { + ret = ret2; + done = 1; + break; + } else if (ret2 && + (!f2fs_compress_write_end(inode, + fsdata, page->index, 1) || + !f2fs_all_cluster_page_loaded(&cc, + &pvec, i, nr_pages))) { + retry = 1; + break; } } #endif diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b339ae89c1ad..ce9fc9f13000 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -55,6 +55,7 @@ enum { FAULT_DISCARD, FAULT_WRITE_IO, FAULT_SLAB_ALLOC, + FAULT_DQUOT_INIT, FAULT_MAX, }; @@ -561,6 +562,9 @@ enum { #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ +/* dirty segments threshold for triggering CP */ +#define DEFAULT_DIRTY_THRESHOLD 4 + /* for in-memory extent cache entry */ #define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ @@ -617,6 +621,7 @@ struct extent_tree { F2FS_MAP_UNWRITTEN) struct f2fs_map_blocks { + struct block_device *m_bdev; /* for multi-device dio */ block_t m_pblk; block_t m_lblk; unsigned int m_len; @@ -625,6 +630,7 @@ struct f2fs_map_blocks { pgoff_t *m_next_extent; /* point to next possible extent */ int m_seg_type; bool m_may_create; /* indicate it is from write path */ + bool m_multidev_dio; /* indicate it allows multi-device dio */ }; /* for flag in get_data_block */ @@ -1284,8 +1290,10 @@ enum { }; enum { - FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ - FS_MODE_LFS, /* use lfs allocation only */ + FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ + FS_MODE_LFS, /* use lfs allocation only */ + FS_MODE_FRAGMENT_SEG, /* segment fragmentation mode */ + FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */ }; enum { @@ -1728,12 +1736,15 @@ struct f2fs_sb_info { /* For shrinker support */ struct list_head s_list; + struct mutex umount_mutex; + unsigned int shrinker_run_no; + + /* For multi devices */ int s_ndevs; /* number of devices */ struct f2fs_dev_info *devs; /* for device list */ unsigned int dirty_device; /* for checkpoint data flush */ spinlock_t dev_lock; /* protect dirty_device */ - struct mutex umount_mutex; - unsigned int shrinker_run_no; + bool aligned_blksize; /* all devices has the same logical blksize */ /* For write statistics */ u64 sectors_written_start; @@ -1756,6 +1767,9 @@ struct f2fs_sb_info { unsigned long seq_file_ra_mul; /* multiplier for ra_pages of seq. files in fadvise */ + int max_fragment_chunk; /* max chunk size for block fragmentation mode */ + int max_fragment_hole; /* max hole size for block fragmentation mode */ + #ifdef CONFIG_F2FS_FS_COMPRESSION struct kmem_cache *page_array_slab; /* page array entry */ unsigned int page_array_slab_size; /* default page array slab size */ @@ -3363,6 +3377,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) */ int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); +int f2fs_dquot_initialize(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); int f2fs_quota_sync(struct super_block *sb, int type); loff_t max_file_blocks(struct inode *inode); @@ -3492,6 +3507,8 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio); +void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, + block_t blkaddr, unsigned int blkcnt); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered, bool locked); void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); @@ -3516,6 +3533,16 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, unsigned int segno); +#define DEF_FRAGMENT_SIZE 4 +#define MIN_FRAGMENT_SIZE 1 +#define MAX_FRAGMENT_SIZE 512 + +static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi) +{ + return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG || + F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK; +} + /* * checkpoint.c */ @@ -4027,6 +4054,8 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed, block_t blkaddr); bool f2fs_cluster_is_empty(struct compress_ctx *cc); bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index); +bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec, + int index, int nr_pages); bool f2fs_sanity_check_cluster(struct dnode_of_data *dn); void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page); int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -4152,8 +4181,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) if (!f2fs_compressed_file(inode)) return true; - if (S_ISREG(inode->i_mode) && - (get_dirty_pages(inode) || atomic_read(&fi->i_compr_blocks))) + if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) return false; fi->i_flags &= ~F2FS_COMPR_FL; @@ -4302,6 +4330,16 @@ static inline int block_unaligned_IO(struct inode *inode, return align & blocksize_mask; } +static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, + int flag) +{ + if (!f2fs_is_multi_device(sbi)) + return false; + if (flag != F2FS_GET_BLOCK_DIO) + return false; + return sbi->aligned_blksize; +} + static inline bool f2fs_force_buffered_io(struct inode *inode, struct kiocb *iocb, struct iov_iter *iter) { @@ -4310,7 +4348,9 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (f2fs_post_read_required(inode)) return true; - if (f2fs_is_multi_device(sbi)) + + /* disallow direct IO if any of devices has unaligned blksize */ + if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) return true; /* * for blkzoned device, fallback direct IO to buffered IO, so diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index eb971e1e7227..92ec2699bc85 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -786,7 +786,7 @@ int f2fs_truncate(struct inode *inode) return -EIO; } - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; @@ -916,7 +916,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, return err; if (is_quota_modification(inode, attr)) { - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; } @@ -3020,7 +3020,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid) } f2fs_put_page(ipage, 1); - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 77391e3b7d68..a946ce0ead34 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -14,6 +14,7 @@ #include <linux/delay.h> #include <linux/freezer.h> #include <linux/sched/signal.h> +#include <linux/random.h> #include "f2fs.h" #include "node.h" @@ -257,7 +258,9 @@ 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 in no_heap mode*/ - if (test_opt(sbi, NOHEAP) && + if (f2fs_need_rand_seg(sbi)) + p->offset = prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec); + else if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) p->offset = 0; else diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 56a20d5c15da..ea08f0dfa1bd 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -192,7 +192,7 @@ int f2fs_convert_inline_inode(struct inode *inode) f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) return 0; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 9141147b5bb0..0f8b2df3e1e0 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -527,7 +527,7 @@ make_now: inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (S_ISLNK(inode->i_mode)) { if (file_is_encrypt(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; @@ -754,7 +754,7 @@ void f2fs_evict_inode(struct inode *inode) if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) { err = 0; set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 9c528e583c9d..a728a0af9ce0 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -74,7 +74,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) goto fail_drop; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) goto fail_drop; @@ -345,7 +345,7 @@ static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -404,7 +404,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, F2FS_I(old_dentry->d_inode)->i_projid))) return -EXDEV; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -460,7 +460,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) return 0; } - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -598,10 +598,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) goto fail; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) goto fail; @@ -675,7 +675,7 @@ static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -746,7 +746,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -757,7 +757,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); @@ -803,7 +803,7 @@ static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -841,7 +841,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, struct inode *inode; int err; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -965,16 +965,16 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, return err; } - err = dquot_initialize(old_dir); + err = f2fs_dquot_initialize(old_dir); if (err) goto out; - err = dquot_initialize(new_dir); + err = f2fs_dquot_initialize(new_dir); if (err) goto out; if (new_inode) { - err = dquot_initialize(new_inode); + err = f2fs_dquot_initialize(new_inode); if (err) goto out; } @@ -1138,11 +1138,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, F2FS_I(new_dentry->d_inode)->i_projid))) return -EXDEV; - err = dquot_initialize(old_dir); + err = f2fs_dquot_initialize(old_dir); if (err) goto out; - err = dquot_initialize(new_dir); + err = f2fs_dquot_initialize(new_dir); if (err) goto out; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e863136081b4..556fcd8457f3 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1443,6 +1443,7 @@ page_hit: nid, nid_of_node(page), ino_of_node(page), ofs_of_node(page), cpver_of_node(page), next_blkaddr_of_node(page)); + set_sbi_flag(sbi, SBI_NEED_FSCK); err = -EINVAL; out_err: ClearPageUptodate(page); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index ff14a6e5ac1c..18b98cf0465b 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -138,11 +138,6 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi) return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD; } -static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi) -{ - return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8; -} - enum mem_type { FREE_NIDS, /* indicates the free nid list */ NAT_ENTRIES, /* indicates the cached nat entry */ diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 04655511d7f5..6a1b4668d933 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -81,7 +81,7 @@ static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi, if (IS_ERR(inode)) return ERR_CAST(inode); - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) goto err_out; @@ -203,7 +203,7 @@ retry: goto out_put; } - err = dquot_initialize(einode); + err = f2fs_dquot_initialize(einode); if (err) { iput(einode); goto out_put; @@ -508,7 +508,7 @@ got_it: if (IS_ERR(inode)) return PTR_ERR(inode); - ret = dquot_initialize(inode); + ret = f2fs_dquot_initialize(inode); if (ret) { iput(inode); return ret; @@ -787,8 +787,6 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) } #ifdef CONFIG_QUOTA - /* Needed for iput() to work correctly and not trash data */ - sbi->sb->s_flags |= SB_ACTIVE; /* Turn on quotas so that they are updated correctly */ quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY); #endif @@ -816,10 +814,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); - else { - /* restore s_flags to let iput() trash data */ - sbi->sb->s_flags = s_flags; - } + else + f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE); skip: fix_curseg_write_pointer = !check_only || list_empty(&inode_list); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a135d2247415..df9ed75f0b7a 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -15,6 +15,7 @@ #include <linux/timer.h> #include <linux/freezer.h> #include <linux/sched/signal.h> +#include <linux/random.h> #include "f2fs.h" #include "segment.h" @@ -529,6 +530,25 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) } } +static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi) +{ + int factor = rwsem_is_locked(&sbi->cp_rwsem) ? 3 : 2; + unsigned int dents = get_pages(sbi, F2FS_DIRTY_DENTS); + unsigned int qdata = get_pages(sbi, F2FS_DIRTY_QDATA); + unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES); + unsigned int meta = get_pages(sbi, F2FS_DIRTY_META); + unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA); + unsigned int threshold = sbi->blocks_per_seg * factor * + DEFAULT_DIRTY_THRESHOLD; + unsigned int global_threshold = threshold * 3 / 2; + + if (dents >= threshold || qdata >= threshold || + nodes >= threshold || meta >= threshold || + imeta >= threshold) + return true; + return dents + qdata + nodes + meta + imeta > global_threshold; +} + void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) { if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) @@ -547,8 +567,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) else f2fs_build_free_nids(sbi, false, false); - if (excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) || - excess_prefree_segs(sbi)) + if (excess_dirty_nats(sbi) || excess_dirty_threshold(sbi) || + excess_prefree_segs(sbi) || !f2fs_space_for_roll_forward(sbi)) goto do_sync; /* there is background inflight IO or foreground operation recently */ @@ -561,7 +581,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) goto do_sync; /* checkpoint is the only way to shrink partial cached entries */ - if (f2fs_available_free_memory(sbi, NAT_ENTRIES) || + if (f2fs_available_free_memory(sbi, NAT_ENTRIES) && f2fs_available_free_memory(sbi, INO_ENTRIES)) return; @@ -2630,6 +2650,8 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) unsigned short seg_type = curseg->seg_type; sanity_check_seg_type(sbi, seg_type); + if (f2fs_need_rand_seg(sbi)) + return prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec); /* if segs_per_sec is large than 1, we need to keep original policy. */ if (__is_large_section(sbi)) @@ -2681,6 +2703,9 @@ static void 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) + curseg->fragment_remained_chunk = + prandom_u32() % sbi->max_fragment_chunk + 1; } static int __next_free_blkoff(struct f2fs_sb_info *sbi, @@ -2707,12 +2732,22 @@ static int __next_free_blkoff(struct f2fs_sb_info *sbi, static void __refresh_next_blkoff(struct f2fs_sb_info *sbi, struct curseg_info *seg) { - if (seg->alloc_type == SSR) + if (seg->alloc_type == SSR) { seg->next_blkoff = __next_free_blkoff(sbi, seg->segno, seg->next_blkoff + 1); - else + } else { seg->next_blkoff++; + if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) { + /* To allocate block chunks in different sizes, use random number */ + if (--seg->fragment_remained_chunk <= 0) { + seg->fragment_remained_chunk = + prandom_u32() % sbi->max_fragment_chunk + 1; + seg->next_blkoff += + prandom_u32() % sbi->max_fragment_hole + 1; + } + } + } } bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno) @@ -3485,24 +3520,30 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, up_read(&SM_I(sbi)->curseg_lock); } -static void update_device_state(struct f2fs_io_info *fio) +void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, + block_t blkaddr, unsigned int blkcnt) { - struct f2fs_sb_info *sbi = fio->sbi; - unsigned int devidx; - if (!f2fs_is_multi_device(sbi)) return; - devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); + while (1) { + unsigned int devidx = f2fs_target_device_index(sbi, blkaddr); + unsigned int blks = FDEV(devidx).end_blk - blkaddr + 1; - /* update device state for fsync */ - f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO); + /* update device state for fsync */ + f2fs_set_dirty_device(sbi, ino, devidx, FLUSH_INO); - /* update device state for checkpoint */ - if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { - spin_lock(&sbi->dev_lock); - f2fs_set_bit(devidx, (char *)&sbi->dirty_device); - spin_unlock(&sbi->dev_lock); + /* update device state for checkpoint */ + if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { + spin_lock(&sbi->dev_lock); + f2fs_set_bit(devidx, (char *)&sbi->dirty_device); + spin_unlock(&sbi->dev_lock); + } + + if (blkcnt <= blks) + break; + blkcnt -= blks; + blkaddr += blks; } } @@ -3529,7 +3570,7 @@ reallocate: goto reallocate; } - update_device_state(fio); + f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1); if (keep_order) up_read(&fio->sbi->io_order_lock); @@ -3611,6 +3652,9 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) goto drop_bio; } + invalidate_mapping_pages(META_MAPPING(sbi), + fio->new_blkaddr, fio->new_blkaddr); + stat_inc_inplace_blocks(fio->sbi); if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE))) @@ -3618,7 +3662,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) else err = f2fs_submit_page_bio(fio); if (!err) { - update_device_state(fio); + f2fs_update_device_state(fio->sbi, fio->ino, + fio->new_blkaddr, 1); f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 89fff258727d..46fde9f3f28e 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -314,6 +314,7 @@ struct curseg_info { unsigned short next_blkoff; /* next block offset to write */ unsigned int zone; /* current zone number */ unsigned int next_segno; /* preallocated segment */ + int fragment_remained_chunk; /* remained block size in a chunk for block fragmentation mode */ bool inited; /* indicate inmem log is inited */ }; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index cf049a042482..7960ce066c1b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -58,6 +58,7 @@ const char *f2fs_fault_name[FAULT_MAX] = { [FAULT_DISCARD] = "discard error", [FAULT_WRITE_IO] = "write IO error", [FAULT_SLAB_ALLOC] = "slab alloc", + [FAULT_DQUOT_INIT] = "dquot initialize", }; void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, @@ -817,6 +818,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; } else if (!strcmp(name, "lfs")) { F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; + } else if (!strcmp(name, "fragment:segment")) { + F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_SEG; + } else if (!strcmp(name, "fragment:block")) { + F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_BLK; } else { kfree(name); return -EINVAL; @@ -1292,7 +1297,7 @@ default_check: /* Not pass down write hints if the number of active logs is lesser * than NR_CURSEG_PERSIST_TYPE. */ - if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE) + if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE) F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { @@ -1896,6 +1901,10 @@ 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) + seq_puts(seq, "fragment:segment"); + else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) + seq_puts(seq, "fragment:block"); seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); if (test_opt(sbi, RESERVE_ROOT)) seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u", @@ -2491,6 +2500,16 @@ retry: return len - towrite; } +int f2fs_dquot_initialize(struct inode *inode) +{ + if (time_to_inject(F2FS_I_SB(inode), FAULT_DQUOT_INIT)) { + f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_DQUOT_INIT); + return -ESRCH; + } + + return dquot_initialize(inode); +} + static struct dquot **f2fs_get_dquots(struct inode *inode) { return F2FS_I(inode)->i_dquot; @@ -2875,6 +2894,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = { .get_nextdqblk = dquot_get_next_dqblk, }; #else +int f2fs_dquot_initialize(struct inode *inode) +{ + return 0; +} + int f2fs_quota_sync(struct super_block *sb, int type) { return 0; @@ -3486,7 +3510,7 @@ skip_cross: NR_CURSEG_PERSIST_TYPE + nat_bits_blocks >= blocks_per_seg)) { f2fs_warn(sbi, "Insane cp_payload: %u, nat_bits_blocks: %u)", cp_payload, nat_bits_blocks); - return -EFSCORRUPTED; + return 1; } if (unlikely(f2fs_cp_error(sbi))) { @@ -3522,6 +3546,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; sbi->migration_granularity = sbi->segs_per_sec; sbi->seq_file_ra_mul = MIN_RA_MUL; + sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE; + sbi->max_fragment_hole = DEF_FRAGMENT_SIZE; sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; @@ -3746,6 +3772,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); unsigned int max_devices = MAX_DEVICES; + unsigned int logical_blksize; int i; /* Initialize single device information */ @@ -3766,6 +3793,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) if (!sbi->devs) return -ENOMEM; + logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev); + sbi->aligned_blksize = true; + for (i = 0; i < max_devices; i++) { if (i > 0 && !RDEV(i).path[0]) @@ -3802,6 +3832,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) /* to release errored devices */ sbi->s_ndevs = i + 1; + if (logical_blksize != bdev_logical_block_size(FDEV(i).bdev)) + sbi->aligned_blksize = false; + #ifdef CONFIG_BLK_DEV_ZONED if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM && !f2fs_sb_has_blkzoned(sbi)) { @@ -4351,6 +4384,8 @@ free_node_inode: free_stats: f2fs_destroy_stats(sbi); free_nm: + /* stop discard thread before destroying node manager */ + f2fs_stop_discard_thread(sbi); f2fs_destroy_node_manager(sbi); free_sm: f2fs_destroy_segment_manager(sbi); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a32fe31c33b8..7d289249cd7e 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -196,7 +196,7 @@ static ssize_t encoding_show(struct f2fs_attr *a, struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) - return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n", + return sysfs_emit(buf, "%s (%d.%d.%d)\n", sb->s_encoding->charset, (sb->s_encoding->version >> 16) & 0xff, (sb->s_encoding->version >> 8) & 0xff, @@ -245,7 +245,7 @@ static ssize_t avg_vblocks_show(struct f2fs_attr *a, static ssize_t main_blkaddr_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", (unsigned long long)MAIN_BLKADDR(sbi)); } @@ -551,6 +551,22 @@ out: return count; } + if (!strcmp(a->attr.name, "max_fragment_chunk")) { + if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE) + sbi->max_fragment_chunk = t; + else + return -EINVAL; + return count; + } + + if (!strcmp(a->attr.name, "max_fragment_hole")) { + if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE) + sbi->max_fragment_hole = t; + else + return -EINVAL; + return count; + } + *ui = (unsigned int)t; return count; @@ -781,6 +797,8 @@ F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_threshold, age_threshold); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, seq_file_ra_mul, seq_file_ra_mul); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_segment_mode, gc_segment_mode); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_chunk, max_fragment_chunk); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_hole, max_fragment_hole); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -859,6 +877,8 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(seq_file_ra_mul), ATTR_LIST(gc_segment_mode), ATTR_LIST(gc_reclaimed_segments), + ATTR_LIST(max_fragment_chunk), + ATTR_LIST(max_fragment_hole), NULL, }; ATTRIBUTE_GROUPS(f2fs); diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index 03549b5ba204..fe5acdccaae1 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -136,7 +136,7 @@ static int f2fs_begin_enable_verity(struct file *filp) * here and not rely on ->open() doing it. This must be done before * evicting the inline data. */ - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 1d2d29dcd41c..e348f33bcb2b 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -773,7 +773,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/io-wq.c b/fs/io-wq.c index afd955d53db9..88202de519f6 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -423,9 +423,10 @@ static inline unsigned int io_get_work_hash(struct io_wq_work *work) return work->flags >> IO_WQ_HASH_SHIFT; } -static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) +static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) { struct io_wq *wq = wqe->wq; + bool ret = false; spin_lock_irq(&wq->hash->wait.lock); if (list_empty(&wqe->wait.entry)) { @@ -433,9 +434,11 @@ static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) if (!test_bit(hash, &wq->hash->map)) { __set_current_state(TASK_RUNNING); list_del_init(&wqe->wait.entry); + ret = true; } } spin_unlock_irq(&wq->hash->wait.lock); + return ret; } static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, @@ -475,14 +478,21 @@ static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, } if (stall_hash != -1U) { + bool unstalled; + /* * Set this before dropping the lock to avoid racing with new * work being added and clearing the stalled bit. */ set_bit(IO_ACCT_STALLED_BIT, &acct->flags); raw_spin_unlock(&wqe->lock); - io_wait_on_hash(wqe, stall_hash); + unstalled = io_wait_on_hash(wqe, stall_hash); raw_spin_lock(&wqe->lock); + if (unstalled) { + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + if (wq_has_sleeper(&wqe->wq->hash->wait)) + wake_up(&wqe->wq->hash->wait); + } } return NULL; @@ -564,8 +574,11 @@ get_next: io_wqe_enqueue(wqe, linked); if (hash != -1U && !next_hashed) { + /* serialize hash clear with wake_up() */ + spin_lock_irq(&wq->hash->wait.lock); clear_bit(hash, &wq->hash->map); clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + spin_unlock_irq(&wq->hash->wait.lock); if (wq_has_sleeper(&wq->hash->wait)) wake_up(&wq->hash->wait); raw_spin_lock(&wqe->lock); diff --git a/fs/ksmbd/Kconfig b/fs/ksmbd/Kconfig index b83cbd756ae5..e1fe17747ed6 100644 --- a/fs/ksmbd/Kconfig +++ b/fs/ksmbd/Kconfig @@ -6,7 +6,6 @@ config SMB_SERVER select NLS select NLS_UTF8 select CRYPTO - select CRYPTO_MD4 select CRYPTO_MD5 select CRYPTO_HMAC select CRYPTO_ECB @@ -19,6 +18,7 @@ config SMB_SERVER select CRYPTO_GCM select ASN1 select OID_REGISTRY + select CRC32 default n help Choose Y here if you want to allow SMB3 compliant clients diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 30a92ddc1817..3503b1c48cb4 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -873,9 +873,9 @@ int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf, __u8 *pi_hash) { int rc; - struct smb2_hdr *rcv_hdr = (struct smb2_hdr *)buf; + struct smb2_hdr *rcv_hdr = smb2_get_msg(buf); char *all_bytes_msg = (char *)&rcv_hdr->ProtocolId; - int msg_size = be32_to_cpu(rcv_hdr->smb2_buf_length); + int msg_size = get_rfc1002_len(buf); struct ksmbd_crypto_ctx *ctx = NULL; if (conn->preauth_info->Preauth_HashId != @@ -983,7 +983,7 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, u8 *sign) { struct scatterlist *sg; - unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24; + unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int i, nr_entries[3] = {0}, total_entries = 0, sg_idx = 0; if (!nvec) @@ -1047,9 +1047,8 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, int ksmbd_crypt_message(struct ksmbd_conn *conn, struct kvec *iov, unsigned int nvec, int enc) { - struct smb2_transform_hdr *tr_hdr = - (struct smb2_transform_hdr *)iov[0].iov_base; - unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24; + struct smb2_transform_hdr *tr_hdr = smb2_get_msg(iov[0].iov_base); + unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int rc; struct scatterlist *sg; u8 sign[SMB2_SIGNATURE_SIZE] = {}; diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index b57a0d8a392f..83a94d0bb480 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -158,26 +158,25 @@ void ksmbd_conn_wait_idle(struct ksmbd_conn *conn) int ksmbd_conn_write(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb_hdr *rsp_hdr = work->response_buf; size_t len = 0; int sent; struct kvec iov[3]; int iov_idx = 0; ksmbd_conn_try_dequeue_request(work); - if (!rsp_hdr) { + if (!work->response_buf) { pr_err("NULL response header\n"); return -EINVAL; } if (work->tr_buf) { iov[iov_idx] = (struct kvec) { work->tr_buf, - sizeof(struct smb2_transform_hdr) }; + sizeof(struct smb2_transform_hdr) + 4 }; len += iov[iov_idx++].iov_len; } if (work->aux_payload_sz) { - iov[iov_idx] = (struct kvec) { rsp_hdr, work->resp_hdr_sz }; + iov[iov_idx] = (struct kvec) { work->response_buf, work->resp_hdr_sz }; len += iov[iov_idx++].iov_len; iov[iov_idx] = (struct kvec) { work->aux_payload_buf, work->aux_payload_sz }; len += iov[iov_idx++].iov_len; @@ -185,8 +184,8 @@ int ksmbd_conn_write(struct ksmbd_work *work) if (work->tr_buf) iov[iov_idx].iov_len = work->resp_hdr_sz; else - iov[iov_idx].iov_len = get_rfc1002_len(rsp_hdr) + 4; - iov[iov_idx].iov_base = rsp_hdr; + iov[iov_idx].iov_len = get_rfc1002_len(work->response_buf) + 4; + iov[iov_idx].iov_base = work->response_buf; len += iov[iov_idx++].iov_len; } diff --git a/fs/ksmbd/ksmbd_work.c b/fs/ksmbd/ksmbd_work.c index fd58eb4809f6..14b9caebf7a4 100644 --- a/fs/ksmbd/ksmbd_work.c +++ b/fs/ksmbd/ksmbd_work.c @@ -69,7 +69,6 @@ int ksmbd_workqueue_init(void) void ksmbd_workqueue_destroy(void) { - flush_workqueue(ksmbd_wq); destroy_workqueue(ksmbd_wq); ksmbd_wq = NULL; } diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h index f7156bc50049..5ece58e40c97 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/ksmbd/ksmbd_work.h @@ -92,7 +92,7 @@ struct ksmbd_work { */ static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work) { - return work->response_buf + work->next_smb2_rsp_hdr_off; + return work->response_buf + work->next_smb2_rsp_hdr_off + 4; } /** @@ -101,7 +101,7 @@ static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work) */ static inline void *ksmbd_req_buf_next(struct ksmbd_work *work) { - return work->request_buf + work->next_smb2_rcv_hdr_off; + return work->request_buf + work->next_smb2_rcv_hdr_off + 4; } struct ksmbd_work *ksmbd_alloc_work_struct(void); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index f9dae6ef2115..077b8761d099 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -629,10 +629,10 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) return; } - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(0); @@ -645,7 +645,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = work->response_buf; + rsp = smb2_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(24); if (!br_info->open_trunc && @@ -659,7 +659,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp->PersistentFid = cpu_to_le64(fp->persistent_id); rsp->VolatileFid = cpu_to_le64(fp->volatile_id); - inc_rfc1001_len(rsp, 24); + inc_rfc1001_len(work->response_buf, 24); ksmbd_debug(OPLOCK, "sending oplock break v_id %llu p_id = %llu lock level = %d\n", @@ -736,10 +736,10 @@ static void __smb2_lease_break_noti(struct work_struct *wk) return; } - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(0); @@ -752,7 +752,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = work->response_buf; + rsp = smb2_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(44); rsp->Epoch = br_info->epoch; rsp->Flags = 0; @@ -768,7 +768,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) rsp->AccessMaskHint = 0; rsp->ShareMaskHint = 0; - inc_rfc1001_len(rsp, 44); + inc_rfc1001_len(work->response_buf, 44); ksmbd_conn_write(work); ksmbd_free_work_struct(work); @@ -1335,19 +1335,16 @@ __u8 smb2_map_lease_to_oplock(__le32 lease_state) */ void create_lease_buf(u8 *rbuf, struct lease *lease) { - char *LeaseKey = (char *)&lease->lease_key; - if (lease->version == 2) { struct create_lease_v2 *buf = (struct create_lease_v2 *)rbuf; - char *ParentLeaseKey = (char *)&lease->parent_lease_key; memset(buf, 0, sizeof(struct create_lease_v2)); - buf->lcontext.LeaseKeyLow = *((__le64 *)LeaseKey); - buf->lcontext.LeaseKeyHigh = *((__le64 *)(LeaseKey + 8)); + memcpy(buf->lcontext.LeaseKey, lease->lease_key, + SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.LeaseState = lease->state; - buf->lcontext.ParentLeaseKeyLow = *((__le64 *)ParentLeaseKey); - buf->lcontext.ParentLeaseKeyHigh = *((__le64 *)(ParentLeaseKey + 8)); + memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, + SMB2_LEASE_KEY_SIZE); buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease_v2, lcontext)); buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2)); @@ -1362,8 +1359,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) struct create_lease *buf = (struct create_lease *)rbuf; memset(buf, 0, sizeof(struct create_lease)); - buf->lcontext.LeaseKeyLow = *((__le64 *)LeaseKey); - buf->lcontext.LeaseKeyHigh = *((__le64 *)(LeaseKey + 8)); + memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.LeaseState = lease->state; buf->ccontext.DataOffset = cpu_to_le16(offsetof @@ -1398,7 +1394,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (!lreq) return NULL; - data_offset = (char *)req + 4 + le32_to_cpu(req->CreateContextsOffset); + data_offset = (char *)req + le32_to_cpu(req->CreateContextsOffset); cc = (struct create_context *)data_offset; do { cc = (struct create_context *)((char *)cc + next); @@ -1416,19 +1412,17 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (sizeof(struct lease_context_v2) == le32_to_cpu(cc->DataLength)) { struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; - *((__le64 *)lreq->lease_key) = lc->lcontext.LeaseKeyLow; - *((__le64 *)(lreq->lease_key + 8)) = lc->lcontext.LeaseKeyHigh; + memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; lreq->duration = lc->lcontext.LeaseDuration; - *((__le64 *)lreq->parent_lease_key) = lc->lcontext.ParentLeaseKeyLow; - *((__le64 *)(lreq->parent_lease_key + 8)) = lc->lcontext.ParentLeaseKeyHigh; + memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, + SMB2_LEASE_KEY_SIZE); lreq->version = 2; } else { struct create_lease *lc = (struct create_lease *)cc; - *((__le64 *)lreq->lease_key) = lc->lcontext.LeaseKeyLow; - *((__le64 *)(lreq->lease_key + 8)) = lc->lcontext.LeaseKeyHigh; + memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; lreq->duration = lc->lcontext.LeaseDuration; @@ -1462,7 +1456,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) * CreateContextsOffset and CreateContextsLength are guaranteed to * be valid because of ksmbd_smb2_check_message(). */ - cc = (struct create_context *)((char *)req + 4 + + cc = (struct create_context *)((char *)req + le32_to_cpu(req->CreateContextsOffset)); remain_len = le32_to_cpu(req->CreateContextsLength); do { diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 119b8047cfbd..0cf7a2b5bbc0 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -28,8 +28,6 @@ #define OPLOCK_WRITE_TO_NONE 0x04 #define OPLOCK_READ_TO_NONE 0x08 -#define SMB2_LEASE_KEY_SIZE 16 - struct lease_ctx_info { __u8 lease_key[SMB2_LEASE_KEY_SIZE]; __le32 req_state; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 2a2b2135bfde..2e12f6d8483b 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -622,7 +622,6 @@ MODULE_DESCRIPTION("Linux kernel CIFS/SMB SERVER"); MODULE_LICENSE("GPL"); MODULE_SOFTDEP("pre: ecb"); MODULE_SOFTDEP("pre: hmac"); -MODULE_SOFTDEP("pre: md4"); MODULE_SOFTDEP("pre: md5"); MODULE_SOFTDEP("pre: nls"); MODULE_SOFTDEP("pre: aes"); @@ -632,5 +631,6 @@ MODULE_SOFTDEP("pre: sha512"); MODULE_SOFTDEP("pre: aead2"); MODULE_SOFTDEP("pre: ccm"); MODULE_SOFTDEP("pre: gcm"); +MODULE_SOFTDEP("pre: crc32"); module_init(ksmbd_server_init) module_exit(ksmbd_server_exit) diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index 030ca57c3784..50d0b1022289 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -6,7 +6,6 @@ #include "glob.h" #include "nterr.h" -#include "smb2pdu.h" #include "smb_common.h" #include "smbstatus.h" #include "mgmt/user_session.h" @@ -347,23 +346,16 @@ static int smb2_validate_credit_charge(struct ksmbd_conn *conn, int ksmbd_smb2_check_message(struct ksmbd_work *work) { - struct smb2_pdu *pdu = work->request_buf; + struct smb2_pdu *pdu = ksmbd_req_buf_next(work); struct smb2_hdr *hdr = &pdu->hdr; int command; __u32 clc_len; /* calculated length */ - __u32 len = get_rfc1002_len(pdu); + __u32 len = get_rfc1002_len(work->request_buf); - if (work->next_smb2_rcv_hdr_off) { - pdu = ksmbd_req_buf_next(work); - hdr = &pdu->hdr; - } - - if (le32_to_cpu(hdr->NextCommand) > 0) { + if (le32_to_cpu(hdr->NextCommand) > 0) len = le32_to_cpu(hdr->NextCommand); - } else if (work->next_smb2_rcv_hdr_off) { + else if (work->next_smb2_rcv_hdr_off) len -= work->next_smb2_rcv_hdr_off; - len = round_up(len, 8); - } if (check_smb2_hdr(hdr)) return 1; diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c index fb6a65d23139..0a5d8450e835 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/ksmbd/smb2ops.c @@ -6,7 +6,6 @@ #include <linux/slab.h> #include "glob.h" -#include "smb2pdu.h" #include "auth.h" #include "connection.h" @@ -199,7 +198,7 @@ void init_smb2_1_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256; + conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; @@ -217,7 +216,7 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_AES_CMAC; + conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; @@ -242,7 +241,7 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_AES_CMAC; + conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; @@ -267,7 +266,7 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_AES_CMAC; + conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 7e448df3f847..121f8e8c70ac 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -13,7 +13,6 @@ #include <linux/falloc.h> #include "glob.h" -#include "smb2pdu.h" #include "smbfsctl.h" #include "oplock.h" #include "smbacl.h" @@ -44,8 +43,8 @@ static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) *req = ksmbd_req_buf_next(work); *rsp = ksmbd_resp_buf_next(work); } else { - *req = work->request_buf; - *rsp = work->response_buf; + *req = smb2_get_msg(work->request_buf); + *rsp = smb2_get_msg(work->response_buf); } } @@ -93,13 +92,14 @@ struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn */ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) { - struct smb2_hdr *req_hdr = work->request_buf; + struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf); + unsigned int cmd = le16_to_cpu(req_hdr->Command); int tree_id; work->tcon = NULL; - if (work->conn->ops->get_cmd_val(work) == SMB2_TREE_CONNECT_HE || - work->conn->ops->get_cmd_val(work) == SMB2_CANCEL_HE || - work->conn->ops->get_cmd_val(work) == SMB2_LOGOFF_HE) { + if (cmd == SMB2_TREE_CONNECT_HE || + cmd == SMB2_CANCEL_HE || + cmd == SMB2_LOGOFF_HE) { ksmbd_debug(SMB, "skip to check tree connect request\n"); return 0; } @@ -130,7 +130,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) err_rsp = ksmbd_resp_buf_next(work); else - err_rsp = work->response_buf; + err_rsp = smb2_get_msg(work->response_buf); if (err_rsp->hdr.Status != STATUS_STOPPED_ON_SYMLINK) { err_rsp->StructureSize = SMB2_ERROR_STRUCTURE_SIZE2_LE; @@ -150,7 +150,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work) */ bool is_smb2_neg_cmd(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); /* is it SMB2 header ? */ if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -174,7 +174,7 @@ bool is_smb2_neg_cmd(struct ksmbd_work *work) */ bool is_smb2_rsp(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->response_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->response_buf); /* is it SMB2 header ? */ if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -200,7 +200,7 @@ u16 get_smb2_cmd_val(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) rcv_hdr = ksmbd_req_buf_next(work); else - rcv_hdr = work->request_buf; + rcv_hdr = smb2_get_msg(work->request_buf); return le16_to_cpu(rcv_hdr->Command); } @@ -216,7 +216,7 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) if (work->next_smb2_rcv_hdr_off) rsp_hdr = ksmbd_resp_buf_next(work); else - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Status = err; smb2_set_err_rsp(work); } @@ -237,13 +237,11 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) if (conn->need_neg == false) return -EINVAL; - rsp_hdr = work->response_buf; + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); + rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); - rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(2); @@ -256,7 +254,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = work->response_buf; + rsp = smb2_get_msg(work->response_buf); WARN_ON(ksmbd_conn_good(work)); @@ -277,12 +275,12 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp->SecurityBufferOffset = cpu_to_le16(128); rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH); - ksmbd_copy_gss_neg_header(((char *)(&rsp->hdr) + - sizeof(rsp->hdr.smb2_buf_length)) + + ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) + le16_to_cpu(rsp->SecurityBufferOffset)); - inc_rfc1001_len(rsp, sizeof(struct smb2_negotiate_rsp) - - sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + - AUTH_GSS_LENGTH); + inc_rfc1001_len(work->response_buf, + sizeof(struct smb2_negotiate_rsp) - + sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + + AUTH_GSS_LENGTH); rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE; if (server_conf.signing == KSMBD_CONFIG_OPT_MANDATORY) rsp->SecurityMode |= SMB2_NEGOTIATE_SIGNING_REQUIRED_LE; @@ -387,8 +385,8 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) next_hdr_offset = le32_to_cpu(req->NextCommand); new_len = ALIGN(len, 8); - inc_rfc1001_len(work->response_buf, ((sizeof(struct smb2_hdr) - 4) - + new_len - len)); + inc_rfc1001_len(work->response_buf, + sizeof(struct smb2_hdr) + new_len - len); rsp->NextCommand = cpu_to_le32(new_len); work->next_smb2_rcv_hdr_off += next_hdr_offset; @@ -406,7 +404,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) work->compound_fid = KSMBD_NO_FID; work->compound_pfid = KSMBD_NO_FID; } - memset((char *)rsp_hdr + 4, 0, sizeof(struct smb2_hdr) + 2); + memset((char *)rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->Command = rcv_hdr->Command; @@ -432,7 +430,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) */ bool is_chained_smb2_message(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); unsigned int len, next_cmd; if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -483,13 +481,13 @@ bool is_chained_smb2_message(struct ksmbd_work *work) */ int init_smb2_rsp_hdr(struct ksmbd_work *work) { - struct smb2_hdr *rsp_hdr = work->response_buf; - struct smb2_hdr *rcv_hdr = work->request_buf; + struct smb2_hdr *rsp_hdr = smb2_get_msg(work->response_buf); + struct smb2_hdr *rcv_hdr = smb2_get_msg(work->request_buf); struct ksmbd_conn *conn = work->conn; memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = rcv_hdr->ProtocolId; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->Command = rcv_hdr->Command; @@ -522,7 +520,7 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) */ int smb2_allocate_rsp_buf(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); size_t small_sz = MAX_CIFS_SMALL_BUFFER_SIZE; size_t large_sz = small_sz + work->conn->vals->max_trans_size; size_t sz = small_sz; @@ -534,7 +532,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) if (cmd == SMB2_QUERY_INFO_HE) { struct smb2_query_info_req *req; - req = work->request_buf; + req = smb2_get_msg(work->request_buf); if (req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || req->FileInfoClass == FILE_ALL_INFORMATION)) @@ -561,7 +559,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) */ int smb2_check_user_session(struct ksmbd_work *work) { - struct smb2_hdr *req_hdr = work->request_buf; + struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf); struct ksmbd_conn *conn = work->conn; unsigned int cmd = conn->ops->get_cmd_val(work); unsigned long long sess_id; @@ -642,7 +640,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) struct ksmbd_conn *conn = work->conn; int id; - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; id = ksmbd_acquire_async_msg_id(&conn->async_ida); @@ -674,7 +672,7 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); smb2_set_err_rsp(work); rsp_hdr->Status = status; @@ -715,17 +713,17 @@ static int smb2_get_dos_mode(struct kstat *stat, int attribute) int attr = 0; if (S_ISDIR(stat->mode)) { - attr = ATTR_DIRECTORY | - (attribute & (ATTR_HIDDEN | ATTR_SYSTEM)); + attr = FILE_ATTRIBUTE_DIRECTORY | + (attribute & (FILE_ATTRIBUTE_HIDDEN | FILE_ATTRIBUTE_SYSTEM)); } else { - attr = (attribute & 0x00005137) | ATTR_ARCHIVE; - attr &= ~(ATTR_DIRECTORY); + attr = (attribute & 0x00005137) | FILE_ATTRIBUTE_ARCHIVE; + attr &= ~(FILE_ATTRIBUTE_DIRECTORY); if (S_ISREG(stat->mode) && (server_conf.share_fake_fscaps & FILE_SUPPORTS_SPARSE_FILES)) - attr |= ATTR_SPARSE; + attr |= FILE_ATTRIBUTE_SPARSE_FILE; if (smb2_get_reparse_tag_special_file(stat->mode)) - attr |= ATTR_REPARSE; + attr |= FILE_ATTRIBUTE_REPARSE_POINT; } return attr; @@ -753,16 +751,16 @@ static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt, pneg_ctxt->Ciphers[0] = cipher_type; } -static void build_compression_ctxt(struct smb2_compression_ctx *pneg_ctxt, +static void build_compression_ctxt(struct smb2_compression_capabilities_context *pneg_ctxt, __le16 comp_algo) { pneg_ctxt->ContextType = SMB2_COMPRESSION_CAPABILITIES; pneg_ctxt->DataLength = - cpu_to_le16(sizeof(struct smb2_compression_ctx) + cpu_to_le16(sizeof(struct smb2_compression_capabilities_context) - sizeof(struct smb2_neg_context)); pneg_ctxt->Reserved = cpu_to_le32(0); pneg_ctxt->CompressionAlgorithmCount = cpu_to_le16(1); - pneg_ctxt->Reserved1 = cpu_to_le32(0); + pneg_ctxt->Flags = cpu_to_le32(0); pneg_ctxt->CompressionAlgorithms[0] = comp_algo; } @@ -802,11 +800,11 @@ static void build_posix_ctxt(struct smb2_posix_neg_context *pneg_ctxt) } static void assemble_neg_contexts(struct ksmbd_conn *conn, - struct smb2_negotiate_rsp *rsp) + struct smb2_negotiate_rsp *rsp, + void *smb2_buf_len) { - /* +4 is to account for the RFC1001 len field */ char *pneg_ctxt = (char *)rsp + - le32_to_cpu(rsp->NegotiateContextOffset) + 4; + le32_to_cpu(rsp->NegotiateContextOffset); int neg_ctxt_cnt = 1; int ctxt_size; @@ -815,7 +813,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt, conn->preauth_info->Preauth_HashId); rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt); - inc_rfc1001_len(rsp, AUTH_GSS_PADDING); + inc_rfc1001_len(smb2_buf_len, AUTH_GSS_PADDING); ctxt_size = sizeof(struct smb2_preauth_neg_context); /* Round to 8 byte boundary */ pneg_ctxt += round_up(sizeof(struct smb2_preauth_neg_context), 8); @@ -839,12 +837,12 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ksmbd_debug(SMB, "assemble SMB2_COMPRESSION_CAPABILITIES context\n"); /* Temporarily set to SMB3_COMPRESS_NONE */ - build_compression_ctxt((struct smb2_compression_ctx *)pneg_ctxt, + build_compression_ctxt((struct smb2_compression_capabilities_context *)pneg_ctxt, conn->compress_algorithm); rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); - ctxt_size += sizeof(struct smb2_compression_ctx) + 2; + ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2; /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_compression_ctx) + 2, + pneg_ctxt += round_up(sizeof(struct smb2_compression_capabilities_context) + 2, 8); } @@ -869,7 +867,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ctxt_size += sizeof(struct smb2_signing_capabilities) + 2; } - inc_rfc1001_len(rsp, ctxt_size); + inc_rfc1001_len(smb2_buf_len, ctxt_size); } static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, @@ -918,7 +916,7 @@ static void decode_encrypt_ctxt(struct ksmbd_conn *conn, } static void decode_compress_ctxt(struct ksmbd_conn *conn, - struct smb2_compression_ctx *pneg_ctxt) + struct smb2_compression_capabilities_context *pneg_ctxt) { conn->compress_algorithm = SMB3_COMPRESS_NONE; } @@ -939,8 +937,8 @@ static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, } for (i = 0; i < sign_algo_cnt; i++) { - if (pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_HMAC_SHA256 || - pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_AES_CMAC) { + if (pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_HMAC_SHA256_LE || + pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_AES_CMAC_LE) { ksmbd_debug(SMB, "Signing Algorithm ID = 0x%x\n", pneg_ctxt->SigningAlgorithms[i]); conn->signing_negotiated = true; @@ -952,14 +950,14 @@ static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, } static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, - struct smb2_negotiate_req *req) + struct smb2_negotiate_req *req, + int len_of_smb) { /* +4 is to account for the RFC1001 len field */ - struct smb2_neg_context *pctx = (struct smb2_neg_context *)((char *)req + 4); + struct smb2_neg_context *pctx = (struct smb2_neg_context *)req; int i = 0, len_of_ctxts; int offset = le32_to_cpu(req->NegotiateContextOffset); int neg_ctxt_cnt = le16_to_cpu(req->NegotiateContextCount); - int len_of_smb = be32_to_cpu(req->hdr.smb2_buf_length); __le32 status = STATUS_INVALID_PARAMETER; ksmbd_debug(SMB, "decoding %d negotiate contexts\n", neg_ctxt_cnt); @@ -1011,7 +1009,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, break; decode_compress_ctxt(conn, - (struct smb2_compression_ctx *)pctx); + (struct smb2_compression_capabilities_context *)pctx); } else if (pctx->ContextType == SMB2_NETNAME_NEGOTIATE_CONTEXT_ID) { ksmbd_debug(SMB, "deassemble SMB2_NETNAME_NEGOTIATE_CONTEXT_ID context\n"); @@ -1044,8 +1042,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, int smb2_handle_negotiate(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_negotiate_req *req = work->request_buf; - struct smb2_negotiate_rsp *rsp = work->response_buf; + struct smb2_negotiate_req *req = smb2_get_msg(work->request_buf); + struct smb2_negotiate_rsp *rsp = smb2_get_msg(work->response_buf); int rc = 0; unsigned int smb2_buf_len, smb2_neg_size; __le32 status; @@ -1066,7 +1064,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) } smb2_buf_len = get_rfc1002_len(work->request_buf); - smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects) - 4; + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; @@ -1115,7 +1113,8 @@ int smb2_handle_negotiate(struct ksmbd_work *work) goto err_out; } - status = deassemble_neg_contexts(conn, req); + status = deassemble_neg_contexts(conn, req, + get_rfc1002_len(work->request_buf)); if (status != STATUS_SUCCESS) { pr_err("deassemble_neg_contexts error(0x%x)\n", status); @@ -1135,7 +1134,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) conn->preauth_info->Preauth_HashValue); rsp->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT); - assemble_neg_contexts(conn, rsp); + assemble_neg_contexts(conn, rsp, work->response_buf); break; case SMB302_PROT_ID: init_smb3_02_server(conn); @@ -1183,10 +1182,9 @@ int smb2_handle_negotiate(struct ksmbd_work *work) rsp->SecurityBufferOffset = cpu_to_le16(128); rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH); - ksmbd_copy_gss_neg_header(((char *)(&rsp->hdr) + - sizeof(rsp->hdr.smb2_buf_length)) + - le16_to_cpu(rsp->SecurityBufferOffset)); - inc_rfc1001_len(rsp, sizeof(struct smb2_negotiate_rsp) - + ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) + + le16_to_cpu(rsp->SecurityBufferOffset)); + inc_rfc1001_len(work->response_buf, sizeof(struct smb2_negotiate_rsp) - sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + AUTH_GSS_LENGTH); rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE; @@ -1278,7 +1276,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, struct negotiate_message *negblob, size_t negblob_len) { - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct challenge_message *chgblob; unsigned char *spnego_blob = NULL; u16 spnego_blob_len; @@ -1386,8 +1384,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, static int ntlm_authenticate(struct ksmbd_work *work) { - struct smb2_sess_setup_req *req = work->request_buf; - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf); + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; struct channel *chann = NULL; @@ -1410,7 +1408,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); - inc_rfc1001_len(rsp, spnego_blob_len - 1); + inc_rfc1001_len(work->response_buf, spnego_blob_len - 1); } user = session_user(conn, req); @@ -1522,8 +1520,8 @@ binding_session: #ifdef CONFIG_SMB_SERVER_KERBEROS5 static int krb5_authenticate(struct ksmbd_work *work) { - struct smb2_sess_setup_req *req = work->request_buf; - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf); + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; char *in_blob, *out_blob; @@ -1538,8 +1536,7 @@ static int krb5_authenticate(struct ksmbd_work *work) out_blob = (char *)&rsp->hdr.ProtocolId + le16_to_cpu(rsp->SecurityBufferOffset); out_len = work->response_sz - - offsetof(struct smb2_hdr, smb2_buf_length) - - le16_to_cpu(rsp->SecurityBufferOffset); + (le16_to_cpu(rsp->SecurityBufferOffset) + 4); /* Check previous session */ prev_sess_id = le64_to_cpu(req->PreviousSessionId); @@ -1556,7 +1553,7 @@ static int krb5_authenticate(struct ksmbd_work *work) return -EINVAL; } rsp->SecurityBufferLength = cpu_to_le16(out_len); - inc_rfc1001_len(rsp, out_len - 1); + inc_rfc1001_len(work->response_buf, out_len - 1); if ((conn->sign || server_conf.enforced_signing) || (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED)) @@ -1612,8 +1609,8 @@ static int krb5_authenticate(struct ksmbd_work *work) int smb2_sess_setup(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_sess_setup_req *req = work->request_buf; - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf); + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess; struct negotiate_message *negblob; unsigned int negblob_len, negblob_off; @@ -1625,7 +1622,7 @@ int smb2_sess_setup(struct ksmbd_work *work) rsp->SessionFlags = 0; rsp->SecurityBufferOffset = cpu_to_le16(72); rsp->SecurityBufferLength = 0; - inc_rfc1001_len(rsp, 9); + inc_rfc1001_len(work->response_buf, 9); if (!req->hdr.SessionId) { sess = ksmbd_smb2_session_create(); @@ -1699,7 +1696,7 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); - if (negblob_off < (offsetof(struct smb2_sess_setup_req, Buffer) - 4) || + if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) return -EINVAL; @@ -1739,7 +1736,8 @@ int smb2_sess_setup(struct ksmbd_work *work) * Note: here total size -1 is done as an * adjustment for 0 size blob */ - inc_rfc1001_len(rsp, le16_to_cpu(rsp->SecurityBufferLength) - 1); + inc_rfc1001_len(work->response_buf, + le16_to_cpu(rsp->SecurityBufferLength) - 1); } else if (negblob->MessageType == NtLmAuthenticate) { rc = ntlm_authenticate(work); @@ -1828,8 +1826,8 @@ out_err: int smb2_tree_connect(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_tree_connect_req *req = work->request_buf; - struct smb2_tree_connect_rsp *rsp = work->response_buf; + struct smb2_tree_connect_req *req = smb2_get_msg(work->request_buf); + struct smb2_tree_connect_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess = work->sess; char *treename = NULL, *name = NULL; struct ksmbd_tree_conn_status status; @@ -1894,7 +1892,7 @@ out_err1: rsp->Reserved = 0; /* default manual caching */ rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING; - inc_rfc1001_len(rsp, 16); + inc_rfc1001_len(work->response_buf, 16); if (!IS_ERR(treename)) kfree(treename); @@ -1999,17 +1997,18 @@ static int smb2_create_open_flags(bool file_present, __le32 access, */ int smb2_tree_disconnect(struct ksmbd_work *work) { - struct smb2_tree_disconnect_rsp *rsp = work->response_buf; + struct smb2_tree_disconnect_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess = work->sess; struct ksmbd_tree_connect *tcon = work->tcon; rsp->StructureSize = cpu_to_le16(4); - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); ksmbd_debug(SMB, "request\n"); if (!tcon) { - struct smb2_tree_disconnect_req *req = work->request_buf; + struct smb2_tree_disconnect_req *req = + smb2_get_msg(work->request_buf); ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -2031,11 +2030,11 @@ int smb2_tree_disconnect(struct ksmbd_work *work) int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_logoff_rsp *rsp = work->response_buf; + struct smb2_logoff_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess = work->sess; rsp->StructureSize = cpu_to_le16(4); - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); ksmbd_debug(SMB, "request\n"); @@ -2048,7 +2047,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { - struct smb2_logoff_req *req = work->request_buf; + struct smb2_logoff_req *req = smb2_get_msg(work->request_buf); ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -2075,8 +2074,8 @@ int smb2_session_logoff(struct ksmbd_work *work) */ static noinline int create_smb2_pipe(struct ksmbd_work *work) { - struct smb2_create_rsp *rsp = work->response_buf; - struct smb2_create_req *req = work->request_buf; + struct smb2_create_rsp *rsp = smb2_get_msg(work->response_buf); + struct smb2_create_req *req = smb2_get_msg(work->request_buf); int id; int err; char *name; @@ -2099,7 +2098,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) rsp->hdr.Status = STATUS_SUCCESS; rsp->StructureSize = cpu_to_le16(89); rsp->OplockLevel = SMB2_OPLOCK_LEVEL_NONE; - rsp->Reserved = 0; + rsp->Flags = 0; rsp->CreateAction = cpu_to_le32(FILE_OPENED); rsp->CreationTime = cpu_to_le64(0); @@ -2107,14 +2106,14 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) rsp->ChangeTime = cpu_to_le64(0); rsp->AllocationSize = cpu_to_le64(0); rsp->EndofFile = cpu_to_le64(0); - rsp->FileAttributes = ATTR_NORMAL_LE; + rsp->FileAttributes = FILE_ATTRIBUTE_NORMAL_LE; rsp->Reserved2 = 0; rsp->VolatileFileId = cpu_to_le64(id); rsp->PersistentFileId = 0; rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; - inc_rfc1001_len(rsp, 88); /* StructureSize - 1*/ + inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/ kfree(name); return 0; @@ -2353,7 +2352,7 @@ static void smb2_update_xattrs(struct ksmbd_tree_connect *tcon, struct xattr_dos_attrib da; int rc; - fp->f_ci->m_fattr &= ~(ATTR_HIDDEN_LE | ATTR_SYSTEM_LE); + fp->f_ci->m_fattr &= ~(FILE_ATTRIBUTE_HIDDEN_LE | FILE_ATTRIBUTE_SYSTEM_LE); /* get FileAttributes from XATTR_NAME_DOS_ATTRIBUTE */ if (!test_share_config_flag(tcon->share_conf, @@ -2463,7 +2462,7 @@ int smb2_open(struct ksmbd_work *work) struct ksmbd_session *sess = work->sess; struct ksmbd_tree_connect *tcon = work->tcon; struct smb2_create_req *req; - struct smb2_create_rsp *rsp, *rsp_org; + struct smb2_create_rsp *rsp; struct path path; struct ksmbd_share_config *share = tcon->share_conf; struct ksmbd_file *fp = NULL; @@ -2489,7 +2488,6 @@ int smb2_open(struct ksmbd_work *work) umode_t posix_mode = 0; __le32 daccess, maximal_access = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (req->hdr.NextCommand && !work->next_smb2_rcv_hdr_off && @@ -2559,7 +2557,7 @@ int smb2_open(struct ksmbd_work *work) if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) lc = parse_lease_state(req); - if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE_LE)) { + if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); rc = -EIO; @@ -2567,7 +2565,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK)) { + if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) { pr_err("Invalid create options : 0x%x\n", le32_to_cpu(req->CreateOptions)); rc = -EINVAL; @@ -2609,7 +2607,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - if (req->FileAttributes && !(req->FileAttributes & ATTR_MASK_LE)) { + if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) { pr_err("Invalid file attribute : 0x%x\n", le32_to_cpu(req->FileAttributes)); rc = -EINVAL; @@ -2740,7 +2738,7 @@ int smb2_open(struct ksmbd_work *work) } if (req->CreateOptions & FILE_DIRECTORY_FILE_LE && - req->FileAttributes & ATTR_NORMAL_LE) { + req->FileAttributes & FILE_ATTRIBUTE_NORMAL_LE) { rsp->hdr.Status = STATUS_NOT_A_DIRECTORY; rc = -EIO; } @@ -3119,7 +3117,7 @@ int smb2_open(struct ksmbd_work *work) opinfo = rcu_dereference(fp->f_opinfo); rsp->OplockLevel = opinfo != NULL ? opinfo->level : 0; rcu_read_unlock(); - rsp->Reserved = 0; + rsp->Flags = 0; rsp->CreateAction = cpu_to_le32(file_info); rsp->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -3140,7 +3138,7 @@ int smb2_open(struct ksmbd_work *work) rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; - inc_rfc1001_len(rsp_org, 88); /* StructureSize - 1*/ + inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/ /* If lease is request send lease context response */ if (opinfo && opinfo->is_lease) { @@ -3155,7 +3153,8 @@ int smb2_open(struct ksmbd_work *work) create_lease_buf(rsp->Buffer, opinfo->o_lease); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_lease_size); - inc_rfc1001_len(rsp_org, conn->vals->create_lease_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_lease_size); next_ptr = &lease_ccontext->Next; next_off = conn->vals->create_lease_size; } @@ -3175,7 +3174,8 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(maximal_access)); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_mxac_size); - inc_rfc1001_len(rsp_org, conn->vals->create_mxac_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_mxac_size); if (next_ptr) *next_ptr = cpu_to_le32(next_off); next_ptr = &mxac_ccontext->Next; @@ -3193,7 +3193,8 @@ int smb2_open(struct ksmbd_work *work) stat.ino, tcon->id); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_disk_id_size); - inc_rfc1001_len(rsp_org, conn->vals->create_disk_id_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_disk_id_size); if (next_ptr) *next_ptr = cpu_to_le32(next_off); next_ptr = &disk_id_ccontext->Next; @@ -3207,15 +3208,15 @@ int smb2_open(struct ksmbd_work *work) fp); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_posix_size); - inc_rfc1001_len(rsp_org, conn->vals->create_posix_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_posix_size); if (next_ptr) *next_ptr = cpu_to_le32(next_off); } if (contxt_cnt > 0) { rsp->CreateContextsOffset = - cpu_to_le32(offsetof(struct smb2_create_rsp, Buffer) - - 4); + cpu_to_le32(offsetof(struct smb2_create_rsp, Buffer)); } err_out: @@ -3422,9 +3423,9 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, ffdinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (ffdinfo->EaSize) - ffdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + ffdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; if (d_info->hide_dot_file && d_info->name[0] == '.') - ffdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + ffdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(ffdinfo->FileName, conv_name, conv_len); ffdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3438,11 +3439,11 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, fbdinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (fbdinfo->EaSize) - fbdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + fbdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; fbdinfo->ShortNameLength = 0; fbdinfo->Reserved = 0; if (d_info->hide_dot_file && d_info->name[0] == '.') - fbdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + fbdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(fbdinfo->FileName, conv_name, conv_len); fbdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3454,7 +3455,7 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, fdinfo = (struct file_directory_info *)kstat; fdinfo->FileNameLength = cpu_to_le32(conv_len); if (d_info->hide_dot_file && d_info->name[0] == '.') - fdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + fdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(fdinfo->FileName, conv_name, conv_len); fdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3478,11 +3479,11 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, dinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (dinfo->EaSize) - dinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + dinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; dinfo->Reserved = 0; dinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino); if (d_info->hide_dot_file && d_info->name[0] == '.') - dinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + dinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(dinfo->FileName, conv_name, conv_len); dinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3496,13 +3497,13 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, fibdinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (fibdinfo->EaSize) - fibdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + fibdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; fibdinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino); fibdinfo->ShortNameLength = 0; fibdinfo->Reserved = 0; fibdinfo->Reserved2 = cpu_to_le16(0); if (d_info->hide_dot_file && d_info->name[0] == '.') - fibdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + fibdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(fibdinfo->FileName, conv_name, conv_len); fibdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3528,9 +3529,10 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode); posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = - S_ISDIR(ksmbd_kstat->kstat->mode) ? ATTR_DIRECTORY_LE : ATTR_ARCHIVE_LE; + S_ISDIR(ksmbd_kstat->kstat->mode) ? + FILE_ATTRIBUTE_DIRECTORY_LE : FILE_ATTRIBUTE_ARCHIVE_LE; if (d_info->hide_dot_file && d_info->name[0] == '.') - posix_info->DosAttributes |= ATTR_HIDDEN_LE; + posix_info->DosAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; id_to_sid(from_kuid_munged(&init_user_ns, ksmbd_kstat->kstat->uid), SIDNFS_USER, (struct smb_sid *)&posix_info->SidBuffer[0]); id_to_sid(from_kgid_munged(&init_user_ns, ksmbd_kstat->kstat->gid), @@ -3816,7 +3818,7 @@ int smb2_query_dir(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; struct smb2_query_directory_req *req; - struct smb2_query_directory_rsp *rsp, *rsp_org; + struct smb2_query_directory_rsp *rsp; struct ksmbd_share_config *share = work->tcon->share_conf; struct ksmbd_file *dir_fp = NULL; struct ksmbd_dir_info d_info; @@ -3826,7 +3828,6 @@ int smb2_query_dir(struct ksmbd_work *work) int buffer_sz; struct smb2_query_dir_private query_dir_private = {NULL, }; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (ksmbd_override_fsids(work)) { @@ -3947,7 +3948,7 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->OutputBufferOffset = cpu_to_le16(0); rsp->OutputBufferLength = cpu_to_le32(0); rsp->Buffer[0] = 0; - inc_rfc1001_len(rsp_org, 9); + inc_rfc1001_len(work->response_buf, 9); } else { ((struct file_directory_info *) ((char *)rsp->Buffer + d_info.last_entry_offset)) @@ -3956,7 +3957,7 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); rsp->OutputBufferLength = cpu_to_le32(d_info.data_count); - inc_rfc1001_len(rsp_org, 8 + d_info.data_count); + inc_rfc1001_len(work->response_buf, 8 + d_info.data_count); } kfree(srch_ptr); @@ -3999,26 +4000,28 @@ err_out2: * Return: 0 on success, otherwise error */ static int buffer_check_err(int reqOutputBufferLength, - struct smb2_query_info_rsp *rsp, int infoclass_size) + struct smb2_query_info_rsp *rsp, + void *rsp_org, int infoclass_size) { if (reqOutputBufferLength < le32_to_cpu(rsp->OutputBufferLength)) { if (reqOutputBufferLength < infoclass_size) { pr_err("Invalid Buffer Size Requested\n"); rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH; - rsp->hdr.smb2_buf_length = cpu_to_be32(sizeof(struct smb2_hdr) - 4); + *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr)); return -EINVAL; } ksmbd_debug(SMB, "Buffer Overflow\n"); rsp->hdr.Status = STATUS_BUFFER_OVERFLOW; - rsp->hdr.smb2_buf_length = cpu_to_be32(sizeof(struct smb2_hdr) - 4 + + *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr) + reqOutputBufferLength); rsp->OutputBufferLength = cpu_to_le32(reqOutputBufferLength); } return 0; } -static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp) +static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp, + void *rsp_org) { struct smb2_file_standard_info *sinfo; @@ -4031,10 +4034,11 @@ static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp) sinfo->Directory = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); - inc_rfc1001_len(rsp, sizeof(struct smb2_file_standard_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_standard_info)); } -static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num) +static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num, + void *rsp_org) { struct smb2_file_internal_info *file_info; @@ -4044,12 +4048,13 @@ static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num) file_info->IndexNumber = cpu_to_le64(num | (1ULL << 63)); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); - inc_rfc1001_len(rsp, sizeof(struct smb2_file_internal_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_internal_info)); } static int smb2_get_info_file_pipe(struct ksmbd_session *sess, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp) + struct smb2_query_info_rsp *rsp, + void *rsp_org) { u64 id; int rc; @@ -4067,14 +4072,16 @@ static int smb2_get_info_file_pipe(struct ksmbd_session *sess, switch (req->FileInfoClass) { case FILE_STANDARD_INFORMATION: - get_standard_info_pipe(rsp); + get_standard_info_pipe(rsp, rsp_org); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, FILE_STANDARD_INFORMATION_SIZE); + rsp, rsp_org, + FILE_STANDARD_INFORMATION_SIZE); break; case FILE_INTERNAL_INFORMATION: - get_internal_info_pipe(rsp, id); + get_internal_info_pipe(rsp, id, rsp_org); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, FILE_INTERNAL_INFORMATION_SIZE); + rsp, rsp_org, + FILE_INTERNAL_INFORMATION_SIZE); break; default: ksmbd_debug(SMB, "smb2_info_file_pipe for %u not supported\n", @@ -4688,7 +4695,7 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, static int smb2_get_info_file(struct ksmbd_work *work, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, void *rsp_org) + struct smb2_query_info_rsp *rsp) { struct ksmbd_file *fp; int fileinfoclass = 0; @@ -4699,7 +4706,8 @@ static int smb2_get_info_file(struct ksmbd_work *work, if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { /* smb2 info file called for pipe */ - return smb2_get_info_file_pipe(work->sess, req, rsp); + return smb2_get_info_file_pipe(work->sess, req, rsp, + work->response_buf); } if (work->next_smb2_rcv_hdr_off) { @@ -4724,77 +4732,77 @@ static int smb2_get_info_file(struct ksmbd_work *work, switch (fileinfoclass) { case FILE_ACCESS_INFORMATION: - get_file_access_info(rsp, fp, rsp_org); + get_file_access_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_ACCESS_INFORMATION_SIZE; break; case FILE_BASIC_INFORMATION: - rc = get_file_basic_info(rsp, fp, rsp_org); + rc = get_file_basic_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_BASIC_INFORMATION_SIZE; break; case FILE_STANDARD_INFORMATION: - get_file_standard_info(rsp, fp, rsp_org); + get_file_standard_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_STANDARD_INFORMATION_SIZE; break; case FILE_ALIGNMENT_INFORMATION: - get_file_alignment_info(rsp, rsp_org); + get_file_alignment_info(rsp, work->response_buf); file_infoclass_size = FILE_ALIGNMENT_INFORMATION_SIZE; break; case FILE_ALL_INFORMATION: - rc = get_file_all_info(work, rsp, fp, rsp_org); + rc = get_file_all_info(work, rsp, fp, work->response_buf); file_infoclass_size = FILE_ALL_INFORMATION_SIZE; break; case FILE_ALTERNATE_NAME_INFORMATION: - get_file_alternate_info(work, rsp, fp, rsp_org); + get_file_alternate_info(work, rsp, fp, work->response_buf); file_infoclass_size = FILE_ALTERNATE_NAME_INFORMATION_SIZE; break; case FILE_STREAM_INFORMATION: - get_file_stream_info(work, rsp, fp, rsp_org); + get_file_stream_info(work, rsp, fp, work->response_buf); file_infoclass_size = FILE_STREAM_INFORMATION_SIZE; break; case FILE_INTERNAL_INFORMATION: - get_file_internal_info(rsp, fp, rsp_org); + get_file_internal_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_INTERNAL_INFORMATION_SIZE; break; case FILE_NETWORK_OPEN_INFORMATION: - rc = get_file_network_open_info(rsp, fp, rsp_org); + rc = get_file_network_open_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_NETWORK_OPEN_INFORMATION_SIZE; break; case FILE_EA_INFORMATION: - get_file_ea_info(rsp, rsp_org); + get_file_ea_info(rsp, work->response_buf); file_infoclass_size = FILE_EA_INFORMATION_SIZE; break; case FILE_FULL_EA_INFORMATION: - rc = smb2_get_ea(work, fp, req, rsp, rsp_org); + rc = smb2_get_ea(work, fp, req, rsp, work->response_buf); file_infoclass_size = FILE_FULL_EA_INFORMATION_SIZE; break; case FILE_POSITION_INFORMATION: - get_file_position_info(rsp, fp, rsp_org); + get_file_position_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_POSITION_INFORMATION_SIZE; break; case FILE_MODE_INFORMATION: - get_file_mode_info(rsp, fp, rsp_org); + get_file_mode_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_MODE_INFORMATION_SIZE; break; case FILE_COMPRESSION_INFORMATION: - get_file_compression_info(rsp, fp, rsp_org); + get_file_compression_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_COMPRESSION_INFORMATION_SIZE; break; case FILE_ATTRIBUTE_TAG_INFORMATION: - rc = get_file_attribute_tag_info(rsp, fp, rsp_org); + rc = get_file_attribute_tag_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_ATTRIBUTE_TAG_INFORMATION_SIZE; break; case SMB_FIND_FILE_POSIX_INFO: @@ -4802,7 +4810,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n"); rc = -EOPNOTSUPP; } else { - rc = find_file_posix_info(rsp, fp, rsp_org); + rc = find_file_posix_info(rsp, fp, work->response_buf); file_infoclass_size = sizeof(struct smb311_posix_qinfo); } break; @@ -4813,7 +4821,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, } if (!rc) rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, + rsp, work->response_buf, file_infoclass_size); ksmbd_fd_put(work, fp); return rc; @@ -4821,7 +4829,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, static int smb2_get_info_filesystem(struct ksmbd_work *work, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, void *rsp_org) + struct smb2_query_info_rsp *rsp) { struct ksmbd_session *sess = work->sess; struct ksmbd_conn *conn = sess->conn; @@ -4857,7 +4865,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->DeviceType = cpu_to_le32(stfs.f_type); info->DeviceCharacteristics = cpu_to_le32(0x00000020); rsp->OutputBufferLength = cpu_to_le32(8); - inc_rfc1001_len(rsp_org, 8); + inc_rfc1001_len(work->response_buf, 8); fs_infoclass_size = FS_DEVICE_INFORMATION_SIZE; break; } @@ -4883,7 +4891,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FileSystemNameLen = cpu_to_le32(len); sz = sizeof(struct filesystem_attribute_info) - 2 + len; rsp->OutputBufferLength = cpu_to_le32(sz); - inc_rfc1001_len(rsp_org, sz); + inc_rfc1001_len(work->response_buf, sz); fs_infoclass_size = FS_ATTRIBUTE_INFORMATION_SIZE; break; } @@ -4891,11 +4899,18 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, { struct filesystem_vol_info *info; size_t sz; + unsigned int serial_crc = 0; info = (struct filesystem_vol_info *)(rsp->Buffer); info->VolumeCreationTime = 0; + serial_crc = crc32_le(serial_crc, share->name, + strlen(share->name)); + serial_crc = crc32_le(serial_crc, share->path, + strlen(share->path)); + serial_crc = crc32_le(serial_crc, ksmbd_netbios_name(), + strlen(ksmbd_netbios_name())); /* Taking dummy value of serial number*/ - info->SerialNumber = cpu_to_le32(0xbc3ac512); + info->SerialNumber = cpu_to_le32(serial_crc); len = smbConvertToUTF16((__le16 *)info->VolumeLabel, share->name, PATH_MAX, conn->local_nls, 0); @@ -4904,7 +4919,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->Reserved = 0; sz = sizeof(struct filesystem_vol_info) - 2 + len; rsp->OutputBufferLength = cpu_to_le32(sz); - inc_rfc1001_len(rsp_org, sz); + inc_rfc1001_len(work->response_buf, sz); fs_infoclass_size = FS_VOLUME_INFORMATION_SIZE; break; } @@ -4918,7 +4933,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->SectorsPerAllocationUnit = cpu_to_le32(1); info->BytesPerSector = cpu_to_le32(stfs.f_bsize); rsp->OutputBufferLength = cpu_to_le32(24); - inc_rfc1001_len(rsp_org, 24); + inc_rfc1001_len(work->response_buf, 24); fs_infoclass_size = FS_SIZE_INFORMATION_SIZE; break; } @@ -4935,7 +4950,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->SectorsPerAllocationUnit = cpu_to_le32(1); info->BytesPerSector = cpu_to_le32(stfs.f_bsize); rsp->OutputBufferLength = cpu_to_le32(32); - inc_rfc1001_len(rsp_org, 32); + inc_rfc1001_len(work->response_buf, 32); fs_infoclass_size = FS_FULL_SIZE_INFORMATION_SIZE; break; } @@ -4956,7 +4971,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->extended_info.rel_date = 0; memcpy(info->extended_info.version_string, "1.1.0", strlen("1.1.0")); rsp->OutputBufferLength = cpu_to_le32(64); - inc_rfc1001_len(rsp_org, 64); + inc_rfc1001_len(work->response_buf, 64); fs_infoclass_size = FS_OBJECT_ID_INFORMATION_SIZE; break; } @@ -4977,7 +4992,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->ByteOffsetForSectorAlignment = 0; info->ByteOffsetForPartitionAlignment = 0; rsp->OutputBufferLength = cpu_to_le32(28); - inc_rfc1001_len(rsp_org, 28); + inc_rfc1001_len(work->response_buf, 28); fs_infoclass_size = FS_SECTOR_SIZE_INFORMATION_SIZE; break; } @@ -4999,7 +5014,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); - inc_rfc1001_len(rsp_org, 48); + inc_rfc1001_len(work->response_buf, 48); fs_infoclass_size = FS_CONTROL_INFORMATION_SIZE; break; } @@ -5020,7 +5035,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); rsp->OutputBufferLength = cpu_to_le32(56); - inc_rfc1001_len(rsp_org, 56); + inc_rfc1001_len(work->response_buf, 56); fs_infoclass_size = FS_POSIX_INFORMATION_SIZE; } break; @@ -5030,7 +5045,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, return -EOPNOTSUPP; } rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, + rsp, work->response_buf, fs_infoclass_size); path_put(&path); return rc; @@ -5038,7 +5053,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, static int smb2_get_info_sec(struct ksmbd_work *work, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, void *rsp_org) + struct smb2_query_info_rsp *rsp) { struct ksmbd_file *fp; struct user_namespace *user_ns; @@ -5065,7 +5080,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, secdesclen = sizeof(struct smb_ntsd); rsp->OutputBufferLength = cpu_to_le32(secdesclen); - inc_rfc1001_len(rsp_org, secdesclen); + inc_rfc1001_len(work->response_buf, secdesclen); return 0; } @@ -5107,7 +5122,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, return rc; rsp->OutputBufferLength = cpu_to_le32(secdesclen); - inc_rfc1001_len(rsp_org, secdesclen); + inc_rfc1001_len(work->response_buf, secdesclen); return 0; } @@ -5120,10 +5135,9 @@ static int smb2_get_info_sec(struct ksmbd_work *work, int smb2_query_info(struct ksmbd_work *work) { struct smb2_query_info_req *req; - struct smb2_query_info_rsp *rsp, *rsp_org; + struct smb2_query_info_rsp *rsp; int rc = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); ksmbd_debug(SMB, "GOT query info request\n"); @@ -5131,15 +5145,15 @@ int smb2_query_info(struct ksmbd_work *work) switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); - rc = smb2_get_info_file(work, req, rsp, (void *)rsp_org); + rc = smb2_get_info_file(work, req, rsp); break; case SMB2_O_INFO_FILESYSTEM: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILESYSTEM\n"); - rc = smb2_get_info_filesystem(work, req, rsp, (void *)rsp_org); + rc = smb2_get_info_filesystem(work, req, rsp); break; case SMB2_O_INFO_SECURITY: ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n"); - rc = smb2_get_info_sec(work, req, rsp, (void *)rsp_org); + rc = smb2_get_info_sec(work, req, rsp); break; default: ksmbd_debug(SMB, "InfoType %d not supported yet\n", @@ -5164,7 +5178,7 @@ int smb2_query_info(struct ksmbd_work *work) } rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); - inc_rfc1001_len(rsp_org, 8); + inc_rfc1001_len(work->response_buf, 8); return 0; } @@ -5177,8 +5191,8 @@ int smb2_query_info(struct ksmbd_work *work) static noinline int smb2_close_pipe(struct ksmbd_work *work) { u64 id; - struct smb2_close_req *req = work->request_buf; - struct smb2_close_rsp *rsp = work->response_buf; + struct smb2_close_req *req = smb2_get_msg(work->request_buf); + struct smb2_close_rsp *rsp = smb2_get_msg(work->response_buf); id = le64_to_cpu(req->VolatileFileId); ksmbd_session_rpc_close(work->sess, id); @@ -5193,7 +5207,7 @@ static noinline int smb2_close_pipe(struct ksmbd_work *work) rsp->AllocationSize = 0; rsp->EndOfFile = 0; rsp->Attributes = 0; - inc_rfc1001_len(rsp, 60); + inc_rfc1001_len(work->response_buf, 60); return 0; } @@ -5209,14 +5223,12 @@ int smb2_close(struct ksmbd_work *work) u64 sess_id; struct smb2_close_req *req; struct smb2_close_rsp *rsp; - struct smb2_close_rsp *rsp_org; struct ksmbd_conn *conn = work->conn; struct ksmbd_file *fp; struct inode *inode; u64 time; int err = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (test_share_config_flag(work->tcon->share_conf, @@ -5306,7 +5318,7 @@ out: rsp->hdr.Status = STATUS_FILE_CLOSED; smb2_set_err_rsp(work); } else { - inc_rfc1001_len(rsp_org, 60); + inc_rfc1001_len(work->response_buf, 60); } return 0; @@ -5320,11 +5332,11 @@ out: */ int smb2_echo(struct ksmbd_work *work) { - struct smb2_echo_rsp *rsp = work->response_buf; + struct smb2_echo_rsp *rsp = smb2_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(4); rsp->Reserved = 0; - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); return 0; } @@ -5566,14 +5578,14 @@ static int set_file_basic_info(struct ksmbd_file *fp, if (file_info->Attributes) { if (!S_ISDIR(inode->i_mode) && - file_info->Attributes & ATTR_DIRECTORY_LE) { + file_info->Attributes & FILE_ATTRIBUTE_DIRECTORY_LE) { pr_err("can't change a file to a directory\n"); return -EINVAL; } - if (!(S_ISDIR(inode->i_mode) && file_info->Attributes == ATTR_NORMAL_LE)) + if (!(S_ISDIR(inode->i_mode) && file_info->Attributes == FILE_ATTRIBUTE_NORMAL_LE)) fp->f_ci->m_fattr = file_info->Attributes | - (fp->f_ci->m_fattr & ATTR_DIRECTORY_LE); + (fp->f_ci->m_fattr & FILE_ATTRIBUTE_DIRECTORY_LE); } if (test_share_config_flag(share, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS) && @@ -5794,9 +5806,7 @@ static int set_file_mode_info(struct ksmbd_file *fp, mode = file_info->Mode; - if ((mode & ~FILE_MODE_INFO_MASK) || - (mode & FILE_SYNCHRONOUS_IO_ALERT_LE && - mode & FILE_SYNCHRONOUS_IO_NONALERT_LE)) { + if ((mode & ~FILE_MODE_INFO_MASK)) { pr_err("Mode is not valid : 0x%x\n", le32_to_cpu(mode)); return -EINVAL; } @@ -5943,14 +5953,13 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info, int smb2_set_info(struct ksmbd_work *work) { struct smb2_set_info_req *req; - struct smb2_set_info_rsp *rsp, *rsp_org; + struct smb2_set_info_rsp *rsp; struct ksmbd_file *fp; int rc = 0; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; ksmbd_debug(SMB, "Received set info request\n"); - rsp_org = work->response_buf; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); @@ -5961,8 +5970,8 @@ int smb2_set_info(struct ksmbd_work *work) pid = work->compound_pfid; } } else { - req = work->request_buf; - rsp = work->response_buf; + req = smb2_get_msg(work->request_buf); + rsp = smb2_get_msg(work->response_buf); } if (!has_file_id(id)) { @@ -6002,7 +6011,7 @@ int smb2_set_info(struct ksmbd_work *work) goto err_out; rsp->StructureSize = cpu_to_le16(2); - inc_rfc1001_len(rsp_org, 2); + inc_rfc1001_len(work->response_buf, 2); ksmbd_fd_put(work, fp); return 0; @@ -6042,12 +6051,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) int nbytes = 0, err; u64 id; struct ksmbd_rpc_command *rpc_resp; - struct smb2_read_req *req = work->request_buf; - struct smb2_read_rsp *rsp = work->response_buf; + struct smb2_read_req *req = smb2_get_msg(work->request_buf); + struct smb2_read_rsp *rsp = smb2_get_msg(work->response_buf); id = le64_to_cpu(req->VolatileFileId); - inc_rfc1001_len(rsp, 16); + inc_rfc1001_len(work->response_buf, 16); rpc_resp = ksmbd_rpc_read(work->sess, id); if (rpc_resp) { if (rpc_resp->flags != KSMBD_RPC_OK) { @@ -6066,7 +6075,7 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; - work->resp_hdr_sz = get_rfc1002_len(rsp) + 4; + work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4; work->aux_payload_sz = nbytes; kvfree(rpc_resp); } @@ -6076,8 +6085,8 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) rsp->Reserved = 0; rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = 0; - rsp->Reserved2 = 0; - inc_rfc1001_len(rsp, nbytes); + rsp->Flags = 0; + inc_rfc1001_len(work->response_buf, nbytes); return 0; out: @@ -6127,14 +6136,13 @@ int smb2_read(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; struct smb2_read_req *req; - struct smb2_read_rsp *rsp, *rsp_org; + struct smb2_read_rsp *rsp; struct ksmbd_file *fp; loff_t offset; size_t length, mincount; ssize_t nbytes = 0, remain_bytes = 0; int err = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (test_share_config_flag(work->tcon->share_conf, @@ -6215,11 +6223,11 @@ int smb2_read(struct ksmbd_work *work) rsp->Reserved = 0; rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = cpu_to_le32(remain_bytes); - rsp->Reserved2 = 0; - inc_rfc1001_len(rsp_org, 16); - work->resp_hdr_sz = get_rfc1002_len(rsp_org) + 4; + rsp->Flags = 0; + inc_rfc1001_len(work->response_buf, 16); + work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4; work->aux_payload_sz = nbytes; - inc_rfc1001_len(rsp_org, nbytes); + inc_rfc1001_len(work->response_buf, nbytes); ksmbd_fd_put(work, fp); return 0; @@ -6254,8 +6262,8 @@ out: */ static noinline int smb2_write_pipe(struct ksmbd_work *work) { - struct smb2_write_req *req = work->request_buf; - struct smb2_write_rsp *rsp = work->response_buf; + struct smb2_write_req *req = smb2_get_msg(work->request_buf); + struct smb2_write_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_rpc_command *rpc_resp; u64 id = 0; int err = 0, ret = 0; @@ -6266,13 +6274,14 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) id = le64_to_cpu(req->VolatileFileId); if (le16_to_cpu(req->DataOffset) == - (offsetof(struct smb2_write_req, Buffer) - 4)) { + offsetof(struct smb2_write_req, Buffer)) { data_buf = (char *)&req->Buffer[0]; } else { - if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) { + if ((u64)le16_to_cpu(req->DataOffset) + length > + get_rfc1002_len(work->request_buf)) { pr_err("invalid write data offset %u, smb_len %u\n", le16_to_cpu(req->DataOffset), - get_rfc1002_len(req)); + get_rfc1002_len(work->request_buf)); err = -EINVAL; goto out; } @@ -6304,7 +6313,7 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(length); rsp->DataRemaining = 0; rsp->Reserved2 = 0; - inc_rfc1001_len(rsp, 16); + inc_rfc1001_len(work->response_buf, 16); return 0; out: if (err) { @@ -6372,7 +6381,7 @@ static ssize_t smb2_write_rdma_channel(struct ksmbd_work *work, int smb2_write(struct ksmbd_work *work) { struct smb2_write_req *req; - struct smb2_write_rsp *rsp, *rsp_org; + struct smb2_write_rsp *rsp; struct ksmbd_file *fp = NULL; loff_t offset; size_t length; @@ -6381,7 +6390,6 @@ int smb2_write(struct ksmbd_work *work) bool writethrough = false; int err = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { @@ -6424,13 +6432,14 @@ int smb2_write(struct ksmbd_work *work) if (req->Channel != SMB2_CHANNEL_RDMA_V1 && req->Channel != SMB2_CHANNEL_RDMA_V1_INVALIDATE) { if (le16_to_cpu(req->DataOffset) == - (offsetof(struct smb2_write_req, Buffer) - 4)) { + offsetof(struct smb2_write_req, Buffer)) { data_buf = (char *)&req->Buffer[0]; } else { - if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) { + if ((u64)le16_to_cpu(req->DataOffset) + length > + get_rfc1002_len(work->request_buf)) { pr_err("invalid write data offset %u, smb_len %u\n", le16_to_cpu(req->DataOffset), - get_rfc1002_len(req)); + get_rfc1002_len(work->request_buf)); err = -EINVAL; goto out; } @@ -6468,7 +6477,7 @@ int smb2_write(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = 0; rsp->Reserved2 = 0; - inc_rfc1001_len(rsp_org, 16); + inc_rfc1001_len(work->response_buf, 16); ksmbd_fd_put(work, fp); return 0; @@ -6502,10 +6511,9 @@ out: int smb2_flush(struct ksmbd_work *work) { struct smb2_flush_req *req; - struct smb2_flush_rsp *rsp, *rsp_org; + struct smb2_flush_rsp *rsp; int err; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); ksmbd_debug(SMB, "SMB2_FLUSH called for fid %llu\n", @@ -6519,7 +6527,7 @@ int smb2_flush(struct ksmbd_work *work) rsp->StructureSize = cpu_to_le16(4); rsp->Reserved = 0; - inc_rfc1001_len(rsp_org, 4); + inc_rfc1001_len(work->response_buf, 4); return 0; out: @@ -6540,7 +6548,7 @@ out: int smb2_cancel(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); struct smb2_hdr *chdr; struct ksmbd_work *cancel_work = NULL; int canceled = 0; @@ -6555,7 +6563,7 @@ int smb2_cancel(struct ksmbd_work *work) spin_lock(&conn->request_lock); list_for_each_entry(cancel_work, command_list, async_request_entry) { - chdr = cancel_work->request_buf; + chdr = smb2_get_msg(cancel_work->request_buf); if (cancel_work->async_id != le64_to_cpu(hdr->Id.AsyncId)) @@ -6574,7 +6582,7 @@ int smb2_cancel(struct ksmbd_work *work) spin_lock(&conn->request_lock); list_for_each_entry(cancel_work, command_list, request_entry) { - chdr = cancel_work->request_buf; + chdr = smb2_get_msg(cancel_work->request_buf); if (chdr->MessageId != hdr->MessageId || cancel_work == work) @@ -6709,8 +6717,8 @@ static inline bool lock_defer_pending(struct file_lock *fl) */ int smb2_lock(struct ksmbd_work *work) { - struct smb2_lock_req *req = work->request_buf; - struct smb2_lock_rsp *rsp = work->response_buf; + struct smb2_lock_req *req = smb2_get_msg(work->request_buf); + struct smb2_lock_rsp *rsp = smb2_get_msg(work->response_buf); struct smb2_lock_element *lock_ele; struct ksmbd_file *fp = NULL; struct file_lock *flock = NULL; @@ -7017,7 +7025,7 @@ skip: ksmbd_debug(SMB, "successful in taking lock\n"); rsp->hdr.Status = STATUS_SUCCESS; rsp->Reserved = 0; - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); ksmbd_fd_put(work, fp); return 0; @@ -7312,7 +7320,7 @@ static int fsctl_validate_negotiate_info(struct ksmbd_conn *conn, int ret = 0; int dialect; - if (in_buf_len < sizeof(struct validate_negotiate_info_req) + + if (in_buf_len < offsetof(struct validate_negotiate_info_req, Dialects) + le16_to_cpu(neg_req->DialectCount) * sizeof(__le16)) return -EINVAL; @@ -7435,9 +7443,9 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, old_fattr = fp->f_ci->m_fattr; if (sparse->SetSparse) - fp->f_ci->m_fattr |= ATTR_SPARSE_FILE_LE; + fp->f_ci->m_fattr |= FILE_ATTRIBUTE_SPARSE_FILE_LE; else - fp->f_ci->m_fattr &= ~ATTR_SPARSE_FILE_LE; + fp->f_ci->m_fattr &= ~FILE_ATTRIBUTE_SPARSE_FILE_LE; if (fp->f_ci->m_fattr != old_fattr && test_share_config_flag(work->tcon->share_conf, @@ -7490,13 +7498,12 @@ static int fsctl_request_resume_key(struct ksmbd_work *work, int smb2_ioctl(struct ksmbd_work *work) { struct smb2_ioctl_req *req; - struct smb2_ioctl_rsp *rsp, *rsp_org; + struct smb2_ioctl_rsp *rsp; unsigned int cnt_code, nbytes = 0, out_buf_len, in_buf_len; u64 id = KSMBD_NO_FID; struct ksmbd_conn *conn = work->conn; int ret = 0; - rsp_org = work->response_buf; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); @@ -7506,8 +7513,8 @@ int smb2_ioctl(struct ksmbd_work *work) id = work->compound_fid; } } else { - req = work->request_buf; - rsp = work->response_buf; + req = smb2_get_msg(work->request_buf); + rsp = smb2_get_msg(work->response_buf); } if (!has_file_id(id)) @@ -7787,7 +7794,7 @@ dup_ext_out: rsp->Reserved = cpu_to_le16(0); rsp->Flags = cpu_to_le32(0); rsp->Reserved2 = cpu_to_le32(0); - inc_rfc1001_len(rsp_org, 48 + nbytes); + inc_rfc1001_len(work->response_buf, 48 + nbytes); return 0; @@ -7814,8 +7821,8 @@ out: */ static void smb20_oplock_break_ack(struct ksmbd_work *work) { - struct smb2_oplock_break *req = work->request_buf; - struct smb2_oplock_break *rsp = work->response_buf; + struct smb2_oplock_break *req = smb2_get_msg(work->request_buf); + struct smb2_oplock_break *rsp = smb2_get_msg(work->response_buf); struct ksmbd_file *fp; struct oplock_info *opinfo = NULL; __le32 err = 0; @@ -7922,7 +7929,7 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->Reserved2 = 0; rsp->VolatileFid = cpu_to_le64(volatile_id); rsp->PersistentFid = cpu_to_le64(persistent_id); - inc_rfc1001_len(rsp, 24); + inc_rfc1001_len(work->response_buf, 24); return; err_out: @@ -7958,8 +7965,8 @@ static int check_lease_state(struct lease *lease, __le32 req_state) static void smb21_lease_break_ack(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_lease_ack *req = work->request_buf; - struct smb2_lease_ack *rsp = work->response_buf; + struct smb2_lease_ack *req = smb2_get_msg(work->request_buf); + struct smb2_lease_ack *rsp = smb2_get_msg(work->response_buf); struct oplock_info *opinfo; __le32 err = 0; int ret = 0; @@ -8071,7 +8078,7 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) memcpy(rsp->LeaseKey, req->LeaseKey, 16); rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; - inc_rfc1001_len(rsp, 36); + inc_rfc1001_len(work->response_buf, 36); return; err_out: @@ -8092,8 +8099,8 @@ err_out: */ int smb2_oplock_break(struct ksmbd_work *work) { - struct smb2_oplock_break *req = work->request_buf; - struct smb2_oplock_break *rsp = work->response_buf; + struct smb2_oplock_break *req = smb2_get_msg(work->request_buf); + struct smb2_oplock_break *rsp = smb2_get_msg(work->response_buf); switch (le16_to_cpu(req->StructureSize)) { case OP_BREAK_STRUCT_SIZE_20: @@ -8120,8 +8127,8 @@ int smb2_oplock_break(struct ksmbd_work *work) */ int smb2_notify(struct ksmbd_work *work) { - struct smb2_notify_req *req; - struct smb2_notify_rsp *rsp; + struct smb2_change_notify_req *req; + struct smb2_change_notify_rsp *rsp; WORK_BUFFERS(work, req, rsp); @@ -8145,7 +8152,7 @@ int smb2_notify(struct ksmbd_work *work) */ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command) { - struct smb2_hdr *rcv_hdr2 = work->request_buf; + struct smb2_hdr *rcv_hdr2 = smb2_get_msg(work->request_buf); if ((rcv_hdr2->Flags & SMB2_FLAGS_SIGNED) && command != SMB2_NEGOTIATE_HE && @@ -8164,22 +8171,22 @@ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command) */ int smb2_check_sign_req(struct ksmbd_work *work) { - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *hdr; char signature_req[SMB2_SIGNATURE_SIZE]; char signature[SMB2_HMACSHA256_SIZE]; struct kvec iov[1]; size_t len; - hdr_org = hdr = work->request_buf; + hdr = smb2_get_msg(work->request_buf); if (work->next_smb2_rcv_hdr_off) hdr = ksmbd_req_buf_next(work); if (!hdr->NextCommand && !work->next_smb2_rcv_hdr_off) - len = be32_to_cpu(hdr_org->smb2_buf_length); + len = get_rfc1002_len(work->request_buf); else if (hdr->NextCommand) len = le32_to_cpu(hdr->NextCommand); else - len = be32_to_cpu(hdr_org->smb2_buf_length) - + len = get_rfc1002_len(work->request_buf) - work->next_smb2_rcv_hdr_off; memcpy(signature_req, hdr->Signature, SMB2_SIGNATURE_SIZE); @@ -8207,25 +8214,26 @@ int smb2_check_sign_req(struct ksmbd_work *work) */ void smb2_set_sign_rsp(struct ksmbd_work *work) { - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *hdr; struct smb2_hdr *req_hdr; char signature[SMB2_HMACSHA256_SIZE]; struct kvec iov[2]; size_t len; int n_vec = 1; - hdr_org = hdr = work->response_buf; + hdr = smb2_get_msg(work->response_buf); if (work->next_smb2_rsp_hdr_off) hdr = ksmbd_resp_buf_next(work); req_hdr = ksmbd_req_buf_next(work); if (!work->next_smb2_rsp_hdr_off) { - len = get_rfc1002_len(hdr_org); + len = get_rfc1002_len(work->response_buf); if (req_hdr->NextCommand) len = ALIGN(len, 8); } else { - len = get_rfc1002_len(hdr_org) - work->next_smb2_rsp_hdr_off; + len = get_rfc1002_len(work->response_buf) - + work->next_smb2_rsp_hdr_off; len = ALIGN(len, 8); } @@ -8261,23 +8269,23 @@ int smb3_check_sign_req(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; char *signing_key; - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *hdr; struct channel *chann; char signature_req[SMB2_SIGNATURE_SIZE]; char signature[SMB2_CMACAES_SIZE]; struct kvec iov[1]; size_t len; - hdr_org = hdr = work->request_buf; + hdr = smb2_get_msg(work->request_buf); if (work->next_smb2_rcv_hdr_off) hdr = ksmbd_req_buf_next(work); if (!hdr->NextCommand && !work->next_smb2_rcv_hdr_off) - len = be32_to_cpu(hdr_org->smb2_buf_length); + len = get_rfc1002_len(work->request_buf); else if (hdr->NextCommand) len = le32_to_cpu(hdr->NextCommand); else - len = be32_to_cpu(hdr_org->smb2_buf_length) - + len = get_rfc1002_len(work->request_buf) - work->next_smb2_rcv_hdr_off; if (le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) { @@ -8318,8 +8326,7 @@ int smb3_check_sign_req(struct ksmbd_work *work) void smb3_set_sign_rsp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *req_hdr; - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *req_hdr, *hdr; struct channel *chann; char signature[SMB2_CMACAES_SIZE]; struct kvec iov[2]; @@ -8327,18 +8334,19 @@ void smb3_set_sign_rsp(struct ksmbd_work *work) size_t len; char *signing_key; - hdr_org = hdr = work->response_buf; + hdr = smb2_get_msg(work->response_buf); if (work->next_smb2_rsp_hdr_off) hdr = ksmbd_resp_buf_next(work); req_hdr = ksmbd_req_buf_next(work); if (!work->next_smb2_rsp_hdr_off) { - len = get_rfc1002_len(hdr_org); + len = get_rfc1002_len(work->response_buf); if (req_hdr->NextCommand) len = ALIGN(len, 8); } else { - len = get_rfc1002_len(hdr_org) - work->next_smb2_rsp_hdr_off; + len = get_rfc1002_len(work->response_buf) - + work->next_smb2_rsp_hdr_off; len = ALIGN(len, 8); } @@ -8391,7 +8399,7 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE && conn->preauth_info) - ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, + ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, conn->preauth_info->Preauth_HashValue); if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && sess) { @@ -8409,35 +8417,34 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) if (!hash_value) return; } - ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, + ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, hash_value); } } -static void fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, char *old_buf, - __le16 cipher_type) +static void fill_transform_hdr(void *tr_buf, char *old_buf, __le16 cipher_type) { - struct smb2_hdr *hdr = (struct smb2_hdr *)old_buf; + struct smb2_transform_hdr *tr_hdr = tr_buf + 4; + struct smb2_hdr *hdr = smb2_get_msg(old_buf); unsigned int orig_len = get_rfc1002_len(old_buf); - memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr)); + memset(tr_buf, 0, sizeof(struct smb2_transform_hdr) + 4); tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM; tr_hdr->OriginalMessageSize = cpu_to_le32(orig_len); - tr_hdr->Flags = cpu_to_le16(0x01); + tr_hdr->Flags = cpu_to_le16(TRANSFORM_FLAG_ENCRYPTED); if (cipher_type == SMB2_ENCRYPTION_AES128_GCM || cipher_type == SMB2_ENCRYPTION_AES256_GCM) get_random_bytes(&tr_hdr->Nonce, SMB3_AES_GCM_NONCE); else get_random_bytes(&tr_hdr->Nonce, SMB3_AES_CCM_NONCE); memcpy(&tr_hdr->SessionId, &hdr->SessionId, 8); - inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - 4); - inc_rfc1001_len(tr_hdr, orig_len); + inc_rfc1001_len(tr_buf, sizeof(struct smb2_transform_hdr)); + inc_rfc1001_len(tr_buf, orig_len); } int smb3_encrypt_resp(struct ksmbd_work *work) { char *buf = work->response_buf; - struct smb2_transform_hdr *tr_hdr; struct kvec iov[3]; int rc = -ENOMEM; int buf_size = 0, rq_nvec = 2 + (work->aux_payload_sz ? 1 : 0); @@ -8445,15 +8452,15 @@ int smb3_encrypt_resp(struct ksmbd_work *work) if (ARRAY_SIZE(iov) < rq_nvec) return -ENOMEM; - tr_hdr = kzalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL); - if (!tr_hdr) + work->tr_buf = kzalloc(sizeof(struct smb2_transform_hdr) + 4, GFP_KERNEL); + if (!work->tr_buf) return rc; /* fill transform header */ - fill_transform_hdr(tr_hdr, buf, work->conn->cipher_type); + fill_transform_hdr(work->tr_buf, buf, work->conn->cipher_type); - iov[0].iov_base = tr_hdr; - iov[0].iov_len = sizeof(struct smb2_transform_hdr); + iov[0].iov_base = work->tr_buf; + iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; buf_size += iov[0].iov_len - 4; iov[1].iov_base = buf + 4; @@ -8473,15 +8480,14 @@ int smb3_encrypt_resp(struct ksmbd_work *work) return rc; memmove(buf, iov[1].iov_base, iov[1].iov_len); - tr_hdr->smb2_buf_length = cpu_to_be32(buf_size); - work->tr_buf = tr_hdr; + *(__be32 *)work->tr_buf = cpu_to_be32(buf_size); return rc; } bool smb3_is_transform_hdr(void *buf) { - struct smb2_transform_hdr *trhdr = buf; + struct smb2_transform_hdr *trhdr = smb2_get_msg(buf); return trhdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM; } @@ -8491,12 +8497,10 @@ int smb3_decrypt_req(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess; char *buf = work->request_buf; - struct smb2_hdr *hdr; unsigned int pdu_length = get_rfc1002_len(buf); struct kvec iov[2]; - int buf_data_size = pdu_length + 4 - - sizeof(struct smb2_transform_hdr); - struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf; + int buf_data_size = pdu_length - sizeof(struct smb2_transform_hdr); + struct smb2_transform_hdr *tr_hdr = smb2_get_msg(buf); int rc = 0; if (buf_data_size < sizeof(struct smb2_hdr)) { @@ -8518,16 +8522,15 @@ int smb3_decrypt_req(struct ksmbd_work *work) } iov[0].iov_base = buf; - iov[0].iov_len = sizeof(struct smb2_transform_hdr); - iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr); + iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; + iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr) + 4; iov[1].iov_len = buf_data_size; rc = ksmbd_crypt_message(conn, iov, 2, 0); if (rc) return rc; memmove(buf + 4, iov[1].iov_base, buf_data_size); - hdr = (struct smb2_hdr *)buf; - hdr->smb2_buf_length = cpu_to_be32(buf_data_size); + *(__be32 *)buf = cpu_to_be32(buf_data_size); return rc; } @@ -8535,7 +8538,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *rsp = work->response_buf; + struct smb2_hdr *rsp = smb2_get_msg(work->response_buf); if (conn->dialect < SMB30_PROT_ID) return false; diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index ff5a2f01d34a..4a3e4339d4c4 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -10,60 +10,6 @@ #include "ntlmssp.h" #include "smbacl.h" -/* - * Note that, due to trying to use names similar to the protocol specifications, - * there are many mixed case field names in the structures below. Although - * this does not match typical Linux kernel style, it is necessary to be - * able to match against the protocol specfication. - * - * SMB2 commands - * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses - * (ie no useful data other than the SMB error code itself) and are marked such. - * Knowing this helps avoid response buffer allocations and copy in some cases. - */ - -/* List of commands in host endian */ -#define SMB2_NEGOTIATE_HE 0x0000 -#define SMB2_SESSION_SETUP_HE 0x0001 -#define SMB2_LOGOFF_HE 0x0002 /* trivial request/resp */ -#define SMB2_TREE_CONNECT_HE 0x0003 -#define SMB2_TREE_DISCONNECT_HE 0x0004 /* trivial req/resp */ -#define SMB2_CREATE_HE 0x0005 -#define SMB2_CLOSE_HE 0x0006 -#define SMB2_FLUSH_HE 0x0007 /* trivial resp */ -#define SMB2_READ_HE 0x0008 -#define SMB2_WRITE_HE 0x0009 -#define SMB2_LOCK_HE 0x000A -#define SMB2_IOCTL_HE 0x000B -#define SMB2_CANCEL_HE 0x000C -#define SMB2_ECHO_HE 0x000D -#define SMB2_QUERY_DIRECTORY_HE 0x000E -#define SMB2_CHANGE_NOTIFY_HE 0x000F -#define SMB2_QUERY_INFO_HE 0x0010 -#define SMB2_SET_INFO_HE 0x0011 -#define SMB2_OPLOCK_BREAK_HE 0x0012 - -/* The same list in little endian */ -#define SMB2_NEGOTIATE cpu_to_le16(SMB2_NEGOTIATE_HE) -#define SMB2_SESSION_SETUP cpu_to_le16(SMB2_SESSION_SETUP_HE) -#define SMB2_LOGOFF cpu_to_le16(SMB2_LOGOFF_HE) -#define SMB2_TREE_CONNECT cpu_to_le16(SMB2_TREE_CONNECT_HE) -#define SMB2_TREE_DISCONNECT cpu_to_le16(SMB2_TREE_DISCONNECT_HE) -#define SMB2_CREATE cpu_to_le16(SMB2_CREATE_HE) -#define SMB2_CLOSE cpu_to_le16(SMB2_CLOSE_HE) -#define SMB2_FLUSH cpu_to_le16(SMB2_FLUSH_HE) -#define SMB2_READ cpu_to_le16(SMB2_READ_HE) -#define SMB2_WRITE cpu_to_le16(SMB2_WRITE_HE) -#define SMB2_LOCK cpu_to_le16(SMB2_LOCK_HE) -#define SMB2_IOCTL cpu_to_le16(SMB2_IOCTL_HE) -#define SMB2_CANCEL cpu_to_le16(SMB2_CANCEL_HE) -#define SMB2_ECHO cpu_to_le16(SMB2_ECHO_HE) -#define SMB2_QUERY_DIRECTORY cpu_to_le16(SMB2_QUERY_DIRECTORY_HE) -#define SMB2_CHANGE_NOTIFY cpu_to_le16(SMB2_CHANGE_NOTIFY_HE) -#define SMB2_QUERY_INFO cpu_to_le16(SMB2_QUERY_INFO_HE) -#define SMB2_SET_INFO cpu_to_le16(SMB2_SET_INFO_HE) -#define SMB2_OPLOCK_BREAK cpu_to_le16(SMB2_OPLOCK_BREAK_HE) - /*Create Action Flags*/ #define FILE_SUPERSEDED 0x00000000 #define FILE_OPENED 0x00000001 @@ -96,9 +42,6 @@ /* SMB2 Max Credits */ #define SMB2_MAX_CREDITS 8192 -#define SMB2_CLIENT_GUID_SIZE 16 -#define SMB2_CREATE_GUID_SIZE 16 - /* Maximum buffer size value we can send with 1 credit */ #define SMB2_MAX_BUFFER_SIZE 65536 @@ -107,9 +50,6 @@ /* BB FIXME - analyze following length BB */ #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ -#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) /* 'B''M''S' */ -#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) - #define SMB21_DEFAULT_IOSIZE (1024 * 1024) #define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024) #define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) @@ -117,78 +57,6 @@ #define SMB3_MAX_IOSIZE (8 * 1024 * 1024) /* - * SMB2 Header Definition - * - * "MBZ" : Must be Zero - * "BB" : BugBug, Something to check/review/analyze later - * "PDU" : "Protocol Data Unit" (ie a network "frame") - * - */ - -#define __SMB2_HEADER_STRUCTURE_SIZE 64 -#define SMB2_HEADER_STRUCTURE_SIZE \ - cpu_to_le16(__SMB2_HEADER_STRUCTURE_SIZE) - -struct smb2_hdr { - __be32 smb2_buf_length; /* big endian on wire */ - /* - * length is only two or three bytes - with - * one or two byte type preceding it that MBZ - */ - __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */ - __le16 StructureSize; /* 64 */ - __le16 CreditCharge; /* MBZ */ - __le32 Status; /* Error from server */ - __le16 Command; - __le16 CreditRequest; /* CreditResponse */ - __le32 Flags; - __le32 NextCommand; - __le64 MessageId; - union { - struct { - __le32 ProcessId; - __le32 TreeId; - } __packed SyncId; - __le64 AsyncId; - } __packed Id; - __le64 SessionId; - __u8 Signature[16]; -} __packed; - -struct smb2_pdu { - struct smb2_hdr hdr; - __le16 StructureSize2; /* size of wct area (varies, request specific) */ -} __packed; - -#define SMB3_AES_CCM_NONCE 11 -#define SMB3_AES_GCM_NONCE 12 - -struct smb2_transform_hdr { - __be32 smb2_buf_length; /* big endian on wire */ - /* - * length is only two or three bytes - with - * one or two byte type preceding it that MBZ - */ - __le32 ProtocolId; /* 0xFD 'S' 'M' 'B' */ - __u8 Signature[16]; - __u8 Nonce[16]; - __le32 OriginalMessageSize; - __u16 Reserved1; - __le16 Flags; /* EncryptionAlgorithm */ - __le64 SessionId; -} __packed; - -/* - * SMB2 flag definitions - */ -#define SMB2_FLAGS_SERVER_TO_REDIR cpu_to_le32(0x00000001) -#define SMB2_FLAGS_ASYNC_COMMAND cpu_to_le32(0x00000002) -#define SMB2_FLAGS_RELATED_OPERATIONS cpu_to_le32(0x00000004) -#define SMB2_FLAGS_SIGNED cpu_to_le32(0x00000008) -#define SMB2_FLAGS_DFS_OPERATIONS cpu_to_le32(0x10000000) -#define SMB2_FLAGS_REPLAY_OPERATIONS cpu_to_le32(0x20000000) - -/* * Definitions for SMB2 Protocol Data Units (network frames) * * See MS-SMB2.PDF specification for protocol details. @@ -209,425 +77,30 @@ struct smb2_err_rsp { __u8 ErrorData[1]; /* variable length */ } __packed; -struct smb2_negotiate_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 36 */ - __le16 DialectCount; - __le16 SecurityMode; - __le16 Reserved; /* MBZ */ - __le32 Capabilities; - __u8 ClientGUID[SMB2_CLIENT_GUID_SIZE]; - /* In SMB3.02 and earlier next three were MBZ le64 ClientStartTime */ - __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */ - __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */ - __le16 Reserved2; - __le16 Dialects[1]; /* One dialect (vers=) at a time for now */ -} __packed; - -/* SecurityMode flags */ -#define SMB2_NEGOTIATE_SIGNING_ENABLED_LE cpu_to_le16(0x0001) -#define SMB2_NEGOTIATE_SIGNING_REQUIRED 0x0002 -#define SMB2_NEGOTIATE_SIGNING_REQUIRED_LE cpu_to_le16(0x0002) -/* Capabilities flags */ -#define SMB2_GLOBAL_CAP_DFS 0x00000001 -#define SMB2_GLOBAL_CAP_LEASING 0x00000002 /* Resp only New to SMB2.1 */ -#define SMB2_GLOBAL_CAP_LARGE_MTU 0X00000004 /* Resp only New to SMB2.1 */ -#define SMB2_GLOBAL_CAP_MULTI_CHANNEL 0x00000008 /* New to SMB3 */ -#define SMB2_GLOBAL_CAP_PERSISTENT_HANDLES 0x00000010 /* New to SMB3 */ -#define SMB2_GLOBAL_CAP_DIRECTORY_LEASING 0x00000020 /* New to SMB3 */ -#define SMB2_GLOBAL_CAP_ENCRYPTION 0x00000040 /* New to SMB3 */ -/* Internal types */ -#define SMB2_NT_FIND 0x00100000 -#define SMB2_LARGE_FILES 0x00200000 - -#define SMB311_SALT_SIZE 32 -/* Hash Algorithm Types */ -#define SMB2_PREAUTH_INTEGRITY_SHA512 cpu_to_le16(0x0001) - -#define PREAUTH_HASHVALUE_SIZE 64 - struct preauth_integrity_info { /* PreAuth integrity Hash ID */ __le16 Preauth_HashId; /* PreAuth integrity Hash Value */ - __u8 Preauth_HashValue[PREAUTH_HASHVALUE_SIZE]; + __u8 Preauth_HashValue[SMB2_PREAUTH_HASH_SIZE]; }; -/* offset is sizeof smb2_negotiate_rsp - 4 but rounded up to 8 bytes. */ +/* offset is sizeof smb2_negotiate_rsp but rounded up to 8 bytes. */ #ifdef CONFIG_SMB_SERVER_KERBEROS5 -/* sizeof(struct smb2_negotiate_rsp) - 4 = +/* sizeof(struct smb2_negotiate_rsp) = * header(64) + response(64) + GSS_LENGTH(96) + GSS_PADDING(0) */ #define OFFSET_OF_NEG_CONTEXT 0xe0 #else -/* sizeof(struct smb2_negotiate_rsp) - 4 = +/* sizeof(struct smb2_negotiate_rsp) = * header(64) + response(64) + GSS_LENGTH(74) + GSS_PADDING(6) */ #define OFFSET_OF_NEG_CONTEXT 0xd0 #endif -#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1) -#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2) -#define SMB2_COMPRESSION_CAPABILITIES cpu_to_le16(3) -#define SMB2_NETNAME_NEGOTIATE_CONTEXT_ID cpu_to_le16(5) -#define SMB2_SIGNING_CAPABILITIES cpu_to_le16(8) -#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100) - -struct smb2_neg_context { - __le16 ContextType; - __le16 DataLength; - __le32 Reserved; - /* Followed by array of data */ -} __packed; - -struct smb2_preauth_neg_context { - __le16 ContextType; /* 1 */ - __le16 DataLength; - __le32 Reserved; - __le16 HashAlgorithmCount; /* 1 */ - __le16 SaltLength; - __le16 HashAlgorithms; /* HashAlgorithms[0] since only one defined */ - __u8 Salt[SMB311_SALT_SIZE]; -} __packed; - -/* Encryption Algorithms Ciphers */ -#define SMB2_ENCRYPTION_AES128_CCM cpu_to_le16(0x0001) -#define SMB2_ENCRYPTION_AES128_GCM cpu_to_le16(0x0002) -#define SMB2_ENCRYPTION_AES256_CCM cpu_to_le16(0x0003) -#define SMB2_ENCRYPTION_AES256_GCM cpu_to_le16(0x0004) - -struct smb2_encryption_neg_context { - __le16 ContextType; /* 2 */ - __le16 DataLength; - __le32 Reserved; - /* CipherCount usally 2, but can be 3 when AES256-GCM enabled */ - __le16 CipherCount; /* AES-128-GCM and AES-128-CCM by default */ - __le16 Ciphers[]; -} __packed; - -#define SMB3_COMPRESS_NONE cpu_to_le16(0x0000) -#define SMB3_COMPRESS_LZNT1 cpu_to_le16(0x0001) -#define SMB3_COMPRESS_LZ77 cpu_to_le16(0x0002) -#define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003) - -struct smb2_compression_ctx { - __le16 ContextType; /* 3 */ - __le16 DataLength; - __le32 Reserved; - __le16 CompressionAlgorithmCount; - __u16 Padding; - __le32 Reserved1; - __le16 CompressionAlgorithms[]; -} __packed; - -#define POSIX_CTXT_DATA_LEN 16 -struct smb2_posix_neg_context { - __le16 ContextType; /* 0x100 */ - __le16 DataLength; - __le32 Reserved; - __u8 Name[16]; /* POSIX ctxt GUID 93AD25509CB411E7B42383DE968BCD7C */ -} __packed; - -struct smb2_netname_neg_context { - __le16 ContextType; /* 0x100 */ - __le16 DataLength; - __le32 Reserved; - __le16 NetName[]; /* hostname of target converted to UCS-2 */ -} __packed; - -/* Signing algorithms */ -#define SIGNING_ALG_HMAC_SHA256 cpu_to_le16(0) -#define SIGNING_ALG_AES_CMAC cpu_to_le16(1) -#define SIGNING_ALG_AES_GMAC cpu_to_le16(2) - -struct smb2_signing_capabilities { - __le16 ContextType; /* 8 */ - __le16 DataLength; - __le32 Reserved; - __le16 SigningAlgorithmCount; - __le16 SigningAlgorithms[]; -} __packed; - -struct smb2_negotiate_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 65 */ - __le16 SecurityMode; - __le16 DialectRevision; - __le16 NegotiateContextCount; /* Prior to SMB3.1.1 was Reserved & MBZ */ - __u8 ServerGUID[16]; - __le32 Capabilities; - __le32 MaxTransactSize; - __le32 MaxReadSize; - __le32 MaxWriteSize; - __le64 SystemTime; /* MBZ */ - __le64 ServerStartTime; - __le16 SecurityBufferOffset; - __le16 SecurityBufferLength; - __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */ - __u8 Buffer[1]; /* variable length GSS security buffer */ -} __packed; - -/* Flags */ -#define SMB2_SESSION_REQ_FLAG_BINDING 0x01 -#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA 0x04 - #define SMB2_SESSION_EXPIRED (0) #define SMB2_SESSION_IN_PROGRESS BIT(0) #define SMB2_SESSION_VALID BIT(1) -/* Flags */ -#define SMB2_SESSION_REQ_FLAG_BINDING 0x01 -#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA 0x04 - -struct smb2_sess_setup_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 25 */ - __u8 Flags; - __u8 SecurityMode; - __le32 Capabilities; - __le32 Channel; - __le16 SecurityBufferOffset; - __le16 SecurityBufferLength; - __le64 PreviousSessionId; - __u8 Buffer[1]; /* variable length GSS security buffer */ -} __packed; - -/* Flags/Reserved for SMB3.1.1 */ -#define SMB2_SHAREFLAG_CLUSTER_RECONNECT 0x0001 - -/* Currently defined SessionFlags */ -#define SMB2_SESSION_FLAG_IS_GUEST_LE cpu_to_le16(0x0001) -#define SMB2_SESSION_FLAG_IS_NULL_LE cpu_to_le16(0x0002) -#define SMB2_SESSION_FLAG_ENCRYPT_DATA_LE cpu_to_le16(0x0004) -struct smb2_sess_setup_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 SessionFlags; - __le16 SecurityBufferOffset; - __le16 SecurityBufferLength; - __u8 Buffer[1]; /* variable length GSS security buffer */ -} __packed; - -struct smb2_logoff_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_logoff_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_tree_connect_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 Reserved; /* Flags in SMB3.1.1 */ - __le16 PathOffset; - __le16 PathLength; - __u8 Buffer[1]; /* variable length */ -} __packed; - -struct smb2_tree_connect_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 16 */ - __u8 ShareType; /* see below */ - __u8 Reserved; - __le32 ShareFlags; /* see below */ - __le32 Capabilities; /* see below */ - __le32 MaximalAccess; -} __packed; - -/* Possible ShareType values */ -#define SMB2_SHARE_TYPE_DISK 0x01 -#define SMB2_SHARE_TYPE_PIPE 0x02 -#define SMB2_SHARE_TYPE_PRINT 0x03 - -/* - * Possible ShareFlags - exactly one and only one of the first 4 caching flags - * must be set (any of the remaining, SHI1005, flags may be set individually - * or in combination. - */ -#define SMB2_SHAREFLAG_MANUAL_CACHING 0x00000000 -#define SMB2_SHAREFLAG_AUTO_CACHING 0x00000010 -#define SMB2_SHAREFLAG_VDO_CACHING 0x00000020 -#define SMB2_SHAREFLAG_NO_CACHING 0x00000030 -#define SHI1005_FLAGS_DFS 0x00000001 -#define SHI1005_FLAGS_DFS_ROOT 0x00000002 -#define SHI1005_FLAGS_RESTRICT_EXCLUSIVE_OPENS 0x00000100 -#define SHI1005_FLAGS_FORCE_SHARED_DELETE 0x00000200 -#define SHI1005_FLAGS_ALLOW_NAMESPACE_CACHING 0x00000400 -#define SHI1005_FLAGS_ACCESS_BASED_DIRECTORY_ENUM 0x00000800 -#define SHI1005_FLAGS_FORCE_LEVELII_OPLOCK 0x00001000 -#define SHI1005_FLAGS_ENABLE_HASH 0x00002000 - -/* Possible share capabilities */ -#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) - -struct smb2_tree_disconnect_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_tree_disconnect_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -#define ATTR_READONLY_LE cpu_to_le32(ATTR_READONLY) -#define ATTR_HIDDEN_LE cpu_to_le32(ATTR_HIDDEN) -#define ATTR_SYSTEM_LE cpu_to_le32(ATTR_SYSTEM) -#define ATTR_DIRECTORY_LE cpu_to_le32(ATTR_DIRECTORY) -#define ATTR_ARCHIVE_LE cpu_to_le32(ATTR_ARCHIVE) -#define ATTR_NORMAL_LE cpu_to_le32(ATTR_NORMAL) -#define ATTR_TEMPORARY_LE cpu_to_le32(ATTR_TEMPORARY) -#define ATTR_SPARSE_FILE_LE cpu_to_le32(ATTR_SPARSE) -#define ATTR_REPARSE_POINT_LE cpu_to_le32(ATTR_REPARSE) -#define ATTR_COMPRESSED_LE cpu_to_le32(ATTR_COMPRESSED) -#define ATTR_OFFLINE_LE cpu_to_le32(ATTR_OFFLINE) -#define ATTR_NOT_CONTENT_INDEXED_LE cpu_to_le32(ATTR_NOT_CONTENT_INDEXED) -#define ATTR_ENCRYPTED_LE cpu_to_le32(ATTR_ENCRYPTED) -#define ATTR_INTEGRITY_STREAML_LE cpu_to_le32(0x00008000) -#define ATTR_NO_SCRUB_DATA_LE cpu_to_le32(0x00020000) -#define ATTR_MASK_LE cpu_to_le32(0x00007FB7) - -/* Oplock levels */ -#define SMB2_OPLOCK_LEVEL_NONE 0x00 -#define SMB2_OPLOCK_LEVEL_II 0x01 -#define SMB2_OPLOCK_LEVEL_EXCLUSIVE 0x08 -#define SMB2_OPLOCK_LEVEL_BATCH 0x09 -#define SMB2_OPLOCK_LEVEL_LEASE 0xFF -/* Non-spec internal type */ -#define SMB2_OPLOCK_LEVEL_NOCHANGE 0x99 - -/* Desired Access Flags */ -#define FILE_READ_DATA_LE cpu_to_le32(0x00000001) -#define FILE_LIST_DIRECTORY_LE cpu_to_le32(0x00000001) -#define FILE_WRITE_DATA_LE cpu_to_le32(0x00000002) -#define FILE_ADD_FILE_LE cpu_to_le32(0x00000002) -#define FILE_APPEND_DATA_LE cpu_to_le32(0x00000004) -#define FILE_ADD_SUBDIRECTORY_LE cpu_to_le32(0x00000004) -#define FILE_READ_EA_LE cpu_to_le32(0x00000008) -#define FILE_WRITE_EA_LE cpu_to_le32(0x00000010) -#define FILE_EXECUTE_LE cpu_to_le32(0x00000020) -#define FILE_TRAVERSE_LE cpu_to_le32(0x00000020) -#define FILE_DELETE_CHILD_LE cpu_to_le32(0x00000040) -#define FILE_READ_ATTRIBUTES_LE cpu_to_le32(0x00000080) -#define FILE_WRITE_ATTRIBUTES_LE cpu_to_le32(0x00000100) -#define FILE_DELETE_LE cpu_to_le32(0x00010000) -#define FILE_READ_CONTROL_LE cpu_to_le32(0x00020000) -#define FILE_WRITE_DAC_LE cpu_to_le32(0x00040000) -#define FILE_WRITE_OWNER_LE cpu_to_le32(0x00080000) -#define FILE_SYNCHRONIZE_LE cpu_to_le32(0x00100000) -#define FILE_ACCESS_SYSTEM_SECURITY_LE cpu_to_le32(0x01000000) -#define FILE_MAXIMAL_ACCESS_LE cpu_to_le32(0x02000000) -#define FILE_GENERIC_ALL_LE cpu_to_le32(0x10000000) -#define FILE_GENERIC_EXECUTE_LE cpu_to_le32(0x20000000) -#define FILE_GENERIC_WRITE_LE cpu_to_le32(0x40000000) -#define FILE_GENERIC_READ_LE cpu_to_le32(0x80000000) -#define DESIRED_ACCESS_MASK cpu_to_le32(0xF21F01FF) - -/* ShareAccess Flags */ -#define FILE_SHARE_READ_LE cpu_to_le32(0x00000001) -#define FILE_SHARE_WRITE_LE cpu_to_le32(0x00000002) -#define FILE_SHARE_DELETE_LE cpu_to_le32(0x00000004) -#define FILE_SHARE_ALL_LE cpu_to_le32(0x00000007) - -/* CreateDisposition Flags */ -#define FILE_SUPERSEDE_LE cpu_to_le32(0x00000000) -#define FILE_OPEN_LE cpu_to_le32(0x00000001) -#define FILE_CREATE_LE cpu_to_le32(0x00000002) -#define FILE_OPEN_IF_LE cpu_to_le32(0x00000003) -#define FILE_OVERWRITE_LE cpu_to_le32(0x00000004) -#define FILE_OVERWRITE_IF_LE cpu_to_le32(0x00000005) -#define FILE_CREATE_MASK_LE cpu_to_le32(0x00000007) - -#define FILE_READ_DESIRED_ACCESS_LE (FILE_READ_DATA_LE | \ - FILE_READ_EA_LE | \ - FILE_GENERIC_READ_LE) -#define FILE_WRITE_DESIRE_ACCESS_LE (FILE_WRITE_DATA_LE | \ - FILE_APPEND_DATA_LE | \ - FILE_WRITE_EA_LE | \ - FILE_WRITE_ATTRIBUTES_LE | \ - FILE_GENERIC_WRITE_LE) - -/* Impersonation Levels */ -#define IL_ANONYMOUS_LE cpu_to_le32(0x00000000) -#define IL_IDENTIFICATION_LE cpu_to_le32(0x00000001) -#define IL_IMPERSONATION_LE cpu_to_le32(0x00000002) -#define IL_DELEGATE_LE cpu_to_le32(0x00000003) - -/* Create Context Values */ -#define SMB2_CREATE_EA_BUFFER "ExtA" /* extended attributes */ -#define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ -#define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" -#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" -#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" -#define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" -#define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" -#define SMB2_CREATE_REQUEST_LEASE "RqLs" -#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 "DH2Q" -#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C" -#define SMB2_CREATE_APP_INSTANCE_ID "\x45\xBC\xA6\x6A\xEF\xA7\xF7\x4A\x90\x08\xFA\x46\x2E\x14\x4D\x74" - #define SMB2_CREATE_APP_INSTANCE_VERSION "\xB9\x82\xD0\xB7\x3B\x56\x07\x4F\xA0\x7B\x52\x4A\x81\x16\xA0\x10" -#define SVHDX_OPEN_DEVICE_CONTEXT 0x83CE6F1AD851E0986E34401CC9BCFCE9 -#define SMB2_CREATE_TAG_POSIX "\x93\xAD\x25\x50\x9C\xB4\x11\xE7\xB4\x23\x83\xDE\x96\x8B\xCD\x7C" - -struct smb2_create_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 57 */ - __u8 SecurityFlags; - __u8 RequestedOplockLevel; - __le32 ImpersonationLevel; - __le64 SmbCreateFlags; - __le64 Reserved; - __le32 DesiredAccess; - __le32 FileAttributes; - __le32 ShareAccess; - __le32 CreateDisposition; - __le32 CreateOptions; - __le16 NameOffset; - __le16 NameLength; - __le32 CreateContextsOffset; - __le32 CreateContextsLength; - __u8 Buffer[0]; -} __packed; - -struct smb2_create_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 89 */ - __u8 OplockLevel; - __u8 Reserved; - __le32 CreateAction; - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 AllocationSize; - __le64 EndofFile; - __le32 FileAttributes; - __le32 Reserved2; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 CreateContextsOffset; - __le32 CreateContextsLength; - __u8 Buffer[1]; -} __packed; - -struct create_context { - __le32 Next; - __le16 NameOffset; - __le16 NameLength; - __le16 Reserved; - __le16 DataOffset; - __le32 DataLength; - __u8 Buffer[0]; -} __packed; - struct create_durable_req_v2 { struct create_context ccontext; __u8 Name[8]; @@ -743,22 +216,21 @@ struct create_posix_rsp { #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) +#define SMB2_LEASE_KEY_SIZE 16 + struct lease_context { - __le64 LeaseKeyLow; - __le64 LeaseKeyHigh; + __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; __le32 LeaseFlags; __le64 LeaseDuration; } __packed; struct lease_context_v2 { - __le64 LeaseKeyLow; - __le64 LeaseKeyHigh; + __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; __le32 LeaseFlags; __le64 LeaseDuration; - __le64 ParentLeaseKeyLow; - __le64 ParentLeaseKeyHigh; + __u8 ParentLeaseKey[SMB2_LEASE_KEY_SIZE]; __le16 Epoch; __le16 Reserved; } __packed; @@ -776,114 +248,12 @@ struct create_lease_v2 { __u8 Pad[4]; } __packed; -/* Currently defined values for close flags */ -#define SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB cpu_to_le16(0x0001) -struct smb2_close_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 24 */ - __le16 Flags; - __le32 Reserved; - __le64 PersistentFileId; - __le64 VolatileFileId; -} __packed; - -struct smb2_close_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* 60 */ - __le16 Flags; - __le32 Reserved; - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */ - __le64 EndOfFile; - __le32 Attributes; -} __packed; - -struct smb2_flush_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 24 */ - __le16 Reserved1; - __le32 Reserved2; - __le64 PersistentFileId; - __le64 VolatileFileId; -} __packed; - -struct smb2_flush_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; - __le16 Reserved; -} __packed; - struct smb2_buffer_desc_v1 { __le64 offset; __le32 token; __le32 length; } __packed; -#define SMB2_CHANNEL_NONE cpu_to_le32(0x00000000) -#define SMB2_CHANNEL_RDMA_V1 cpu_to_le32(0x00000001) -#define SMB2_CHANNEL_RDMA_V1_INVALIDATE cpu_to_le32(0x00000002) - -struct smb2_read_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 49 */ - __u8 Padding; /* offset from start of SMB2 header to place read */ - __u8 Reserved; - __le32 Length; - __le64 Offset; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 MinimumCount; - __le32 Channel; /* Reserved MBZ */ - __le32 RemainingBytes; - __le16 ReadChannelInfoOffset; /* Reserved MBZ */ - __le16 ReadChannelInfoLength; /* Reserved MBZ */ - __u8 Buffer[1]; -} __packed; - -struct smb2_read_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 17 */ - __u8 DataOffset; - __u8 Reserved; - __le32 DataLength; - __le32 DataRemaining; - __u32 Reserved2; - __u8 Buffer[1]; -} __packed; - -/* For write request Flags field below the following flag is defined: */ -#define SMB2_WRITEFLAG_WRITE_THROUGH 0x00000001 - -struct smb2_write_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 49 */ - __le16 DataOffset; /* offset from start of SMB2 header to write data */ - __le32 Length; - __le64 Offset; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 Channel; /* Reserved MBZ */ - __le32 RemainingBytes; - __le16 WriteChannelInfoOffset; /* Reserved MBZ */ - __le16 WriteChannelInfoLength; /* Reserved MBZ */ - __le32 Flags; - __u8 Buffer[1]; -} __packed; - -struct smb2_write_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 17 */ - __u8 DataOffset; - __u8 Reserved; - __le32 DataLength; - __le32 DataRemaining; - __u32 Reserved2; - __u8 Buffer[1]; -} __packed; - #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 struct duplicate_extents_to_file { @@ -1033,43 +403,6 @@ struct reparse_data_buffer { __u8 DataBuffer[]; /* Variable Length */ } __packed; -/* Completion Filter flags for Notify */ -#define FILE_NOTIFY_CHANGE_FILE_NAME 0x00000001 -#define FILE_NOTIFY_CHANGE_DIR_NAME 0x00000002 -#define FILE_NOTIFY_CHANGE_NAME 0x00000003 -#define FILE_NOTIFY_CHANGE_ATTRIBUTES 0x00000004 -#define FILE_NOTIFY_CHANGE_SIZE 0x00000008 -#define FILE_NOTIFY_CHANGE_LAST_WRITE 0x00000010 -#define FILE_NOTIFY_CHANGE_LAST_ACCESS 0x00000020 -#define FILE_NOTIFY_CHANGE_CREATION 0x00000040 -#define FILE_NOTIFY_CHANGE_EA 0x00000080 -#define FILE_NOTIFY_CHANGE_SECURITY 0x00000100 -#define FILE_NOTIFY_CHANGE_STREAM_NAME 0x00000200 -#define FILE_NOTIFY_CHANGE_STREAM_SIZE 0x00000400 -#define FILE_NOTIFY_CHANGE_STREAM_WRITE 0x00000800 - -/* Flags */ -#define SMB2_WATCH_TREE 0x0001 - -struct smb2_notify_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 32 */ - __le16 Flags; - __le32 OutputBufferLength; - __le64 PersistentFileId; - __le64 VolatileFileId; - __u32 CompletionFileter; - __u32 Reserved; -} __packed; - -struct smb2_notify_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 OutputBufferOffset; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - /* SMB2 Notify Action Flags */ #define FILE_ACTION_ADDED 0x00000001 #define FILE_ACTION_REMOVED 0x00000002 @@ -1528,7 +861,7 @@ struct smb2_file_pos_info { __le64 CurrentByteOffset; } __packed; -#define FILE_MODE_INFO_MASK cpu_to_le32(0x0000103e) +#define FILE_MODE_INFO_MASK cpu_to_le32(0x0000100e) struct smb2_file_mode_info { __le32 Mode; @@ -1705,4 +1038,13 @@ int smb2_ioctl(struct ksmbd_work *work); int smb2_oplock_break(struct ksmbd_work *work); int smb2_notify(struct ksmbd_work *ksmbd_work); +/* + * Get the body of the smb2 message excluding the 4 byte rfc1002 headers + * from request/response buffer. + */ +static inline void *smb2_get_msg(void *buf) +{ + return buf + 4; +} + #endif /* _SMB2PDU_H */ diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 707490ab1f4c..ef7f42b0290a 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -132,7 +132,7 @@ int ksmbd_lookup_protocol_idx(char *str) */ int ksmbd_verify_smb_message(struct ksmbd_work *work) { - struct smb2_hdr *smb2_hdr = work->request_buf + work->next_smb2_rcv_hdr_off; + struct smb2_hdr *smb2_hdr = ksmbd_req_buf_next(work); struct smb_hdr *hdr; if (smb2_hdr->ProtocolId == SMB2_PROTO_NUMBER) @@ -239,14 +239,14 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count) static int ksmbd_negotiate_smb_dialect(void *buf) { int smb_buf_length = get_rfc1002_len(buf); - __le32 proto = ((struct smb2_hdr *)buf)->ProtocolId; + __le32 proto = ((struct smb2_hdr *)smb2_get_msg(buf))->ProtocolId; if (proto == SMB2_PROTO_NUMBER) { struct smb2_negotiate_req *req; int smb2_neg_size = - offsetof(struct smb2_negotiate_req, Dialects) - 4; + offsetof(struct smb2_negotiate_req, Dialects); - req = (struct smb2_negotiate_req *)buf; + req = (struct smb2_negotiate_req *)smb2_get_msg(buf); if (smb2_neg_size > smb_buf_length) goto err_out; @@ -445,11 +445,12 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) struct ksmbd_conn *conn = work->conn; int ret; - conn->dialect = ksmbd_negotiate_smb_dialect(work->request_buf); + conn->dialect = + ksmbd_negotiate_smb_dialect(work->request_buf); ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); if (command == SMB2_NEGOTIATE_HE) { - struct smb2_hdr *smb2_hdr = work->request_buf; + struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf); if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) { ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n"); diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index 6e79e7577f6b..50590842b651 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -10,6 +10,7 @@ #include "glob.h" #include "nterr.h" +#include "../smbfs_common/smb2pdu.h" #include "smb2pdu.h" /* ksmbd's Specific ERRNO */ @@ -32,17 +33,6 @@ #define SMB302_VERSION_STRING "3.02" #define SMB311_VERSION_STRING "3.1.1" -/* Dialects */ -#define SMB10_PROT_ID 0x00 -#define SMB20_PROT_ID 0x0202 -#define SMB21_PROT_ID 0x0210 -/* multi-protocol negotiate request */ -#define SMB2X_PROT_ID 0x02FF -#define SMB30_PROT_ID 0x0300 -#define SMB302_PROT_ID 0x0302 -#define SMB311_PROT_ID 0x0311 -#define BAD_PROT_ID 0xFFFF - #define SMB_ECHO_INTERVAL (60 * HZ) #define CIFS_DEFAULT_IOSIZE (64 * 1024) @@ -59,21 +49,6 @@ /* * File Attribute flags */ -#define ATTR_READONLY 0x0001 -#define ATTR_HIDDEN 0x0002 -#define ATTR_SYSTEM 0x0004 -#define ATTR_VOLUME 0x0008 -#define ATTR_DIRECTORY 0x0010 -#define ATTR_ARCHIVE 0x0020 -#define ATTR_DEVICE 0x0040 -#define ATTR_NORMAL 0x0080 -#define ATTR_TEMPORARY 0x0100 -#define ATTR_SPARSE 0x0200 -#define ATTR_REPARSE 0x0400 -#define ATTR_COMPRESSED 0x0800 -#define ATTR_OFFLINE 0x1000 -#define ATTR_NOT_CONTENT_INDEXED 0x2000 -#define ATTR_ENCRYPTED 0x4000 #define ATTR_POSIX_SEMANTICS 0x01000000 #define ATTR_BACKUP_SEMANTICS 0x02000000 #define ATTR_DELETE_ON_CLOSE 0x04000000 @@ -82,23 +57,6 @@ #define ATTR_NO_BUFFERING 0x20000000 #define ATTR_WRITE_THROUGH 0x80000000 -#define ATTR_READONLY_LE cpu_to_le32(ATTR_READONLY) -#define ATTR_HIDDEN_LE cpu_to_le32(ATTR_HIDDEN) -#define ATTR_SYSTEM_LE cpu_to_le32(ATTR_SYSTEM) -#define ATTR_DIRECTORY_LE cpu_to_le32(ATTR_DIRECTORY) -#define ATTR_ARCHIVE_LE cpu_to_le32(ATTR_ARCHIVE) -#define ATTR_NORMAL_LE cpu_to_le32(ATTR_NORMAL) -#define ATTR_TEMPORARY_LE cpu_to_le32(ATTR_TEMPORARY) -#define ATTR_SPARSE_FILE_LE cpu_to_le32(ATTR_SPARSE) -#define ATTR_REPARSE_POINT_LE cpu_to_le32(ATTR_REPARSE) -#define ATTR_COMPRESSED_LE cpu_to_le32(ATTR_COMPRESSED) -#define ATTR_OFFLINE_LE cpu_to_le32(ATTR_OFFLINE) -#define ATTR_NOT_CONTENT_INDEXED_LE cpu_to_le32(ATTR_NOT_CONTENT_INDEXED) -#define ATTR_ENCRYPTED_LE cpu_to_le32(ATTR_ENCRYPTED) -#define ATTR_INTEGRITY_STREAML_LE cpu_to_le32(0x00008000) -#define ATTR_NO_SCRUB_DATA_LE cpu_to_le32(0x00020000) -#define ATTR_MASK_LE cpu_to_le32(0x00007FB7) - /* List of FileSystemAttributes - see 2.5.1 of MS-FSCC */ #define FILE_SUPPORTS_SPARSE_VDL 0x10000000 /* faster nonsparse extend */ #define FILE_SUPPORTS_BLOCK_REFCOUNTING 0x08000000 /* allow ioctl dup extents */ @@ -160,11 +118,6 @@ /* file_execute, file_read_attributes*/ /* write_dac, and delete. */ -#define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES) -#define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \ - | FILE_WRITE_EA | FILE_WRITE_ATTRIBUTES) -#define FILE_EXEC_RIGHTS (FILE_EXECUTE) - #define SET_FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA \ | FILE_READ_ATTRIBUTES \ | DELETE | READ_CONTROL | WRITE_DAC \ @@ -477,12 +430,6 @@ struct smb_version_cmds { int (*proc)(struct ksmbd_work *swork); }; -static inline size_t -smb2_hdr_size_no_buflen(struct smb_version_values *vals) -{ - return vals->header_size - 4; -} - int ksmbd_min_protocol(void); int ksmbd_max_protocol(void); diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index a2fd5a4d4cd5..7e57cbb0bb35 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -484,7 +484,7 @@ static int smb_direct_check_recvmsg(struct smb_direct_recvmsg *recvmsg) struct smb_direct_data_transfer *req = (struct smb_direct_data_transfer *)recvmsg->packet; struct smb2_hdr *hdr = (struct smb2_hdr *)(recvmsg->packet - + le32_to_cpu(req->data_offset) - 4); + + le32_to_cpu(req->data_offset)); ksmbd_debug(RDMA, "CreditGranted: %u, CreditRequested: %u, DataLength: %u, RemainingDataLength: %u, SMB: %x, Command: %u\n", le16_to_cpu(req->credits_granted), @@ -2043,7 +2043,6 @@ int ksmbd_rdma_destroy(void) smb_direct_listener.cm_id = NULL; if (smb_direct_wq) { - flush_workqueue(smb_direct_wq); destroy_workqueue(smb_direct_wq); smb_direct_wq = NULL; } diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 835b384b0895..19d36393974c 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -1013,7 +1013,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp, loff_t off, loff_t len) { smb_break_all_levII_oplock(work, fp, 1); - if (fp->f_ci->m_fattr & ATTR_SPARSE_FILE_LE) + if (fp->f_ci->m_fattr & FILE_ATTRIBUTE_SPARSE_FILE_LE) return vfs_fallocate(fp->filp, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, off, len); @@ -1624,7 +1624,7 @@ void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat) time = ksmbd_UnixTimeToNT(kstat->ctime); info->ChangeTime = cpu_to_le64(time); - if (ksmbd_kstat->file_attributes & ATTR_DIRECTORY_LE) { + if (ksmbd_kstat->file_attributes & FILE_ATTRIBUTE_DIRECTORY_LE) { info->EndOfFile = 0; info->AllocationSize = 0; } else { @@ -1654,9 +1654,9 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, * or that acl is disable in server's filesystem and the config is yes. */ if (S_ISDIR(ksmbd_kstat->kstat->mode)) - ksmbd_kstat->file_attributes = ATTR_DIRECTORY_LE; + ksmbd_kstat->file_attributes = FILE_ATTRIBUTE_DIRECTORY_LE; else - ksmbd_kstat->file_attributes = ATTR_ARCHIVE_LE; + ksmbd_kstat->file_attributes = FILE_ATTRIBUTE_ARCHIVE_LE; if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS)) { diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index b0d5b8feb4a3..adf94a4f22fa 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -25,48 +25,9 @@ enum { }; /* CreateOptions */ -/* Flag is set, it must not be a file , valid for directory only */ -#define FILE_DIRECTORY_FILE_LE cpu_to_le32(0x00000001) -#define FILE_WRITE_THROUGH_LE cpu_to_le32(0x00000002) -#define FILE_SEQUENTIAL_ONLY_LE cpu_to_le32(0x00000004) - -/* Should not buffer on server*/ -#define FILE_NO_INTERMEDIATE_BUFFERING_LE cpu_to_le32(0x00000008) -/* MBZ */ -#define FILE_SYNCHRONOUS_IO_ALERT_LE cpu_to_le32(0x00000010) -/* MBZ */ -#define FILE_SYNCHRONOUS_IO_NONALERT_LE cpu_to_le32(0x00000020) - -/* Flaf must not be set for directory */ -#define FILE_NON_DIRECTORY_FILE_LE cpu_to_le32(0x00000040) - -/* Should be zero */ #define CREATE_TREE_CONNECTION cpu_to_le32(0x00000080) -#define FILE_COMPLETE_IF_OPLOCKED_LE cpu_to_le32(0x00000100) -#define FILE_NO_EA_KNOWLEDGE_LE cpu_to_le32(0x00000200) -#define FILE_OPEN_REMOTE_INSTANCE cpu_to_le32(0x00000400) - -/** - * Doc says this is obsolete "open for recovery" flag should be zero - * in any case. - */ -#define CREATE_OPEN_FOR_RECOVERY cpu_to_le32(0x00000400) -#define FILE_RANDOM_ACCESS_LE cpu_to_le32(0x00000800) -#define FILE_DELETE_ON_CLOSE_LE cpu_to_le32(0x00001000) -#define FILE_OPEN_BY_FILE_ID_LE cpu_to_le32(0x00002000) -#define FILE_OPEN_FOR_BACKUP_INTENT_LE cpu_to_le32(0x00004000) -#define FILE_NO_COMPRESSION_LE cpu_to_le32(0x00008000) - -/* Should be zero*/ -#define FILE_OPEN_REQUIRING_OPLOCK cpu_to_le32(0x00010000) -#define FILE_DISALLOW_EXCLUSIVE cpu_to_le32(0x00020000) #define FILE_RESERVE_OPFILTER_LE cpu_to_le32(0x00100000) -#define FILE_OPEN_REPARSE_POINT_LE cpu_to_le32(0x00200000) -#define FILE_OPEN_NO_RECALL_LE cpu_to_le32(0x00400000) -/* Should be zero */ -#define FILE_OPEN_FOR_FREE_SPACE_QUERY_LE cpu_to_le32(0x00800000) -#define CREATE_OPTIONS_MASK cpu_to_le32(0x00FFFFFF) #define CREATE_OPTION_READONLY 0x10000000 /* system. NB not sent over wire */ #define CREATE_OPTION_SPECIAL 0x20000000 diff --git a/fs/libfs.c b/fs/libfs.c index 51b4de3b3447..ba7438ab9371 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -448,6 +448,30 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry) } EXPORT_SYMBOL(simple_rmdir); +int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + bool old_is_dir = d_is_dir(old_dentry); + bool new_is_dir = d_is_dir(new_dentry); + + if (old_dir != new_dir && old_is_dir != new_is_dir) { + if (old_is_dir) { + drop_nlink(old_dir); + inc_nlink(new_dir); + } else { + drop_nlink(new_dir); + inc_nlink(old_dir); + } + } + old_dir->i_ctime = old_dir->i_mtime = + new_dir->i_ctime = new_dir->i_mtime = + d_inode(old_dentry)->i_ctime = + d_inode(new_dentry)->i_ctime = current_time(old_dir); + + return 0; +} +EXPORT_SYMBOL_GPL(simple_rename_exchange); + int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -455,9 +479,12 @@ int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir, struct inode *inode = d_inode(old_dentry); int they_are_dirs = d_is_dir(old_dentry); - if (flags & ~RENAME_NOREPLACE) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; + if (flags & RENAME_EXCHANGE) + return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); + if (!simple_empty(new_dentry)) return -ENOTEMPTY; diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index b11f2afa84f1..99fffc9cb958 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -794,9 +794,6 @@ static void nlmclnt_cancel_callback(struct rpc_task *task, void *data) goto retry_cancel; } - dprintk("lockd: cancel status %u (task %u)\n", - status, task->tk_pid); - switch (status) { case NLM_LCK_GRANTED: case NLM_LCK_DENIED_GRACE_PERIOD: diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index b632be3ad57b..b220e1b91726 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -780,11 +780,9 @@ module_exit(exit_nlm); static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *procp = rqstp->rq_procinfo; - struct kvec *argv = rqstp->rq_arg.head; - struct kvec *resv = rqstp->rq_res.head; svcxdr_init_decode(rqstp); - if (!procp->pc_decode(rqstp, argv->iov_base)) + if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; *statp = procp->pc_func(rqstp); @@ -794,7 +792,7 @@ static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) return 1; svcxdr_init_encode(rqstp); - if (!procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) + if (!procp->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; return 1; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index e10ae2c41279..176b468a61c7 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -269,8 +269,6 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp) */ static void nlm4svc_callback_exit(struct rpc_task *task, void *data) { - dprintk("lockd: %5u callback returned %d\n", task->tk_pid, - -task->tk_status); } static void nlm4svc_callback_release(void *data) diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 99696d3f6dd6..4dc1b40a489a 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -301,8 +301,6 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp) */ static void nlmsvc_callback_exit(struct rpc_task *task, void *data) { - dprintk("lockd: %5u callback returned %d\n", task->tk_pid, - -task->tk_status); } void nlmsvc_release_call(struct nlm_rqst *call) diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 9235e60b1769..2fb5748dae0c 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -145,137 +145,131 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) * Decode Call arguments */ -int -nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int -nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; argp->monitor = 1; /* monitor client by default */ - return 1; + return true; } -int -nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int -nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; argp->lock.fl.fl_type = F_UNLCK; - return 1; + return true; } -int -nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_decode_stats(xdr, &resp->status)) - return 0; + return false; - return 1; + return true; } -int -nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_reboot *argp = rqstp->rq_argp; + __be32 *p; u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) - return 0; + return false; if (len > SM_MAXSTRLEN) - return 0; + return false; p = xdr_inline_decode(xdr, len); if (!p) - return 0; + return false; argp->len = len; argp->mon = (char *)p; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; p = xdr_inline_decode(xdr, SM_PRIV_SIZE); if (!p) - return 0; + return false; memcpy(&argp->priv.data, p, sizeof(argp->priv.data)); - return 1; + return true; } -int -nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; @@ -284,35 +278,34 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) lock->svid = ~(u32)0; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (!svcxdr_decode_fhandle(xdr, &lock->fh)) - return 0; + return false; if (!svcxdr_decode_owner(xdr, &lock->oh)) - return 0; + return false; /* XXX: Range checks are missing in the original code */ if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0) - return 0; + return false; - return 1; + return true; } -int -nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; - return 1; + return true; } @@ -320,45 +313,42 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) * Encode Reply results */ -int -nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_testrply(xdr, resp); } -int -nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_stats(xdr, resp->status); } -int -nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_encode_stats(xdr, resp->status)) - return 0; + return false; /* sequence */ if (xdr_stream_encode_u32(xdr, 0) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 98e957e4566c..856267c0864b 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -144,136 +144,131 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) * Decode Call arguments */ -int -nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int -nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; argp->monitor = 1; /* monitor client by default */ - return 1; + return true; } -int -nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + + return true; } -int -nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; argp->lock.fl.fl_type = F_UNLCK; - return 1; + return true; } -int -nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_decode_stats(xdr, &resp->status)) - return 0; + return false; - return 1; + return true; } -int -nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_reboot *argp = rqstp->rq_argp; + __be32 *p; u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) - return 0; + return false; if (len > SM_MAXSTRLEN) - return 0; + return false; p = xdr_inline_decode(xdr, len); if (!p) - return 0; + return false; argp->len = len; argp->mon = (char *)p; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; p = xdr_inline_decode(xdr, SM_PRIV_SIZE); if (!p) - return 0; + return false; memcpy(&argp->priv.data, p, sizeof(argp->priv.data)); - return 1; + return true; } -int -nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; @@ -282,35 +277,34 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) lock->svid = ~(u32)0; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (!svcxdr_decode_fhandle(xdr, &lock->fh)) - return 0; + return false; if (!svcxdr_decode_owner(xdr, &lock->oh)) - return 0; + return false; /* XXX: Range checks are missing in the original code */ if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0) - return 0; + return false; - return 1; + return true; } -int -nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; - return 1; + return true; } @@ -318,45 +312,42 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) * Encode Reply results */ -int -nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_testrply(xdr, resp); } -int -nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_stats(xdr, resp->status); } -int -nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_encode_stats(xdr, resp->status)) - return 0; + return false; /* sequence */ if (xdr_stream_encode_u32(xdr, 0) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 994ec22d4040..9320a42dfaf9 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -230,7 +230,7 @@ static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async /* * Deal with the completion of writing the data to the cache. We have to clear - * the PG_fscache bits on the pages involved and release the caller's ref. + * the PG_fscache bits on the folios involved and release the caller's ref. * * May be called in softirq mode and we inherit a ref from the caller. */ @@ -238,7 +238,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, bool was_async) { struct netfs_read_subrequest *subreq; - struct page *page; + struct folio *folio; pgoff_t unlocked = 0; bool have_unlocked = false; @@ -247,14 +247,14 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - xas_for_each(&xas, page, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { /* We might have multiple writes from the same huge - * page, but we mustn't unlock a page more than once. + * folio, but we mustn't unlock a folio more than once. */ - if (have_unlocked && page->index <= unlocked) + if (have_unlocked && folio_index(folio) <= unlocked) continue; - unlocked = page->index; - end_page_fscache(page); + unlocked = folio_index(folio); + folio_end_fscache(folio); have_unlocked = true; } } @@ -367,18 +367,17 @@ static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq, } /* - * Unlock the pages in a read operation. We need to set PG_fscache on any - * pages we're going to write back before we unlock them. + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. */ static void netfs_rreq_unlock(struct netfs_read_request *rreq) { struct netfs_read_subrequest *subreq; - struct page *page; + struct folio *folio; unsigned int iopos, account = 0; pgoff_t start_page = rreq->start / PAGE_SIZE; pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; bool subreq_failed = false; - int i; XA_STATE(xas, &rreq->mapping->i_pages, start_page); @@ -403,9 +402,9 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); rcu_read_lock(); - xas_for_each(&xas, page, last_page) { - unsigned int pgpos = (page->index - start_page) * PAGE_SIZE; - unsigned int pgend = pgpos + thp_size(page); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); bool pg_failed = false; for (;;) { @@ -414,7 +413,7 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) break; } if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - set_page_fscache(page); + folio_start_fscache(folio); pg_failed |= subreq_failed; if (pgend < iopos + subreq->len) break; @@ -433,17 +432,16 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) } if (!pg_failed) { - for (i = 0; i < thp_nr_pages(page); i++) - flush_dcache_page(page); - SetPageUptodate(page); + flush_dcache_folio(folio); + folio_mark_uptodate(folio); } - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_PAGES, &rreq->flags)) { - if (page->index == rreq->no_unlock_page && - test_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags)) + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) _debug("no unlock"); else - unlock_page(page); + folio_unlock(folio); } } rcu_read_unlock(); @@ -876,7 +874,6 @@ void netfs_readahead(struct readahead_control *ractl, void *netfs_priv) { struct netfs_read_request *rreq; - struct page *page; unsigned int debug_index = 0; int ret; @@ -911,11 +908,11 @@ void netfs_readahead(struct readahead_control *ractl, } while (rreq->submitted < rreq->len); - /* Drop the refs on the pages here rather than in the cache or + /* Drop the refs on the folios here rather than in the cache or * filesystem. The locks will be dropped in netfs_rreq_unlock(). */ - while ((page = readahead_page(ractl))) - put_page(page); + while (readahead_folio(ractl)) + ; /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ if (atomic_dec_and_test(&rreq->nr_rd_ops)) @@ -935,7 +932,7 @@ EXPORT_SYMBOL(netfs_readahead); /** * netfs_readpage - Helper to manage a readpage request * @file: The file to read from - * @page: The page to read + * @folio: The folio to read * @ops: The network filesystem's operations for the helper to use * @netfs_priv: Private netfs data to be retained in the request * @@ -950,7 +947,7 @@ EXPORT_SYMBOL(netfs_readahead); * This is usable whether or not caching is enabled. */ int netfs_readpage(struct file *file, - struct page *page, + struct folio *folio, const struct netfs_read_request_ops *ops, void *netfs_priv) { @@ -958,23 +955,23 @@ int netfs_readpage(struct file *file, unsigned int debug_index = 0; int ret; - _enter("%lx", page_index(page)); + _enter("%lx", folio_index(folio)); rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) { if (netfs_priv) - ops->cleanup(netfs_priv, page_file_mapping(page)); - unlock_page(page); + ops->cleanup(netfs_priv, folio_file_mapping(folio)); + folio_unlock(folio); return -ENOMEM; } - rreq->mapping = page_file_mapping(page); - rreq->start = page_file_offset(page); - rreq->len = thp_size(page); + rreq->mapping = folio_file_mapping(folio); + rreq->start = folio_file_pos(folio); + rreq->len = folio_size(folio); if (ops->begin_cache_operation) { ret = ops->begin_cache_operation(rreq); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) { - unlock_page(page); + folio_unlock(folio); goto out; } } @@ -1012,40 +1009,40 @@ out: EXPORT_SYMBOL(netfs_readpage); /** - * netfs_skip_page_read - prep a page for writing without reading first - * @page: page being prepared + * netfs_skip_folio_read - prep a folio for writing without reading first + * @folio: The folio being prepared * @pos: starting position for the write * @len: length of write * * In some cases, write_begin doesn't need to read at all: - * - full page write - * - write that lies in a page that is completely beyond EOF - * - write that covers the the page from start to EOF or beyond it + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it * * If any of these criteria are met, then zero out the unwritten parts - * of the page and return true. Otherwise, return false. + * of the folio and return true. Otherwise, return false. */ -static bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len) +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio_inode(folio); loff_t i_size = i_size_read(inode); - size_t offset = offset_in_thp(page, pos); + size_t offset = offset_in_folio(folio, pos); - /* Full page write */ - if (offset == 0 && len >= thp_size(page)) + /* Full folio write */ + if (offset == 0 && len >= folio_size(folio)) return true; - /* pos beyond last page in the file */ + /* pos beyond last folio in the file */ if (pos - offset >= i_size) goto zero_out; - /* Write that covers from the start of the page to EOF or beyond */ + /* Write that covers from the start of the folio to EOF or beyond */ if (offset == 0 && (pos + len) >= i_size) goto zero_out; return false; zero_out: - zero_user_segments(page, 0, offset, offset + len, thp_size(page)); + zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio)); return true; } @@ -1054,9 +1051,9 @@ zero_out: * @file: The file to read from * @mapping: The mapping to read from * @pos: File position at which the write will begin - * @len: The length of the write (may extend beyond the end of the page chosen) - * @flags: AOP_* flags - * @_page: Where to put the resultant page + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @aop_flags: AOP_* flags + * @_folio: Where to put the resultant folio * @_fsdata: Place for the netfs to store a cookie * @ops: The network filesystem's operations for the helper to use * @netfs_priv: Private netfs data to be retained in the request @@ -1072,37 +1069,41 @@ zero_out: * issue_op, is mandatory. * * The check_write_begin() operation can be provided to check for and flush - * conflicting writes once the page is grabbed and locked. It is passed a + * conflicting writes once the folio is grabbed and locked. It is passed a * pointer to the fsdata cookie that gets returned to the VM to be passed to * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the page and return -EAGAIN to cause the page to be - * regot; or return an error. + * should go ahead; unlock the folio and return -EAGAIN to cause the folio to + * be regot; or return an error. * * This is usable whether or not caching is enabled. */ int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int flags, - struct page **_page, void **_fsdata, + loff_t pos, unsigned int len, unsigned int aop_flags, + struct folio **_folio, void **_fsdata, const struct netfs_read_request_ops *ops, void *netfs_priv) { struct netfs_read_request *rreq; - struct page *page, *xpage; + struct folio *folio; struct inode *inode = file_inode(file); - unsigned int debug_index = 0; + unsigned int debug_index = 0, fgp_flags; pgoff_t index = pos >> PAGE_SHIFT; int ret; DEFINE_READAHEAD(ractl, file, NULL, mapping, index); retry: - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) + fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) return -ENOMEM; if (ops->check_write_begin) { /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ops->check_write_begin(file, pos, len, page, _fsdata); + ret = ops->check_write_begin(file, pos, len, folio, _fsdata); if (ret < 0) { trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); if (ret == -EAGAIN) @@ -1111,28 +1112,28 @@ retry: } } - if (PageUptodate(page)) - goto have_page; + if (folio_test_uptodate(folio)) + goto have_folio; /* If the page is beyond the EOF, we want to clear it - unless it's * within the cache granule containing the EOF, in which case we need * to preload the granule. */ if (!ops->is_cache_enabled(inode) && - netfs_skip_page_read(page, pos, len)) { + netfs_skip_folio_read(folio, pos, len)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_page_no_wait; + goto have_folio_no_wait; } ret = -ENOMEM; rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) goto error; - rreq->mapping = page->mapping; - rreq->start = page_offset(page); - rreq->len = thp_size(page); - rreq->no_unlock_page = page->index; - __set_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags); + rreq->mapping = folio_file_mapping(folio); + rreq->start = folio_file_pos(folio); + rreq->len = folio_size(folio); + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); netfs_priv = NULL; if (ops->begin_cache_operation) { @@ -1147,14 +1148,14 @@ retry: /* Expand the request to meet caching requirements and download * preferences. */ - ractl._nr_pages = thp_nr_pages(page); + ractl._nr_pages = folio_nr_pages(folio); netfs_rreq_expand(rreq, &ractl); netfs_get_read_request(rreq); - /* We hold the page locks, so we can drop the references */ - while ((xpage = readahead_page(&ractl))) - if (xpage != page) - put_page(xpage); + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; atomic_set(&rreq->nr_rd_ops, 1); do { @@ -1184,22 +1185,22 @@ retry: if (ret < 0) goto error; -have_page: - ret = wait_on_page_fscache_killable(page); +have_folio: + ret = folio_wait_fscache_killable(folio); if (ret < 0) goto error; -have_page_no_wait: +have_folio_no_wait: if (netfs_priv) ops->cleanup(netfs_priv, mapping); - *_page = page; + *_folio = folio; _leave(" = 0"); return 0; error_put: netfs_put_read_request(rreq, false); error: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (netfs_priv) ops->cleanup(netfs_priv, mapping); _leave(" = %d", ret); diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index ed9d580826f5..09c5b1cb3e07 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -739,6 +739,9 @@ out: kfree(copy); spin_unlock(&cps->clp->cl_lock); + trace_nfs4_cb_offload(&args->coa_fh, &args->coa_stateid, + args->wr_count, args->error, + args->wr_writeverf.committed); return 0; } #endif /* CONFIG_NFS_V4_2 */ diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 4c48d85f6517..a67c41ec545f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -67,9 +67,9 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp) * svc_process_common() looks for an XDR encoder to know when * not to drop a Reply. */ -static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p) +static bool nfs4_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return xdr_ressize_check(rqstp, p); + return true; } static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 23e165d5ec9c..1e4dc1ab9312 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -828,7 +828,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, /* * Probe filesystem information, including the FSID on v2/v3 */ -int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr) +static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr) { struct nfs_fsinfo fsinfo; struct nfs_client *clp = server->nfs_client; @@ -862,7 +862,30 @@ int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs return 0; } -EXPORT_SYMBOL_GPL(nfs_probe_fsinfo); + +/* + * Grab the destination's particulars, including lease expiry time. + * + * Returns zero if probe succeeded and retrieved FSID matches the FSID + * we have cached. + */ +int nfs_probe_server(struct nfs_server *server, struct nfs_fh *mntfh) +{ + struct nfs_fattr *fattr; + int error; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + return -ENOMEM; + + /* Sanity: the probe won't work if the destination server + * does not recognize the migrated FH. */ + error = nfs_probe_fsinfo(server, mntfh, fattr); + + nfs_free_fattr(fattr); + return error; +} +EXPORT_SYMBOL_GPL(nfs_probe_server); /* * Copy useful information when duplicating a server record @@ -1025,7 +1048,7 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (!(fattr->valid & NFS_ATTR_FATTR)) { error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, - fattr, NULL, NULL); + fattr, NULL); if (error < 0) { dprintk("nfs_create_server: getattr error = %d\n", -error); goto error; @@ -1058,7 +1081,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, rpc_authflavor_t flavor) { struct nfs_server *server; - struct nfs_fattr *fattr_fsinfo; int error; server = nfs_alloc_server(); @@ -1067,11 +1089,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, server->cred = get_cred(source->cred); - error = -ENOMEM; - fattr_fsinfo = nfs_alloc_fattr(); - if (fattr_fsinfo == NULL) - goto out_free_server; - /* Copy data from the source */ server->nfs_client = source->nfs_client; server->destroy = source->destroy; @@ -1087,7 +1104,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, goto out_free_server; /* probe the filesystem info for this server filesystem */ - error = nfs_probe_fsinfo(server, fh, fattr_fsinfo); + error = nfs_probe_server(server, fh); if (error < 0) goto out_free_server; @@ -1101,11 +1118,9 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, nfs_server_insert_lists(server); server->mount_time = jiffies; - nfs_free_fattr(fattr_fsinfo); return server; out_free_server: - nfs_free_fattr(fattr_fsinfo); nfs_free_server(server); return ERR_PTR(error); } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 11118398f495..7c9eb679dbdb 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -755,11 +755,13 @@ int nfs4_inode_return_delegation(struct inode *inode) struct nfs_delegation *delegation; delegation = nfs_start_delegation_return(nfsi); - /* Synchronous recall of any application leases */ - break_lease(inode, O_WRONLY | O_RDWR); - nfs_wb_all(inode); - if (delegation != NULL) + if (delegation != NULL) { + /* Synchronous recall of any application leases */ + break_lease(inode, O_WRONLY | O_RDWR); + if (S_ISREG(inode->i_mode)) + nfs_wb_all(inode); return nfs_end_delegation_return(inode, delegation, 1); + } return 0; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 1a6d2867fba4..731d31015b6a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -78,6 +78,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir ctx->attr_gencount = nfsi->attr_gencount; ctx->dir_cookie = 0; ctx->dup_cookie = 0; + ctx->page_index = 0; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) @@ -85,6 +86,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add(&ctx->list, &nfsi->open_files); + clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); spin_unlock(&dir->i_lock); return ctx; } @@ -411,7 +413,8 @@ out_eof: static bool nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi) { - if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA)) + if (nfsi->cache_validity & (NFS_INO_INVALID_CHANGE | + NFS_INO_INVALID_DATA)) return false; smp_rmb(); return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags); @@ -626,8 +629,7 @@ void nfs_force_use_readdirplus(struct inode *dir) if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && !list_empty(&nfsi->open_files)) { set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); - invalidate_mapping_pages(dir->i_mapping, - nfsi->page_index + 1, -1); + set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); } } @@ -680,7 +682,7 @@ again: nfs_set_verifier(dentry, dir_verifier); status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) - nfs_setsecurity(d_inode(dentry), entry->fattr, entry->label); + nfs_setsecurity(d_inode(dentry), entry->fattr); goto out; } else { d_invalidate(dentry); @@ -694,7 +696,7 @@ again: goto out; } - inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label); + inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); alias = d_splice_alias(inode, dentry); d_lookup_done(dentry); if (alias) { @@ -730,8 +732,8 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, xdr_set_scratch_page(&stream, scratch); do { - if (entry->label) - entry->label->len = NFS4_MAXLABELLEN; + if (entry->fattr->label) + entry->fattr->label->len = NFS4_MAXLABELLEN; status = xdr_decode(desc, entry, &stream); if (status != 0) @@ -836,21 +838,15 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, return -ENOMEM; entry->cookie = nfs_readdir_page_last_cookie(page); entry->fh = nfs_alloc_fhandle(); - entry->fattr = nfs_alloc_fattr(); + entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); entry->server = NFS_SERVER(inode); if (entry->fh == NULL || entry->fattr == NULL) goto out; - entry->label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT); - if (IS_ERR(entry->label)) { - status = PTR_ERR(entry->label); - goto out; - } - array_size = (dtsize + PAGE_SIZE - 1) >> PAGE_SHIFT; pages = nfs_readdir_alloc_pages(array_size); if (!pages) - goto out_release_label; + goto out; do { unsigned int pglen; @@ -873,8 +869,6 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, } while (!status && nfs_readdir_page_needs_filling(page)); nfs_readdir_free_pages(pages, array_size); -out_release_label: - nfs4_label_free(entry->label); out: nfs_free_fattr(entry->fattr); nfs_free_fhandle(entry->fh); @@ -937,10 +931,8 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) sizeof(nfsi->cookieverf)); } res = nfs_readdir_search_array(desc); - if (res == 0) { - nfsi->page_index = desc->page_index; + if (res == 0) return 0; - } nfs_readdir_page_unlock_and_put_cached(desc); return res; } @@ -1079,6 +1071,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_dir_context *dir_ctx = file->private_data; struct nfs_readdir_descriptor *desc; + pgoff_t page_index; int res; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", @@ -1109,10 +1102,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->dir_cookie = dir_ctx->dir_cookie; desc->dup_cookie = dir_ctx->dup_cookie; desc->duped = dir_ctx->duped; + page_index = dir_ctx->page_index; desc->attr_gencount = dir_ctx->attr_gencount; memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); spin_unlock(&file->f_lock); + if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && + list_is_singular(&nfsi->open_files)) + invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); + do { res = readdir_search_pagecache(desc); @@ -1149,6 +1147,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) dir_ctx->dup_cookie = desc->dup_cookie; dir_ctx->duped = desc->duped; dir_ctx->attr_gencount = desc->attr_gencount; + dir_ctx->page_index = desc->page_index; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); @@ -1269,13 +1268,12 @@ static bool nfs_verifier_is_delegated(struct dentry *dentry) static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) { struct inode *inode = d_inode(dentry); + struct inode *dir = d_inode(dentry->d_parent); - if (!nfs_verifier_is_delegated(dentry) && - !nfs_verify_change_attribute(d_inode(dentry->d_parent), verf)) - goto out; + if (!nfs_verify_change_attribute(dir, verf)) + return; if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) nfs_set_verifier_delegated(&verf); -out: dentry->d_time = verf; } @@ -1413,7 +1411,7 @@ out_force: static void nfs_mark_dir_for_revalidate(struct inode *inode) { spin_lock(&inode->i_lock); - nfs_set_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE); spin_unlock(&inode->i_lock); } @@ -1495,19 +1493,17 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, { struct nfs_fh *fhandle; struct nfs_fattr *fattr; - struct nfs4_label *label; unsigned long dir_verifier; int ret; ret = -ENOMEM; fhandle = nfs_alloc_fhandle(); - fattr = nfs_alloc_fattr(); - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (fhandle == NULL || fattr == NULL || IS_ERR(label)) + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); + if (fhandle == NULL || fattr == NULL) goto out; dir_verifier = nfs_save_change_attribute(dir); - ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); + ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); if (ret < 0) { switch (ret) { case -ESTALE: @@ -1526,7 +1522,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, if (nfs_refresh_inode(inode, fattr) < 0) goto out; - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr); nfs_set_verifier(dentry, dir_verifier); /* set a readdirplus hint that we had a cache miss */ @@ -1535,7 +1531,6 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, out: nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); - nfs4_label_free(label); /* * If the lookup failed despite the dentry change attribute being @@ -1721,10 +1716,6 @@ static void nfs_drop_nlink(struct inode *inode) */ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) { - if (S_ISDIR(inode->i_mode)) - /* drop any readdir cache as it could easily be old */ - nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); - if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { nfs_complete_unlink(dentry, inode); nfs_drop_nlink(inode); @@ -1759,7 +1750,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in struct inode *inode = NULL; struct nfs_fh *fhandle = NULL; struct nfs_fattr *fattr = NULL; - struct nfs4_label *label = NULL; unsigned long dir_verifier; int error; @@ -1778,27 +1768,23 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in res = ERR_PTR(-ENOMEM); fhandle = nfs_alloc_fhandle(); - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(dir)); if (fhandle == NULL || fattr == NULL) goto out; - label = nfs4_label_alloc(NFS_SERVER(dir), GFP_NOWAIT); - if (IS_ERR(label)) - goto out; - dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); + error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); if (error == -ENOENT) goto no_entry; if (error < 0) { res = ERR_PTR(error); - goto out_label; + goto out; } - inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); + inode = nfs_fhget(dentry->d_sb, fhandle, fattr); res = ERR_CAST(inode); if (IS_ERR(res)) - goto out_label; + goto out; /* Notify readdir to use READDIRPLUS */ nfs_force_use_readdirplus(dir); @@ -1807,14 +1793,12 @@ no_entry: res = d_splice_alias(inode, dentry); if (res != NULL) { if (IS_ERR(res)) - goto out_label; + goto out; dentry = res; } nfs_set_verifier(dentry, dir_verifier); -out_label: - trace_nfs_lookup_exit(dir, dentry, flags, error); - nfs4_label_free(label); out: + trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res)); nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); return res; @@ -2051,8 +2035,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct dentry * nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fattr *fattr) { struct dentry *parent = dget_parent(dentry); struct inode *dir = d_inode(parent); @@ -2063,7 +2046,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, d_drop(dentry); if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, NULL); + error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); if (error) goto out_error; } @@ -2071,11 +2054,11 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, if (!(fattr->valid & NFS_ATTR_FATTR)) { struct nfs_server *server = NFS_SB(dentry->d_sb); error = server->nfs_client->rpc_ops->getattr(server, fhandle, - fattr, NULL, NULL); + fattr, NULL); if (error < 0) goto out_error; } - inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); + inode = nfs_fhget(dentry->d_sb, fhandle, fattr); d = d_splice_alias(inode, dentry); out: dput(parent); @@ -2090,12 +2073,11 @@ EXPORT_SYMBOL_GPL(nfs_add_or_obtain); * Code common to create, mkdir, and mknod. */ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fattr *fattr) { struct dentry *d; - d = nfs_add_or_obtain(dentry, fhandle, fattr, label); + d = nfs_add_or_obtain(dentry, fhandle, fattr); if (IS_ERR(d)) return PTR_ERR(d); @@ -2197,6 +2179,18 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry) d_delete(dentry); } +static void nfs_dentry_remove_handle_error(struct inode *dir, + struct dentry *dentry, int error) +{ + switch (error) { + case -ENOENT: + d_delete(dentry); + fallthrough; + case 0: + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + } +} + int nfs_rmdir(struct inode *dir, struct dentry *dentry) { int error; @@ -2219,6 +2213,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) up_write(&NFS_I(d_inode(dentry))->rmdir_sem); } else error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + nfs_dentry_remove_handle_error(dir, dentry, error); trace_nfs_rmdir_exit(dir, dentry, error); return error; @@ -2288,9 +2283,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) } spin_unlock(&dentry->d_lock); error = nfs_safe_remove(dentry); - if (!error || error == -ENOENT) { - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - } else if (need_rehash) + nfs_dentry_remove_handle_error(dir, dentry, error); + if (need_rehash) d_rehash(dentry); out: trace_nfs_unlink_exit(dir, dentry, error); @@ -2352,6 +2346,8 @@ int nfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, return error; } + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + /* * No big deal if we can't add this page to the page cache here. * READLINK will get the missing page from the server if needed. @@ -2385,6 +2381,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) d_drop(dentry); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); ihold(inode); d_add(dentry, inode); } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 7a5f287c5391..9cff8709c80a 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -620,7 +620,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_unlock_and_release_request(req); } - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + if (nfs_commit_end(cinfo.mds)) nfs_direct_write_complete(dreq); } diff --git a/fs/nfs/export.c b/fs/nfs/export.c index d772c20bbfd1..171c424cb6d5 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -64,7 +64,6 @@ static struct dentry * nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { - struct nfs4_label *label = NULL; struct nfs_fattr *fattr = NULL; struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw); size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; @@ -79,7 +78,7 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, if (fh_len < len || fh_type != len) return NULL; - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SB(sb)); if (fattr == NULL) { dentry = ERR_PTR(-ENOMEM); goto out; @@ -95,28 +94,19 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, if (inode) goto out_found; - label = nfs4_label_alloc(NFS_SB(sb), GFP_KERNEL); - if (IS_ERR(label)) { - dentry = ERR_CAST(label); - goto out_free_fattr; - } - rpc_ops = NFS_SB(sb)->nfs_client->rpc_ops; - ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label, NULL); + ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, NULL); if (ret) { dprintk("%s: getattr failed %d\n", __func__, ret); trace_nfs_fh_to_dentry(sb, server_fh, fattr->fileid, ret); dentry = ERR_PTR(ret); - goto out_free_label; + goto out_free_fattr; } - inode = nfs_fhget(sb, server_fh, fattr, label); + inode = nfs_fhget(sb, server_fh, fattr); out_found: dentry = d_obtain_alias(inode); - -out_free_label: - nfs4_label_free(label); out_free_fattr: nfs_free_fattr(fattr); out: @@ -131,7 +121,6 @@ nfs_get_parent(struct dentry *dentry) struct super_block *sb = inode->i_sb; struct nfs_server *server = NFS_SB(sb); struct nfs_fattr *fattr = NULL; - struct nfs4_label *label = NULL; struct dentry *parent; struct nfs_rpc_ops const *ops = server->nfs_client->rpc_ops; struct nfs_fh fh; @@ -139,31 +128,20 @@ nfs_get_parent(struct dentry *dentry) if (!ops->lookupp) return ERR_PTR(-EACCES); - fattr = nfs_alloc_fattr(); - if (fattr == NULL) { - parent = ERR_PTR(-ENOMEM); - goto out; - } + fattr = nfs_alloc_fattr_with_label(server); + if (fattr == NULL) + return ERR_PTR(-ENOMEM); - label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(label)) { - parent = ERR_CAST(label); - goto out_free_fattr; - } - - ret = ops->lookupp(inode, &fh, fattr, label); + ret = ops->lookupp(inode, &fh, fattr); if (ret) { parent = ERR_PTR(ret); - goto out_free_label; + goto out; } - pinode = nfs_fhget(sb, &fh, fattr, label); + pinode = nfs_fhget(sb, &fh, fattr); parent = d_obtain_alias(pinode); -out_free_label: - nfs4_label_free(label); -out_free_fattr: - nfs_free_fattr(fattr); out: + nfs_free_fattr(fattr); return parent; } diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index d2103852475f..9c96e3e5ed35 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -293,8 +293,6 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; - dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs41_sequence_done(task, &hdr->res.seq_res); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index d383de00d486..a553d59afa8b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1414,8 +1414,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; - dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs4_sequence_done(task, &hdr->res.seq_res); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index c9b61b818ec1..bfa7202ca7be 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -378,10 +378,10 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, goto noconnect; ds = mirror->mirror_ds->ds; + if (READ_ONCE(ds->ds_clp)) + goto out; /* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */ smp_rmb(); - if (ds->ds_clp) - goto out; /* FIXME: For now we assume the server sent only one version of NFS * to use for the DS. diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 59355c106ece..11ff2b2e060f 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -80,31 +80,28 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) goto out; /* get the actual root for this mount */ - fsinfo.fattr = nfs_alloc_fattr(); + fsinfo.fattr = nfs_alloc_fattr_with_label(server); if (fsinfo.fattr == NULL) goto out_name; - fsinfo.fattr->label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(fsinfo.fattr->label)) - goto out_fattr; error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo); if (error < 0) { dprintk("nfs_get_root: getattr error = %d\n", -error); nfs_errorf(fc, "NFS: Couldn't getattr on root"); - goto out_label; + goto out_fattr; } - inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr, NULL); + inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr); if (IS_ERR(inode)) { dprintk("nfs_get_root: get root inode failed\n"); error = PTR_ERR(inode); nfs_errorf(fc, "NFS: Couldn't get root inode"); - goto out_label; + goto out_fattr; } error = nfs_superblock_set_dummy_root(s, inode); if (error != 0) - goto out_label; + goto out_fattr; /* root dentries normally start off anonymous and get spliced in later * if the dentry tree reaches them; however if the dentry already @@ -115,7 +112,7 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) dprintk("nfs_get_root: get root dentry failed\n"); error = PTR_ERR(root); nfs_errorf(fc, "NFS: Couldn't get root dentry"); - goto out_label; + goto out_fattr; } security_d_instantiate(root, inode); @@ -151,11 +148,9 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) server->caps &= ~NFS_CAP_SECURITY_LABEL; - nfs_setsecurity(inode, fsinfo.fattr, fsinfo.fattr->label); + nfs_setsecurity(inode, fsinfo.fattr); error = 0; -out_label: - nfs4_label_free(fsinfo.fattr->label); out_fattr: nfs_free_fattr(fsinfo.fattr); out_name: @@ -165,5 +160,5 @@ out: error_splat_root: dput(fc->root); fc->root = NULL; - goto out_label; + goto out_fattr; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 853213b3a209..dd53704c3f40 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -210,10 +210,15 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) nfs_fscache_invalidate(inode); - if (inode->i_mapping->nrpages == 0) - flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER); flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + nfsi->cache_validity |= flags; + + if (inode->i_mapping->nrpages == 0) + nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA | + NFS_INO_DATA_INVAL_DEFER); + else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); @@ -350,37 +355,32 @@ static void nfs_clear_label_invalid(struct inode *inode) spin_unlock(&inode->i_lock); } -void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label) +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { int error; - if (label == NULL) + if (fattr->label == NULL) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { - error = security_inode_notifysecctx(inode, label->label, - label->len); + error = security_inode_notifysecctx(inode, fattr->label->label, + fattr->label->len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, - (char *)label->label, - label->len, error); + (char *)fattr->label->label, + fattr->label->len, error); nfs_clear_label_invalid(inode); } } struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { - struct nfs4_label *label = NULL; - int minor_version = server->nfs_client->cl_minorversion; - - if (minor_version < 2) - return label; + struct nfs4_label *label; if (!(server->caps & NFS_CAP_SECURITY_LABEL)) - return label; + return NULL; label = kzalloc(sizeof(struct nfs4_label), flags); if (label == NULL) @@ -397,8 +397,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else -void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label) +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { } #endif @@ -426,12 +425,28 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) return inode; } +static void nfs_inode_init_regular(struct nfs_inode *nfsi) +{ + atomic_long_set(&nfsi->nrequests, 0); + INIT_LIST_HEAD(&nfsi->commit_info.list); + atomic_long_set(&nfsi->commit_info.ncommit, 0); + atomic_set(&nfsi->commit_info.rpcs_out, 0); + mutex_init(&nfsi->commit_mutex); +} + +static void nfs_inode_init_dir(struct nfs_inode *nfsi) +{ + nfsi->cache_change_attribute = 0; + memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + init_rwsem(&nfsi->rmdir_sem); +} + /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. */ struct inode * -nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label) +nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) { struct nfs_find_desc desc = { .fh = fh, @@ -480,10 +495,12 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; + nfs_inode_init_regular(nfsi); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; + nfs_inode_init_dir(nfsi); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { @@ -509,7 +526,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_uid = make_kuid(&init_user_ns, -2); inode->i_gid = make_kgid(&init_user_ns, -2); inode->i_blocks = 0; - memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); nfsi->write_io = 0; nfsi->read_io = 0; @@ -563,7 +579,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; @@ -632,7 +648,7 @@ nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { error = -ENOMEM; goto out; @@ -666,6 +682,7 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset) if (err) goto out; + trace_nfs_size_truncate(inode, offset); i_size_write(inode, offset); /* Optimisation */ if (offset == 0) @@ -1024,7 +1041,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, ctx->cred = get_cred(filp->f_cred); else ctx->cred = get_current_cred(); - ctx->ll_cred = NULL; + rcu_assign_pointer(ctx->ll_cred, NULL); ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; @@ -1063,7 +1080,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); - put_rpccred(ctx->ll_cred); + put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); kfree_rcu(ctx, rcu_head); } @@ -1175,7 +1192,6 @@ int __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { int status = -ESTALE; - struct nfs4_label *label = NULL; struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); @@ -1197,20 +1213,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) } status = -ENOMEM; - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) goto out; nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (IS_ERR(label)) { - status = PTR_ERR(label); - goto out; - } - - status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, - label, inode); + status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, inode); if (status != 0) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, @@ -1227,7 +1236,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) else nfs_zap_caches(inode); } - goto err_out; + goto out; } status = nfs_refresh_inode(inode, fattr); @@ -1235,20 +1244,18 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); - goto err_out; + goto out; } if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); -err_out: - nfs4_label_free(label); out: nfs_free_fattr(fattr); trace_nfs_revalidate_inode_exit(inode, status); @@ -1446,13 +1453,12 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec64_equal(&ts, &fattr->pre_mtime)) { inode->i_mtime = fattr->mtime; - if (S_ISDIR(inode->i_mode)) - nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) && !nfs_have_writebacks(inode)) { + trace_nfs_size_wcc(inode, fattr->size); i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } } @@ -1580,12 +1586,31 @@ struct nfs_fattr *nfs_alloc_fattr(void) struct nfs_fattr *fattr; fattr = kmalloc(sizeof(*fattr), GFP_NOFS); - if (fattr != NULL) + if (fattr != NULL) { nfs_fattr_init(fattr); + fattr->label = NULL; + } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr); +struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) +{ + struct nfs_fattr *fattr = nfs_alloc_fattr(); + + if (!fattr) + return NULL; + + fattr->label = nfs4_label_alloc(server, GFP_NOFS); + if (IS_ERR(fattr->label)) { + kfree(fattr); + return NULL; + } + + return fattr; +} +EXPORT_SYMBOL_GPL(nfs_alloc_fattr_with_label); + struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; @@ -1777,8 +1802,10 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_NLINK; unsigned long cache_validity = NFS_I(inode)->cache_validity; + enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type; - if (!(cache_validity & NFS_INO_INVALID_CHANGE) && + if (ctype != NFS4_CHANGE_TYPE_IS_UNDEFINED && + !(cache_validity & NFS_INO_INVALID_CHANGE) && (cache_validity & check_valid) != 0 && (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0) @@ -2095,16 +2122,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ if (!nfs_have_writebacks(inode) || new_isize > cur_isize) { + trace_nfs_size_update(inode, new_isize); i_size_write(inode, new_isize); if (!have_writers) invalid |= NFS_INO_INVALID_DATA; } - dprintk("NFS: isize change on server for file %s/%ld " - "(%Ld to %Ld)\n", - inode->i_sb->s_id, - inode->i_ino, - (long long)cur_isize, - (long long)new_isize); } if (new_isize == 0 && !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED | @@ -2155,11 +2177,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_NLINK) { - if (inode->i_nlink != fattr->nlink) { - if (S_ISDIR(inode->i_mode)) - invalid |= NFS_INO_INVALID_DATA; + if (inode->i_nlink != fattr->nlink) set_nlink(inode, fattr->nlink); - } } else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_NLINK; @@ -2260,14 +2279,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); - INIT_LIST_HEAD(&nfsi->commit_info.list); - atomic_long_set(&nfsi->nrequests, 0); - atomic_long_set(&nfsi->commit_info.ncommit, 0); - atomic_set(&nfsi->commit_info.rpcs_out, 0); - init_rwsem(&nfsi->rmdir_sem); - mutex_init(&nfsi->commit_mutex); nfs4_init_once(nfsi); - nfsi->cache_change_attribute = 0; } static int __init nfs_init_inodecache(void) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 66fc936834f2..12f6acb483bb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -193,7 +193,7 @@ extern void nfs_clients_exit(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); struct nfs_client *nfs_get_client(const struct nfs_client_initdata *); -int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); +int nfs_probe_server(struct nfs_server *, struct nfs_fh *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); @@ -209,6 +209,7 @@ extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); extern struct nfs_server *nfs_create_server(struct fs_context *); +extern void nfs4_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, @@ -341,14 +342,6 @@ nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) return dst; } -static inline void nfs4_label_free(struct nfs4_label *label) -{ - if (label) { - kfree(label->label); - kfree(label); - } - return; -} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { @@ -357,7 +350,6 @@ static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } -static inline void nfs4_label_free(void *label) {} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index bc0c698f3350..3295af4110f1 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -308,8 +308,7 @@ int nfs_submount(struct fs_context *fc, struct nfs_server *server) /* Look it up again to get its attributes */ err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, - ctx->mntfh, ctx->clone_data.fattr, - NULL); + ctx->mntfh, ctx->clone_data.fattr); dput(parent); if (err != 0) return err; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index f7524310ddf4..7100514d306b 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -100,8 +100,7 @@ nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, */ static int nfs3_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { struct rpc_message msg = { .rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR], @@ -193,8 +192,7 @@ __nfs3_proc_lookup(struct inode *dir, const char *name, size_t len, static int nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { unsigned short task_flags = 0; @@ -209,7 +207,7 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, } static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { const char dotdot[] = ".."; const size_t len = strlen(dotdot); @@ -323,7 +321,7 @@ nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata if (status != 0) return ERR_PTR(status); - return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr, NULL); + return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr); } static void nfs3_free_createdata(struct nfs3_createdata *data) diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index e6eca1d7481b..9274c9c5efea 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2227,7 +2227,7 @@ static int decode_fsinfo3resok(struct xdr_stream *xdr, /* ignore properties */ result->lease_time = 0; - result->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA; + result->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED; return 0; } diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index a24349512ffe..08355b66e7cb 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -83,6 +83,10 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, status = nfs_post_op_update_inode_force_wcc(inode, res.falloc_fattr); + if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE]) + trace_nfs4_fallocate(inode, &args, status); + else + trace_nfs4_deallocate(inode, &args, status); kfree(res.falloc_fattr); return status; } @@ -363,6 +367,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); + trace_nfs4_copy(src_inode, dst_inode, args, res, nss, status); if (status == -ENOTSUPP) dst_server->caps &= ~NFS_CAP_COPY; if (status) @@ -504,6 +509,7 @@ static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata) { struct nfs42_offloadcancel_data *data = calldata; + trace_nfs4_offload_cancel(&data->args, task->tk_status); nfs41_sequence_done(task, &data->res.osr_seq_res); if (task->tk_status && nfs4_async_handle_error(task, data->seq_server, NULL, @@ -598,6 +604,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, status = nfs4_call_sync(src_server->client, src_server, &msg, &args->cna_seq_args, &res->cnr_seq_res, 0); + trace_nfs4_copy_notify(file_inode(src), args, res, status); if (status == -ENOTSUPP) src_server->caps &= ~NFS_CAP_COPY_NOTIFY; @@ -678,6 +685,7 @@ static loff_t _nfs42_proc_llseek(struct file *filep, status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + trace_nfs4_llseek(inode, &args, &res, status); if (status == -ENOTSUPP) server->caps &= ~NFS_CAP_SEEK; if (status) @@ -1071,6 +1079,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); + trace_nfs4_clone(src_inode, dst_inode, &args, status); if (status == 0) { nfs42_copy_dest_done(dst_inode, dst_offset, count); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ba78df4b13d9..ed5eaca6801e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -234,7 +234,6 @@ struct nfs4_opendata { struct nfs4_string group_name; struct nfs4_label *a_label; struct nfs_fattr f_attr; - struct nfs4_label *f_label; struct dentry *dir; struct dentry *dentry; struct nfs4_state_owner *owner; @@ -317,8 +316,7 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_lock_context *l_ctx, fmode_t fmode); extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode); + struct nfs_fattr *fattr, struct inode *inode); extern int update_open_stateid(struct nfs4_state *state, const nfs4_stateid *open_stateid, const nfs4_stateid *deleg_stateid, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index af57332503be..d8b5a250ca05 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1059,31 +1059,15 @@ static void nfs4_session_limit_xasize(struct nfs_server *server) #endif } -static int nfs4_server_common_setup(struct nfs_server *server, - struct nfs_fh *mntfh, bool auth_probe) +void nfs4_server_set_init_caps(struct nfs_server *server) { - struct nfs_fattr *fattr; - int error; - - /* data servers support only a subset of NFSv4.1 */ - if (is_ds_only_client(server->nfs_client)) - return -EPROTONOSUPPORT; - - fattr = nfs_alloc_fattr(); - if (fattr == NULL) - return -ENOMEM; - - /* We must ensure the session is initialised first */ - error = nfs4_init_session(server->nfs_client); - if (error < 0) - goto out; - /* Set the basic capabilities */ server->caps |= server->nfs_client->cl_mvops->init_caps; if (server->flags & NFS_MOUNT_NORDIRPLUS) server->caps &= ~NFS_CAP_READDIRPLUS; if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA) server->caps &= ~NFS_CAP_READ_PLUS; + /* * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower * authentication. @@ -1091,7 +1075,23 @@ static int nfs4_server_common_setup(struct nfs_server *server, if (nfs4_disable_idmapping && server->client->cl_auth->au_flavor == RPC_AUTH_UNIX) server->caps |= NFS_CAP_UIDGID_NOMAP; +} +static int nfs4_server_common_setup(struct nfs_server *server, + struct nfs_fh *mntfh, bool auth_probe) +{ + int error; + + /* data servers support only a subset of NFSv4.1 */ + if (is_ds_only_client(server->nfs_client)) + return -EPROTONOSUPPORT; + + /* We must ensure the session is initialised first */ + error = nfs4_init_session(server->nfs_client); + if (error < 0) + goto out; + + nfs4_server_set_init_caps(server); /* Probe the root fh to retrieve its FSID and filehandle */ error = nfs4_get_rootfh(server, mntfh, auth_probe); @@ -1103,7 +1103,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, (unsigned long long) server->fsid.minor); nfs_display_fhandle(mntfh, "Pseudo-fs root FH"); - error = nfs_probe_fsinfo(server, mntfh, fattr); + error = nfs_probe_server(server, mntfh); if (error < 0) goto out; @@ -1117,7 +1117,6 @@ static int nfs4_server_common_setup(struct nfs_server *server, server->mount_time = jiffies; server->destroy = nfs4_destroy_server; out: - nfs_free_fattr(fattr); return error; } @@ -1288,30 +1287,6 @@ error: return ERR_PTR(error); } -/* - * Grab the destination's particulars, including lease expiry time. - * - * Returns zero if probe succeeded and retrieved FSID matches the FSID - * we have cached. - */ -static int nfs_probe_destination(struct nfs_server *server) -{ - struct inode *inode = d_inode(server->super->s_root); - struct nfs_fattr *fattr; - int error; - - fattr = nfs_alloc_fattr(); - if (fattr == NULL) - return -ENOMEM; - - /* Sanity: the probe won't work if the destination server - * does not recognize the migrated FH. */ - error = nfs_probe_fsinfo(server, NFS_FH(inode), fattr); - - nfs_free_fattr(fattr); - return error; -} - /** * nfs4_update_server - Move an nfs_server to a different nfs_client * @@ -1372,5 +1347,5 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); nfs_server_insert_lists(server); - return nfs_probe_destination(server); + return nfs_probe_server(server, NFS_FH(d_inode(server->super->s_root))); } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index c91565227ea2..e79ae4cbc395 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -317,7 +317,7 @@ static int read_name_gen = 1; static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, struct nfs_fh *src_fh, nfs4_stateid *stateid) { - struct nfs_fattr fattr; + struct nfs_fattr *fattr = nfs_alloc_fattr(); struct file *filep, *res; struct nfs_server *server; struct inode *r_ino = NULL; @@ -328,9 +328,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, server = NFS_SERVER(ss_mnt->mnt_root->d_inode); - nfs_fattr_init(&fattr); + if (!fattr) + return ERR_PTR(-ENOMEM); - status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL); + status = nfs4_proc_getattr(server, src_fh, fattr, NULL); if (status < 0) { res = ERR_PTR(status); goto out; @@ -343,20 +344,18 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++); - r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr, - NULL); + r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr); if (IS_ERR(r_ino)) { res = ERR_CAST(r_ino); goto out_free_name; } - filep = alloc_file_pseudo(r_ino, ss_mnt, read_name, FMODE_READ, + filep = alloc_file_pseudo(r_ino, ss_mnt, read_name, O_RDONLY, r_ino->i_fop); if (IS_ERR(filep)) { res = ERR_CAST(filep); goto out_free_name; } - filep->f_mode |= FMODE_READ; ctx = alloc_nfs_open_context(filep->f_path.dentry, filep->f_mode, filep); @@ -388,6 +387,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, out_free_name: kfree(read_name); out: + nfs_free_fattr(fattr); return res; out_stateowner: nfs4_put_state_owner(sp); diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 8d8aba305ecc..f331866dd418 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -487,7 +487,7 @@ nfs_idmap_new(struct nfs_client *clp) err_destroy_pipe: rpc_destroy_pipe_data(idmap->idmap_pipe); err: - get_user_ns(idmap->user_ns); + put_user_ns(idmap->user_ns); kfree(idmap); return error; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 459860aa8fd7..ee3bc79f6ca3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -93,11 +93,11 @@ struct nfs4_opendata; static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); -static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode); +static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct inode *inode); static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, - struct nfs_open_context *ctx, struct nfs4_label *ilabel, - struct nfs4_label *olabel); + struct nfs_open_context *ctx, struct nfs4_label *ilabel); #ifdef CONFIG_NFS_V4_1 static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, const struct cred *cred, @@ -1330,7 +1330,6 @@ nfs4_map_atomic_open_claim(struct nfs_server *server, static void nfs4_init_opendata_res(struct nfs4_opendata *p) { p->o_res.f_attr = &p->f_attr; - p->o_res.f_label = p->f_label; p->o_res.seqid = p->o_arg.seqid; p->c_res.seqid = p->c_arg.seqid; p->o_res.server = p->o_arg.server; @@ -1356,8 +1355,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, if (p == NULL) goto err; - p->f_label = nfs4_label_alloc(server, gfp_mask); - if (IS_ERR(p->f_label)) + p->f_attr.label = nfs4_label_alloc(server, gfp_mask); + if (IS_ERR(p->f_attr.label)) goto err_free_p; p->a_label = nfs4_label_alloc(server, gfp_mask); @@ -1389,27 +1388,22 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, sizeof(p->o_arg.u.verifier.data)); } } - /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS - * will return permission denied for all bits until close */ - if (!(flags & O_EXCL)) { - /* ask server to check for all possible rights as results - * are cached */ - switch (p->o_arg.claim) { - default: - break; - case NFS4_OPEN_CLAIM_NULL: - case NFS4_OPEN_CLAIM_FH: - p->o_arg.access = NFS4_ACCESS_READ | - NFS4_ACCESS_MODIFY | - NFS4_ACCESS_EXTEND | - NFS4_ACCESS_EXECUTE; + /* ask server to check for all possible rights as results + * are cached */ + switch (p->o_arg.claim) { + default: + break; + case NFS4_OPEN_CLAIM_NULL: + case NFS4_OPEN_CLAIM_FH: + p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY | + NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE | + NFS4_ACCESS_EXECUTE; #ifdef CONFIG_NFS_V4_2 - if (server->caps & NFS_CAP_XATTR) - p->o_arg.access |= NFS4_ACCESS_XAREAD | - NFS4_ACCESS_XAWRITE | - NFS4_ACCESS_XALIST; + if (!(server->caps & NFS_CAP_XATTR)) + break; + p->o_arg.access |= NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | + NFS4_ACCESS_XALIST; #endif - } } p->o_arg.clientid = server->nfs_client->cl_clientid; p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time); @@ -1440,7 +1434,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, err_free_label: nfs4_label_free(p->a_label); err_free_f: - nfs4_label_free(p->f_label); + nfs4_label_free(p->f_attr.label); err_free_p: kfree(p); err: @@ -1462,7 +1456,7 @@ static void nfs4_opendata_free(struct kref *kref) nfs4_put_state_owner(p->owner); nfs4_label_free(p->a_label); - nfs4_label_free(p->f_label); + nfs4_label_free(p->f_attr.label); dput(p->dir); dput(p->dentry); @@ -1610,15 +1604,16 @@ static bool nfs_stateid_is_sequential(struct nfs4_state *state, { if (test_bit(NFS_OPEN_STATE, &state->flags)) { /* The common case - we're updating to a new sequence number */ - if (nfs4_stateid_match_other(stateid, &state->open_stateid) && - nfs4_stateid_is_next(&state->open_stateid, stateid)) { - return true; + if (nfs4_stateid_match_other(stateid, &state->open_stateid)) { + if (nfs4_stateid_is_next(&state->open_stateid, stateid)) + return true; + return false; } - } else { - /* This is the first OPEN in this generation */ - if (stateid->seqid == cpu_to_be32(1)) - return true; + /* The server returned a new stateid */ } + /* This is the first OPEN in this generation */ + if (stateid->seqid == cpu_to_be32(1)) + return true; return false; } @@ -2014,7 +2009,7 @@ nfs4_opendata_get_inode(struct nfs4_opendata *data) if (!(data->f_attr.valid & NFS_ATTR_FATTR)) return ERR_PTR(-EAGAIN); inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, - &data->f_attr, data->f_label); + &data->f_attr); break; default: inode = d_inode(data->dentry); @@ -2473,11 +2468,15 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) /* Set the create mode (note dependency on the session type) */ data->o_arg.createmode = NFS4_CREATE_UNCHECKED; if (data->o_arg.open_flags & O_EXCL) { - data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE; - if (nfs4_has_persistent_session(clp)) + data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1; + if (clp->cl_mvops->minor_version == 0) { + data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE; + /* don't put an ACCESS op in OPEN compound if O_EXCL, + * because ACCESS will return permission denied for + * all bits until close */ + data->o_res.access_request = data->o_arg.access = 0; + } else if (nfs4_has_persistent_session(clp)) data->o_arg.createmode = NFS4_CREATE_GUARDED; - else if (clp->cl_mvops->minor_version > 0) - data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1; } return; unlock_no_action: @@ -2709,8 +2708,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data, } if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) { nfs4_sequence_free_slot(&o_res->seq_res); - nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, - o_res->f_label, NULL); + nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, NULL); } return 0; } @@ -3126,7 +3124,6 @@ static int _nfs4_do_open(struct inode *dir, enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; struct iattr *sattr = c->sattr; struct nfs4_label *label = c->label; - struct nfs4_label *olabel = NULL; int status; /* Protect against reboot recovery conflicts */ @@ -3149,19 +3146,11 @@ static int _nfs4_do_open(struct inode *dir, if (opendata == NULL) goto err_put_state_owner; - if (label) { - olabel = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(olabel)) { - status = PTR_ERR(olabel); - goto err_opendata_put; - } - } - if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { if (!opendata->f_attr.mdsthreshold) { opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); if (!opendata->f_attr.mdsthreshold) - goto err_free_label; + goto err_opendata_put; } opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0]; } @@ -3170,7 +3159,7 @@ static int _nfs4_do_open(struct inode *dir, status = _nfs4_open_and_get_state(opendata, flags, ctx); if (status != 0) - goto err_free_label; + goto err_opendata_put; state = ctx->state; if ((opendata->o_arg.open_flags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL) && @@ -3187,11 +3176,11 @@ static int _nfs4_do_open(struct inode *dir, nfs_fattr_init(opendata->o_res.f_attr); status = nfs4_do_setattr(state->inode, cred, opendata->o_res.f_attr, sattr, - ctx, label, olabel); + ctx, label); if (status == 0) { nfs_setattr_update_inode(state->inode, sattr, opendata->o_res.f_attr); - nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel); + nfs_setsecurity(state->inode, opendata->o_res.f_attr); } sattr->ia_valid = ia_old; } @@ -3204,13 +3193,9 @@ static int _nfs4_do_open(struct inode *dir, opendata->f_attr.mdsthreshold = NULL; } - nfs4_label_free(olabel); - nfs4_opendata_put(opendata); nfs4_put_state_owner(sp); return 0; -err_free_label: - nfs4_label_free(olabel); err_opendata_put: nfs4_opendata_put(opendata); err_put_state_owner: @@ -3355,8 +3340,7 @@ zero_stateid: static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, - struct nfs_open_context *ctx, struct nfs4_label *ilabel, - struct nfs4_label *olabel) + struct nfs_open_context *ctx, struct nfs4_label *ilabel) { struct nfs_server *server = NFS_SERVER(inode); __u32 bitmask[NFS4_BITMASK_SZ]; @@ -3370,7 +3354,6 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, }; struct nfs_setattrres res = { .fattr = fattr, - .label = olabel, .server = server, }; struct nfs4_exception exception = { @@ -3387,7 +3370,7 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, adjust_flags |= NFS_INO_INVALID_OTHER; do { - nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, olabel), + nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), inode, adjust_flags); err = _nfs4_do_setattr(inode, &arg, &res, cred, ctx); @@ -3562,7 +3545,6 @@ static void nfs4_close_done(struct rpc_task *task, void *data) .stateid = &calldata->arg.stateid, }; - dprintk("%s: begin!\n", __func__); if (!nfs4_sequence_done(task, &calldata->res.seq_res)) return; trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status); @@ -3617,7 +3599,7 @@ out_release: task->tk_status = 0; nfs_release_seqid(calldata->arg.seqid); nfs_refresh_inode(calldata->inode, &calldata->fattr); - dprintk("%s: done, ret = %d!\n", __func__, task->tk_status); + dprintk("%s: ret = %d\n", __func__, task->tk_status); return; out_restart: task->tk_status = 0; @@ -3635,7 +3617,6 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) bool is_rdonly, is_wronly, is_rdwr; int call_close = 0; - dprintk("%s: begin!\n", __func__); if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) goto out_wait; @@ -3709,7 +3690,6 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) &calldata->res.seq_res, task) != 0) nfs_release_seqid(calldata->arg.seqid); - dprintk("%s: done!\n", __func__); return; out_no_action: task->tk_action = NULL; @@ -3942,6 +3922,8 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) .interruptible = true, }; int err; + + nfs4_server_set_init_caps(server); do { err = nfs4_handle_exception(server, _nfs4_server_capabilities(server, fhandle), @@ -4105,7 +4087,6 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh, { int error; struct nfs_fattr *fattr = info->fattr; - struct nfs4_label *label = fattr->label; error = nfs4_server_capabilities(server, mntfh); if (error < 0) { @@ -4113,7 +4094,7 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh, return error; } - error = nfs4_proc_getattr(server, mntfh, fattr, label, NULL); + error = nfs4_proc_getattr(server, mntfh, fattr, NULL); if (error < 0) { dprintk("nfs4_get_root: getattr error = %d\n", -error); goto out; @@ -4176,8 +4157,7 @@ out: } static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { __u32 bitmask[NFS4_BITMASK_SZ]; struct nfs4_getattr_arg args = { @@ -4186,7 +4166,6 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, }; struct nfs4_getattr_res res = { .fattr = fattr, - .label = label, .server = server, }; struct rpc_message msg = { @@ -4203,7 +4182,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) task_flags |= RPC_TASK_TIMEOUT; - nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode, 0); + nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), inode, 0); nfs_fattr_init(fattr); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); return nfs4_do_call_sync(server->client, server, &msg, @@ -4211,15 +4190,14 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, } int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_getattr(server, fhandle, fattr, label, inode); + err = _nfs4_proc_getattr(server, fhandle, fattr, inode); trace_nfs4_getattr(server, fhandle, fattr, err); err = nfs4_handle_exception(server, err, &exception); @@ -4251,7 +4229,6 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, struct inode *inode = d_inode(dentry); const struct cred *cred = NULL; struct nfs_open_context *ctx = NULL; - struct nfs4_label *label = NULL; int status; if (pnfs_ld_layoutret_on_setattr(inode) && @@ -4277,26 +4254,21 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, cred = ctx->cred; } - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (IS_ERR(label)) - return PTR_ERR(label); - /* Return any delegations if we're going to change ACLs */ if ((sattr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) nfs4_inode_make_writeable(inode); - status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL, label); + status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL); if (status == 0) { nfs_setattr_update_inode(inode, sattr, fattr); - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr); } - nfs4_label_free(label); return status; } static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(dir); int status; @@ -4308,7 +4280,6 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct nfs4_lookup_res res = { .server = server, .fattr = fattr, - .label = label, .fh = fhandle, }; struct rpc_message msg = { @@ -4325,7 +4296,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, if (nfs_lookup_is_soft_revalidate(dentry)) task_flags |= RPC_TASK_TIMEOUT; - args.bitmask = nfs4_bitmask(server, label); + args.bitmask = nfs4_bitmask(server, fattr->label); nfs_fattr_init(fattr); @@ -4347,7 +4318,7 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { struct nfs4_exception exception = { .interruptible = true, @@ -4356,7 +4327,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, const struct qstr *name = &dentry->d_name; int err; do { - err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr, label); + err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr); trace_nfs4_lookup(dir, name, err); switch (err) { case -NFS4ERR_BADNAME: @@ -4392,13 +4363,12 @@ out: } static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; struct rpc_clnt *client = NFS_CLIENT(dir); - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, label); + status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); if (client != NFS_CLIENT(dir)) { rpc_shutdown_client(client); nfs_fixup_secinfo_attributes(fattr); @@ -4413,15 +4383,14 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry, struct rpc_clnt *client = NFS_CLIENT(dir); int status; - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, NULL); + status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); if (status < 0) return ERR_PTR(status); return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; } static int _nfs4_proc_lookupp(struct inode *inode, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct rpc_clnt *clnt = NFS_CLIENT(inode); struct nfs_server *server = NFS_SERVER(inode); @@ -4433,7 +4402,6 @@ static int _nfs4_proc_lookupp(struct inode *inode, struct nfs4_lookupp_res res = { .server = server, .fattr = fattr, - .label = label, .fh = fhandle, }; struct rpc_message msg = { @@ -4446,7 +4414,7 @@ static int _nfs4_proc_lookupp(struct inode *inode, if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL) task_flags |= RPC_TASK_TIMEOUT; - args.bitmask = nfs4_bitmask(server, label); + args.bitmask = nfs4_bitmask(server, fattr->label); nfs_fattr_init(fattr); @@ -4458,14 +4426,14 @@ static int _nfs4_proc_lookupp(struct inode *inode, } static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_lookupp(inode, fhandle, fattr, label); + err = _nfs4_proc_lookupp(inode, fhandle, fattr); trace_nfs4_lookupp(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); @@ -4792,7 +4760,6 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct }; struct nfs4_link_res res = { .server = server, - .label = NULL, }; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LINK], @@ -4801,18 +4768,12 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct }; int status = -ENOMEM; - res.fattr = nfs_alloc_fattr(); + res.fattr = nfs_alloc_fattr_with_label(server); if (res.fattr == NULL) goto out; - res.label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(res.label)) { - status = PTR_ERR(res.label); - goto out; - } - nfs4_inode_make_writeable(inode); - nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.label), inode, + nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.fattr->label), inode, NFS_INO_INVALID_CHANGE); status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { @@ -4821,12 +4782,9 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct nfs4_inc_nlink(inode); status = nfs_post_op_update_inode(inode, res.fattr); if (!status) - nfs_setsecurity(inode, res.fattr, res.label); + nfs_setsecurity(inode, res.fattr); } - - nfs4_label_free(res.label); - out: nfs_free_fattr(res.fattr); return status; @@ -4852,7 +4810,6 @@ struct nfs4_createdata { struct nfs4_create_res res; struct nfs_fh fh; struct nfs_fattr fattr; - struct nfs4_label *label; }; static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, @@ -4864,8 +4821,8 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, if (data != NULL) { struct nfs_server *server = NFS_SERVER(dir); - data->label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(data->label)) + data->fattr.label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(data->fattr.label)) goto out_free; data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE]; @@ -4876,12 +4833,11 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, data->arg.name = name; data->arg.attrs = sattr; data->arg.ftype = ftype; - data->arg.bitmask = nfs4_bitmask(server, data->label); + data->arg.bitmask = nfs4_bitmask(server, data->fattr.label); data->arg.umask = current_umask(); data->res.server = server; data->res.fh = &data->fh; data->res.fattr = &data->fattr; - data->res.label = data->label; nfs_fattr_init(data->res.fattr); } return data; @@ -4903,14 +4859,14 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ data->res.fattr->time_start, NFS_INO_INVALID_DATA); spin_unlock(&dir->i_lock); - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); } return status; } static void nfs4_free_createdata(struct nfs4_createdata *data) { - nfs4_label_free(data->label); + nfs4_label_free(data->fattr.label); kfree(data); } @@ -5348,8 +5304,6 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { - dprintk("--> %s\n", __func__); - if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) @@ -6005,17 +5959,18 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, size_t buflen) { struct nfs_server *server = NFS_SERVER(inode); - struct nfs_fattr fattr; struct nfs4_label label = {0, 0, buflen, buf}; u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL }; + struct nfs_fattr fattr = { + .label = &label, + }; struct nfs4_getattr_arg arg = { .fh = NFS_FH(inode), .bitmask = bitmask, }; struct nfs4_getattr_res res = { .fattr = &fattr, - .label = &label, .server = server, }; struct rpc_message msg = { @@ -6057,8 +6012,7 @@ static int nfs4_get_security_label(struct inode *inode, void *buf, static int _nfs4_do_set_security_label(struct inode *inode, struct nfs4_label *ilabel, - struct nfs_fattr *fattr, - struct nfs4_label *olabel) + struct nfs_fattr *fattr) { struct iattr sattr = {0}; @@ -6073,7 +6027,6 @@ static int _nfs4_do_set_security_label(struct inode *inode, }; struct nfs_setattrres res = { .fattr = fattr, - .label = olabel, .server = server, }; struct rpc_message msg = { @@ -6094,15 +6047,13 @@ static int _nfs4_do_set_security_label(struct inode *inode, static int nfs4_do_set_security_label(struct inode *inode, struct nfs4_label *ilabel, - struct nfs_fattr *fattr, - struct nfs4_label *olabel) + struct nfs_fattr *fattr) { struct nfs4_exception exception = { }; int err; do { - err = _nfs4_do_set_security_label(inode, ilabel, - fattr, olabel); + err = _nfs4_do_set_security_label(inode, ilabel, fattr); trace_nfs4_set_security_label(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); @@ -6113,32 +6064,21 @@ static int nfs4_do_set_security_label(struct inode *inode, static int nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) { - struct nfs4_label ilabel, *olabel = NULL; - struct nfs_fattr fattr; + struct nfs4_label ilabel = {0, 0, buflen, (char *)buf }; + struct nfs_fattr *fattr; int status; if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) return -EOPNOTSUPP; - nfs_fattr_init(&fattr); - - ilabel.pi = 0; - ilabel.lfs = 0; - ilabel.label = (char *)buf; - ilabel.len = buflen; - - olabel = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (IS_ERR(olabel)) { - status = -PTR_ERR(olabel); - goto out; - } + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); + if (fattr == NULL) + return -ENOMEM; - status = nfs4_do_set_security_label(inode, &ilabel, &fattr, olabel); + status = nfs4_do_set_security_label(inode, &ilabel, fattr); if (status == 0) - nfs_setsecurity(inode, &fattr, olabel); + nfs_setsecurity(inode, fattr); - nfs4_label_free(olabel); -out: return status; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ @@ -7004,7 +6944,6 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) struct nfs4_lockdata *data = calldata; struct nfs4_state *state = data->lsp->ls_state; - dprintk("%s: begin!\n", __func__); if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) goto out_wait; /* Do we need to do an open_to_lock_owner? */ @@ -7038,7 +6977,7 @@ out_release_lock_seqid: nfs_release_seqid(data->arg.lock_seqid); out_wait: nfs4_sequence_done(task, &data->res.seq_res); - dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status); + dprintk("%s: ret = %d\n", __func__, data->rpc_status); } static void nfs4_lock_done(struct rpc_task *task, void *calldata) @@ -7046,8 +6985,6 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) struct nfs4_lockdata *data = calldata; struct nfs4_lock_state *lsp = data->lsp; - dprintk("%s: begin!\n", __func__); - if (!nfs4_sequence_done(task, &data->res.seq_res)) return; @@ -7081,7 +7018,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) goto out_restart; } out_done: - dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); + dprintk("%s: ret = %d!\n", __func__, data->rpc_status); return; out_restart: if (!data->cancelled) @@ -7093,7 +7030,6 @@ static void nfs4_lock_release(void *calldata) { struct nfs4_lockdata *data = calldata; - dprintk("%s: begin!\n", __func__); nfs_free_seqid(data->arg.open_seqid); if (data->cancelled && data->rpc_status == 0) { struct rpc_task *task; @@ -7107,7 +7043,6 @@ static void nfs4_lock_release(void *calldata) nfs4_put_lock_state(data->lsp); put_nfs_open_context(data->ctx); kfree(data); - dprintk("%s: done!\n", __func__); } static const struct rpc_call_ops nfs4_lock_ops = { @@ -7154,7 +7089,6 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f if (client->cl_minorversion) task_setup_data.flags |= RPC_TASK_MOVEABLE; - dprintk("%s: begin!\n", __func__); data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file), fl->fl_u.nfs4_fl.owner, recovery_type == NFS_LOCK_NEW ? GFP_KERNEL : GFP_NOFS); @@ -7185,7 +7119,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f data->cancelled = true; trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); rpc_put_task(task); - dprintk("%s: done, ret = %d!\n", __func__, ret); + dprintk("%s: ret = %d\n", __func__, ret); return ret; } @@ -8856,14 +8790,12 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task, struct nfs4_get_lease_time_data *data = (struct nfs4_get_lease_time_data *)calldata; - dprintk("--> %s\n", __func__); /* just setup sequence, do not trigger session recovery since we're invoked within one */ nfs4_setup_sequence(data->clp, &data->args->la_seq_args, &data->res->lr_seq_res, task); - dprintk("<-- %s\n", __func__); } /* @@ -8875,13 +8807,11 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata) struct nfs4_get_lease_time_data *data = (struct nfs4_get_lease_time_data *)calldata; - dprintk("--> %s\n", __func__); if (!nfs4_sequence_done(task, &data->res->lr_seq_res)) return; switch (task->tk_status) { case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: - dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status); rpc_delay(task, NFS4_POLL_RETRY_MIN); task->tk_status = 0; fallthrough; @@ -8889,7 +8819,6 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); return; } - dprintk("<-- %s\n", __func__); } static const struct rpc_call_ops nfs4_get_lease_time_ops = { @@ -9121,7 +9050,6 @@ int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred) dprintk("%s client>seqid %d sessionid %u:%u:%u:%u\n", __func__, clp->cl_seqid, ptr[0], ptr[1], ptr[2], ptr[3]); out: - dprintk("<-- %s\n", __func__); return status; } @@ -9139,8 +9067,6 @@ int nfs4_proc_destroy_session(struct nfs4_session *session, }; int status = 0; - dprintk("--> nfs4_proc_destroy_session\n"); - /* session is still being setup */ if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state)) return 0; @@ -9152,8 +9078,6 @@ int nfs4_proc_destroy_session(struct nfs4_session *session, if (status) dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " "Session has been destroyed regardless...\n", status); - - dprintk("<-- nfs4_proc_destroy_session\n"); return status; } @@ -9201,7 +9125,7 @@ static void nfs41_sequence_call_done(struct rpc_task *task, void *data) if (task->tk_status < 0) { dprintk("%s ERROR %d\n", __func__, task->tk_status); if (refcount_read(&clp->cl_count) == 1) - goto out; + return; if (nfs41_sequence_handle_errors(task, clp) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -9209,8 +9133,6 @@ static void nfs41_sequence_call_done(struct rpc_task *task, void *data) } } dprintk("%s rpc_cred %p\n", __func__, task->tk_msg.rpc_cred); -out: - dprintk("<-- %s\n", __func__); } static void nfs41_sequence_prepare(struct rpc_task *task, void *data) @@ -9357,7 +9279,6 @@ static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data) struct nfs_client *clp = calldata->clp; struct nfs4_sequence_res *res = &calldata->res.seq_res; - dprintk("--> %s\n", __func__); if (!nfs41_sequence_done(task, res)) return; @@ -9366,7 +9287,6 @@ static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data) rpc_restart_call_prepare(task); return; } - dprintk("<-- %s\n", __func__); } static void nfs4_free_reclaim_complete_data(void *data) @@ -9401,7 +9321,6 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp, }; int status = -ENOMEM; - dprintk("--> %s\n", __func__); calldata = kzalloc(sizeof(*calldata), GFP_NOFS); if (calldata == NULL) goto out; @@ -9424,19 +9343,15 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) struct nfs4_layoutget *lgp = calldata; struct nfs_server *server = NFS_SERVER(lgp->args.inode); - dprintk("--> %s\n", __func__); nfs4_setup_sequence(server->nfs_client, &lgp->args.seq_args, &lgp->res.seq_res, task); - dprintk("<-- %s\n", __func__); } static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) { struct nfs4_layoutget *lgp = calldata; - dprintk("--> %s\n", __func__); nfs41_sequence_process(task, &lgp->res.seq_res); - dprintk("<-- %s\n", __func__); } static int @@ -9525,7 +9440,6 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, status = err; } out: - dprintk("<-- %s\n", __func__); return status; } @@ -9539,10 +9453,8 @@ static void nfs4_layoutget_release(void *calldata) { struct nfs4_layoutget *lgp = calldata; - dprintk("--> %s\n", __func__); nfs4_sequence_free_slot(&lgp->res.seq_res); pnfs_layoutget_free(lgp); - dprintk("<-- %s\n", __func__); } static const struct rpc_call_ops nfs4_layoutget_call_ops = { @@ -9578,8 +9490,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) }; int status = 0; - dprintk("--> %s\n", __func__); - nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); @@ -9615,7 +9525,6 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata) { struct nfs4_layoutreturn *lrp = calldata; - dprintk("--> %s\n", __func__); nfs4_setup_sequence(lrp->clp, &lrp->args.seq_args, &lrp->res.seq_res, @@ -9629,8 +9538,6 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) struct nfs4_layoutreturn *lrp = calldata; struct nfs_server *server; - dprintk("--> %s\n", __func__); - if (!nfs41_sequence_process(task, &lrp->res.seq_res)) return; @@ -9661,7 +9568,6 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) break; goto out_restart; } - dprintk("<-- %s\n", __func__); return; out_restart: task->tk_status = 0; @@ -9674,7 +9580,6 @@ static void nfs4_layoutreturn_release(void *calldata) struct nfs4_layoutreturn *lrp = calldata; struct pnfs_layout_hdr *lo = lrp->args.layout; - dprintk("--> %s\n", __func__); pnfs_layoutreturn_free_lsegs(lo, &lrp->args.stateid, &lrp->args.range, lrp->res.lrs_present ? &lrp->res.stateid : NULL); nfs4_sequence_free_slot(&lrp->res.seq_res); @@ -9684,7 +9589,6 @@ static void nfs4_layoutreturn_release(void *calldata) nfs_iput_and_deactive(lrp->inode); put_cred(lrp->cred); kfree(calldata); - dprintk("<-- %s\n", __func__); } static const struct rpc_call_ops nfs4_layoutreturn_call_ops = { @@ -9715,7 +9619,6 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) NFS_SP4_MACH_CRED_PNFS_CLEANUP, &task_setup_data.rpc_client, &msg); - dprintk("--> %s\n", __func__); lrp->inode = nfs_igrab_and_active(lrp->args.inode); if (!sync) { if (!lrp->inode) { @@ -9762,7 +9665,6 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server, }; int status; - dprintk("--> %s\n", __func__); status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); if (res.notification & ~args.notify_types) dprintk("%s: unsupported notification\n", __func__); @@ -9934,7 +9836,6 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, msg.rpc_cred = cred; } - dprintk("--> %s\n", __func__); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); status = nfs4_call_sync_custom(&task_setup); dprintk("<-- %s status=%d\n", __func__, status); @@ -10158,6 +10059,10 @@ static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata) static void nfs41_free_stateid_release(void *calldata) { + struct nfs_free_stateid_data *data = calldata; + struct nfs_client *clp = data->server->nfs_client; + + nfs_put_client(clp); kfree(calldata); } @@ -10194,6 +10099,10 @@ static int nfs41_free_stateid(struct nfs_server *server, }; struct nfs_free_stateid_data *data; struct rpc_task *task; + struct nfs_client *clp = server->nfs_client; + + if (!refcount_inc_not_zero(&clp->cl_count)) + return -EIO; nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID, &task_setup.rpc_client, &msg); diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index 4145a0138907..5db460476bf2 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -511,12 +511,16 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, struct nfs4_slot *slot, struct nfs4_sequence_res *res) { + u32 target_highest_slotid = min(res->sr_target_highest_slotid, + NFS4_MAX_SLOTID); + u32 highest_slotid = min(res->sr_highest_slotid, NFS4_MAX_SLOTID); + spin_lock(&tbl->slot_tbl_lock); - if (!nfs41_is_outlier_target_slotid(tbl, res->sr_target_highest_slotid)) - nfs41_set_target_slotid_locked(tbl, res->sr_target_highest_slotid); + if (!nfs41_is_outlier_target_slotid(tbl, target_highest_slotid)) + nfs41_set_target_slotid_locked(tbl, target_highest_slotid); if (tbl->generation == slot->generation) - nfs41_set_server_slotid_locked(tbl, res->sr_highest_slotid); - nfs41_set_max_slotid_locked(tbl, res->sr_target_highest_slotid); + nfs41_set_server_slotid_locked(tbl, highest_slotid); + nfs41_set_max_slotid_locked(tbl, target_highest_slotid); spin_unlock(&tbl->slot_tbl_lock); } diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 3de425f59b3a..351616c61df5 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -12,6 +12,7 @@ #define NFS4_DEF_SLOT_TABLE_SIZE (64U) #define NFS4_DEF_CB_SLOT_TABLE_SIZE (16U) #define NFS4_MAX_SLOT_TABLE (1024U) +#define NFS4_MAX_SLOTID (NFS4_MAX_SLOT_TABLE - 1U) #define NFS4_NO_SLOT ((u32)-1) #if IS_ENABLED(CONFIG_NFS_V4) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index f22818a80c2c..ecc4594299d6 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1194,10 +1194,7 @@ static int nfs4_run_state_manager(void *); static void nfs4_clear_state_manager_bit(struct nfs_client *clp) { - smp_mb__before_atomic(); - clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); - smp_mb__after_atomic(); - wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING); + clear_and_wake_up_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); rpc_wake_up(&clp->cl_rpcwaitq); } diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 7a2567aa2b86..6ee6ad3674a2 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -9,322 +9,10 @@ #define _TRACE_NFS4_H #include <linux/tracepoint.h> +#include <trace/events/sunrpc_base.h> -TRACE_DEFINE_ENUM(EPERM); -TRACE_DEFINE_ENUM(ENOENT); -TRACE_DEFINE_ENUM(EIO); -TRACE_DEFINE_ENUM(ENXIO); -TRACE_DEFINE_ENUM(EACCES); -TRACE_DEFINE_ENUM(EEXIST); -TRACE_DEFINE_ENUM(EXDEV); -TRACE_DEFINE_ENUM(ENOTDIR); -TRACE_DEFINE_ENUM(EISDIR); -TRACE_DEFINE_ENUM(EFBIG); -TRACE_DEFINE_ENUM(ENOSPC); -TRACE_DEFINE_ENUM(EROFS); -TRACE_DEFINE_ENUM(EMLINK); -TRACE_DEFINE_ENUM(ENAMETOOLONG); -TRACE_DEFINE_ENUM(ENOTEMPTY); -TRACE_DEFINE_ENUM(EDQUOT); -TRACE_DEFINE_ENUM(ESTALE); -TRACE_DEFINE_ENUM(EBADHANDLE); -TRACE_DEFINE_ENUM(EBADCOOKIE); -TRACE_DEFINE_ENUM(ENOTSUPP); -TRACE_DEFINE_ENUM(ETOOSMALL); -TRACE_DEFINE_ENUM(EREMOTEIO); -TRACE_DEFINE_ENUM(EBADTYPE); -TRACE_DEFINE_ENUM(EAGAIN); -TRACE_DEFINE_ENUM(ELOOP); -TRACE_DEFINE_ENUM(EOPNOTSUPP); -TRACE_DEFINE_ENUM(EDEADLK); -TRACE_DEFINE_ENUM(ENOMEM); -TRACE_DEFINE_ENUM(EKEYEXPIRED); -TRACE_DEFINE_ENUM(ETIMEDOUT); -TRACE_DEFINE_ENUM(ERESTARTSYS); -TRACE_DEFINE_ENUM(ECONNREFUSED); -TRACE_DEFINE_ENUM(ECONNRESET); -TRACE_DEFINE_ENUM(ENETUNREACH); -TRACE_DEFINE_ENUM(EHOSTUNREACH); -TRACE_DEFINE_ENUM(EHOSTDOWN); -TRACE_DEFINE_ENUM(EPIPE); -TRACE_DEFINE_ENUM(EPFNOSUPPORT); -TRACE_DEFINE_ENUM(EPROTONOSUPPORT); - -TRACE_DEFINE_ENUM(NFS4_OK); -TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); -TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); -TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); -TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); -TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); -TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); -TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); -TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); -TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); -TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); -TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DELAY); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); -TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); -TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_EXIST); -TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FBIG); -TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); -TRACE_DEFINE_ENUM(NFS4ERR_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_INVAL); -TRACE_DEFINE_ENUM(NFS4ERR_IO); -TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); -TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); -TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); -TRACE_DEFINE_ENUM(NFS4ERR_MLINK); -TRACE_DEFINE_ENUM(NFS4ERR_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFS4ERR_NOENT); -TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); -TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); -TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_NXIO); -TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); -TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); -TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_PERM); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); -TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); -TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); -TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); -TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_ROFS); -TRACE_DEFINE_ENUM(NFS4ERR_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); -TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFS4ERR_STALE); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); -TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); -TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); -TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); -TRACE_DEFINE_ENUM(NFS4ERR_XDEV); - -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); - -#define show_nfsv4_errors(error) \ - __print_symbolic(error, \ - { NFS4_OK, "OK" }, \ - /* Mapped by nfs4_stat_to_errno() */ \ - { EPERM, "EPERM" }, \ - { ENOENT, "ENOENT" }, \ - { EIO, "EIO" }, \ - { ENXIO, "ENXIO" }, \ - { EACCES, "EACCES" }, \ - { EEXIST, "EEXIST" }, \ - { EXDEV, "EXDEV" }, \ - { ENOTDIR, "ENOTDIR" }, \ - { EISDIR, "EISDIR" }, \ - { EFBIG, "EFBIG" }, \ - { ENOSPC, "ENOSPC" }, \ - { EROFS, "EROFS" }, \ - { EMLINK, "EMLINK" }, \ - { ENAMETOOLONG, "ENAMETOOLONG" }, \ - { ENOTEMPTY, "ENOTEMPTY" }, \ - { EDQUOT, "EDQUOT" }, \ - { ESTALE, "ESTALE" }, \ - { EBADHANDLE, "EBADHANDLE" }, \ - { EBADCOOKIE, "EBADCOOKIE" }, \ - { ENOTSUPP, "ENOTSUPP" }, \ - { ETOOSMALL, "ETOOSMALL" }, \ - { EREMOTEIO, "EREMOTEIO" }, \ - { EBADTYPE, "EBADTYPE" }, \ - { EAGAIN, "EAGAIN" }, \ - { ELOOP, "ELOOP" }, \ - { EOPNOTSUPP, "EOPNOTSUPP" }, \ - { EDEADLK, "EDEADLK" }, \ - /* RPC errors */ \ - { ENOMEM, "ENOMEM" }, \ - { EKEYEXPIRED, "EKEYEXPIRED" }, \ - { ETIMEDOUT, "ETIMEDOUT" }, \ - { ERESTARTSYS, "ERESTARTSYS" }, \ - { ECONNREFUSED, "ECONNREFUSED" }, \ - { ECONNRESET, "ECONNRESET" }, \ - { ENETUNREACH, "ENETUNREACH" }, \ - { EHOSTUNREACH, "EHOSTUNREACH" }, \ - { EHOSTDOWN, "EHOSTDOWN" }, \ - { EPIPE, "EPIPE" }, \ - { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ - { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ - /* NFSv4 native errors */ \ - { NFS4ERR_ACCESS, "ACCESS" }, \ - { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ - { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ - { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ - { NFS4ERR_BADCHAR, "BADCHAR" }, \ - { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ - { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ - { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ - { NFS4ERR_BADLABEL, "BADLABEL" }, \ - { NFS4ERR_BADNAME, "BADNAME" }, \ - { NFS4ERR_BADOWNER, "BADOWNER" }, \ - { NFS4ERR_BADSESSION, "BADSESSION" }, \ - { NFS4ERR_BADSLOT, "BADSLOT" }, \ - { NFS4ERR_BADTYPE, "BADTYPE" }, \ - { NFS4ERR_BADXDR, "BADXDR" }, \ - { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ - { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ - { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ - { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ - { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ - { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ - { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ - { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ - { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ - { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ - "CONN_NOT_BOUND_TO_SESSION" }, \ - { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ - { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ - { NFS4ERR_DELAY, "DELAY" }, \ - { NFS4ERR_DELEG_ALREADY_WANTED, \ - "DELEG_ALREADY_WANTED" }, \ - { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ - { NFS4ERR_DENIED, "DENIED" }, \ - { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ - { NFS4ERR_DQUOT, "DQUOT" }, \ - { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ - { NFS4ERR_EXIST, "EXIST" }, \ - { NFS4ERR_EXPIRED, "EXPIRED" }, \ - { NFS4ERR_FBIG, "FBIG" }, \ - { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ - { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ - { NFS4ERR_GRACE, "GRACE" }, \ - { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ - { NFS4ERR_INVAL, "INVAL" }, \ - { NFS4ERR_IO, "IO" }, \ - { NFS4ERR_ISDIR, "ISDIR" }, \ - { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ - { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ - { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ - { NFS4ERR_LOCKED, "LOCKED" }, \ - { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ - { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ - { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ - { NFS4ERR_MLINK, "MLINK" }, \ - { NFS4ERR_MOVED, "MOVED" }, \ - { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFS4ERR_NOENT, "NOENT" }, \ - { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ - { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ - { NFS4ERR_NOSPC, "NOSPC" }, \ - { NFS4ERR_NOTDIR, "NOTDIR" }, \ - { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ - { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ - { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ - { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ - { NFS4ERR_NXIO, "NXIO" }, \ - { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ - { NFS4ERR_OPENMODE, "OPENMODE" }, \ - { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ - { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ - { NFS4ERR_PERM, "PERM" }, \ - { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ - { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ - { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ - { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ - { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ - { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ - { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ - { NFS4ERR_REP_TOO_BIG_TO_CACHE, \ - "REP_TOO_BIG_TO_CACHE" }, \ - { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ - { NFS4ERR_RESOURCE, "RESOURCE" }, \ - { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ - { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ - { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ - { NFS4ERR_ROFS, "ROFS" }, \ - { NFS4ERR_SAME, "SAME" }, \ - { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ - { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ - { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ - { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ - { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ - { NFS4ERR_STALE, "STALE" }, \ - { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ - { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ - { NFS4ERR_SYMLINK, "SYMLINK" }, \ - { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ - { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ - { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ - { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ - { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ - { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ - { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ - { NFS4ERR_XDEV, "XDEV" }, \ - /* ***** Internal to Linux NFS client ***** */ \ - { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ - { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) - -#define show_open_flags(flags) \ - __print_flags(flags, "|", \ - { O_CREAT, "O_CREAT" }, \ - { O_EXCL, "O_EXCL" }, \ - { O_TRUNC, "O_TRUNC" }, \ - { O_DIRECT, "O_DIRECT" }) - -#define show_fmode_flags(mode) \ - __print_flags(mode, "|", \ - { ((__force unsigned long)FMODE_READ), "READ" }, \ - { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ - { ((__force unsigned long)FMODE_EXEC), "EXEC" }) +#include <trace/events/fs.h> +#include <trace/events/nfs.h> #define show_nfs_fattr_flags(valid) \ __print_flags((unsigned long)valid, "|", \ @@ -365,7 +53,7 @@ DECLARE_EVENT_CLASS(nfs4_clientid_event, TP_printk( "error=%ld (%s) dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __get_str(dstaddr) ) ); @@ -389,29 +77,6 @@ DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session); DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence); DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete); -#define show_nfs4_sequence_status_flags(status) \ - __print_flags((unsigned long)status, "|", \ - { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, \ - "CB_GSS_CONTEXTS_EXPIRING" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, \ - "CB_GSS_CONTEXTS_EXPIRED" }, \ - { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, \ - "EXPIRED_ALL_STATE_REVOKED" }, \ - { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, \ - "EXPIRED_SOME_STATE_REVOKED" }, \ - { SEQ4_STATUS_ADMIN_STATE_REVOKED, \ - "ADMIN_STATE_REVOKED" }, \ - { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, \ - "RECALLABLE_STATE_REVOKED" }, \ - { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ - { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, \ - "RESTART_RECLAIM_NEEDED" }, \ - { SEQ4_STATUS_CB_PATH_DOWN_SESSION, \ - "CB_PATH_DOWN_SESSION" }, \ - { SEQ4_STATUS_BACKCHANNEL_FAULT, \ - "BACKCHANNEL_FAULT" }) - TRACE_EVENT(nfs4_sequence_done, TP_PROTO( const struct nfs4_session *session, @@ -425,7 +90,7 @@ TRACE_EVENT(nfs4_sequence_done, __field(unsigned int, seq_nr) __field(unsigned int, highest_slotid) __field(unsigned int, target_highest_slotid) - __field(unsigned int, status_flags) + __field(unsigned long, status_flags) __field(unsigned long, error) ), @@ -444,16 +109,16 @@ TRACE_EVENT(nfs4_sequence_done, TP_printk( "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u target_highest_slotid=%u " - "status_flags=%u (%s)", + "status_flags=0x%lx (%s)", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, __entry->highest_slotid, __entry->target_highest_slotid, __entry->status_flags, - show_nfs4_sequence_status_flags(__entry->status_flags) + show_nfs4_seq4_status(__entry->status_flags) ) ); @@ -490,7 +155,7 @@ TRACE_EVENT(nfs4_cb_sequence, "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, @@ -527,7 +192,7 @@ TRACE_EVENT(nfs4_cb_seqid_err, "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, @@ -535,6 +200,49 @@ TRACE_EVENT(nfs4_cb_seqid_err, ) ); +TRACE_EVENT(nfs4_cb_offload, + TP_PROTO( + const struct nfs_fh *cb_fh, + const nfs4_stateid *cb_stateid, + uint64_t cb_count, + int cb_error, + int cb_how_stable + ), + + TP_ARGS(cb_fh, cb_stateid, cb_count, cb_error, + cb_how_stable), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(u32, fhandle) + __field(loff_t, cb_count) + __field(int, cb_how) + __field(int, cb_stateid_seq) + __field(u32, cb_stateid_hash) + ), + + TP_fast_assign( + __entry->error = cb_error < 0 ? -cb_error : 0; + __entry->fhandle = nfs_fhandle_hash(cb_fh); + __entry->cb_stateid_seq = + be32_to_cpu(cb_stateid->seqid); + __entry->cb_stateid_hash = + nfs_stateid_hash(cb_stateid); + __entry->cb_count = cb_count; + __entry->cb_how = cb_how_stable; + ), + + TP_printk( + "error=%ld (%s) fhandle=0x%08x cb_stateid=%d:0x%08x " + "cb_count=%llu cb_how=%s", + -__entry->error, + show_nfs4_status(__entry->error), + __entry->fhandle, + __entry->cb_stateid_seq, __entry->cb_stateid_hash, + __entry->cb_count, + show_nfs_stable_how(__entry->cb_how) + ) +); #endif /* CONFIG_NFS_V4_1 */ TRACE_EVENT(nfs4_setup_sequence, @@ -661,7 +369,7 @@ TRACE_EVENT(nfs4_state_mgr_failed, "hostname=%s clp state=%s error=%ld (%s) section=%s", __get_str(hostname), show_nfs4_clp_state(__entry->state), -__entry->error, - show_nfsv4_errors(__entry->error), __get_str(section) + show_nfs4_status(__entry->error), __get_str(section) ) ) @@ -694,8 +402,8 @@ TRACE_EVENT(nfs4_xdr_bad_operation, __entry->expected = expected; ), - TP_printk( - "task:%u@%d xid=0x%08x operation=%u, expected=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x operation=%u, expected=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->op, __entry->expected ) @@ -729,10 +437,10 @@ DECLARE_EVENT_CLASS(nfs4_xdr_event, __entry->error = error; ), - TP_printk( - "task:%u@%d xid=0x%08x error=%ld (%s) operation=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x error=%ld (%s) operation=%u", __entry->task_id, __entry->client_id, __entry->xid, - -__entry->error, show_nfsv4_errors(__entry->error), + -__entry->error, show_nfs4_status(__entry->error), __entry->op ) ); @@ -793,8 +501,8 @@ DECLARE_EVENT_CLASS(nfs4_open_event, TP_STRUCT__entry( __field(unsigned long, error) - __field(unsigned int, flags) - __field(unsigned int, fmode) + __field(unsigned long, flags) + __field(unsigned long, fmode) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) @@ -812,7 +520,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->error = -error; __entry->flags = flags; - __entry->fmode = (__force unsigned int)ctx->mode; + __entry->fmode = (__force unsigned long)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; if (!IS_ERR_OR_NULL(state)) { inode = state->inode; @@ -842,15 +550,15 @@ DECLARE_EVENT_CLASS(nfs4_open_event, ), TP_printk( - "error=%ld (%s) flags=%d (%s) fmode=%s " + "error=%ld (%s) flags=%lu (%s) fmode=%s " "fileid=%02x:%02x:%llu fhandle=0x%08x " "name=%02x:%02x:%llu/%s stateid=%d:0x%08x " "openstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->flags, - show_open_flags(__entry->flags), - show_fmode_flags(__entry->fmode), + show_fs_fcntl_open_flags(__entry->flags), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -904,7 +612,7 @@ TRACE_EVENT(nfs4_cached_open, TP_printk( "fmode=%s fileid=%02x:%02x:%llu " "fhandle=0x%08x stateid=%d:0x%08x", - __entry->fmode ? show_fmode_flags(__entry->fmode) : + __entry->fmode ? show_fs_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, @@ -951,8 +659,8 @@ TRACE_EVENT(nfs4_close, "error=%ld (%s) fmode=%s fileid=%02x:%02x:%llu " "fhandle=0x%08x openstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), - __entry->fmode ? show_fmode_flags(__entry->fmode) : + show_nfs4_status(__entry->error), + __entry->fmode ? show_fs_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, @@ -961,24 +669,6 @@ TRACE_EVENT(nfs4_close, ) ); -TRACE_DEFINE_ENUM(F_GETLK); -TRACE_DEFINE_ENUM(F_SETLK); -TRACE_DEFINE_ENUM(F_SETLKW); -TRACE_DEFINE_ENUM(F_RDLCK); -TRACE_DEFINE_ENUM(F_WRLCK); -TRACE_DEFINE_ENUM(F_UNLCK); - -#define show_lock_cmd(type) \ - __print_symbolic((int)type, \ - { F_GETLK, "GETLK" }, \ - { F_SETLK, "SETLK" }, \ - { F_SETLKW, "SETLKW" }) -#define show_lock_type(type) \ - __print_symbolic((int)type, \ - { F_RDLCK, "RDLCK" }, \ - { F_WRLCK, "WRLCK" }, \ - { F_UNLCK, "UNLCK" }) - DECLARE_EVENT_CLASS(nfs4_lock_event, TP_PROTO( const struct file_lock *request, @@ -991,8 +681,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, TP_STRUCT__entry( __field(unsigned long, error) - __field(int, cmd) - __field(char, type) + __field(unsigned long, cmd) + __field(unsigned long, type) __field(loff_t, start) __field(loff_t, end) __field(dev_t, dev) @@ -1024,9 +714,9 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, "fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), - show_lock_cmd(__entry->cmd), - show_lock_type(__entry->type), + show_nfs4_status(__entry->error), + show_fs_fcntl_cmd(__entry->cmd), + show_fs_fcntl_lock_type(__entry->type), (long long)__entry->start, (long long)__entry->end, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1061,8 +751,8 @@ TRACE_EVENT(nfs4_set_lock, TP_STRUCT__entry( __field(unsigned long, error) - __field(int, cmd) - __field(char, type) + __field(unsigned long, cmd) + __field(unsigned long, type) __field(loff_t, start) __field(loff_t, end) __field(dev_t, dev) @@ -1100,9 +790,9 @@ TRACE_EVENT(nfs4_set_lock, "fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x lockstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), - show_lock_cmd(__entry->cmd), - show_lock_type(__entry->type), + show_nfs4_status(__entry->error), + show_fs_fcntl_cmd(__entry->cmd), + show_fs_fcntl_lock_type(__entry->type), (long long)__entry->start, (long long)__entry->end, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1219,7 +909,7 @@ DECLARE_EVENT_CLASS(nfs4_set_delegation_event, TP_printk( "fmode=%s fileid=%02x:%02x:%llu fhandle=0x%08x", - show_fmode_flags(__entry->fmode), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle @@ -1266,7 +956,7 @@ TRACE_EVENT(nfs4_delegreturn_exit, "error=%ld (%s) dev=%02x:%02x fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fhandle, __entry->stateid_seq, __entry->stateid_hash @@ -1309,7 +999,7 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1356,7 +1046,7 @@ DECLARE_EVENT_CLASS(nfs4_lookup_event, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -1403,7 +1093,7 @@ TRACE_EVENT(nfs4_lookupp, TP_printk( "error=%ld (%s) inode=%02x:%02x:%llu", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->ino ) @@ -1442,7 +1132,7 @@ TRACE_EVENT(nfs4_rename, "error=%ld (%s) oldname=%02x:%02x:%llu/%s " "newname=%02x:%02x:%llu/%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->olddir, __get_str(oldname), @@ -1477,7 +1167,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_event, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle @@ -1535,7 +1225,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1588,7 +1278,7 @@ DECLARE_EVENT_CLASS(nfs4_getattr_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "valid=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1644,7 +1334,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1705,7 +1395,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1754,7 +1444,7 @@ DECLARE_EVENT_CLASS(nfs4_idmap_event, TP_printk( "error=%ld (%s) id=%u name=%s", - -__entry->error, show_nfsv4_errors(__entry->error), + -__entry->error, show_nfs4_status(__entry->error), __entry->id, __get_str(name) ) @@ -1832,7 +1522,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event, "offset=%lld count=%u res=%u stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1906,7 +1596,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event, "offset=%lld count=%u res=%u stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1970,7 +1660,7 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1990,16 +1680,6 @@ DEFINE_NFS4_COMMIT_EVENT(nfs4_commit); #ifdef CONFIG_NFS_V4_1 DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds); -TRACE_DEFINE_ENUM(IOMODE_READ); -TRACE_DEFINE_ENUM(IOMODE_RW); -TRACE_DEFINE_ENUM(IOMODE_ANY); - -#define show_pnfs_iomode(iomode) \ - __print_symbolic(iomode, \ - { IOMODE_READ, "READ" }, \ - { IOMODE_RW, "RW" }, \ - { IOMODE_ANY, "ANY" }) - TRACE_EVENT(nfs4_layoutget, TP_PROTO( const struct nfs_open_context *ctx, @@ -2055,11 +1735,11 @@ TRACE_EVENT(nfs4_layoutget, "iomode=%s offset=%llu count=%llu stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->offset, (unsigned long long)__entry->count, __entry->stateid_seq, __entry->stateid_hash, @@ -2153,7 +1833,7 @@ TRACE_EVENT(pnfs_update_layout, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->pos, (unsigned long long)__entry->count, __entry->layoutstateid_seq, __entry->layoutstateid_hash, @@ -2207,7 +1887,7 @@ DECLARE_EVENT_CLASS(pnfs_layout_event, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->pos, (unsigned long long)__entry->count, __entry->layoutstateid_seq, __entry->layoutstateid_hash, @@ -2352,7 +2032,7 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -2408,7 +2088,7 @@ TRACE_EVENT(ff_layout_commit_error, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%llu count=%u dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -2417,6 +2097,406 @@ TRACE_EVENT(ff_layout_commit_error, ) ); +TRACE_DEFINE_ENUM(NFS4_CONTENT_DATA); +TRACE_DEFINE_ENUM(NFS4_CONTENT_HOLE); + +#define show_llseek_mode(what) \ + __print_symbolic(what, \ + { NFS4_CONTENT_DATA, "DATA" }, \ + { NFS4_CONTENT_HOLE, "HOLE" }) + +#ifdef CONFIG_NFS_V4_2 +TRACE_EVENT(nfs4_llseek, + TP_PROTO( + const struct inode *inode, + const struct nfs42_seek_args *args, + const struct nfs42_seek_res *res, + int error + ), + + TP_ARGS(inode, args, res, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(u32, fhandle) + __field(u32, fileid) + __field(dev_t, dev) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(loff_t, offset_s) + __field(u32, what) + __field(loff_t, offset_r) + __field(u32, eof) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = args->sa_fh; + + __entry->fileid = nfsi->fileid; + __entry->dev = inode->i_sb->s_dev; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->offset_s = args->sa_offset; + __entry->stateid_seq = + be32_to_cpu(args->sa_stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&args->sa_stateid); + __entry->what = args->sa_what; + if (error) { + __entry->error = -error; + __entry->offset_r = 0; + __entry->eof = 0; + } else { + __entry->error = 0; + __entry->offset_r = res->sr_offset; + __entry->eof = res->sr_eof; + } + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x offset_s=%llu what=%s " + "offset_r=%llu eof=%u", + -__entry->error, + show_nfs4_status(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + __entry->offset_s, + show_llseek_mode(__entry->what), + __entry->offset_r, + __entry->eof + ) +); + +DECLARE_EVENT_CLASS(nfs4_sparse_event, + TP_PROTO( + const struct inode *inode, + const struct nfs42_falloc_args *args, + int error + ), + + TP_ARGS(inode, args, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(loff_t, offset) + __field(loff_t, len) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + __entry->error = error < 0 ? -error : 0; + __entry->offset = args->falloc_offset; + __entry->len = args->falloc_length; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(args->falloc_stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&args->falloc_stateid); + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x offset=%llu len=%llu", + -__entry->error, + show_nfs4_status(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + (long long)__entry->offset, + (long long)__entry->len + ) +); +#define DEFINE_NFS4_SPARSE_EVENT(name) \ + DEFINE_EVENT(nfs4_sparse_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + const struct nfs42_falloc_args *args, \ + int error \ + ), \ + TP_ARGS(inode, args, error)) +DEFINE_NFS4_SPARSE_EVENT(nfs4_fallocate); +DEFINE_NFS4_SPARSE_EVENT(nfs4_deallocate); + +TRACE_EVENT(nfs4_copy, + TP_PROTO( + const struct inode *src_inode, + const struct inode *dst_inode, + const struct nfs42_copy_args *args, + const struct nfs42_copy_res *res, + const struct nl4_server *nss, + int error + ), + + TP_ARGS(src_inode, dst_inode, args, res, nss, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(u32, src_fhandle) + __field(u32, src_fileid) + __field(u32, dst_fhandle) + __field(u32, dst_fileid) + __field(dev_t, src_dev) + __field(dev_t, dst_dev) + __field(int, src_stateid_seq) + __field(u32, src_stateid_hash) + __field(int, dst_stateid_seq) + __field(u32, dst_stateid_hash) + __field(loff_t, src_offset) + __field(loff_t, dst_offset) + __field(bool, sync) + __field(loff_t, len) + __field(int, res_stateid_seq) + __field(u32, res_stateid_hash) + __field(loff_t, res_count) + __field(bool, res_sync) + __field(bool, res_cons) + __field(bool, intra) + ), + + TP_fast_assign( + const struct nfs_inode *src_nfsi = NFS_I(src_inode); + const struct nfs_inode *dst_nfsi = NFS_I(dst_inode); + + __entry->src_fileid = src_nfsi->fileid; + __entry->src_dev = src_inode->i_sb->s_dev; + __entry->src_fhandle = nfs_fhandle_hash(args->src_fh); + __entry->src_offset = args->src_pos; + __entry->dst_fileid = dst_nfsi->fileid; + __entry->dst_dev = dst_inode->i_sb->s_dev; + __entry->dst_fhandle = nfs_fhandle_hash(args->dst_fh); + __entry->dst_offset = args->dst_pos; + __entry->len = args->count; + __entry->sync = args->sync; + __entry->src_stateid_seq = + be32_to_cpu(args->src_stateid.seqid); + __entry->src_stateid_hash = + nfs_stateid_hash(&args->src_stateid); + __entry->dst_stateid_seq = + be32_to_cpu(args->dst_stateid.seqid); + __entry->dst_stateid_hash = + nfs_stateid_hash(&args->dst_stateid); + __entry->intra = nss ? 0 : 1; + if (error) { + __entry->error = -error; + __entry->res_stateid_seq = 0; + __entry->res_stateid_hash = 0; + __entry->res_count = 0; + __entry->res_sync = 0; + __entry->res_cons = 0; + } else { + __entry->error = 0; + __entry->res_stateid_seq = + be32_to_cpu(res->write_res.stateid.seqid); + __entry->res_stateid_hash = + nfs_stateid_hash(&res->write_res.stateid); + __entry->res_count = res->write_res.count; + __entry->res_sync = res->synchronous; + __entry->res_cons = res->consecutive; + } + ), + + TP_printk( + "error=%ld (%s) intra=%d src_fileid=%02x:%02x:%llu " + "src_fhandle=0x%08x dst_fileid=%02x:%02x:%llu " + "dst_fhandle=0x%08x src_stateid=%d:0x%08x " + "dst_stateid=%d:0x%08x src_offset=%llu dst_offset=%llu " + "len=%llu sync=%d cb_stateid=%d:0x%08x res_sync=%d " + "res_cons=%d res_count=%llu", + -__entry->error, + show_nfs4_status(__entry->error), + __entry->intra, + MAJOR(__entry->src_dev), MINOR(__entry->src_dev), + (unsigned long long)__entry->src_fileid, + __entry->src_fhandle, + MAJOR(__entry->dst_dev), MINOR(__entry->dst_dev), + (unsigned long long)__entry->dst_fileid, + __entry->dst_fhandle, + __entry->src_stateid_seq, __entry->src_stateid_hash, + __entry->dst_stateid_seq, __entry->dst_stateid_hash, + __entry->src_offset, + __entry->dst_offset, + __entry->len, + __entry->sync, + __entry->res_stateid_seq, __entry->res_stateid_hash, + __entry->res_sync, + __entry->res_cons, + __entry->res_count + ) +); + +TRACE_EVENT(nfs4_clone, + TP_PROTO( + const struct inode *src_inode, + const struct inode *dst_inode, + const struct nfs42_clone_args *args, + int error + ), + + TP_ARGS(src_inode, dst_inode, args, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(u32, src_fhandle) + __field(u32, src_fileid) + __field(u32, dst_fhandle) + __field(u32, dst_fileid) + __field(dev_t, src_dev) + __field(dev_t, dst_dev) + __field(loff_t, src_offset) + __field(loff_t, dst_offset) + __field(int, src_stateid_seq) + __field(u32, src_stateid_hash) + __field(int, dst_stateid_seq) + __field(u32, dst_stateid_hash) + __field(loff_t, len) + ), + + TP_fast_assign( + const struct nfs_inode *src_nfsi = NFS_I(src_inode); + const struct nfs_inode *dst_nfsi = NFS_I(dst_inode); + + __entry->src_fileid = src_nfsi->fileid; + __entry->src_dev = src_inode->i_sb->s_dev; + __entry->src_fhandle = nfs_fhandle_hash(args->src_fh); + __entry->src_offset = args->src_offset; + __entry->dst_fileid = dst_nfsi->fileid; + __entry->dst_dev = dst_inode->i_sb->s_dev; + __entry->dst_fhandle = nfs_fhandle_hash(args->dst_fh); + __entry->dst_offset = args->dst_offset; + __entry->len = args->count; + __entry->error = error < 0 ? -error : 0; + __entry->src_stateid_seq = + be32_to_cpu(args->src_stateid.seqid); + __entry->src_stateid_hash = + nfs_stateid_hash(&args->src_stateid); + __entry->dst_stateid_seq = + be32_to_cpu(args->dst_stateid.seqid); + __entry->dst_stateid_hash = + nfs_stateid_hash(&args->dst_stateid); + ), + + TP_printk( + "error=%ld (%s) src_fileid=%02x:%02x:%llu " + "src_fhandle=0x%08x dst_fileid=%02x:%02x:%llu " + "dst_fhandle=0x%08x src_stateid=%d:0x%08x " + "dst_stateid=%d:0x%08x src_offset=%llu " + "dst_offset=%llu len=%llu", + -__entry->error, + show_nfs4_status(__entry->error), + MAJOR(__entry->src_dev), MINOR(__entry->src_dev), + (unsigned long long)__entry->src_fileid, + __entry->src_fhandle, + MAJOR(__entry->dst_dev), MINOR(__entry->dst_dev), + (unsigned long long)__entry->dst_fileid, + __entry->dst_fhandle, + __entry->src_stateid_seq, __entry->src_stateid_hash, + __entry->dst_stateid_seq, __entry->dst_stateid_hash, + __entry->src_offset, + __entry->dst_offset, + __entry->len + ) +); + +TRACE_EVENT(nfs4_copy_notify, + TP_PROTO( + const struct inode *inode, + const struct nfs42_copy_notify_args *args, + const struct nfs42_copy_notify_res *res, + int error + ), + + TP_ARGS(inode, args, res, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(u32, fhandle) + __field(u32, fileid) + __field(dev_t, dev) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, res_stateid_seq) + __field(u32, res_stateid_hash) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->fileid = nfsi->fileid; + __entry->dev = inode->i_sb->s_dev; + __entry->fhandle = nfs_fhandle_hash(args->cna_src_fh); + __entry->stateid_seq = + be32_to_cpu(args->cna_src_stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&args->cna_src_stateid); + if (error) { + __entry->error = -error; + __entry->res_stateid_seq = 0; + __entry->res_stateid_hash = 0; + } else { + __entry->error = 0; + __entry->res_stateid_seq = + be32_to_cpu(res->cnr_stateid.seqid); + __entry->res_stateid_hash = + nfs_stateid_hash(&res->cnr_stateid); + } + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x res_stateid=%d:0x%08x", + -__entry->error, + show_nfs4_status(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + __entry->res_stateid_seq, __entry->res_stateid_hash + ) +); + +TRACE_EVENT(nfs4_offload_cancel, + TP_PROTO( + const struct nfs42_offload_status_args *args, + int error + ), + + TP_ARGS(args, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(u32, fhandle) + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + __entry->fhandle = nfs_fhandle_hash(args->osa_src_fh); + __entry->error = error < 0 ? -error : 0; + __entry->stateid_seq = + be32_to_cpu(args->osa_stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&args->osa_stateid); + ), + + TP_printk( + "error=%ld (%s) fhandle=0x%08x stateid=%d:0x%08x", + -__entry->error, + show_nfs4_status(__entry->error), + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash + ) +); +#endif /* CONFIG_NFS_V4_2 */ #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index a8cff19c6f00..69862bf6db00 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3168,20 +3168,23 @@ static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) { - __be32 *p; + ssize_t ret; + void *ptr; + u32 tmp; - p = xdr_inline_decode(xdr, 8); - if (unlikely(!p)) + if (xdr_stream_decode_u32(xdr, &tmp) < 0) return -EIO; - hdr->status = be32_to_cpup(p++); - hdr->taglen = be32_to_cpup(p); + hdr->status = tmp; - p = xdr_inline_decode(xdr, hdr->taglen + 4); - if (unlikely(!p)) + ret = xdr_stream_decode_opaque_inline(xdr, &ptr, NFS4_OPAQUE_LIMIT); + if (ret < 0) + return -EIO; + hdr->taglen = ret; + hdr->tag = ptr; + + if (xdr_stream_decode_u32(xdr, &tmp) < 0) return -EIO; - hdr->tag = (char *)p; - p += XDR_QUADLEN(hdr->taglen); - hdr->nops = be32_to_cpup(p); + hdr->nops = tmp; if (unlikely(hdr->nops < 1)) return nfs4_stat_to_errno(hdr->status); return 0; @@ -4582,8 +4585,7 @@ static int decode_attr_mdsthreshold(struct xdr_stream *xdr, static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fattr *fattr, struct nfs_fh *fh, - struct nfs4_fs_locations *fs_loc, struct nfs4_label *label, - const struct nfs_server *server) + struct nfs4_fs_locations *fs_loc, const struct nfs_server *server) { int status; umode_t fmode = 0; @@ -4698,8 +4700,8 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, if (status < 0) goto xdr_error; - if (label) { - status = decode_attr_security_label(xdr, bitmap, label); + if (fattr->label) { + status = decode_attr_security_label(xdr, bitmap, fattr->label); if (status < 0) goto xdr_error; fattr->valid |= status; @@ -4712,7 +4714,7 @@ xdr_error: static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr, struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc, - struct nfs4_label *label, const struct nfs_server *server) + const struct nfs_server *server) { unsigned int savep; uint32_t attrlen, @@ -4731,8 +4733,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat if (status < 0) goto xdr_error; - status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc, - label, server); + status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc, server); if (status < 0) goto xdr_error; @@ -4742,16 +4743,10 @@ xdr_error: return status; } -static int decode_getfattr_label(struct xdr_stream *xdr, struct nfs_fattr *fattr, - struct nfs4_label *label, const struct nfs_server *server) -{ - return decode_getfattr_generic(xdr, fattr, NULL, NULL, label, server); -} - static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, const struct nfs_server *server) { - return decode_getfattr_generic(xdr, fattr, NULL, NULL, NULL, server); + return decode_getfattr_generic(xdr, fattr, NULL, NULL, server); } /* @@ -5572,20 +5567,9 @@ static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_re static int decode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) { - __be32 *p; - uint32_t bitmap_words; - unsigned int i; - - p = xdr_inline_decode(xdr, 4); - if (!p) - return -EIO; - bitmap_words = be32_to_cpup(p++); - if (bitmap_words > NFS4_OP_MAP_NUM_WORDS) + if (xdr_stream_decode_uint32_array(xdr, op_map->u.words, + ARRAY_SIZE(op_map->u.words)) < 0) return -EIO; - p = xdr_inline_decode(xdr, 4 * bitmap_words); - for (i = 0; i < bitmap_words; i++) - op_map->u.words[i] = be32_to_cpup(p++); - return 0; } @@ -6179,7 +6163,7 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); + status = decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6209,7 +6193,7 @@ static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); + status = decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6236,8 +6220,7 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, goto out; status = decode_getfh(xdr, res->fh); if (status == 0) - status = decode_getfattr_label(xdr, res->fattr, - res->label, res->server); + status = decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6331,7 +6314,7 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_restorefh(xdr); if (status) goto out; - decode_getfattr_label(xdr, res->fattr, res->label, res->server); + decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6361,7 +6344,7 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - decode_getfattr_label(xdr, res->fattr, res->label, res->server); + decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6394,7 +6377,7 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_putfh(xdr); if (status) goto out; - status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); + status = decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6532,7 +6515,7 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, goto out; if (res->access_request) decode_access(xdr, &res->access_supported, &res->access_result); - decode_getfattr_label(xdr, res->f_attr, res->f_label, res->server); + decode_getfattr(xdr, res->f_attr, res->server); if (res->lg_res) decode_layoutget(xdr, rqstp, res->lg_res); out: @@ -6616,7 +6599,7 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, status = decode_setattr(xdr); if (status) goto out; - decode_getfattr_label(xdr, res->fattr, res->label, res->server); + decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -7031,7 +7014,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, status = decode_getfattr_generic(xdr, &res->fs_locations->fattr, NULL, res->fs_locations, - NULL, res->fs_locations->server); + res->fs_locations->server); if (status) goto out; if (res->renew) @@ -7044,7 +7027,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, status = decode_getfattr_generic(xdr, &res->fs_locations->fattr, NULL, res->fs_locations, - NULL, res->fs_locations->server); + res->fs_locations->server); } out: return status; @@ -7475,7 +7458,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, return -EAGAIN; if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh, - NULL, entry->label, entry->server) < 0) + NULL, entry->server) < 0) return -EAGAIN; if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) entry->ino = entry->fattr->mounted_on_fileid; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 8a224871be74..21dac847f1e4 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -11,45 +11,9 @@ #include <linux/tracepoint.h> #include <linux/iversion.h> -TRACE_DEFINE_ENUM(DT_UNKNOWN); -TRACE_DEFINE_ENUM(DT_FIFO); -TRACE_DEFINE_ENUM(DT_CHR); -TRACE_DEFINE_ENUM(DT_DIR); -TRACE_DEFINE_ENUM(DT_BLK); -TRACE_DEFINE_ENUM(DT_REG); -TRACE_DEFINE_ENUM(DT_LNK); -TRACE_DEFINE_ENUM(DT_SOCK); -TRACE_DEFINE_ENUM(DT_WHT); - -#define nfs_show_file_type(ftype) \ - __print_symbolic(ftype, \ - { DT_UNKNOWN, "UNKNOWN" }, \ - { DT_FIFO, "FIFO" }, \ - { DT_CHR, "CHR" }, \ - { DT_DIR, "DIR" }, \ - { DT_BLK, "BLK" }, \ - { DT_REG, "REG" }, \ - { DT_LNK, "LNK" }, \ - { DT_SOCK, "SOCK" }, \ - { DT_WHT, "WHT" }) - -TRACE_DEFINE_ENUM(NFS_INO_INVALID_DATA); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_ATIME); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACCESS); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACL); -TRACE_DEFINE_ENUM(NFS_INO_REVAL_PAGECACHE); -TRACE_DEFINE_ENUM(NFS_INO_REVAL_FORCED); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_LABEL); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_CHANGE); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_CTIME); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_MTIME); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_SIZE); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER); -TRACE_DEFINE_ENUM(NFS_INO_DATA_INVAL_DEFER); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_BLOCKS); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_XATTR); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_NLINK); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE); +#include <trace/events/fs.h> +#include <trace/events/nfs.h> +#include <trace/events/sunrpc_base.h> #define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ @@ -71,17 +35,6 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE); { NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \ { NFS_INO_INVALID_MODE, "INVALID_MODE" }) -TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS); -TRACE_DEFINE_ENUM(NFS_INO_STALE); -TRACE_DEFINE_ENUM(NFS_INO_ACL_LRU_SET); -TRACE_DEFINE_ENUM(NFS_INO_INVALIDATING); -TRACE_DEFINE_ENUM(NFS_INO_FSCACHE); -TRACE_DEFINE_ENUM(NFS_INO_FSCACHE_LOCK); -TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMIT); -TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMITTING); -TRACE_DEFINE_ENUM(NFS_INO_LAYOUTSTATS); -TRACE_DEFINE_ENUM(NFS_INO_ODIRECT); - #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ { BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \ @@ -163,12 +116,12 @@ DECLARE_EVENT_CLASS(nfs_inode_event_done, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, - nfs_show_file_type(__entry->type), + show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, @@ -254,12 +207,12 @@ TRACE_EVENT(nfs_access_exit, "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) " "mask=0x%x permitted=0x%x", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, - nfs_show_file_type(__entry->type), + show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, @@ -270,33 +223,55 @@ TRACE_EVENT(nfs_access_exit, ) ); -TRACE_DEFINE_ENUM(LOOKUP_FOLLOW); -TRACE_DEFINE_ENUM(LOOKUP_DIRECTORY); -TRACE_DEFINE_ENUM(LOOKUP_AUTOMOUNT); -TRACE_DEFINE_ENUM(LOOKUP_PARENT); -TRACE_DEFINE_ENUM(LOOKUP_REVAL); -TRACE_DEFINE_ENUM(LOOKUP_RCU); -TRACE_DEFINE_ENUM(LOOKUP_OPEN); -TRACE_DEFINE_ENUM(LOOKUP_CREATE); -TRACE_DEFINE_ENUM(LOOKUP_EXCL); -TRACE_DEFINE_ENUM(LOOKUP_RENAME_TARGET); -TRACE_DEFINE_ENUM(LOOKUP_EMPTY); -TRACE_DEFINE_ENUM(LOOKUP_DOWN); - -#define show_lookup_flags(flags) \ - __print_flags(flags, "|", \ - { LOOKUP_FOLLOW, "FOLLOW" }, \ - { LOOKUP_DIRECTORY, "DIRECTORY" }, \ - { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ - { LOOKUP_PARENT, "PARENT" }, \ - { LOOKUP_REVAL, "REVAL" }, \ - { LOOKUP_RCU, "RCU" }, \ - { LOOKUP_OPEN, "OPEN" }, \ - { LOOKUP_CREATE, "CREATE" }, \ - { LOOKUP_EXCL, "EXCL" }, \ - { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \ - { LOOKUP_EMPTY, "EMPTY" }, \ - { LOOKUP_DOWN, "DOWN" }) +DECLARE_EVENT_CLASS(nfs_update_size_class, + TP_PROTO( + const struct inode *inode, + loff_t new_size + ), + + TP_ARGS(inode, new_size), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, cur_size) + __field(loff_t, new_size) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fileid = nfsi->fileid; + __entry->version = inode_peek_iversion_raw(inode); + __entry->cur_size = i_size_read(inode); + __entry->new_size = new_size; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu cursize=%lld newsize=%lld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->cur_size, __entry->new_size + ) +); + +#define DEFINE_NFS_UPDATE_SIZE_EVENT(name) \ + DEFINE_EVENT(nfs_update_size_class, nfs_size_##name, \ + TP_PROTO( \ + const struct inode *inode, \ + loff_t new_size \ + ), \ + TP_ARGS(inode, new_size)) + +DEFINE_NFS_UPDATE_SIZE_EVENT(truncate); +DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); +DEFINE_NFS_UPDATE_SIZE_EVENT(update); +DEFINE_NFS_UPDATE_SIZE_EVENT(grow); DECLARE_EVENT_CLASS(nfs_lookup_event, TP_PROTO( @@ -324,7 +299,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event, TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s", __entry->flags, - show_lookup_flags(__entry->flags), + show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -368,9 +343,9 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done, TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, - show_lookup_flags(__entry->flags), + show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -392,46 +367,6 @@ DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); -TRACE_DEFINE_ENUM(O_WRONLY); -TRACE_DEFINE_ENUM(O_RDWR); -TRACE_DEFINE_ENUM(O_CREAT); -TRACE_DEFINE_ENUM(O_EXCL); -TRACE_DEFINE_ENUM(O_NOCTTY); -TRACE_DEFINE_ENUM(O_TRUNC); -TRACE_DEFINE_ENUM(O_APPEND); -TRACE_DEFINE_ENUM(O_NONBLOCK); -TRACE_DEFINE_ENUM(O_DSYNC); -TRACE_DEFINE_ENUM(O_DIRECT); -TRACE_DEFINE_ENUM(O_LARGEFILE); -TRACE_DEFINE_ENUM(O_DIRECTORY); -TRACE_DEFINE_ENUM(O_NOFOLLOW); -TRACE_DEFINE_ENUM(O_NOATIME); -TRACE_DEFINE_ENUM(O_CLOEXEC); - -#define show_open_flags(flags) \ - __print_flags(flags, "|", \ - { O_WRONLY, "O_WRONLY" }, \ - { O_RDWR, "O_RDWR" }, \ - { O_CREAT, "O_CREAT" }, \ - { O_EXCL, "O_EXCL" }, \ - { O_NOCTTY, "O_NOCTTY" }, \ - { O_TRUNC, "O_TRUNC" }, \ - { O_APPEND, "O_APPEND" }, \ - { O_NONBLOCK, "O_NONBLOCK" }, \ - { O_DSYNC, "O_DSYNC" }, \ - { O_DIRECT, "O_DIRECT" }, \ - { O_LARGEFILE, "O_LARGEFILE" }, \ - { O_DIRECTORY, "O_DIRECTORY" }, \ - { O_NOFOLLOW, "O_NOFOLLOW" }, \ - { O_NOATIME, "O_NOATIME" }, \ - { O_CLOEXEC, "O_CLOEXEC" }) - -#define show_fmode_flags(mode) \ - __print_flags(mode, "|", \ - { ((__force unsigned long)FMODE_READ), "READ" }, \ - { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ - { ((__force unsigned long)FMODE_EXEC), "EXEC" }) - TRACE_EVENT(nfs_atomic_open_enter, TP_PROTO( const struct inode *dir, @@ -443,7 +378,7 @@ TRACE_EVENT(nfs_atomic_open_enter, TP_STRUCT__entry( __field(unsigned long, flags) - __field(unsigned int, fmode) + __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) @@ -453,15 +388,15 @@ TRACE_EVENT(nfs_atomic_open_enter, __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; - __entry->fmode = (__force unsigned int)ctx->mode; + __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name, ctx->dentry->d_name.name); ), TP_printk( "flags=0x%lx (%s) fmode=%s name=%02x:%02x:%llu/%s", __entry->flags, - show_open_flags(__entry->flags), - show_fmode_flags(__entry->fmode), + show_fs_fcntl_open_flags(__entry->flags), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -481,7 +416,7 @@ TRACE_EVENT(nfs_atomic_open_exit, TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) - __field(unsigned int, fmode) + __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) @@ -492,17 +427,17 @@ TRACE_EVENT(nfs_atomic_open_exit, __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; - __entry->fmode = (__force unsigned int)ctx->mode; + __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name, ctx->dentry->d_name.name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) fmode=%s " "name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, - show_open_flags(__entry->flags), - show_fmode_flags(__entry->fmode), + show_fs_fcntl_open_flags(__entry->flags), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -535,7 +470,7 @@ TRACE_EVENT(nfs_create_enter, TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s", __entry->flags, - show_open_flags(__entry->flags), + show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -570,9 +505,9 @@ TRACE_EVENT(nfs_create_exit, TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, - show_open_flags(__entry->flags), + show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -640,7 +575,7 @@ DECLARE_EVENT_CLASS(nfs_directory_event_done, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -730,7 +665,7 @@ TRACE_EVENT(nfs_link_exit, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -817,7 +752,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done, TP_printk( "error=%ld (%s) old_name=%02x:%02x:%llu/%s " "new_name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), @@ -871,13 +806,163 @@ TRACE_EVENT(nfs_sillyrename_unlink, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); +TRACE_EVENT(nfs_aop_readpage, + TP_PROTO( + const struct inode *inode, + struct page *page + ), + + TP_ARGS(inode, page), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, offset) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode_peek_iversion_raw(inode); + __entry->offset = page_index(page) << PAGE_SHIFT; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->offset + ) +); + +TRACE_EVENT(nfs_aop_readpage_done, + TP_PROTO( + const struct inode *inode, + struct page *page, + int ret + ), + + TP_ARGS(inode, page, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(int, ret) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, offset) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode_peek_iversion_raw(inode); + __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->ret = ret; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld ret=%d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->offset, __entry->ret + ) +); + +TRACE_EVENT(nfs_aop_readahead, + TP_PROTO( + const struct inode *inode, + struct page *page, + unsigned int nr_pages + ), + + TP_ARGS(inode, page, nr_pages), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, offset) + __field(unsigned int, nr_pages) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode_peek_iversion_raw(inode); + __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->nr_pages = nr_pages; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld nr_pages=%u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->offset, __entry->nr_pages + ) +); + +TRACE_EVENT(nfs_aop_readahead_done, + TP_PROTO( + const struct inode *inode, + unsigned int nr_pages, + int ret + ), + + TP_ARGS(inode, nr_pages, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(int, ret) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, offset) + __field(unsigned int, nr_pages) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode_peek_iversion_raw(inode); + __entry->nr_pages = nr_pages; + __entry->ret = ret; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu nr_pages=%u ret=%d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->nr_pages, __entry->ret + ) +); + TRACE_EVENT(nfs_initiate_read, TP_PROTO( const struct nfs_pgio_header *hdr @@ -1054,16 +1139,6 @@ TRACE_EVENT(nfs_pgio_error, ) ); -TRACE_DEFINE_ENUM(NFS_UNSTABLE); -TRACE_DEFINE_ENUM(NFS_DATA_SYNC); -TRACE_DEFINE_ENUM(NFS_FILE_SYNC); - -#define nfs_show_stable(stable) \ - __print_symbolic(stable, \ - { NFS_UNSTABLE, "UNSTABLE" }, \ - { NFS_DATA_SYNC, "DATA_SYNC" }, \ - { NFS_FILE_SYNC, "FILE_SYNC" }) - TRACE_EVENT(nfs_initiate_write, TP_PROTO( const struct nfs_pgio_header *hdr @@ -1077,7 +1152,7 @@ TRACE_EVENT(nfs_initiate_write, __field(u64, fileid) __field(loff_t, offset) __field(u32, count) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) ), TP_fast_assign( @@ -1101,7 +1176,7 @@ TRACE_EVENT(nfs_initiate_write, (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count, - nfs_show_stable(__entry->stable) + show_nfs_stable_how(__entry->stable) ) ); @@ -1121,7 +1196,7 @@ TRACE_EVENT(nfs_writeback_done, __field(u32, arg_count) __field(u32, res_count) __field(int, status) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1154,8 +1229,8 @@ TRACE_EVENT(nfs_writeback_done, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->status, - nfs_show_stable(__entry->stable), - __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + show_nfs_stable_how(__entry->stable), + show_nfs4_verifier(__entry->verifier) ) ); @@ -1256,7 +1331,7 @@ TRACE_EVENT(nfs_commit_done, __field(u64, fileid) __field(loff_t, offset) __field(int, status) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1285,8 +1360,8 @@ TRACE_EVENT(nfs_commit_done, (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->status, - nfs_show_stable(__entry->stable), - __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + show_nfs_stable_how(__entry->stable), + show_nfs4_verifier(__entry->verifier) ) ); @@ -1323,76 +1398,6 @@ TRACE_EVENT(nfs_fh_to_dentry, ) ); -TRACE_DEFINE_ENUM(NFS_OK); -TRACE_DEFINE_ENUM(NFSERR_PERM); -TRACE_DEFINE_ENUM(NFSERR_NOENT); -TRACE_DEFINE_ENUM(NFSERR_IO); -TRACE_DEFINE_ENUM(NFSERR_NXIO); -TRACE_DEFINE_ENUM(ECHILD); -TRACE_DEFINE_ENUM(NFSERR_EAGAIN); -TRACE_DEFINE_ENUM(NFSERR_ACCES); -TRACE_DEFINE_ENUM(NFSERR_EXIST); -TRACE_DEFINE_ENUM(NFSERR_XDEV); -TRACE_DEFINE_ENUM(NFSERR_NODEV); -TRACE_DEFINE_ENUM(NFSERR_NOTDIR); -TRACE_DEFINE_ENUM(NFSERR_ISDIR); -TRACE_DEFINE_ENUM(NFSERR_INVAL); -TRACE_DEFINE_ENUM(NFSERR_FBIG); -TRACE_DEFINE_ENUM(NFSERR_NOSPC); -TRACE_DEFINE_ENUM(NFSERR_ROFS); -TRACE_DEFINE_ENUM(NFSERR_MLINK); -TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFSERR_DQUOT); -TRACE_DEFINE_ENUM(NFSERR_STALE); -TRACE_DEFINE_ENUM(NFSERR_REMOTE); -TRACE_DEFINE_ENUM(NFSERR_WFLUSH); -TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); -TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFSERR_BADTYPE); -TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); - -#define nfs_show_status(x) \ - __print_symbolic(x, \ - { NFS_OK, "OK" }, \ - { NFSERR_PERM, "PERM" }, \ - { NFSERR_NOENT, "NOENT" }, \ - { NFSERR_IO, "IO" }, \ - { NFSERR_NXIO, "NXIO" }, \ - { ECHILD, "CHILD" }, \ - { NFSERR_EAGAIN, "AGAIN" }, \ - { NFSERR_ACCES, "ACCES" }, \ - { NFSERR_EXIST, "EXIST" }, \ - { NFSERR_XDEV, "XDEV" }, \ - { NFSERR_NODEV, "NODEV" }, \ - { NFSERR_NOTDIR, "NOTDIR" }, \ - { NFSERR_ISDIR, "ISDIR" }, \ - { NFSERR_INVAL, "INVAL" }, \ - { NFSERR_FBIG, "FBIG" }, \ - { NFSERR_NOSPC, "NOSPC" }, \ - { NFSERR_ROFS, "ROFS" }, \ - { NFSERR_MLINK, "MLINK" }, \ - { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ - { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFSERR_DQUOT, "DQUOT" }, \ - { NFSERR_STALE, "STALE" }, \ - { NFSERR_REMOTE, "REMOTE" }, \ - { NFSERR_WFLUSH, "WFLUSH" }, \ - { NFSERR_BADHANDLE, "BADHANDLE" }, \ - { NFSERR_NOT_SYNC, "NOTSYNC" }, \ - { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ - { NFSERR_NOTSUPP, "NOTSUPP" }, \ - { NFSERR_TOOSMALL, "TOOSMALL" }, \ - { NFSERR_SERVERFAULT, "REMOTEIO" }, \ - { NFSERR_BADTYPE, "BADTYPE" }, \ - { NFSERR_JUKEBOX, "JUKEBOX" }) - DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, @@ -1427,12 +1432,12 @@ DECLARE_EVENT_CLASS(nfs_xdr_event, __assign_str(procedure, task->tk_msg.rpc_proc->p_name); ), - TP_printk( - "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, __get_str(program), __entry->version, __get_str(procedure), -__entry->error, - nfs_show_status(__entry->error) + show_nfs_status(__entry->error) ) ); #define DEFINE_NFS_XDR_EVENT(name) \ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index cc232d1f16f2..ad7f83dc9a2d 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -271,8 +271,7 @@ nfs_page_set_headlock(struct nfs_page *req) void nfs_page_clear_headlock(struct nfs_page *req) { - smp_mb__before_atomic(); - clear_bit(PG_HEADLOCK, &req->wb_flags); + clear_bit_unlock(PG_HEADLOCK, &req->wb_flags); smp_mb__after_atomic(); if (!test_bit(PG_CONTENDED1, &req->wb_flags)) return; @@ -525,12 +524,7 @@ nfs_create_subreq(struct nfs_page *req, */ void nfs_unlock_request(struct nfs_page *req) { - if (!NFS_WBACK_BUSY(req)) { - printk(KERN_ERR "NFS: Invalid unlock attempted\n"); - BUG(); - } - smp_mb__before_atomic(); - clear_bit(PG_BUSY, &req->wb_flags); + clear_bit_unlock(PG_BUSY, &req->wb_flags); smp_mb__after_atomic(); if (!test_bit(PG_CONTENDED2, &req->wb_flags)) return; @@ -870,9 +864,6 @@ static void nfs_pgio_result(struct rpc_task *task, void *calldata) struct nfs_pgio_header *hdr = calldata; struct inode *inode = hdr->inode; - dprintk("NFS: %s: %5u, (status %d)\n", __func__, - task->tk_pid, task->tk_status); - if (hdr->rw_ops->rw_done(task, hdr, inode) != 0) return; if (task->tk_status < 0) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index d810ae674f4e..f4d7548d67b2 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -82,10 +82,6 @@ enum pnfs_try_status { PNFS_TRY_AGAIN = 2, }; -/* error codes for internal use */ -#define NFS4ERR_RESET_TO_MDS 12001 -#define NFS4ERR_RESET_TO_PNFS 12002 - #ifdef CONFIG_NFS_V4_1 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" @@ -517,7 +513,7 @@ pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, { struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; - if (!lseg || !fl_cinfo->ops->mark_request_commit) + if (!lseg || !fl_cinfo->ops || !fl_cinfo->ops->mark_request_commit) return false; fl_cinfo->ops->mark_request_commit(req, lseg, cinfo, ds_commit_idx); return true; diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index cf19914fec81..316f68f96e57 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -468,7 +468,6 @@ pnfs_bucket_alloc_ds_commits(struct list_head *list, goto out_error; data->ds_commit_index = i; list_add_tail(&data->list, list); - atomic_inc(&cinfo->mds->rpcs_out); nreq++; } mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); @@ -520,7 +519,6 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, data->ds_commit_index = -1; list_splice_init(mds_pages, &data->pages); list_add_tail(&data->list, &list); - atomic_inc(&cinfo->mds->rpcs_out); nreq++; } @@ -895,7 +893,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, } smp_wmb(); - ds->ds_clp = clp; + WRITE_ONCE(ds->ds_clp, clp); dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); out: return status; @@ -973,7 +971,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, } smp_wmb(); - ds->ds_clp = clp; + WRITE_ONCE(ds->ds_clp, clp); dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); out: return status; diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index ea19dbf12301..73dcaa99fa9b 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -91,7 +91,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, info->dtpref = fsinfo.tsize; info->maxfilesize = 0x7FFFFFFF; info->lease_time = 0; - info->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA; + info->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED; return 0; } @@ -100,8 +100,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, */ static int nfs_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_GETATTR], @@ -154,8 +153,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, static int nfs_proc_lookup(struct inode *dir, struct dentry *dentry, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { .fh = NFS_FH(dir), @@ -257,7 +255,7 @@ nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); nfs_mark_for_revalidate(dir); if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); nfs_free_createdata(data); out: dprintk("NFS reply create: %d\n", status); @@ -304,7 +302,7 @@ nfs_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); } if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); nfs_free_createdata(data); out: dprintk("NFS reply mknod: %d\n", status); @@ -436,7 +434,7 @@ nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, * should fill in the data with a LOOKUP call on the wire. */ if (status == 0) - status = nfs_instantiate(dentry, fh, fattr, NULL); + status = nfs_instantiate(dentry, fh, fattr); out_free: nfs_free_fattr(fattr); @@ -465,7 +463,7 @@ nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); nfs_mark_for_revalidate(dir); if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); nfs_free_createdata(data); out: dprintk("NFS reply mkdir: %d\n", status); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 08d6cc57cbc3..d11af2a9299c 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -337,8 +337,7 @@ int nfs_readpage(struct file *file, struct page *page) struct inode *inode = page_file_mapping(page)->host; int ret; - dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", - page, PAGE_SIZE, page_index(page)); + trace_nfs_aop_readpage(inode, page); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); /* @@ -390,9 +389,11 @@ out_wait: } out: put_nfs_open_context(desc.ctx); + trace_nfs_aop_readpage_done(inode, page, ret); return ret; out_unlock: unlock_page(page); + trace_nfs_aop_readpage_done(inode, page, ret); return ret; } @@ -403,10 +404,7 @@ int nfs_readpages(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; int ret; - dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", - inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(inode), - nr_pages); + trace_nfs_aop_readahead(inode, lru_to_page(pages), nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); ret = -ESTALE; @@ -439,6 +437,7 @@ int nfs_readpages(struct file *file, struct address_space *mapping, read_complete: put_nfs_open_context(desc.ctx); out: + trace_nfs_aop_readahead_done(inode, nr_pages, ret); return ret; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index e65c83494c05..3aced401735c 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1004,6 +1004,7 @@ int nfs_reconfigure(struct fs_context *fc) struct nfs_fs_context *ctx = nfs_fc2context(fc); struct super_block *sb = fc->root->d_sb; struct nfs_server *nfss = sb->s_fs_info; + int ret; sync_filesystem(sb); @@ -1028,7 +1029,11 @@ int nfs_reconfigure(struct fs_context *fc) } /* compare new mount options with old ones */ - return nfs_compare_remount_data(nfss, ctx); + ret = nfs_compare_remount_data(nfss, ctx); + if (ret) + return ret; + + return nfs_probe_server(nfss, NFS_FH(d_inode(fc->root))); } EXPORT_SYMBOL_GPL(nfs_reconfigure); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index eae9bf114041..9b7619ce17a7 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -288,6 +288,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c end = page_file_offset(page) + ((loff_t)offset+count); if (i_size >= end) goto out; + trace_nfs_size_grow(inode, end); i_size_write(inode, end); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); @@ -1038,25 +1039,11 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_page *req, *tmp; int ret = 0; -restart: list_for_each_entry_safe(req, tmp, src, wb_list) { kref_get(&req->wb_kref); if (!nfs_lock_request(req)) { - int status; - - /* Prevent deadlock with nfs_lock_and_join_requests */ - if (!list_empty(dst)) { - nfs_release_request(req); - continue; - } - /* Ensure we make progress to prevent livelock */ - mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); - status = nfs_wait_on_request(req); nfs_release_request(req); - mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); - if (status < 0) - break; - goto restart; + continue; } nfs_request_remove_commit_list(req, cinfo); clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); @@ -1246,7 +1233,7 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode) struct nfs_open_context *ctx = nfs_file_open_context(filp); if (nfs_ctx_key_to_expire(ctx, inode) && - !ctx->ll_cred) + !rcu_access_pointer(ctx->ll_cred)) /* Already expired! */ return -EACCES; return 0; @@ -1258,23 +1245,38 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode) bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode) { struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; - struct rpc_cred *cred = ctx->ll_cred; + struct rpc_cred *cred, *new, *old = NULL; struct auth_cred acred = { .cred = ctx->cred, }; + bool ret = false; - if (cred && !cred->cr_ops->crmatch(&acred, cred, 0)) { - put_rpccred(cred); - ctx->ll_cred = NULL; - cred = NULL; - } - if (!cred) - cred = auth->au_ops->lookup_cred(auth, &acred, 0); - if (!cred || IS_ERR(cred)) + rcu_read_lock(); + cred = rcu_dereference(ctx->ll_cred); + if (cred && !(cred->cr_ops->crkey_timeout && + cred->cr_ops->crkey_timeout(cred))) + goto out; + rcu_read_unlock(); + + new = auth->au_ops->lookup_cred(auth, &acred, 0); + if (new == cred) { + put_rpccred(new); return true; - ctx->ll_cred = cred; - return !!(cred->cr_ops->crkey_timeout && - cred->cr_ops->crkey_timeout(cred)); + } + if (IS_ERR_OR_NULL(new)) { + new = NULL; + ret = true; + } else if (new->cr_ops->crkey_timeout && + new->cr_ops->crkey_timeout(new)) + ret = true; + + rcu_read_lock(); + old = rcu_dereference_protected(xchg(&ctx->ll_cred, + RCU_INITIALIZER(new)), 1); +out: + rcu_read_unlock(); + put_rpccred(old); + return ret; } /* @@ -1382,8 +1384,6 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) nfs_set_pageerror(mapping); - else - __set_page_dirty_nobuffers(page); out: dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n", status, (long long)i_size_read(inode)); @@ -1671,10 +1671,13 @@ static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) atomic_inc(&cinfo->rpcs_out); } -static void nfs_commit_end(struct nfs_mds_commit_info *cinfo) +bool nfs_commit_end(struct nfs_mds_commit_info *cinfo) { - if (atomic_dec_and_test(&cinfo->rpcs_out)) + if (atomic_dec_and_test(&cinfo->rpcs_out)) { wake_up_var(&cinfo->rpcs_out); + return true; + } + return false; } void nfs_commitdata_release(struct nfs_commit_data *data) @@ -1774,6 +1777,7 @@ void nfs_init_commit(struct nfs_commit_data *data, data->res.fattr = &data->fattr; data->res.verf = &data->verf; nfs_fattr_init(&data->fattr); + nfs_commit_begin(cinfo->mds); } EXPORT_SYMBOL_GPL(nfs_init_commit); @@ -1820,7 +1824,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, /* Set up the argument struct */ nfs_init_commit(data, head, NULL, cinfo); - atomic_inc(&cinfo->mds->rpcs_out); if (NFS_SERVER(inode)->nfs_client->cl_minorversion) task_flags = RPC_TASK_MOVEABLE; return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), @@ -1835,9 +1838,6 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) { struct nfs_commit_data *data = calldata; - dprintk("NFS: %5u nfs_commit_done (status %d)\n", - task->tk_pid, task->tk_status); - /* Call the NFS version-specific code */ NFS_PROTO(data->inode)->commit_done(task, data); trace_nfs_commit_done(task, data); @@ -1936,6 +1936,7 @@ static int __nfs_commit_inode(struct inode *inode, int how, int may_wait = how & FLUSH_SYNC; int ret, nscan; + how &= ~FLUSH_SYNC; nfs_init_cinfo_from_inode(&cinfo, inode); nfs_commit_begin(cinfo.mds); for (;;) { diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index db7ef07ae50c..2e2f1d5e9f62 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -61,7 +61,7 @@ nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, goto out_error; fl->fh.size = fhp->fh_handle.fh_size; - memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size); + memcpy(fl->fh.data, &fhp->fh_handle.fh_raw, fl->fh.size); /* Give whole file layout segments */ seg->offset = 0; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 606fa155c28a..46a7f9b813e5 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -35,7 +35,7 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp, /* must initialize before using! but maxsize doesn't matter */ fh_init(&fh,0); fh.fh_handle.fh_size = f->size; - memcpy((char*)&fh.fh_handle.fh_base, f->data, f->size); + memcpy(&fh.fh_handle.fh_raw, f->data, f->size); fh.fh_export = NULL; access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ; diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 4b43929c1f25..367551bddfc6 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -188,51 +188,51 @@ out: * XDR decode functions */ -static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; - return 1; + return true; } -static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; if (argp->mask & ~NFS_ACL_MASK) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? &argp->acl_access : NULL)) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? &argp->acl_default : NULL)) - return 0; + return false; - return 1; + return true; } -static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->access) < 0) - return 0; + return false; - return 1; + return true; } /* @@ -240,9 +240,9 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETACL */ -static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct inode *inode; @@ -280,9 +280,9 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) } /* ACCESS */ -static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 5dfe7644a517..35b2ebda14da 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -127,38 +127,38 @@ out: * XDR decode functions */ -static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->mask) < 0) - return 0; + return false; - return 1; + return true; } -static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; if (argp->mask & ~NFS_ACL_MASK) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? &argp->acl_access : NULL)) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? &argp->acl_default : NULL)) - return 0; + return false; - return 1; + return true; } /* @@ -166,9 +166,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETACL */ -static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct kvec *head = rqstp->rq_res.head; @@ -178,14 +178,14 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) int w; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: inode = d_inode(dentry); if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; base = (char *)xdr->p - (char *)head->iov_base; @@ -194,7 +194,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 0; + return false; w -= PAGE_SIZE; } @@ -207,20 +207,20 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) resp->mask & NFS_DFACL, NFS_ACL_DEFAULT); if (n <= 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* SETACL */ -static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_encode_setaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 17715a6c7a40..4418517f6f12 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -201,8 +201,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; - nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages, - &argp->first, cnt); + nvecs = svc_fill_write_vector(rqstp, &argp->payload); if (!nvecs) { resp->status = nfserr_io; goto out; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 0a5ebc52e6a9..c3ac1b6aa3aa 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -92,7 +92,7 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp) return false; fh_init(fhp, NFS3_FHSIZE); fhp->fh_handle.fh_size = size; - memcpy(&fhp->fh_handle.fh_base, p, size); + memcpy(&fhp->fh_handle.fh_raw, p, size); return true; } @@ -131,7 +131,7 @@ svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp) *p++ = cpu_to_be32(size); if (size) p[XDR_QUADLEN(size) - 1] = 0; - memcpy(p, &fhp->fh_handle.fh_base, size); + memcpy(p, &fhp->fh_handle.fh_raw, size); return true; } @@ -556,19 +556,17 @@ void fill_post_wcc(struct svc_fh *fhp) * XDR decode functions */ -int -nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->fh); } -int -nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_sattrargs *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->fh) && @@ -576,96 +574,83 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) svcxdr_decode_sattrguard3(xdr, args); } -int -nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_diropargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len); } -int -nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->access) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_writeargs *args = rqstp->rq_argp; u32 max_blocksize = svc_max_payload(rqstp); - struct kvec *head = rqstp->rq_arg.head; - struct kvec *tail = rqstp->rq_arg.tail; - size_t remaining; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->stable) < 0) - return 0; + return false; /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) - return 0; + return false; /* request sanity */ if (args->count != args->len) - return 0; - remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; - remaining -= xdr_stream_pos(xdr); - if (remaining < xdr_align_size(args->len)) - return 0; + return false; if (args->count > max_blocksize) { args->count = max_blocksize; args->len = max_blocksize; } + if (!xdr_stream_subsegment(xdr, &args->payload, args->count)) + return false; - args->first.iov_base = xdr->p; - args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - - return 1; + return true; } -int -nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->createmode) < 0) - return 0; + return false; switch (args->createmode) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: @@ -673,18 +658,17 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) case NFS3_CREATE_EXCLUSIVE: args->verf = xdr_inline_decode(xdr, NFS3_CREATEVERFSIZE); if (!args->verf) - return 0; + return false; break; default: - return 0; + return false; } - return 1; + return true; } -int -nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->fh, @@ -692,44 +676,42 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) svcxdr_decode_sattr3(rqstp, xdr, &args->attrs); } -int -nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; struct kvec *tail = rqstp->rq_arg.tail; size_t remaining; if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen)) - return 0; + return false; if (!svcxdr_decode_sattr3(rqstp, xdr, &args->attrs)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) - return 0; + return false; /* request sanity */ remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; remaining -= xdr_stream_pos(xdr); if (remaining < xdr_align_size(args->tlen)) - return 0; + return false; args->first.iov_base = xdr->p; args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - return 1; + return true; } -int -nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_mknodargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->ftype) < 0) - return 0; + return false; switch (args->ftype) { case NF3CHR: case NF3BLK: @@ -743,16 +725,15 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) /* Valid XDR but illegal file types */ break; default: - return 0; + return false; } - return 1; + return true; } -int -nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_renameargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->ffh, @@ -761,10 +742,9 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_linkargs *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->ffh) && @@ -772,62 +752,59 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) - return 0; + return false; args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); if (!args->verf) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; u32 dircount; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) - return 0; + return false; args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); if (!args->verf) - return 0; + return false; /* dircount is ignored */ if (xdr_stream_decode_u32(xdr, &dircount) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_commitargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } /* @@ -835,30 +812,28 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETATTR */ -int -nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime); if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } /* SETATTR, REMOVE, RMDIR */ -int -nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -866,174 +841,168 @@ nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) } /* LOOKUP */ -int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh)) - return 0; + return false; } - return 1; + return true; } /* ACCESS */ -int -nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* READLINK */ -int -nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->len) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, 0, resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* READ */ -int -nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->eof) < 0) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* WRITE */ -int -nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_writeres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->committed) < 0) - return 0; + return false; if (!svcxdr_encode_writeverf3(xdr, resp->verf)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* CREATE, MKDIR, SYMLINK, MKNOD */ -int -nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh)) - return 0; + return false; } - return 1; + return true; } /* RENAME */ -int -nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_renameres *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -1042,10 +1011,9 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) } /* LINK */ -int -nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_linkres *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -1054,34 +1022,33 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) } /* READDIR */ -int -nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_cookieverf3(xdr, resp->verf)) - return 0; + return false; xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } static __be32 @@ -1308,27 +1275,26 @@ svcxdr_encode_fsstat3resok(struct xdr_stream *xdr, } /* FSSTAT */ -int -nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_fsstatres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_fsstat3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } static bool @@ -1355,27 +1321,26 @@ svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr, } /* FSINFO */ -int -nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_fsinfores *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_fsinfo3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } static bool @@ -1398,51 +1363,49 @@ svcxdr_encode_pathconf3resok(struct xdr_stream *xdr, } /* PATHCONF */ -int -nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_pathconfres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_pathconf3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } /* COMMIT */ -int -nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_commitres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_writeverf3(xdr, resp->verf)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 0f8b10f363e7..11f8715d92d6 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -121,7 +121,7 @@ static void encode_nfs_fh4(struct xdr_stream *xdr, const struct knfsd_fh *fh) BUG_ON(length > NFS4_FHSIZE); p = xdr_reserve_space(xdr, 4 + length); - xdr_encode_opaque(p, &fh->fh_base, length); + xdr_encode_opaque(p, &fh->fh_raw, length); } /* diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 486c5dba4b65..a36261f89bdf 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -519,7 +519,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fh_put(&cstate->current_fh); cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; - memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, + memcpy(&cstate->current_fh.fh_handle.fh_raw, putfh->pf_fhval, putfh->pf_fhlen); ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS); #ifdef CONFIG_NFSD_V4_2_INTER_SSC @@ -1033,8 +1033,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, write->wr_how_written = write->wr_stable_how; - nvecs = svc_fill_write_vector(rqstp, write->wr_payload.pages, - write->wr_payload.head, write->wr_buflen); + nvecs = svc_fill_write_vector(rqstp, &write->wr_payload); WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf, @@ -1178,7 +1177,7 @@ extern void nfs_sb_deactive(struct super_block *sb); static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt) { - struct nfsd4_ssc_umount_item *ni = 0; + struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *work = NULL; struct nfsd4_ssc_umount_item *tmp; DEFINE_WAIT(wait); @@ -1383,7 +1382,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, s_fh = &cstate->save_fh; copy->c_fh.size = s_fh->fh_handle.fh_size; - memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size); + memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_raw, copy->c_fh.size); copy->stateid.seqid = cpu_to_be32(s_stid->si_generation); memcpy(copy->stateid.other, (void *)&s_stid->si_opaque, sizeof(stateid_opaque_t)); @@ -2462,11 +2461,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) __be32 status; resp->xdr = &rqstp->rq_res_stream; + resp->statusp = resp->xdr->p; /* reserve space for: NFS status code */ xdr_reserve_space(resp->xdr, XDR_UNIT); - resp->tagp = resp->xdr->p; /* reserve space for: taglen, tag, and opcnt */ xdr_reserve_space(resp->xdr, XDR_UNIT * 2 + args->taglen); resp->taglen = args->taglen; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 3f4027a5de88..bfad94c70b84 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1010,7 +1010,7 @@ static int delegation_blocked(struct knfsd_fh *fh) } spin_unlock(&blocked_delegations_lock); } - hash = jhash(&fh->fh_base, fh->fh_size, 0); + hash = jhash(&fh->fh_raw, fh->fh_size, 0); if (test_bit(hash&255, bd->set[0]) && test_bit((hash>>8)&255, bd->set[0]) && test_bit((hash>>16)&255, bd->set[0])) @@ -1029,7 +1029,7 @@ static void block_delegations(struct knfsd_fh *fh) u32 hash; struct bloom_pair *bd = &blocked_delegations; - hash = jhash(&fh->fh_base, fh->fh_size, 0); + hash = jhash(&fh->fh_raw, fh->fh_size, 0); spin_lock(&blocked_delegations_lock); __set_bit(hash&255, bd->set[bd->new]); @@ -5541,7 +5541,7 @@ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) { bool do_wakeup = false; - struct nfsd4_ssc_umount_item *ni = 0; + struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *tmp; spin_lock(&nn->nfsd_ssc_lock); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index cf030ebe2827..b2a1d969a172 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2322,7 +2322,7 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op) return true; } -static int +static bool nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { struct nfsd4_op *op; @@ -2335,25 +2335,25 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) int i; if (xdr_stream_decode_u32(argp->xdr, &argp->taglen) < 0) - return 0; + return false; max_reply += XDR_UNIT; argp->tag = NULL; if (unlikely(argp->taglen)) { if (argp->taglen > NFSD4_MAX_TAGLEN) - return 0; + return false; p = xdr_inline_decode(argp->xdr, argp->taglen); if (!p) - return 0; + return false; argp->tag = svcxdr_savemem(argp, p, argp->taglen); if (!argp->tag) - return 0; + return false; max_reply += xdr_align_size(argp->taglen); } if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) - return 0; + return false; if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0) - return 0; + return false; /* * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS @@ -2361,14 +2361,14 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) * nfsd4_proc can handle this is an NFS-level error. */ if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND) - return 1; + return true; if (argp->opcnt > ARRAY_SIZE(argp->iops)) { argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL); if (!argp->ops) { argp->ops = argp->iops; dprintk("nfsd: couldn't allocate room for COMPOUND\n"); - return 0; + return false; } } @@ -2380,7 +2380,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->replay = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) - return 0; + return false; if (nfsd4_opnum_in_range(argp, op)) { op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); if (op->status != nfs_ok) @@ -2427,7 +2427,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); - return 1; + return true; } static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, @@ -3110,7 +3110,7 @@ out_acl: p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4); if (!p) goto out_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, fhp->fh_handle.fh_size); } if (bmval0 & FATTR4_WORD0_FILEID) { @@ -3670,7 +3670,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh p = xdr_reserve_space(xdr, len + 4); if (!p) return nfserr_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len); + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, len); return 0; } @@ -5414,40 +5414,46 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) } } -int -nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundargs *args = rqstp->rq_argp; /* svcxdr_tmp_alloc */ args->to_free = NULL; - args->xdr = &rqstp->rq_arg_stream; + args->xdr = xdr; args->ops = args->iops; args->rqstp = rqstp; return nfsd4_decode_compound(args); } -int -nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundres *resp = rqstp->rq_resp; - struct xdr_buf *buf = resp->xdr->buf; + struct xdr_buf *buf = xdr->buf; + __be32 *p; WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + buf->tail[0].iov_len); - *p = resp->cstate.status; + /* + * Send buffer space for the following items is reserved + * at the top of nfsd4_proc_compound(). + */ + p = resp->statusp; + + *p++ = resp->cstate.status; - rqstp->rq_next_page = resp->xdr->page_ptr + 1; + rqstp->rq_next_page = xdr->page_ptr + 1; - p = resp->tagp; *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); p += XDR_QUADLEN(resp->taglen); *p++ = htonl(resp->opcnt); nfsd4_sequence_done(resp); - return 1; + return true; } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 96cdf77925f3..6e0b6f3148dc 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -241,8 +241,8 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) list_move_tail(&rp->c_lru, &b->lru_head); } -static long -prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) +static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn, + unsigned int max) { struct svc_cacherep *rp, *tmp; long freed = 0; @@ -258,11 +258,17 @@ prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(b, rp, nn); - freed++; + if (max && freed++ > max) + break; } return freed; } +static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) +{ + return prune_bucket(b, nn, 3); +} + /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -279,7 +285,7 @@ prune_cache_entries(struct nfsd_net *nn) if (list_empty(&b->lru_head)) continue; spin_lock(&b->cache_lock); - freed += prune_bucket(b, nn); + freed += prune_bucket(b, nn, 0); spin_unlock(&b->cache_lock); } return freed; @@ -453,8 +459,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) atomic_inc(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp)); - /* go ahead and prune the cache */ - prune_bucket(b, nn); + nfsd_prune_bucket(b, nn); out_unlock: spin_unlock(&b->cache_lock); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 070e5dd03e26..af8531c3854a 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -395,12 +395,12 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) auth_domain_put(dom); if (len) return len; - + mesg = buf; len = SIMPLE_TRANSACTION_LIMIT; - qword_addhex(&mesg, &len, (char*)&fh.fh_base, fh.fh_size); + qword_addhex(&mesg, &len, fh.fh_raw, fh.fh_size); mesg[-1] = '\n'; - return mesg - buf; + return mesg - buf; } /* diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 9664303afdaf..498e5a489826 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -78,8 +78,10 @@ extern const struct seq_operations nfs_exports_op; */ struct nfsd_voidargs { }; struct nfsd_voidres { }; -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p); -int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p); +bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, + struct xdr_stream *xdr); +bool nfssvc_encode_voidres(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* * Function prototypes. diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c475d2271f9c..f3779fa72c89 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -154,11 +154,12 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp, static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) { struct knfsd_fh *fh = &fhp->fh_handle; - struct fid *fid = NULL, sfid; + struct fid *fid = NULL; struct svc_export *exp; struct dentry *dentry; int fileid_type; int data_left = fh->fh_size/4; + int len; __be32 error; error = nfserr_stale; @@ -167,48 +168,35 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) if (rqstp->rq_vers == 4 && fh->fh_size == 0) return nfserr_nofilehandle; - if (fh->fh_version == 1) { - int len; - - if (--data_left < 0) - return error; - if (fh->fh_auth_type != 0) - return error; - len = key_len(fh->fh_fsid_type) / 4; - if (len == 0) - return error; - if (fh->fh_fsid_type == FSID_MAJOR_MINOR) { - /* deprecated, convert to type 3 */ - len = key_len(FSID_ENCODE_DEV)/4; - fh->fh_fsid_type = FSID_ENCODE_DEV; - /* - * struct knfsd_fh uses host-endian fields, which are - * sometimes used to hold net-endian values. This - * confuses sparse, so we must use __force here to - * keep it from complaining. - */ - fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]), - ntohl((__force __be32)fh->fh_fsid[1]))); - fh->fh_fsid[1] = fh->fh_fsid[2]; - } - data_left -= len; - if (data_left < 0) - return error; - exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); - fid = (struct fid *)(fh->fh_fsid + len); - } else { - __u32 tfh[2]; - dev_t xdev; - ino_t xino; - - if (fh->fh_size != NFS_FHSIZE) - return error; - /* assume old filehandle format */ - xdev = old_decode_dev(fh->ofh_xdev); - xino = u32_to_ino_t(fh->ofh_xino); - mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL); - exp = rqst_exp_find(rqstp, FSID_DEV, tfh); + if (fh->fh_version != 1) + return error; + + if (--data_left < 0) + return error; + if (fh->fh_auth_type != 0) + return error; + len = key_len(fh->fh_fsid_type) / 4; + if (len == 0) + return error; + if (fh->fh_fsid_type == FSID_MAJOR_MINOR) { + /* deprecated, convert to type 3 */ + len = key_len(FSID_ENCODE_DEV)/4; + fh->fh_fsid_type = FSID_ENCODE_DEV; + /* + * struct knfsd_fh uses host-endian fields, which are + * sometimes used to hold net-endian values. This + * confuses sparse, so we must use __force here to + * keep it from complaining. + */ + fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]), + ntohl((__force __be32)fh->fh_fsid[1]))); + fh->fh_fsid[1] = fh->fh_fsid[2]; } + data_left -= len; + if (data_left < 0) + return error; + exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); + fid = (struct fid *)(fh->fh_fsid + len); error = nfserr_stale; if (IS_ERR(exp)) { @@ -253,18 +241,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) if (rqstp->rq_vers > 2) error = nfserr_badhandle; - if (fh->fh_version != 1) { - sfid.i32.ino = fh->ofh_ino; - sfid.i32.gen = fh->ofh_generation; - sfid.i32.parent_ino = fh->ofh_dirino; - fid = &sfid; - data_left = 3; - if (fh->ofh_dirino == 0) - fileid_type = FILEID_INO32_GEN; - else - fileid_type = FILEID_INO32_GEN_PARENT; - } else - fileid_type = fh->fh_fileid_type; + fileid_type = fh->fh_fileid_type; if (fileid_type == FILEID_ROOT) dentry = dget(exp->ex_path.dentry); @@ -452,20 +429,6 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp, } } -/* - * for composing old style file handles - */ -static inline void _fh_update_old(struct dentry *dentry, - struct svc_export *exp, - struct knfsd_fh *fh) -{ - fh->ofh_ino = ino_t_to_u32(d_inode(dentry)->i_ino); - fh->ofh_generation = d_inode(dentry)->i_generation; - if (d_is_dir(dentry) || - (exp->ex_flags & NFSEXP_NOSUBTREECHECK)) - fh->ofh_dirino = 0; -} - static bool is_root_export(struct svc_export *exp) { return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root; @@ -562,9 +525,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, /* ref_fh is a reference file handle. * if it is non-null and for the same filesystem, then we should compose * a filehandle which is of the same version, where possible. - * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca - * Then create a 32byte filehandle using nfs_fhbase_old - * */ struct inode * inode = d_inode(dentry); @@ -600,35 +560,21 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, fhp->fh_dentry = dget(dentry); /* our internal copy */ fhp->fh_export = exp_get(exp); - if (fhp->fh_handle.fh_version == 0xca) { - /* old style filehandle please */ - memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE); - fhp->fh_handle.fh_size = NFS_FHSIZE; - fhp->fh_handle.ofh_dcookie = 0xfeebbaca; - fhp->fh_handle.ofh_dev = old_encode_dev(ex_dev); - fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev; - fhp->fh_handle.ofh_xino = - ino_t_to_u32(d_inode(exp->ex_path.dentry)->i_ino); - fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry)); - if (inode) - _fh_update_old(dentry, exp, &fhp->fh_handle); - } else { - fhp->fh_handle.fh_size = - key_len(fhp->fh_handle.fh_fsid_type) + 4; - fhp->fh_handle.fh_auth_type = 0; - - mk_fsid(fhp->fh_handle.fh_fsid_type, - fhp->fh_handle.fh_fsid, - ex_dev, - d_inode(exp->ex_path.dentry)->i_ino, - exp->ex_fsid, exp->ex_uuid); - - if (inode) - _fh_update(fhp, exp, dentry); - if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { - fh_put(fhp); - return nfserr_opnotsupp; - } + fhp->fh_handle.fh_size = + key_len(fhp->fh_handle.fh_fsid_type) + 4; + fhp->fh_handle.fh_auth_type = 0; + + mk_fsid(fhp->fh_handle.fh_fsid_type, + fhp->fh_handle.fh_fsid, + ex_dev, + d_inode(exp->ex_path.dentry)->i_ino, + exp->ex_fsid, exp->ex_uuid); + + if (inode) + _fh_update(fhp, exp, dentry); + if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { + fh_put(fhp); + return nfserr_opnotsupp; } return 0; @@ -649,16 +595,12 @@ fh_update(struct svc_fh *fhp) dentry = fhp->fh_dentry; if (d_really_is_negative(dentry)) goto out_negative; - if (fhp->fh_handle.fh_version != 1) { - _fh_update_old(dentry, fhp->fh_export, &fhp->fh_handle); - } else { - if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT) - return 0; + if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT) + return 0; - _fh_update(fhp, fhp->fh_export, dentry); - if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) - return nfserr_opnotsupp; - } + _fh_update(fhp, fhp->fh_export, dentry); + if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) + return nfserr_opnotsupp; return 0; out_bad: printk(KERN_ERR "fh_update: fh not verified!\n"); @@ -698,16 +640,11 @@ fh_put(struct svc_fh *fhp) char * SVCFH_fmt(struct svc_fh *fhp) { struct knfsd_fh *fh = &fhp->fh_handle; + static char buf[2+1+1+64*3+1]; - static char buf[80]; - sprintf(buf, "%d: %08x %08x %08x %08x %08x %08x", - fh->fh_size, - fh->fh_base.fh_pad[0], - fh->fh_base.fh_pad[1], - fh->fh_base.fh_pad[2], - fh->fh_base.fh_pad[3], - fh->fh_base.fh_pad[4], - fh->fh_base.fh_pad[5]); + if (fh->fh_size < 0 || fh->fh_size> 64) + return "bad-fh"; + sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw); return buf; } diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 6106697adc04..d11e4b6870d6 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -10,9 +10,56 @@ #include <linux/crc32.h> #include <linux/sunrpc/svc.h> -#include <uapi/linux/nfsd/nfsfh.h> #include <linux/iversion.h> #include <linux/exportfs.h> +#include <linux/nfs4.h> + +/* + * The file handle starts with a sequence of four-byte words. + * The first word contains a version number (1) and three descriptor bytes + * that tell how the remaining 3 variable length fields should be handled. + * These three bytes are auth_type, fsid_type and fileid_type. + * + * All four-byte values are in host-byte-order. + * + * The auth_type field is deprecated and must be set to 0. + * + * The fsid_type identifies how the filesystem (or export point) is + * encoded. + * Current values: + * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number + * NOTE: we cannot use the kdev_t device id value, because kdev_t.h + * says we mustn't. We must break it up and reassemble. + * 1 - 4 byte user specified identifier + * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED + * 3 - 4 byte device id, encoded for user-space, 4 byte inode number + * 4 - 4 byte inode number and 4 byte uuid + * 5 - 8 byte uuid + * 6 - 16 byte uuid + * 7 - 8 byte inode number and 16 byte uuid + * + * The fileid_type identifies how the file within the filesystem is encoded. + * The values for this field are filesystem specific, exccept that + * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' + * in include/linux/exportfs.h for currently registered values. + */ + +struct knfsd_fh { + unsigned int fh_size; /* + * Points to the current size while + * building a new file handle. + */ + union { + char fh_raw[NFS4_FHSIZE]; + struct { + u8 fh_version; /* == 1 */ + u8 fh_auth_type; /* deprecated */ + u8 fh_fsid_type; + u8 fh_fileid_type; + u32 fh_fsid[]; /* flexible-array member */ + }; + }; +}; static inline __u32 ino_t_to_u32(ino_t ino) { @@ -188,7 +235,7 @@ static inline void fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) { dst->fh_size = src->fh_size; - memcpy(&dst->fh_base, &src->fh_base, src->fh_size); + memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size); } static __inline__ struct svc_fh * @@ -203,7 +250,7 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) { if (fh1->fh_size != fh2->fh_size) return false; - if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0) + if (memcmp(fh1->fh_raw, fh2->fh_raw, fh1->fh_size) != 0) return false; return true; } @@ -227,7 +274,7 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) */ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) { - return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size); + return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size); } #else static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 90fcd6178823..eea5b59b6a6c 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -234,8 +234,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh), argp->len, argp->offset); - nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages, - &argp->first, cnt); + nvecs = svc_fill_write_vector(rqstp, &argp->payload); if (!nvecs) { resp->status = nfserr_io; goto out; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ccb59e91011b..80431921e5d7 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1004,9 +1004,6 @@ out: int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *proc = rqstp->rq_procinfo; - struct kvec *argv = &rqstp->rq_arg.head[0]; - struct kvec *resv = &rqstp->rq_res.head[0]; - __be32 *p; /* * Give the xdr decoder a chance to change this if it wants @@ -1015,7 +1012,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_cachetype = proc->pc_cachetype; svcxdr_init_decode(rqstp); - if (!proc->pc_decode(rqstp, argv->iov_base)) + if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; switch (nfsd_cache_lookup(rqstp)) { @@ -1031,14 +1028,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) * Need to grab the location to store the status, as * NFSv4 does some encoding while processing */ - p = resv->iov_base + resv->iov_len; svcxdr_init_encode(rqstp); *statp = proc->pc_func(rqstp); if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; - if (!proc->pc_encode(rqstp, p)) + if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1); @@ -1065,29 +1061,29 @@ out_encode_err: /** * nfssvc_decode_voidarg - Decode void arguments * @rqstp: Server RPC transaction context - * @p: buffer containing arguments to decode + * @xdr: XDR stream positioned at arguments to decode * * Return values: - * %0: Arguments were not valid - * %1: Decoding was successful + * %false: Arguments were not valid + * %true: Decoding was successful */ -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p) +bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } /** * nfssvc_encode_voidres - Encode void results * @rqstp: Server RPC transaction context - * @p: buffer in which to encode results + * @xdr: XDR stream into which to encode results * * Return values: - * %0: Local error while encoding - * %1: Encoding was successful + * %false: Local error while encoding + * %true: Encoding was successful */ -int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) +bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } int nfsd_pool_stats_open(struct inode *inode, struct file *file) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index a06c05fe3b42..aba8520b4b8b 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -64,7 +64,7 @@ svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp) if (!p) return false; fh_init(fhp, NFS_FHSIZE); - memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE); + memcpy(&fhp->fh_handle.fh_raw, p, NFS_FHSIZE); fhp->fh_handle.fh_size = NFS_FHSIZE; return true; @@ -78,7 +78,7 @@ svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp) p = xdr_reserve_space(xdr, NFS_FHSIZE); if (!p) return false; - memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE); + memcpy(p, &fhp->fh_handle.fh_raw, NFS_FHSIZE); return true; } @@ -272,94 +272,81 @@ svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, * XDR decode functions */ -int -nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->fh); } -int -nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_sattrargs *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->fh) && svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int -nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_diropargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len); } -int -nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readargs *args = rqstp->rq_argp; u32 totalcount; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; /* totalcount is ignored */ if (xdr_stream_decode_u32(xdr, &totalcount) < 0) - return 0; + return false; - return 1; + return true; } -int -nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_writeargs *args = rqstp->rq_argp; - struct kvec *head = rqstp->rq_arg.head; - struct kvec *tail = rqstp->rq_arg.tail; u32 beginoffset, totalcount; - size_t remaining; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; /* beginoffset is ignored */ if (xdr_stream_decode_u32(xdr, &beginoffset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->offset) < 0) - return 0; + return false; /* totalcount is ignored */ if (xdr_stream_decode_u32(xdr, &totalcount) < 0) - return 0; + return false; /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) - return 0; + return false; if (args->len > NFSSVC_MAXBLKSIZE_V2) - return 0; - remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; - remaining -= xdr_stream_pos(xdr); - if (remaining < xdr_align_size(args->len)) - return 0; - args->first.iov_base = xdr->p; - args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); + return false; + if (!xdr_stream_subsegment(xdr, &args->payload, args->len)) + return false; - return 1; + return true; } -int -nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_createargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->fh, @@ -367,10 +354,9 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int -nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_renameargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->ffh, @@ -379,10 +365,9 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_linkargs *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->ffh) && @@ -390,178 +375,170 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; if (!svcxdr_decode_diropargs(xdr, &args->ffh, &args->fname, &args->flen)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) - return 0; + return false; if (args->tlen == 0) - return 0; + return false; args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); args->first.iov_base = xdr_inline_decode(xdr, args->tlen); if (!args->first.iov_base) - return 0; + return false; return svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int -nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->cookie) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } /* * XDR encode functions */ -int -nfssvc_encode_statres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_stat *resp = rqstp->rq_resp; return svcxdr_encode_stat(xdr, resp->status); } -int -nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fhandle(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (xdr_stream_encode_u32(xdr, resp->len) < 0) - return 0; + return false; xdr_write_pages(xdr, &resp->page, 0, resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_statfsres *resp = rqstp->rq_resp; struct kstatfs *stat = &resp->stats; + __be32 *p; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: p = xdr_reserve_space(xdr, XDR_UNIT * 5); if (!p) - return 0; + return false; *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2); *p++ = cpu_to_be32(stat->f_bsize); *p++ = cpu_to_be32(stat->f_blocks); @@ -570,7 +547,7 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) break; } - return 1; + return true; } /** diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 538520957a81..f1e0d3c51bc2 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,6 +9,7 @@ #define _NFSD_TRACE_H #include <linux/tracepoint.h> + #include "export.h" #include "nfsfh.h" diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 738d564ca4ce..c99857689e2c 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -244,6 +244,7 @@ out_nfserr: * returned. Otherwise the covered directory is returned. * NOTE: this mountpoint crossing is not supported properly by all * clients and is explicitly disallowed for NFSv3 + * NeilBrown <neilb@cse.unsw.edu.au> */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, @@ -729,9 +730,6 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, path.dentry = fhp->fh_dentry; inode = d_inode(path.dentry); - /* Disallow write access to files with the append-only bit set - * or any access when mandatory locking enabled - */ err = nfserr_perm; if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE)) goto out; @@ -1410,7 +1408,8 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (nfsd_create_is_exclusive(createmode)) { /* solaris7 gets confused (bugid 4218508) if these have - * the high bit set, so just clear the high bits. If this is + * the high bit set, as do xfs filesystems without the + * "bigtime" feature. So just clear the high bits. If this is * ever changed to use different attrs for storing the * verifier, then do_open_lookup() will also need to be fixed * accordingly. diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index f45b4bc93f52..528fb299430e 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -33,7 +33,7 @@ struct nfsd_writeargs { svc_fh fh; __u32 offset; int len; - struct kvec first; + struct xdr_buf payload; }; struct nfsd_createargs { @@ -141,23 +141,24 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_fhandleargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfssvc_encode_statres(struct svc_rqst *, __be32 *); -int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *); +bool nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset); int nfssvc_encode_entry(void *data, const char *name, int namlen, diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 933008382bbe..03fe4e21306c 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -40,7 +40,7 @@ struct nfsd3_writeargs { __u32 count; int stable; __u32 len; - struct kvec first; + struct xdr_buf payload; }; struct nfsd3_createargs { @@ -265,36 +265,37 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandleargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); -int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); -int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *); +bool nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfs3svc_release_fhandle(struct svc_rqst *); void nfs3svc_release_fhandle2(struct svc_rqst *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 3e4052e3bd50..846ab6df9d48 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -702,10 +702,11 @@ struct nfsd4_compoundres { struct xdr_stream *xdr; struct svc_rqst * rqstp; + __be32 *statusp; u32 taglen; char * tag; u32 opcnt; - __be32 * tagp; /* tag, opcount encode location */ + struct nfsd4_compound_state cstate; }; @@ -756,8 +757,8 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); +bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index b9c339335a53..dbf9b9e97d74 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1513,10 +1513,7 @@ bail: if (quota_enabled) kfree(rm_quota); - /* no one is callint kthread_stop() for us so the kthread() api - * requires that we call do_exit(). And it isn't exported, but - * complete_and_exit() seems to be a minimal wrapper around it. */ - complete_and_exit(NULL, status); + return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 53b6e9f9de7b..480f9207a4c6 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -278,6 +278,7 @@ struct acpi_device_power { int state; /* Current state */ struct acpi_device_power_flags flags; struct acpi_device_power_state states[ACPI_D_STATE_COUNT]; /* Power states (D0-D3Cold) */ + u8 state_for_enumeration; /* Deepest power state for enumeration */ }; struct acpi_dep_data { diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 20ecb004f5a4..33ad282bd338 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -10,25 +10,12 @@ #ifndef __ACGCC_H__ #define __ACGCC_H__ -/* - * Use compiler specific <stdarg.h> is a good practice for even when - * -nostdinc is specified (i.e., ACPI_USE_STANDARD_HEADERS undefined. - */ #ifndef va_arg -#ifdef ACPI_USE_BUILTIN_STDARG -typedef __builtin_va_list va_list; -#define va_start(v, l) __builtin_va_start(v, l) -#define va_end(v) __builtin_va_end(v) -#define va_arg(v, l) __builtin_va_arg(v, l) -#define va_copy(d, s) __builtin_va_copy(d, s) -#else #ifdef __KERNEL__ #include <linux/stdarg.h> #else -/* Used to build acpi tools */ #include <stdarg.h> #endif /* __KERNEL__ */ -#endif /* ACPI_USE_BUILTIN_STDARG */ #endif /* ! va_arg */ #define ACPI_INLINE __inline__ diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 524218ae3825..81695eb02a12 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -118,22 +118,6 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args); /** - * syscall_set_arguments - change system call parameter value - * @task: task of interest, must be in system call entry tracing - * @regs: task_pt_regs() of @task - * @args: array of argument values to store - * - * Changes 6 arguments to the system call. - * The first argument gets value @args[0], and so on. - * - * It's only valid to call this when @task is stopped for tracing on - * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or - * %SYSCALL_WORK_SYSCALL_AUDIT. - */ -void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - const unsigned long *args); - -/** * syscall_get_arch - return the AUDIT_ARCH for the current system call * @task: task of interest, must be blocked * diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index aafd07388eb7..b84693fbd2b5 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -24,6 +24,8 @@ #ifndef DRM_MODESET_LOCK_H_ #define DRM_MODESET_LOCK_H_ +#include <linux/types.h> /* stackdepot.h is not self-contained */ +#include <linux/stackdepot.h> #include <linux/ww_mutex.h> struct drm_modeset_lock; @@ -52,6 +54,12 @@ struct drm_modeset_acquire_ctx { struct drm_modeset_lock *contended; /* + * Stack depot for debugging when a contended lock was not backed off + * from. + */ + depot_stack_handle_t stack_depot; + + /* * list of held locks (drm_modeset_lock) */ struct list_head locked; diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 76d7c33884da..cd785cfa3123 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -351,9 +351,10 @@ bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, * @bo: Pointer to a ttm_buffer_object to be initialized. * @size: Requested size of buffer object. * @type: Requested type of buffer object. - * @flags: Initial placement flags. + * @placement: Initial placement for buffer object. * @page_alignment: Data alignment in pages. * @ctx: TTM operation context for memory allocation. + * @sg: Scatter-gather table. * @resv: Pointer to a dma_resv, or NULL to let ttm allocate one. * @destroy: Destroy function. Use NULL for kfree(). * @@ -394,7 +395,7 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, * @bo: Pointer to a ttm_buffer_object to be initialized. * @size: Requested size of buffer object. * @type: Requested type of buffer object. - * @flags: Initial placement flags. + * @placement: Initial placement for buffer object. * @page_alignment: Data alignment in pages. * @interruptible: If needing to sleep to wait for GPU resources, * sleep interruptible. @@ -402,6 +403,7 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, * holds a pointer to a persistent shmem object. Typically, this would * point to the shmem object backing a GEM object if TTM is used to back a * GEM user interface. + * @sg: Scatter-gather table. * @resv: Pointer to a dma_resv, or NULL to let ttm allocate one. * @destroy: Destroy function. Use NULL for kfree(). * @@ -582,8 +584,7 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, pgprot_t prot, - pgoff_t num_prefault, - pgoff_t fault_page_size); + pgoff_t num_prefault); vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 375715b0535f..143ce7e0bee1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1014,6 +1014,7 @@ int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); +bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } @@ -1025,6 +1026,10 @@ static inline bool acpi_storage_d3(struct device *dev) { return false; } +static inline bool acpi_dev_state_d0(struct device *dev) +{ + return true; +} #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2be6dfd68df9..f715e8863f4d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -484,6 +484,12 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static inline bool bpf_pseudo_func(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && + insn->src_reg == BPF_PSEUDO_FUNC; +} + struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index bc2699feddbe..7ad6c3d0db7d 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -302,6 +302,8 @@ enum { CEPH_SESSION_REQUEST_FLUSH_MDLOG, }; +#define CEPH_SESSION_BLOCKLISTED (1 << 0) /* session blocklisted */ + extern const char *ceph_session_op_name(int op); struct ceph_mds_session_head { diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 83fa08a06507..3431011f364d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -475,6 +475,14 @@ extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, u64 expected_object_size, u64 expected_write_size, u32 flags); +extern int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u32 dst_fadvise_flags, + u32 truncate_seq, u64 truncate_size, + u8 copy_from_flags); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, @@ -515,17 +523,6 @@ int ceph_osdc_call(struct ceph_osd_client *osdc, struct page *req_page, size_t req_len, struct page **resp_pages, size_t *resp_len); -int ceph_osdc_copy_from(struct ceph_osd_client *osdc, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - struct ceph_object_id *dst_oid, - struct ceph_object_locator *dst_oloc, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags); - /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, diff --git a/include/linux/dax.h b/include/linux/dax.h index 2619d94c308d..8623caa67388 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -38,8 +38,6 @@ struct dax_operations { int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; -extern struct attribute_group dax_attribute_group; - #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 8b6c20636a79..dbd235ab447f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -170,15 +170,20 @@ struct dma_resv_iter { /** @index: index into the shared fences */ unsigned int index; - /** @fences: the shared fences */ + /** @fences: the shared fences; private, *MUST* not dereference */ struct dma_resv_list *fences; + /** @shared_count: number of shared fences */ + unsigned int shared_count; + /** @is_restarted: true if this is the first returned fence */ bool is_restarted; }; struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor); /** * dma_resv_iter_begin - initialize a dma_resv_iter object @@ -244,6 +249,24 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) for (fence = dma_resv_iter_first_unlocked(cursor); \ fence; fence = dma_resv_iter_next_unlocked(cursor)) +/** + * dma_resv_for_each_fence - fence iterator + * @cursor: a struct dma_resv_iter pointer + * @obj: a dma_resv object pointer + * @all_fences: true if all fences should be returned + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object while holding the + * &dma_resv.lock. @all_fences controls if the shared fences are returned as + * well. The cursor initialisation is part of the iterator and the fence stays + * valid as long as the lock is held and so no extra reference to the fence is + * taken. + */ +#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ + for (dma_resv_iter_begin(cursor, obj, all_fences), \ + fence = dma_resv_iter_first(cursor); fence; \ + fence = dma_resv_iter_next(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e5c2c9e71bf1..9000f3ffce8b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -944,10 +944,8 @@ struct dma_device { void (*device_issue_pending)(struct dma_chan *chan); void (*device_release)(struct dma_device *dev); /* debugfs support */ -#ifdef CONFIG_DEBUG_FS void (*dbg_summary_show)(struct seq_file *s, struct dma_device *dev); struct dentry *dbg_dev_root; -#endif }; static inline int dmaengine_slave_config(struct dma_chan *chan, diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index d42010cf5468..7ee708ad7df2 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -12,6 +12,7 @@ struct ocelot_skb_cb { struct sk_buff *clone; unsigned int ptp_class; /* valid only for clones */ + u32 tstamp_lo; u8 ptp_cmd; u8 ts_id; }; diff --git a/include/linux/efi.h b/include/linux/efi.h index 6b5d36babfcc..dbd39b20e034 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -362,6 +362,7 @@ void efi_native_runtime_setup(void); /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) +#define AMD_SEV_MEM_ENCRYPT_GUID EFI_GUID(0x0cf29b71, 0x9e51, 0x433a, 0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75) typedef struct { efi_guid_t guid; diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 1e7bf78cb382..aba348d58ff6 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -10,6 +10,9 @@ #define __ETHTOOL_LINK_MODE_MASK_NWORDS \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) +#define ETHTOOL_PAUSE_STAT_CNT (__ETHTOOL_A_PAUSE_STAT_CNT - \ + ETHTOOL_A_PAUSE_STAT_TX_FRAMES) + enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; diff --git a/include/linux/fb.h b/include/linux/fb.h index 5950f8f5dc74..6f3db99ab990 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -262,7 +262,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another */ + /* Copy data from area to another. Obsolete. */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3afca821df32..1cb616fc1105 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3385,6 +3385,8 @@ extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); +extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 462634b4b48f..74c410263113 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -205,9 +205,9 @@ static inline dev_t disk_devt(struct gendisk *disk) void disk_uevent(struct gendisk *disk, enum kobject_action action); /* block/genhd.c */ -int device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline int add_disk(struct gendisk *disk) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int __must_check add_disk(struct gendisk *disk) { return device_add_disk(NULL, disk, NULL); } diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 2ce3efbe9198..16119ac1aa97 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -11,6 +11,7 @@ #define _LINUX_I2C_H #include <linux/acpi.h> /* for acpi_handle */ +#include <linux/bits.h> #include <linux/mod_devicetable.h> #include <linux/device.h> /* for struct device */ #include <linux/sched.h> /* for completion */ @@ -223,6 +224,15 @@ enum i2c_alert_protocol { }; /** + * enum i2c_driver_flags - Flags for an I2C device driver + * + * @I2C_DRV_ACPI_WAIVE_D0_PROBE: Don't put the device in D0 state for probe + */ +enum i2c_driver_flags { + I2C_DRV_ACPI_WAIVE_D0_PROBE = BIT(0), +}; + +/** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) * @probe: Callback for device binding - soon to be deprecated @@ -236,6 +246,7 @@ enum i2c_alert_protocol { * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) * @clients: List of detected clients we created (for i2c-core use only) + * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. @@ -294,6 +305,8 @@ struct i2c_driver { int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; struct list_head clients; + + u32 flags; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) @@ -1015,6 +1028,7 @@ u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); +bool i2c_acpi_waive_d0_probe(struct device *dev); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) @@ -1038,6 +1052,10 @@ static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle ha { return NULL; } +static inline bool i2c_acpi_waive_d0_probe(struct device *dev) +{ + return false; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ diff --git a/include/linux/input/cy8ctmg110_pdata.h b/include/linux/input/cy8ctmg110_pdata.h deleted file mode 100644 index ee1d44545f30..000000000000 --- a/include/linux/input/cy8ctmg110_pdata.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_CY8CTMG110_PDATA_H -#define _LINUX_CY8CTMG110_PDATA_H - -struct cy8ctmg110_pdata -{ - int reset_pin; /* Reset pin is wired to this GPIO (optional) */ -}; - -#endif diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 9fd0ad80fef6..5f5965246877 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -100,9 +100,12 @@ void kcsan_set_access_mask(unsigned long mask); /* Scoped access information. */ struct kcsan_scoped_access { struct list_head list; + /* Access information. */ const volatile void *ptr; size_t size; int type; + /* Location where scoped access was set up. */ + unsigned long ip; }; /* * Automatically call kcsan_end_scoped_access() when kcsan_scoped_access goes diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 60a35d9fe259..9e0667e3723e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,7 +150,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_BUGGED (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -617,6 +617,7 @@ struct kvm { unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool vm_bugged; + bool vm_dead; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; @@ -650,12 +651,19 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline void kvm_vm_dead(struct kvm *kvm) +{ + kvm->vm_dead = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); +} + static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; - kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED); + kvm_vm_dead(kvm); } + #define KVM_BUG(cond, kvm, fmt...) \ ({ \ int __ret = (cond); \ diff --git a/include/linux/libata.h b/include/linux/libata.h index 2884383f1718..2a8404b26083 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -394,7 +394,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 6, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependent */ @@ -427,6 +427,7 @@ enum { ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ + ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index a98309c0121c..398f70093cd3 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,18 +96,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); +bool nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 5ae766f26e04..9a6b55da8fd6 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,21 +22,20 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) - - -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); +bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); extern const struct rpc_version nlm_version4; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a9ac70ae01ab..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -329,11 +329,11 @@ LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) LSM_HOOK(int, 0, tun_dev_open, void *security) -LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_endpoint *ep, +LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) -LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_endpoint *ep, +LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) #endif /* CONFIG_SECURITY_NETWORK */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0bada4df23fc..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1027,9 +1027,9 @@ * Security hooks for SCTP * * @sctp_assoc_request: - * Passes the @ep and @chunk->skb of the association INIT packet to + * Passes the @asoc and @chunk->skb of the association INIT packet to * the security module. - * @ep pointer to sctp endpoint structure. + * @asoc pointer to sctp association structure. * @skb pointer to skbuff of association packet. * Return 0 on success, error on failure. * @sctp_bind_connect: @@ -1047,9 +1047,9 @@ * Called whenever a new socket is created by accept(2) (i.e. a TCP * style socket) or when a socket is 'peeled off' e.g userspace * calls sctp_peeloff(3). - * @ep pointer to current sctp endpoint structure. + * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. - * @sk pointer to new sock structure. + * @newsk pointer to new sock structure. * * Security hooks for Infiniband * diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 7df557b16c1e..8adcf1fa8096 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -389,7 +389,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 -#define MEMBLOCK_ALLOC_KASAN 1 +#define MEMBLOCK_ALLOC_NOLEAKTRACE 1 /* We are using top down, so it is safe to use 0 here */ #define MEMBLOCK_LOW_LIMIT 0 diff --git a/include/linux/migrate.h b/include/linux/migrate.h index eeb818c4fc78..4850cc5bf813 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -110,7 +110,6 @@ static inline int migrate_misplaced_page(struct page *page, */ #define MIGRATE_PFN_VALID (1UL << 0) #define MIGRATE_PFN_MIGRATE (1UL << 1) -#define MIGRATE_PFN_LOCKED (1UL << 2) #define MIGRATE_PFN_WRITE (1UL << 3) #define MIGRATE_PFN_SHIFT 6 diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 12c4177f7703..ca0683b9e3d1 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -166,13 +166,13 @@ struct netfs_read_request { short error; /* 0 or error that occurred */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ - pgoff_t no_unlock_page; /* Don't unlock this page after read */ + pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t usage; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ #define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ -#define NETFS_RREQ_NO_UNLOCK_PAGE 2 /* Don't unlock no_unlock_page on completion */ -#define NETFS_RREQ_DONT_UNLOCK_PAGES 3 /* Don't unlock the pages on completion */ +#define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ +#define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ const struct netfs_read_request_ops *netfs_ops; @@ -190,7 +190,7 @@ struct netfs_read_request_ops { void (*issue_op)(struct netfs_read_subrequest *subreq); bool (*is_still_valid)(struct netfs_read_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); void (*done)(struct netfs_read_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; @@ -240,11 +240,11 @@ extern void netfs_readahead(struct readahead_control *, const struct netfs_read_request_ops *, void *); extern int netfs_readpage(struct file *, - struct page *, + struct folio *, const struct netfs_read_request_ops *, void *); extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct page **, + loff_t, unsigned int, unsigned int, struct folio **, void **, const struct netfs_read_request_ops *, void *); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 15004c469807..5662d8be04eb 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -292,6 +292,10 @@ enum nfsstat4 { NFS4ERR_XATTR2BIG = 10096, }; +/* error codes for internal client use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + static inline bool seqid_mutating_err(u32 err) { /* See RFC 7530, section 9.1.7 */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b9a8b925db43..05f249f20f55 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -81,7 +81,7 @@ struct nfs_open_context { fl_owner_t flock_owner; struct dentry *dentry; const struct cred *cred; - struct rpc_cred *ll_cred; /* low-level cred - use to check for expiry */ + struct rpc_cred __rcu *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; @@ -103,6 +103,7 @@ struct nfs_open_dir_context { __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 dup_cookie; + pgoff_t page_index; signed char duped; }; @@ -154,36 +155,39 @@ struct nfs_inode { unsigned long attrtimeo_timestamp; unsigned long attr_gencount; - /* "Generation counter" for the attribute cache. This is - * bumped whenever we update the metadata on the - * server. - */ - unsigned long cache_change_attribute; struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; - /* - * This is the cookie verifier used for NFSv3 readdir - * operations - */ - __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; - - atomic_long_t nrequests; - struct nfs_mds_commit_info commit_info; + union { + /* Directory */ + struct { + /* "Generation counter" for the attribute cache. + * This is bumped whenever we update the metadata + * on the server. + */ + unsigned long cache_change_attribute; + /* + * This is the cookie verifier used for NFSv3 readdir + * operations + */ + __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; + /* Readers: in-flight sillydelete RPC calls */ + /* Writers: rmdir */ + struct rw_semaphore rmdir_sem; + }; + /* Regular file */ + struct { + atomic_long_t nrequests; + struct nfs_mds_commit_info commit_info; + struct mutex commit_mutex; + }; + }; /* Open contexts for shared mmap writes */ struct list_head open_files; - /* Readers: in-flight sillydelete RPC calls */ - /* Writers: rmdir */ - struct rw_semaphore rmdir_sem; - struct mutex commit_mutex; - - /* track last access to cached pages */ - unsigned long page_index; - #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -272,6 +276,7 @@ struct nfs4_copy_state { #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ +#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -383,7 +388,7 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_set_inode_stale(struct inode *inode); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); @@ -404,8 +409,7 @@ extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *map extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); -extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label); +extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); @@ -421,9 +425,22 @@ extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); +extern struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server); + +static inline void nfs4_label_free(struct nfs4_label *label) +{ +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + if (label) { + kfree(label->label); + kfree(label); + } +#endif +} static inline void nfs_free_fattr(const struct nfs_fattr *fattr) { + if (fattr) + nfs4_label_free(fattr->label); kfree(fattr); } @@ -511,10 +528,9 @@ extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); extern void nfs_clear_verifier_delegated(struct inode *inode); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, - struct nfs_fh *fh, struct nfs_fattr *fattr, - struct nfs4_label *label); + struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr, struct nfs4_label *label); + struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, @@ -569,11 +585,14 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); +bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int nfs_have_writebacks(struct inode *inode) { - return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + if (S_ISREG(inode->i_mode)) + return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + return 0; } /* diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e9698b6278a5..967a0098f0a9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -488,7 +488,6 @@ struct nfs_openres { struct nfs4_change_info cinfo; __u32 rflags; struct nfs_fattr * f_attr; - struct nfs4_label *f_label; struct nfs_seqid * seqid; const struct nfs_server *server; fmode_t delegation_type; @@ -753,7 +752,6 @@ struct nfs_entry { int eof; struct nfs_fh * fh; struct nfs_fattr * fattr; - struct nfs4_label *label; unsigned char d_type; struct nfs_server * server; }; @@ -834,7 +832,6 @@ struct nfs_getaclres { struct nfs_setattrres { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; - struct nfs4_label *label; const struct nfs_server * server; }; @@ -1041,7 +1038,6 @@ struct nfs4_create_res { const struct nfs_server * server; struct nfs_fh * fh; struct nfs_fattr * fattr; - struct nfs4_label *label; struct nfs4_change_info dir_cinfo; }; @@ -1066,7 +1062,6 @@ struct nfs4_getattr_res { struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_label *label; }; struct nfs4_link_arg { @@ -1081,7 +1076,6 @@ struct nfs4_link_res { struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_label *label; struct nfs4_change_info cinfo; struct nfs_fattr * dir_attr; }; @@ -1098,7 +1092,6 @@ struct nfs4_lookup_res { const struct nfs_server * server; struct nfs_fattr * fattr; struct nfs_fh * fh; - struct nfs4_label *label; }; struct nfs4_lookupp_arg { @@ -1112,7 +1105,6 @@ struct nfs4_lookupp_res { const struct nfs_server *server; struct nfs_fattr *fattr; struct nfs_fh *fh; - struct nfs4_label *label; }; struct nfs4_lookup_root_arg { @@ -1738,15 +1730,13 @@ struct nfs_rpc_ops { int (*submount) (struct fs_context *, struct nfs_server *); int (*try_get_tree) (struct fs_context *); int (*getattr) (struct nfs_server *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *, - struct inode *); + struct nfs_fattr *, struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); int (*lookup) (struct inode *, struct dentry *, - struct nfs_fh *, struct nfs_fattr *, - struct nfs4_label *); + struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 43c638c51c1f..119a0c9d2a8b 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -8,9 +8,9 @@ extern struct static_key_false page_owner_inited; extern struct page_ext_operations page_owner_ops; -extern void __reset_page_owner(struct page *page, unsigned int order); +extern void __reset_page_owner(struct page *page, unsigned short order); extern void __set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask); + unsigned short order, gfp_t gfp_mask); extern void __split_page_owner(struct page *page, unsigned int nr); extern void __folio_copy_owner(struct folio *newfolio, struct folio *old); extern void __set_page_owner_migrate_reason(struct page *page, int reason); @@ -18,14 +18,14 @@ extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone); -static inline void reset_page_owner(struct page *page, unsigned int order) +static inline void reset_page_owner(struct page *page, unsigned short order) { if (static_branch_unlikely(&page_owner_inited)) __reset_page_owner(page, order); } static inline void set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask) + unsigned short order, gfp_t gfp_mask) { if (static_branch_unlikely(&page_owner_inited)) __set_page_owner(page, order, gfp_mask); @@ -52,7 +52,7 @@ static inline void dump_page_owner(const struct page *page) __dump_page_owner(page); } #else -static inline void reset_page_owner(struct page *page, unsigned int order) +static inline void reset_page_owner(struct page *page, unsigned short order) { } static inline void set_page_owner(struct page *page, @@ -60,7 +60,7 @@ static inline void set_page_owner(struct page *page, { } static inline void split_page_owner(struct page *page, - unsigned int order) + unsigned short order) { } static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6a30916b76e5..1a0c646eb6ff 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -253,6 +253,20 @@ static inline struct address_space *page_mapping_file(struct page *page) return folio_mapping(folio); } +/** + * folio_inode - Get the host inode for this folio. + * @folio: The folio. + * + * For folios which are in the page cache, return the inode that this folio + * belongs to. + * + * Do not call this for folios which aren't in the page cache. + */ +static inline struct inode *folio_inode(struct folio *folio) +{ + return folio->mapping->host; +} + static inline bool page_cache_add_speculative(struct page *page, int count) { VM_BUG_ON_PAGE(PageTail(page), page); @@ -280,6 +294,25 @@ static inline void folio_attach_private(struct folio *folio, void *data) } /** + * folio_change_private - Change private data on a folio. + * @folio: Folio to change the data on. + * @data: Data to set on the folio. + * + * Change the private data attached to a folio and return the old + * data. The page must previously have had data attached and the data + * must be detached before the folio will be freed. + * + * Return: Data that was previously attached to the folio. + */ +static inline void *folio_change_private(struct folio *folio, void *data) +{ + void *old = folio_get_private(folio); + + folio->private = data; + return old; +} + +/** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. * diff --git a/include/linux/pci.h b/include/linux/pci.h index c8afbee5da4b..0b9d58098c8b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -342,6 +342,7 @@ struct pci_dev { u16 pcie_flags_reg; /* Cached PCIe Capabilities Register */ unsigned long *dma_alias_mask;/* Mask of enabled devfn aliases */ + struct pci_driver *driver; /* Driver bound to this device */ u64 dma_mask; /* Mask of the bits of bus address this device implements. Normally this is 0xffffffff. You only need to change @@ -1665,6 +1666,7 @@ void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); +void pci_dev_lock(struct pci_dev *dev); int pci_dev_trylock(struct pci_dev *dev); void pci_dev_unlock(struct pci_dev *dev); diff --git a/include/linux/pid.h b/include/linux/pid.h index af308e15f174..343abf22092e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -78,6 +78,7 @@ struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); +struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); static inline struct pid *get_pid(struct pid *pid) diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 02599687770c..df3c78c92ca2 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -205,7 +205,7 @@ struct cros_ec_dev { struct cros_ec_debugfs *debug_info; bool has_kb_wake_angle; u16 cmd_offset; - u32 features[2]; + struct ec_response_get_features features; }; #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) @@ -227,10 +227,13 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); -int cros_ec_check_features(struct cros_ec_dev *ec, int feature); +bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +int cros_ec_command(struct cros_ec_device *ec_dev, unsigned int version, int command, void *outdata, + int outsize, void *indata, int insize); + /** * cros_ec_get_time_ns() - Return time in ns. * diff --git a/include/linux/platform_data/ux500_wdt.h b/include/linux/platform_data/ux500_wdt.h deleted file mode 100644 index de6a4ad41e76..000000000000 --- a/include/linux/platform_data/ux500_wdt.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST Ericsson SA 2011 - * - * STE Ux500 Watchdog platform data - */ -#ifndef __UX500_WDT_H -#define __UX500_WDT_H - -/** - * struct ux500_wdt_data - */ -struct ux500_wdt_data { - unsigned int timeout; - bool has_28_bits_resolution; -}; - -#endif /* __UX500_WDT_H */ diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 84150a22fd7c..879c138c7b8e 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -156,9 +156,9 @@ int devm_pm_opp_set_clkname(struct device *dev, const char *name); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); int devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); -int devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -376,7 +376,7 @@ static inline int devm_pm_opp_set_clkname(struct device *dev, const char *name) return -EOPNOTSUPP; } -static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) +static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs) { return ERR_PTR(-EOPNOTSUPP); } @@ -384,7 +384,7 @@ static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, cons static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} static inline int devm_pm_opp_attach_genpd(struct device *dev, - const char **names, + const char * const *names, struct device ***virt_devs) { return -EOPNOTSUPP; @@ -439,7 +439,9 @@ static inline int dev_pm_opp_sync_regulators(struct device *dev) #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); +int devm_pm_opp_of_add_table_indexed(struct device *dev, int index); int dev_pm_opp_of_add_table_noclk(struct device *dev, int index); +int devm_pm_opp_of_add_table_noclk(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int devm_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); @@ -465,11 +467,21 @@ static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) return -EOPNOTSUPP; } +static inline int devm_pm_opp_of_add_table_indexed(struct device *dev, int index) +{ + return -EOPNOTSUPP; +} + static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) { return -EOPNOTSUPP; } +static inline int devm_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return -EOPNOTSUPP; +} + static inline void dev_pm_opp_of_remove_table(struct device *dev) { } diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h deleted file mode 100644 index 17d7d0d20eca..000000000000 --- a/include/linux/pnfs_osd_xdr.h +++ /dev/null @@ -1,317 +0,0 @@ -/* - * pNFS-osd on-the-wire data structures - * - * Copyright (C) 2007 Panasas Inc. [year of first publication] - * All rights reserved. - * - * Benny Halevy <bhalevy@panasas.com> - * Boaz Harrosh <ooo@electrozaur.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * See the file COPYING included with this distribution for more details. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Panasas company nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ -#ifndef __PNFS_OSD_XDR_H__ -#define __PNFS_OSD_XDR_H__ - -#include <linux/nfs_fs.h> - -/* - * draft-ietf-nfsv4-minorversion-22 - * draft-ietf-nfsv4-pnfs-obj-12 - */ - -/* Layout Structure */ - -enum pnfs_osd_raid_algorithm4 { - PNFS_OSD_RAID_0 = 1, - PNFS_OSD_RAID_4 = 2, - PNFS_OSD_RAID_5 = 3, - PNFS_OSD_RAID_PQ = 4 /* Reed-Solomon P+Q */ -}; - -/* struct pnfs_osd_data_map4 { - * uint32_t odm_num_comps; - * length4 odm_stripe_unit; - * uint32_t odm_group_width; - * uint32_t odm_group_depth; - * uint32_t odm_mirror_cnt; - * pnfs_osd_raid_algorithm4 odm_raid_algorithm; - * }; - */ -struct pnfs_osd_data_map { - u32 odm_num_comps; - u64 odm_stripe_unit; - u32 odm_group_width; - u32 odm_group_depth; - u32 odm_mirror_cnt; - u32 odm_raid_algorithm; -}; - -/* struct pnfs_osd_objid4 { - * deviceid4 oid_device_id; - * uint64_t oid_partition_id; - * uint64_t oid_object_id; - * }; - */ -struct pnfs_osd_objid { - struct nfs4_deviceid oid_device_id; - u64 oid_partition_id; - u64 oid_object_id; -}; - -/* For printout. I use: - * kprint("dev(%llx:%llx)", _DEVID_LO(pointer), _DEVID_HI(pointer)); - * BE style - */ -#define _DEVID_LO(oid_device_id) \ - (unsigned long long)be64_to_cpup((__be64 *)(oid_device_id)->data) - -#define _DEVID_HI(oid_device_id) \ - (unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1) - -enum pnfs_osd_version { - PNFS_OSD_MISSING = 0, - PNFS_OSD_VERSION_1 = 1, - PNFS_OSD_VERSION_2 = 2 -}; - -struct pnfs_osd_opaque_cred { - u32 cred_len; - void *cred; -}; - -enum pnfs_osd_cap_key_sec { - PNFS_OSD_CAP_KEY_SEC_NONE = 0, - PNFS_OSD_CAP_KEY_SEC_SSV = 1, -}; - -/* struct pnfs_osd_object_cred4 { - * pnfs_osd_objid4 oc_object_id; - * pnfs_osd_version4 oc_osd_version; - * pnfs_osd_cap_key_sec4 oc_cap_key_sec; - * opaque oc_capability_key<>; - * opaque oc_capability<>; - * }; - */ -struct pnfs_osd_object_cred { - struct pnfs_osd_objid oc_object_id; - u32 oc_osd_version; - u32 oc_cap_key_sec; - struct pnfs_osd_opaque_cred oc_cap_key; - struct pnfs_osd_opaque_cred oc_cap; -}; - -/* struct pnfs_osd_layout4 { - * pnfs_osd_data_map4 olo_map; - * uint32_t olo_comps_index; - * pnfs_osd_object_cred4 olo_components<>; - * }; - */ -struct pnfs_osd_layout { - struct pnfs_osd_data_map olo_map; - u32 olo_comps_index; - u32 olo_num_comps; - struct pnfs_osd_object_cred *olo_comps; -}; - -/* Device Address */ -enum pnfs_osd_targetid_type { - OBJ_TARGET_ANON = 1, - OBJ_TARGET_SCSI_NAME = 2, - OBJ_TARGET_SCSI_DEVICE_ID = 3, -}; - -/* union pnfs_osd_targetid4 switch (pnfs_osd_targetid_type4 oti_type) { - * case OBJ_TARGET_SCSI_NAME: - * string oti_scsi_name<>; - * - * case OBJ_TARGET_SCSI_DEVICE_ID: - * opaque oti_scsi_device_id<>; - * - * default: - * void; - * }; - * - * union pnfs_osd_targetaddr4 switch (bool ota_available) { - * case TRUE: - * netaddr4 ota_netaddr; - * case FALSE: - * void; - * }; - * - * struct pnfs_osd_deviceaddr4 { - * pnfs_osd_targetid4 oda_targetid; - * pnfs_osd_targetaddr4 oda_targetaddr; - * uint64_t oda_lun; - * opaque oda_systemid<>; - * pnfs_osd_object_cred4 oda_root_obj_cred; - * opaque oda_osdname<>; - * }; - */ -struct pnfs_osd_targetid { - u32 oti_type; - struct nfs4_string oti_scsi_device_id; -}; - -/* struct netaddr4 { - * // see struct rpcb in RFC1833 - * string r_netid<>; // network id - * string r_addr<>; // universal address - * }; - */ -struct pnfs_osd_net_addr { - struct nfs4_string r_netid; - struct nfs4_string r_addr; -}; - -struct pnfs_osd_targetaddr { - u32 ota_available; - struct pnfs_osd_net_addr ota_netaddr; -}; - -struct pnfs_osd_deviceaddr { - struct pnfs_osd_targetid oda_targetid; - struct pnfs_osd_targetaddr oda_targetaddr; - u8 oda_lun[8]; - struct nfs4_string oda_systemid; - struct pnfs_osd_object_cred oda_root_obj_cred; - struct nfs4_string oda_osdname; -}; - -/* LAYOUTCOMMIT: layoutupdate */ - -/* union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) { - * case TRUE: - * int64_t dsu_delta; - * case FALSE: - * void; - * }; - * - * struct pnfs_osd_layoutupdate4 { - * pnfs_osd_deltaspaceused4 olu_delta_space_used; - * bool olu_ioerr_flag; - * }; - */ -struct pnfs_osd_layoutupdate { - u32 dsu_valid; - s64 dsu_delta; - u32 olu_ioerr_flag; -}; - -/* LAYOUTRETURN: I/O Rrror Report */ - -enum pnfs_osd_errno { - PNFS_OSD_ERR_EIO = 1, - PNFS_OSD_ERR_NOT_FOUND = 2, - PNFS_OSD_ERR_NO_SPACE = 3, - PNFS_OSD_ERR_BAD_CRED = 4, - PNFS_OSD_ERR_NO_ACCESS = 5, - PNFS_OSD_ERR_UNREACHABLE = 6, - PNFS_OSD_ERR_RESOURCE = 7 -}; - -/* struct pnfs_osd_ioerr4 { - * pnfs_osd_objid4 oer_component; - * length4 oer_comp_offset; - * length4 oer_comp_length; - * bool oer_iswrite; - * pnfs_osd_errno4 oer_errno; - * }; - */ -struct pnfs_osd_ioerr { - struct pnfs_osd_objid oer_component; - u64 oer_comp_offset; - u64 oer_comp_length; - u32 oer_iswrite; - u32 oer_errno; -}; - -/* OSD XDR Client API */ -/* Layout helpers */ -/* Layout decoding is done in two parts: - * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part - * of the layout. @iter members need not be initialized. - * Returned: - * @layout members are set. (@layout->olo_comps set to NULL). - * - * Zero on success, or negative error if passed xdr is broken. - * - * 2. 2nd Call pnfs_osd_xdr_decode_layout_comp() in a loop until it returns - * false, to decode the next component. - * Returned: - * true if there is more to decode or false if we are done or error. - * - * Example: - * struct pnfs_osd_xdr_decode_layout_iter iter; - * struct pnfs_osd_layout layout; - * struct pnfs_osd_object_cred comp; - * int status; - * - * status = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr); - * if (unlikely(status)) - * goto err; - * while(pnfs_osd_xdr_decode_layout_comp(&comp, &iter, xdr, &status)) { - * // All of @comp strings point to inside the xdr_buffer - * // or scrach buffer. Copy them out to user memory eg. - * copy_single_comp(dest_comp++, &comp); - * } - * if (unlikely(status)) - * goto err; - */ - -struct pnfs_osd_xdr_decode_layout_iter { - unsigned total_comps; - unsigned decoded_comps; -}; - -extern int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout, - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr); - -extern bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp, - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr, - int *err); - -/* Device Info helpers */ - -/* Note: All strings inside @deviceaddr point to space inside @p. - * @p should stay valid while @deviceaddr is in use. - */ -extern void pnfs_osd_xdr_decode_deviceaddr( - struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p); - -/* layoutupdate (layout_commit) xdr helpers */ -extern int -pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr, - struct pnfs_osd_layoutupdate *lou); - -/* osd_ioerror encoding (layout_return) */ -extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr); -extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr); - -#endif /* __PNFS_OSD_XDR_H__ */ diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 725c9b784e60..e6dac95e4960 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -429,16 +429,19 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, #else static inline struct pwm_device *pwm_request(int pwm_id, const char *label) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline void pwm_free(struct pwm_device *pwm) { + might_sleep(); } static inline int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) { + might_sleep(); return -ENOTSUPP; } @@ -450,6 +453,7 @@ static inline int pwm_adjust_config(struct pwm_device *pwm) static inline int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns) { + might_sleep(); return -EINVAL; } @@ -462,11 +466,13 @@ static inline int pwm_capture(struct pwm_device *pwm, static inline int pwm_enable(struct pwm_device *pwm) { + might_sleep(); return -EINVAL; } static inline void pwm_disable(struct pwm_device *pwm) { + might_sleep(); } static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) @@ -493,12 +499,14 @@ static inline struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, unsigned int index, const char *label) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline struct pwm_device *pwm_get(struct device *dev, const char *consumer) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -506,16 +514,19 @@ static inline struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline void pwm_put(struct pwm_device *pwm) { + might_sleep(); } static inline struct pwm_device *devm_pwm_get(struct device *dev, const char *consumer) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -523,6 +534,7 @@ static inline struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -530,6 +542,7 @@ static inline struct pwm_device * devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } #endif diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 83c09ac36b13..e0600e1e5c17 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -684,18 +684,6 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, void *priv); int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); -static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) -{ - return container_of(vdev->dev.parent, struct rproc_vdev, dev); -} - -static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) -{ - struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); - - return rvdev->rproc; -} - void rproc_add_subdev(struct rproc *rproc, struct rproc_subdev *subdev); void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 990b80fb49ad..02fa9116cd60 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -233,7 +233,7 @@ static inline struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev /* This shouldn't be possible */ WARN_ON(1); - return ERR_PTR(-ENXIO); + return NULL; } static inline int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len) diff --git a/include/linux/rtc.h b/include/linux/rtc.h index bd611e26291d..47fd1c2d3a57 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -66,6 +66,8 @@ struct rtc_class_ops { int (*alarm_irq_enable)(struct device *, unsigned int enabled); int (*read_offset)(struct device *, long *offset); int (*set_offset)(struct device *, long offset); + int (*param_get)(struct device *, struct rtc_param *param); + int (*param_set)(struct device *, struct rtc_param *param); }; struct rtc_device; @@ -80,6 +82,7 @@ struct rtc_timer { /* flags */ #define RTC_DEV_BUSY 0 +#define RTC_NO_CDEV 1 struct rtc_device { struct device dev; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index a8fe2a593a3a..23505394ef70 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -351,6 +351,7 @@ extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); +extern void force_fatal_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); diff --git a/include/linux/security.h b/include/linux/security.h index 7e0ba63b5dde..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -179,7 +179,7 @@ struct xfrm_policy; struct xfrm_state; struct xfrm_user_sec_ctx; struct seq_file; -struct sctp_endpoint; +struct sctp_association; #ifdef CONFIG_MMU extern unsigned long mmap_min_addr; @@ -1425,10 +1425,10 @@ int security_tun_dev_create(void); int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); -int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb); +int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb); int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); -void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); #else /* CONFIG_SECURITY_NETWORK */ @@ -1631,7 +1631,7 @@ static inline int security_tun_dev_open(void *security) return 0; } -static inline int security_sctp_assoc_request(struct sctp_endpoint *ep, +static inline int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return 0; @@ -1644,7 +1644,7 @@ static inline int security_sctp_bind_connect(struct sock *sk, int optname, return 0; } -static inline void security_sctp_sk_clone(struct sctp_endpoint *ep, +static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 34cb28b8f16c..a70b2bdbf4d9 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -70,6 +70,9 @@ struct ksignal { int sig; }; +/* Used to kill the race between sigaction and forced signals */ +#define SA_IMMUTABLE 0x00800000 + #ifndef __ARCH_UAPI_SA_FLAGS #ifdef SA_RESTORER #define __ARCH_UAPI_SA_FLAGS SA_RESTORER diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0bd6520329f6..686a666d073d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -454,9 +454,15 @@ enum { * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), + + /* segment contains only zerocopy data and should not be + * charged to the kernel memory. + */ + SKBFL_PURE_ZEROCOPY = BIT(2), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1464,6 +1470,17 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } +static inline bool skb_zcopy_pure(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; +} + +static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ + return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); +} + static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); @@ -1528,7 +1545,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } @@ -1675,6 +1692,22 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) return 0; } +/* This variant of skb_unclone() makes sure skb->truesize is not changed */ +static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) +{ + might_sleep_if(gfpflags_allow_blocking(pri)); + + if (skb_cloned(skb)) { + unsigned int save = skb->truesize; + int res; + + res = pskb_expand_head(skb, 0, 0, pri); + skb->truesize = save; + return res; + } + return 0; +} + /** * skb_header_cloned - is the header a clone * @skb: buffer to check diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index b4256847c707..584d94be9c8b 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -507,6 +507,18 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } +static inline bool sk_is_tcp(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static inline bool sk_is_udp(const struct sock *sk) +{ + return sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; +} + #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) diff --git a/include/linux/spi/ads7846.h b/include/linux/spi/ads7846.h index 1a5eaef3b7f2..d424c1aadf38 100644 --- a/include/linux/spi/ads7846.h +++ b/include/linux/spi/ads7846.h @@ -1,17 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* linux/spi/ads7846.h */ -/* Touchscreen characteristics vary between boards and models. The - * platform_data for the device's "struct device" holds this information. - * - * It's OK if the min/max values are zero. - */ -enum ads7846_filter { - ADS7846_FILTER_OK, - ADS7846_FILTER_REPEAT, - ADS7846_FILTER_IGNORE, -}; - struct ads7846_platform_data { u16 model; /* 7843, 7845, 7846, 7873. */ u16 vref_delay_usecs; /* 0 for external vref; etc */ @@ -51,10 +40,6 @@ struct ads7846_platform_data { int gpio_pendown_debounce; /* platform specific debounce time for * the gpio_pendown */ int (*get_pendown_state)(void); - int (*filter_init) (const struct ads7846_platform_data *pdata, - void **filter_data); - int (*filter) (void *filter_data, int data_idx, int *val); - void (*filter_cleanup)(void *filter_data); void (*wait_for_sync)(void); bool wakeup; unsigned long irq_flags; diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index a4661646adc9..267b7aeaf1a6 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -40,6 +40,7 @@ struct rpc_clnt { unsigned int cl_clid; /* client id */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ + atomic_t cl_pid; /* task PID counter */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ const struct rpc_procinfo *cl_procinfo; /* procedure info */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index a237b8dbf608..db964bb63912 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -150,25 +150,13 @@ struct rpc_task_setup { #define RPC_TASK_MSG_PIN_WAIT 5 #define RPC_TASK_SIGNALLED 6 -#define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -#define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_test_and_set_running(t) \ test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -#define rpc_clear_running(t) \ - do { \ - smp_mb__before_atomic(); \ - clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate); \ - smp_mb__after_atomic(); \ - } while (0) +#define rpc_clear_running(t) clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define RPC_IS_QUEUED(t) test_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) #define rpc_set_queued(t) set_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) -#define rpc_clear_queued(t) \ - do { \ - smp_mb__before_atomic(); \ - clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate); \ - smp_mb__after_atomic(); \ - } while (0) +#define rpc_clear_queued(t) clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) #define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 064c96157d1f..0ae28ae6caf2 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -443,10 +443,7 @@ struct svc_version { /* Need xprt with congestion control */ bool vs_need_cong_ctrl; - /* Override dispatch function (e.g. when caching replies). - * A return value of 0 means drop the request. - * vs_dispatch == NULL means use default dispatcher. - */ + /* Dispatch function */ int (*vs_dispatch)(struct svc_rqst *, __be32 *); }; @@ -457,9 +454,11 @@ struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ - int (*pc_decode)(struct svc_rqst *, __be32 *data); + bool (*pc_decode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR encode result: */ - int (*pc_encode)(struct svc_rqst *, __be32 *data); + bool (*pc_encode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ @@ -532,8 +531,7 @@ int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, - struct page **pages, - struct kvec *first, size_t total); + struct xdr_buf *payload); char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, void *p, size_t total); diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 2c1fc9212cf2..548a028f2dab 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,7 +124,6 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ -#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -135,7 +134,6 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) -#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default diff --git a/include/net/llc.h b/include/net/llc.h index fd1f9a3fd8dd..e250dca03963 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -72,7 +72,9 @@ struct llc_sap { static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { - return &sap->sk_dev_hash[ifindex % LLC_SK_DEV_HASH_ENTRIES]; + u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); + + return &sap->sk_dev_hash[bucket]; } static inline diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 651bba654d77..899c29c326ba 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1355,16 +1355,6 @@ struct sctp_endpoint { reconf_enable:1; __u8 strreset_enable; - - /* Security identifiers from incoming (INIT). These are set by - * security_sctp_assoc_request(). These will only be used by - * SCTP TCP type sockets and peeled off connections as they - * cause a new socket to be generated. security_sctp_sk_clone() - * will then plug these into the new socket. - */ - - u32 secid; - u32 peer_secid; }; /* Recover the outter endpoint structure. */ @@ -2104,6 +2094,16 @@ struct sctp_association { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; + /* Security identifiers from incoming (INIT). These are set by + * security_sctp_assoc_request(). These will only be used by + * SCTP TCP type sockets and peeled off connections as they + * cause a new socket to be generated. security_sctp_sk_clone() + * will then plug these into the new socket. + */ + + u32 secid; + u32 peer_secid; + struct rcu_head rcu; }; diff --git a/include/net/strparser.h b/include/net/strparser.h index 1d20b98493a1..732b7097d78e 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -54,10 +54,28 @@ struct strp_msg { int offset; }; +struct _strp_msg { + /* Internal cb structure. struct strp_msg must be first for passing + * to upper layer. + */ + struct strp_msg strp; + int accum_len; +}; + +struct sk_skb_cb { +#define SK_SKB_CB_PRIV_LEN 20 + unsigned char data[SK_SKB_CB_PRIV_LEN]; + struct _strp_msg strp; + /* temp_reg is a temporary register used for bpf_convert_data_end_access + * when dst_reg == src_reg. + */ + u64 temp_reg; +}; + static inline struct strp_msg *strp_msg(struct sk_buff *skb) { return (struct strp_msg *)((void *)skb->cb + - offsetof(struct qdisc_skb_cb, data)); + offsetof(struct sk_skb_cb, strp)); } /* Structure for an attached lower socket */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 70972f3ac8fa..4da22b41bde6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -293,7 +293,10 @@ static inline bool tcp_out_of_memory(struct sock *sk) static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); - sk_mem_uncharge(sk, skb->truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, skb->truesize); + else + sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb))); __kfree_skb(skb); } @@ -974,7 +977,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && - mptcp_skb_can_collapse(to, from)); + mptcp_skb_can_collapse(to, from) && + skb_pure_zcopy_same(to, from)); } /* Events passed to congestion control interface */ diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index cd9eaa83432b..477a800a9543 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -73,7 +73,7 @@ enum scsi_cmnd_submitter { struct scsi_cmnd { struct scsi_request req; struct scsi_device *device; - struct list_head eh_entry; /* entry for the host eh_cmd_q */ + struct list_head eh_entry; /* entry for the host eh_abort_list/eh_cmd_q */ struct delayed_work abort_work; struct rcu_head rcu; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 83a7890f1479..d1c6fc83b1e3 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -226,12 +226,6 @@ struct scsi_device { struct device sdev_gendev, sdev_dev; - /* - * The array size 6 provides space for one attribute group for the - * SCSI core, four attribute groups defined by SCSI LLDs and one - * terminating NULL pointer. - */ - const struct attribute_group *gendev_attr_groups[6]; struct execute_work ew; /* used to get process context on put */ struct work_struct requeue_work; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index ae715959f886..ebe059badba0 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -551,6 +551,7 @@ struct Scsi_Host { struct mutex scan_mutex;/* serialize scanning activity */ + struct list_head eh_abort_list; struct list_head eh_cmd_q; struct task_struct * ehandler; /* Error recovery thread. */ struct completion * eh_action; /* Wait for specific actions on the diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index 653dfffb3ac8..1051b84e8579 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -36,6 +36,13 @@ struct snd_dma_device { #define SNDRV_DMA_TYPE_CONTINUOUS 1 /* continuous no-DMA memory */ #define SNDRV_DMA_TYPE_DEV 2 /* generic device continuous */ #define SNDRV_DMA_TYPE_DEV_WC 5 /* continuous write-combined */ +#ifdef CONFIG_SND_DMA_SGBUF +#define SNDRV_DMA_TYPE_DEV_SG 3 /* generic device SG-buffer */ +#define SNDRV_DMA_TYPE_DEV_WC_SG 6 /* SG write-combined */ +#else +#define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_DEV /* no SG-buf support */ +#define SNDRV_DMA_TYPE_DEV_WC_SG SNDRV_DMA_TYPE_DEV_WC +#endif #ifdef CONFIG_GENERIC_ALLOCATOR #define SNDRV_DMA_TYPE_DEV_IRAM 4 /* generic device iram-buffer */ #else @@ -44,13 +51,6 @@ struct snd_dma_device { #define SNDRV_DMA_TYPE_VMALLOC 7 /* vmalloc'ed buffer */ #define SNDRV_DMA_TYPE_NONCONTIG 8 /* non-coherent SG buffer */ #define SNDRV_DMA_TYPE_NONCOHERENT 9 /* non-coherent buffer */ -#ifdef CONFIG_SND_DMA_SGBUF -#define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_NONCONTIG -#define SNDRV_DMA_TYPE_DEV_WC_SG 6 /* SG write-combined */ -#else -#define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_DEV /* no SG-buf support */ -#define SNDRV_DMA_TYPE_DEV_WC_SG SNDRV_DMA_TYPE_DEV_WC -#endif /* * info for buffer allocation diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index bca73e8c8cde..499f5fabd20f 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -1016,31 +1016,32 @@ TRACE_EVENT(afs_dir_check_failed, __entry->vnode, __entry->off, __entry->i_size) ); -TRACE_EVENT(afs_page_dirty, - TP_PROTO(struct afs_vnode *vnode, const char *where, struct page *page), +TRACE_EVENT(afs_folio_dirty, + TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio), - TP_ARGS(vnode, where, page), + TP_ARGS(vnode, where, folio), TP_STRUCT__entry( __field(struct afs_vnode *, vnode ) __field(const char *, where ) - __field(pgoff_t, page ) + __field(pgoff_t, index ) __field(unsigned long, from ) __field(unsigned long, to ) ), TP_fast_assign( + unsigned long priv = (unsigned long)folio_get_private(folio); __entry->vnode = vnode; __entry->where = where; - __entry->page = page->index; - __entry->from = afs_page_dirty_from(page, page->private); - __entry->to = afs_page_dirty_to(page, page->private); - __entry->to |= (afs_is_page_dirty_mmapped(page->private) ? - (1UL << (BITS_PER_LONG - 1)) : 0); + __entry->index = folio_index(folio); + __entry->from = afs_folio_dirty_from(folio, priv); + __entry->to = afs_folio_dirty_to(folio, priv); + __entry->to |= (afs_is_folio_dirty_mmapped(priv) ? + (1UL << (BITS_PER_LONG - 1)) : 0); ), TP_printk("vn=%p %lx %s %lx-%lx%s", - __entry->vnode, __entry->page, __entry->where, + __entry->vnode, __entry->index, __entry->where, __entry->from, __entry->to & ~(1UL << (BITS_PER_LONG - 1)), __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "") diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4e881d91c874..f8cb916f3595 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -570,9 +570,10 @@ TRACE_EVENT(f2fs_file_write_iter, ); TRACE_EVENT(f2fs_map_blocks, - TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret), + TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, + int create, int flag, int ret), - TP_ARGS(inode, map, ret), + TP_ARGS(inode, map, create, flag, ret), TP_STRUCT__entry( __field(dev_t, dev) @@ -583,11 +584,14 @@ TRACE_EVENT(f2fs_map_blocks, __field(unsigned int, m_flags) __field(int, m_seg_type) __field(bool, m_may_create) + __field(bool, m_multidev_dio) + __field(int, create) + __field(int, flag) __field(int, ret) ), TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; + __entry->dev = map->m_bdev->bd_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_pblk = map->m_pblk; @@ -595,12 +599,16 @@ TRACE_EVENT(f2fs_map_blocks, __entry->m_flags = map->m_flags; __entry->m_seg_type = map->m_seg_type; __entry->m_may_create = map->m_may_create; + __entry->m_multidev_dio = map->m_multidev_dio; + __entry->create = create; + __entry->flag = flag; __entry->ret = ret; ), TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " - "start blkaddr = 0x%llx, len = 0x%llx, flags = %u," - "seg_type = %d, may_create = %d, err = %d", + "start blkaddr = 0x%llx, len = 0x%llx, flags = %u, " + "seg_type = %d, may_create = %d, multidevice = %d, " + "create = %d, flag = %d, err = %d", show_dev_ino(__entry), (unsigned long long)__entry->m_lblk, (unsigned long long)__entry->m_pblk, @@ -608,6 +616,9 @@ TRACE_EVENT(f2fs_map_blocks, __entry->m_flags, __entry->m_seg_type, __entry->m_may_create, + __entry->m_multidev_dio, + __entry->create, + __entry->flag, __entry->ret) ); @@ -807,20 +818,20 @@ TRACE_EVENT(f2fs_lookup_start, TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) - __field(const char *, name) + __string(name, dentry->d_name.name) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->ino = dir->i_ino; - __entry->name = dentry->d_name.name; + __assign_str(name, dentry->d_name.name); __entry->flags = flags; ), TP_printk("dev = (%d,%d), pino = %lu, name:%s, flags:%u", show_dev_ino(__entry), - __entry->name, + __get_str(name), __entry->flags) ); @@ -834,7 +845,7 @@ TRACE_EVENT(f2fs_lookup_end, TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) - __field(const char *, name) + __string(name, dentry->d_name.name) __field(nid_t, cino) __field(int, err) ), @@ -842,14 +853,14 @@ TRACE_EVENT(f2fs_lookup_end, TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->ino = dir->i_ino; - __entry->name = dentry->d_name.name; + __assign_str(name, dentry->d_name.name); __entry->cino = ino; __entry->err = err; ), TP_printk("dev = (%d,%d), pino = %lu, name:%s, ino:%u, err:%d", show_dev_ino(__entry), - __entry->name, + __get_str(name), __entry->cino, __entry->err) ); diff --git a/include/trace/events/fs.h b/include/trace/events/fs.h new file mode 100644 index 000000000000..738b97f22f36 --- /dev/null +++ b/include/trace/events/fs.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for generic filesystem items + * + * Author: Chuck Lever <chuck.lever@oracle.com> + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include <linux/fs.h> + +#define show_fs_dirent_type(x) \ + __print_symbolic(x, \ + { DT_UNKNOWN, "UNKNOWN" }, \ + { DT_FIFO, "FIFO" }, \ + { DT_CHR, "CHR" }, \ + { DT_DIR, "DIR" }, \ + { DT_BLK, "BLK" }, \ + { DT_REG, "REG" }, \ + { DT_LNK, "LNK" }, \ + { DT_SOCK, "SOCK" }, \ + { DT_WHT, "WHT" }) + +#define show_fs_fcntl_open_flags(x) \ + __print_flags(x, "|", \ + { O_WRONLY, "O_WRONLY" }, \ + { O_RDWR, "O_RDWR" }, \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_NOCTTY, "O_NOCTTY" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_APPEND, "O_APPEND" }, \ + { O_NONBLOCK, "O_NONBLOCK" }, \ + { O_DSYNC, "O_DSYNC" }, \ + { O_DIRECT, "O_DIRECT" }, \ + { O_LARGEFILE, "O_LARGEFILE" }, \ + { O_DIRECTORY, "O_DIRECTORY" }, \ + { O_NOFOLLOW, "O_NOFOLLOW" }, \ + { O_NOATIME, "O_NOATIME" }, \ + { O_CLOEXEC, "O_CLOEXEC" }) + +#define __fmode_flag(x) { (__force unsigned long)FMODE_##x, #x } +#define show_fs_fmode_flags(x) \ + __print_flags(x, "|", \ + __fmode_flag(READ), \ + __fmode_flag(WRITE), \ + __fmode_flag(EXEC)) + +#ifdef CONFIG_64BIT +#define show_fs_fcntl_cmd(x) \ + __print_symbolic(x, \ + { F_DUPFD, "DUPFD" }, \ + { F_GETFD, "GETFD" }, \ + { F_SETFD, "SETFD" }, \ + { F_GETFL, "GETFL" }, \ + { F_SETFL, "SETFL" }, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }, \ + { F_SETOWN, "SETOWN" }, \ + { F_GETOWN, "GETOWN" }, \ + { F_SETSIG, "SETSIG" }, \ + { F_GETSIG, "GETSIG" }, \ + { F_SETOWN_EX, "SETOWN_EX" }, \ + { F_GETOWN_EX, "GETOWN_EX" }, \ + { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ + { F_OFD_GETLK, "OFD_GETLK" }, \ + { F_OFD_SETLK, "OFD_SETLK" }, \ + { F_OFD_SETLKW, "OFD_SETLKW" }) +#else /* CONFIG_64BIT */ +#define show_fs_fcntl_cmd(x) \ + __print_symbolic(x, \ + { F_DUPFD, "DUPFD" }, \ + { F_GETFD, "GETFD" }, \ + { F_SETFD, "SETFD" }, \ + { F_GETFL, "GETFL" }, \ + { F_SETFL, "SETFL" }, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }, \ + { F_SETOWN, "SETOWN" }, \ + { F_GETOWN, "GETOWN" }, \ + { F_SETSIG, "SETSIG" }, \ + { F_GETSIG, "GETSIG" }, \ + { F_GETLK64, "GETLK64" }, \ + { F_SETLK64, "SETLK64" }, \ + { F_SETLKW64, "SETLKW64" }, \ + { F_SETOWN_EX, "SETOWN_EX" }, \ + { F_GETOWN_EX, "GETOWN_EX" }, \ + { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ + { F_OFD_GETLK, "OFD_GETLK" }, \ + { F_OFD_SETLK, "OFD_SETLK" }, \ + { F_OFD_SETLKW, "OFD_SETLKW" }) +#endif /* CONFIG_64BIT */ + +#define show_fs_fcntl_lock_type(x) \ + __print_symbolic(x, \ + { F_RDLCK, "RDLCK" }, \ + { F_WRLCK, "WRLCK" }, \ + { F_UNLCK, "UNLCK" }) + +#define show_fs_lookup_flags(flags) \ + __print_flags(flags, "|", \ + { LOOKUP_FOLLOW, "FOLLOW" }, \ + { LOOKUP_DIRECTORY, "DIRECTORY" }, \ + { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ + { LOOKUP_EMPTY, "EMPTY" }, \ + { LOOKUP_DOWN, "DOWN" }, \ + { LOOKUP_MOUNTPOINT, "MOUNTPOINT" }, \ + { LOOKUP_REVAL, "REVAL" }, \ + { LOOKUP_RCU, "RCU" }, \ + { LOOKUP_OPEN, "OPEN" }, \ + { LOOKUP_CREATE, "CREATE" }, \ + { LOOKUP_EXCL, "EXCL" }, \ + { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \ + { LOOKUP_PARENT, "PARENT" }, \ + { LOOKUP_NO_SYMLINKS, "NO_SYMLINKS" }, \ + { LOOKUP_NO_MAGICLINKS, "NO_MAGICLINKS" }, \ + { LOOKUP_NO_XDEV, "NO_XDEV" }, \ + { LOOKUP_BENEATH, "BENEATH" }, \ + { LOOKUP_IN_ROOT, "IN_ROOT" }, \ + { LOOKUP_CACHED, "CACHED" }) diff --git a/include/trace/events/nfs.h b/include/trace/events/nfs.h new file mode 100644 index 000000000000..09ffdbb04134 --- /dev/null +++ b/include/trace/events/nfs.h @@ -0,0 +1,375 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for NFS protocol elements + * + * Author: Chuck Lever <chuck.lever@oracle.com> + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <uapi/linux/nfs.h> + +TRACE_DEFINE_ENUM(NFS_OK); +TRACE_DEFINE_ENUM(NFSERR_PERM); +TRACE_DEFINE_ENUM(NFSERR_NOENT); +TRACE_DEFINE_ENUM(NFSERR_IO); +TRACE_DEFINE_ENUM(NFSERR_NXIO); +TRACE_DEFINE_ENUM(NFSERR_EAGAIN); +TRACE_DEFINE_ENUM(NFSERR_ACCES); +TRACE_DEFINE_ENUM(NFSERR_EXIST); +TRACE_DEFINE_ENUM(NFSERR_XDEV); +TRACE_DEFINE_ENUM(NFSERR_NODEV); +TRACE_DEFINE_ENUM(NFSERR_NOTDIR); +TRACE_DEFINE_ENUM(NFSERR_ISDIR); +TRACE_DEFINE_ENUM(NFSERR_INVAL); +TRACE_DEFINE_ENUM(NFSERR_FBIG); +TRACE_DEFINE_ENUM(NFSERR_NOSPC); +TRACE_DEFINE_ENUM(NFSERR_ROFS); +TRACE_DEFINE_ENUM(NFSERR_MLINK); +TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFSERR_DQUOT); +TRACE_DEFINE_ENUM(NFSERR_STALE); +TRACE_DEFINE_ENUM(NFSERR_REMOTE); +TRACE_DEFINE_ENUM(NFSERR_WFLUSH); +TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); +TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFSERR_BADTYPE); +TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); + +#define show_nfs_status(x) \ + __print_symbolic(x, \ + { NFS_OK, "OK" }, \ + { NFSERR_PERM, "PERM" }, \ + { NFSERR_NOENT, "NOENT" }, \ + { NFSERR_IO, "IO" }, \ + { NFSERR_NXIO, "NXIO" }, \ + { ECHILD, "CHILD" }, \ + { NFSERR_EAGAIN, "AGAIN" }, \ + { NFSERR_ACCES, "ACCES" }, \ + { NFSERR_EXIST, "EXIST" }, \ + { NFSERR_XDEV, "XDEV" }, \ + { NFSERR_NODEV, "NODEV" }, \ + { NFSERR_NOTDIR, "NOTDIR" }, \ + { NFSERR_ISDIR, "ISDIR" }, \ + { NFSERR_INVAL, "INVAL" }, \ + { NFSERR_FBIG, "FBIG" }, \ + { NFSERR_NOSPC, "NOSPC" }, \ + { NFSERR_ROFS, "ROFS" }, \ + { NFSERR_MLINK, "MLINK" }, \ + { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ + { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFSERR_DQUOT, "DQUOT" }, \ + { NFSERR_STALE, "STALE" }, \ + { NFSERR_REMOTE, "REMOTE" }, \ + { NFSERR_WFLUSH, "WFLUSH" }, \ + { NFSERR_BADHANDLE, "BADHANDLE" }, \ + { NFSERR_NOT_SYNC, "NOTSYNC" }, \ + { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ + { NFSERR_NOTSUPP, "NOTSUPP" }, \ + { NFSERR_TOOSMALL, "TOOSMALL" }, \ + { NFSERR_SERVERFAULT, "REMOTEIO" }, \ + { NFSERR_BADTYPE, "BADTYPE" }, \ + { NFSERR_JUKEBOX, "JUKEBOX" }) + +TRACE_DEFINE_ENUM(NFS_UNSTABLE); +TRACE_DEFINE_ENUM(NFS_DATA_SYNC); +TRACE_DEFINE_ENUM(NFS_FILE_SYNC); + +#define show_nfs_stable_how(x) \ + __print_symbolic(x, \ + { NFS_UNSTABLE, "UNSTABLE" }, \ + { NFS_DATA_SYNC, "DATA_SYNC" }, \ + { NFS_FILE_SYNC, "FILE_SYNC" }) + +TRACE_DEFINE_ENUM(NFS4_OK); +TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); +TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); +TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); +TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); +TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); +TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); +TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); +TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); +TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); +TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); +TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DELAY); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); +TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); +TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_EXIST); +TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FBIG); +TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); +TRACE_DEFINE_ENUM(NFS4ERR_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_INVAL); +TRACE_DEFINE_ENUM(NFS4ERR_IO); +TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); +TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); +TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); +TRACE_DEFINE_ENUM(NFS4ERR_MLINK); +TRACE_DEFINE_ENUM(NFS4ERR_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFS4ERR_NOENT); +TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); +TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); +TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_NXIO); +TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); +TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); +TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_PERM); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); +TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); +TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); +TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); +TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_ROFS); +TRACE_DEFINE_ENUM(NFS4ERR_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); +TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFS4ERR_STALE); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); +TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); +TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); +TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); +TRACE_DEFINE_ENUM(NFS4ERR_XDEV); + +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); + +#define show_nfs4_status(x) \ + __print_symbolic(x, \ + { NFS4_OK, "OK" }, \ + { EPERM, "EPERM" }, \ + { ENOENT, "ENOENT" }, \ + { EIO, "EIO" }, \ + { ENXIO, "ENXIO" }, \ + { EACCES, "EACCES" }, \ + { EEXIST, "EEXIST" }, \ + { EXDEV, "EXDEV" }, \ + { ENOTDIR, "ENOTDIR" }, \ + { EISDIR, "EISDIR" }, \ + { EFBIG, "EFBIG" }, \ + { ENOSPC, "ENOSPC" }, \ + { EROFS, "EROFS" }, \ + { EMLINK, "EMLINK" }, \ + { ENAMETOOLONG, "ENAMETOOLONG" }, \ + { ENOTEMPTY, "ENOTEMPTY" }, \ + { EDQUOT, "EDQUOT" }, \ + { ESTALE, "ESTALE" }, \ + { EBADHANDLE, "EBADHANDLE" }, \ + { EBADCOOKIE, "EBADCOOKIE" }, \ + { ENOTSUPP, "ENOTSUPP" }, \ + { ETOOSMALL, "ETOOSMALL" }, \ + { EREMOTEIO, "EREMOTEIO" }, \ + { EBADTYPE, "EBADTYPE" }, \ + { EAGAIN, "EAGAIN" }, \ + { ELOOP, "ELOOP" }, \ + { EOPNOTSUPP, "EOPNOTSUPP" }, \ + { EDEADLK, "EDEADLK" }, \ + { ENOMEM, "ENOMEM" }, \ + { EKEYEXPIRED, "EKEYEXPIRED" }, \ + { ETIMEDOUT, "ETIMEDOUT" }, \ + { ERESTARTSYS, "ERESTARTSYS" }, \ + { ECONNREFUSED, "ECONNREFUSED" }, \ + { ECONNRESET, "ECONNRESET" }, \ + { ENETUNREACH, "ENETUNREACH" }, \ + { EHOSTUNREACH, "EHOSTUNREACH" }, \ + { EHOSTDOWN, "EHOSTDOWN" }, \ + { EPIPE, "EPIPE" }, \ + { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + { NFS4ERR_ACCESS, "ACCESS" }, \ + { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { NFS4ERR_BADCHAR, "BADCHAR" }, \ + { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { NFS4ERR_BADLABEL, "BADLABEL" }, \ + { NFS4ERR_BADNAME, "BADNAME" }, \ + { NFS4ERR_BADOWNER, "BADOWNER" }, \ + { NFS4ERR_BADSESSION, "BADSESSION" }, \ + { NFS4ERR_BADSLOT, "BADSLOT" }, \ + { NFS4ERR_BADTYPE, "BADTYPE" }, \ + { NFS4ERR_BADXDR, "BADXDR" }, \ + { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, "CONN_NOT_BOUND_TO_SESSION" }, \ + { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { NFS4ERR_DELAY, "DELAY" }, \ + { NFS4ERR_DELEG_ALREADY_WANTED, "DELEG_ALREADY_WANTED" }, \ + { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { NFS4ERR_DENIED, "DENIED" }, \ + { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { NFS4ERR_DQUOT, "DQUOT" }, \ + { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { NFS4ERR_EXIST, "EXIST" }, \ + { NFS4ERR_EXPIRED, "EXPIRED" }, \ + { NFS4ERR_FBIG, "FBIG" }, \ + { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { NFS4ERR_GRACE, "GRACE" }, \ + { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { NFS4ERR_INVAL, "INVAL" }, \ + { NFS4ERR_IO, "IO" }, \ + { NFS4ERR_ISDIR, "ISDIR" }, \ + { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { NFS4ERR_LOCKED, "LOCKED" }, \ + { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { NFS4ERR_MLINK, "MLINK" }, \ + { NFS4ERR_MOVED, "MOVED" }, \ + { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFS4ERR_NOENT, "NOENT" }, \ + { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { NFS4ERR_NOSPC, "NOSPC" }, \ + { NFS4ERR_NOTDIR, "NOTDIR" }, \ + { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { NFS4ERR_NXIO, "NXIO" }, \ + { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { NFS4ERR_OPENMODE, "OPENMODE" }, \ + { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { NFS4ERR_PERM, "PERM" }, \ + { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { NFS4ERR_REP_TOO_BIG_TO_CACHE, "REP_TOO_BIG_TO_CACHE" }, \ + { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { NFS4ERR_RESOURCE, "RESOURCE" }, \ + { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { NFS4ERR_ROFS, "ROFS" }, \ + { NFS4ERR_SAME, "SAME" }, \ + { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { NFS4ERR_STALE, "STALE" }, \ + { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { NFS4ERR_SYMLINK, "SYMLINK" }, \ + { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { NFS4ERR_XDEV, "XDEV" }, \ + /* ***** Internal to Linux NFS client ***** */ \ + { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ + { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) + +#define show_nfs4_verifier(x) \ + __print_hex_str(x, NFS4_VERIFIER_SIZE) + +TRACE_DEFINE_ENUM(IOMODE_READ); +TRACE_DEFINE_ENUM(IOMODE_RW); +TRACE_DEFINE_ENUM(IOMODE_ANY); + +#define show_pnfs_layout_iomode(x) \ + __print_symbolic(x, \ + { IOMODE_READ, "READ" }, \ + { IOMODE_RW, "RW" }, \ + { IOMODE_ANY, "ANY" }) + +#define show_nfs4_seq4_status(x) \ + __print_flags(x, "|", \ + { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, "CB_GSS_CONTEXTS_EXPIRING" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, "CB_GSS_CONTEXTS_EXPIRED" }, \ + { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, "EXPIRED_ALL_STATE_REVOKED" }, \ + { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, "EXPIRED_SOME_STATE_REVOKED" }, \ + { SEQ4_STATUS_ADMIN_STATE_REVOKED, "ADMIN_STATE_REVOKED" }, \ + { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, "RECALLABLE_STATE_REVOKED" }, \ + { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ + { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, "RESTART_RECLAIM_NEEDED" }, \ + { SEQ4_STATUS_CB_PATH_DOWN_SESSION, "CB_PATH_DOWN_SESSION" }, \ + { SEQ4_STATUS_BACKCHANNEL_FAULT, "BACKCHANNEL_FAULT" }) diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index b2a2672e6632..3ba63319af3c 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -13,6 +13,8 @@ #include <linux/tracepoint.h> +#include <trace/events/sunrpc_base.h> + /** ** GSS-API related trace events **/ @@ -99,7 +101,7 @@ DECLARE_EVENT_CLASS(rpcgss_gssapi_event, __entry->maj_stat = maj_stat; ), - TP_printk("task:%u@%u maj_stat=%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " maj_stat=%s", __entry->task_id, __entry->client_id, __entry->maj_stat == 0 ? "GSS_S_COMPLETE" : show_gss_status(__entry->maj_stat)) @@ -332,7 +334,8 @@ TRACE_EVENT(rpcgss_unwrap_failed, __entry->client_id = task->tk_client->cl_clid; ), - TP_printk("task:%u@%u", __entry->task_id, __entry->client_id) + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER, + __entry->task_id, __entry->client_id) ); TRACE_EVENT(rpcgss_bad_seqno, @@ -358,7 +361,8 @@ TRACE_EVENT(rpcgss_bad_seqno, __entry->received = received; ), - TP_printk("task:%u@%u expected seqno %u, received seqno %u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " expected seqno %u, received seqno %u", __entry->task_id, __entry->client_id, __entry->expected, __entry->received) ); @@ -386,7 +390,7 @@ TRACE_EVENT(rpcgss_seqno, __entry->seqno = rqst->rq_seqno; ), - TP_printk("task:%u@%u xid=0x%08x seqno=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x seqno=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->seqno) ); @@ -418,7 +422,8 @@ TRACE_EVENT(rpcgss_need_reencode, __entry->ret = ret; ), - TP_printk("task:%u@%u xid=0x%08x rq_seqno=%u seq_xmit=%u reencode %sneeded", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x rq_seqno=%u seq_xmit=%u reencode %sneeded", __entry->task_id, __entry->client_id, __entry->xid, __entry->seqno, __entry->seq_xmit, __entry->ret ? "" : "un") @@ -452,7 +457,8 @@ TRACE_EVENT(rpcgss_update_slack, __entry->verfsize = auth->au_verfsize; ), - TP_printk("task:%u@%u xid=0x%08x auth=%p rslack=%u ralign=%u verfsize=%u\n", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x auth=%p rslack=%u ralign=%u verfsize=%u\n", __entry->task_id, __entry->client_id, __entry->xid, __entry->auth, __entry->rslack, __entry->ralign, __entry->verfsize) diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index de4195499592..fcd3b3f1020a 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -14,7 +14,9 @@ #include <linux/sunrpc/rpc_rdma_cid.h> #include <linux/tracepoint.h> #include <rdma/ib_cm.h> + #include <trace/events/rdma.h> +#include <trace/events/sunrpc_base.h> /** ** Event classes @@ -60,6 +62,74 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class, ), \ TP_ARGS(wc, cid)) +DECLARE_EVENT_CLASS(rpcrdma_send_completion_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + ), + + TP_printk("cq.id=%u cid=%d", + __entry->cq_id, __entry->completion_id + ) +); + +#define DEFINE_SEND_COMPLETION_EVENT(name) \ + DEFINE_EVENT(rpcrdma_send_completion_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + +DECLARE_EVENT_CLASS(rpcrdma_send_flush_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(unsigned long, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->status = wc->status; + __entry->vendor_err = wc->vendor_err; + ), + + TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)", + __entry->cq_id, __entry->completion_id, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err + ) +); + +#define DEFINE_SEND_FLUSH_EVENT(name) \ + DEFINE_EVENT(rpcrdma_send_flush_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + DECLARE_EVENT_CLASS(rpcrdma_mr_completion_class, TP_PROTO( const struct ib_wc *wc, @@ -145,6 +215,77 @@ DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class, ), \ TP_ARGS(wc, cid)) +DECLARE_EVENT_CLASS(rpcrdma_receive_success_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(u32, received) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->received = wc->byte_len; + ), + + TP_printk("cq.id=%u cid=%d received=%u", + __entry->cq_id, __entry->completion_id, + __entry->received + ) +); + +#define DEFINE_RECEIVE_SUCCESS_EVENT(name) \ + DEFINE_EVENT(rpcrdma_receive_success_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + +DECLARE_EVENT_CLASS(rpcrdma_receive_flush_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(unsigned long, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->status = wc->status; + __entry->vendor_err = wc->vendor_err; + ), + + TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)", + __entry->cq_id, __entry->completion_id, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err + ) +); + +#define DEFINE_RECEIVE_FLUSH_EVENT(name) \ + DEFINE_EVENT(rpcrdma_receive_flush_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + DECLARE_EVENT_CLASS(xprtrdma_reply_class, TP_PROTO( const struct rpcrdma_rep *rep @@ -279,7 +420,8 @@ DECLARE_EVENT_CLASS(xprtrdma_rdch_event, __entry->nsegs = nsegs; ), - TP_printk("task:%u@%u pos=%u %u@0x%016llx:0x%08x (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " pos=%u %u@0x%016llx:0x%08x (%s)", __entry->task_id, __entry->client_id, __entry->pos, __entry->length, (unsigned long long)__entry->offset, __entry->handle, @@ -326,7 +468,8 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event, __entry->nsegs = nsegs; ), - TP_printk("task:%u@%u %u@0x%016llx:0x%08x (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " %u@0x%016llx:0x%08x (%s)", __entry->task_id, __entry->client_id, __entry->length, (unsigned long long)__entry->offset, __entry->handle, @@ -375,10 +518,16 @@ DECLARE_EVENT_CLASS(xprtrdma_mr_class, TP_fast_assign( const struct rpcrdma_req *req = mr->mr_req; - const struct rpc_task *task = req->rl_slot.rq_task; - __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; + if (req) { + const struct rpc_task *task = req->rl_slot.rq_task; + + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client->cl_clid; + } else { + __entry->task_id = 0; + __entry->client_id = -1; + } __entry->mr_id = mr->mr_ibmr->res.id; __entry->nents = mr->mr_nents; __entry->handle = mr->mr_handle; @@ -387,7 +536,8 @@ DECLARE_EVENT_CLASS(xprtrdma_mr_class, __entry->dir = mr->mr_dir; ), - TP_printk("task:%u@%u mr.id=%u nents=%d %u@0x%016llx:0x%08x (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " mr.id=%u nents=%d %u@0x%016llx:0x%08x (%s)", __entry->task_id, __entry->client_id, __entry->mr_id, __entry->nents, __entry->length, (unsigned long long)__entry->offset, __entry->handle, @@ -630,15 +780,16 @@ TRACE_EVENT(xprtrdma_nomrs_err, __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s task:%u@%u", - __get_str(addr), __get_str(port), - __entry->task_id, __entry->client_id + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " peer=[%s]:%s", + __entry->task_id, __entry->client_id, + __get_str(addr), __get_str(port) ) ); DEFINE_RDCH_EVENT(read); DEFINE_WRCH_EVENT(write); DEFINE_WRCH_EVENT(reply); +DEFINE_WRCH_EVENT(wp); TRACE_DEFINE_ENUM(rpcrdma_noch); TRACE_DEFINE_ENUM(rpcrdma_noch_pullup); @@ -693,7 +844,8 @@ TRACE_EVENT(xprtrdma_marshal, __entry->wtype = wtype; ), - TP_printk("task:%u@%u xid=0x%08x: hdr=%u xdr=%u/%u/%u %s/%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x hdr=%u xdr=%u/%u/%u %s/%s", __entry->task_id, __entry->client_id, __entry->xid, __entry->hdrlen, __entry->headlen, __entry->pagelen, __entry->taillen, @@ -723,7 +875,7 @@ TRACE_EVENT(xprtrdma_marshal_failed, __entry->ret = ret; ), - TP_printk("task:%u@%u xid=0x%08x: ret=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x ret=%d", __entry->task_id, __entry->client_id, __entry->xid, __entry->ret ) @@ -750,7 +902,7 @@ TRACE_EVENT(xprtrdma_prepsend_failed, __entry->ret = ret; ), - TP_printk("task:%u@%u xid=0x%08x: ret=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x ret=%d", __entry->task_id, __entry->client_id, __entry->xid, __entry->ret ) @@ -785,7 +937,7 @@ TRACE_EVENT(xprtrdma_post_send, __entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED; ), - TP_printk("task:%u@%u cq.id=%u cid=%d (%d SGE%s) %s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " cq.id=%u cid=%d (%d SGE%s) %s", __entry->task_id, __entry->client_id, __entry->cq_id, __entry->completion_id, __entry->num_sge, (__entry->num_sge == 1 ? "" : "s"), @@ -820,7 +972,7 @@ TRACE_EVENT(xprtrdma_post_send_err, __entry->rc = rc; ), - TP_printk("task:%u@%u cq.id=%u rc=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " cq.id=%u rc=%d", __entry->task_id, __entry->client_id, __entry->cq_id, __entry->rc ) @@ -932,7 +1084,7 @@ TRACE_EVENT(xprtrdma_post_linv_err, __entry->status = status; ), - TP_printk("task:%u@%u status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " status=%d", __entry->task_id, __entry->client_id, __entry->status ) ); @@ -1120,7 +1272,7 @@ TRACE_EVENT(xprtrdma_reply, __entry->credits = credits; ), - TP_printk("task:%u@%u xid=0x%08x credits=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x credits=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->credits ) @@ -1156,7 +1308,7 @@ TRACE_EVENT(xprtrdma_err_vers, __entry->max = be32_to_cpup(max); ), - TP_printk("task:%u@%u xid=0x%08x versions=[%u, %u]", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x versions=[%u, %u]", __entry->task_id, __entry->client_id, __entry->xid, __entry->min, __entry->max ) @@ -1181,7 +1333,7 @@ TRACE_EVENT(xprtrdma_err_chunk, __entry->xid = be32_to_cpu(rqst->rq_xid); ), - TP_printk("task:%u@%u xid=0x%08x", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x", __entry->task_id, __entry->client_id, __entry->xid ) ); @@ -1207,7 +1359,7 @@ TRACE_EVENT(xprtrdma_err_unrecognized, __entry->procedure = be32_to_cpup(procedure); ), - TP_printk("task:%u@%u xid=0x%08x procedure=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x procedure=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->procedure ) @@ -1239,7 +1391,7 @@ TRACE_EVENT(xprtrdma_fixup, __entry->taillen = rqst->rq_rcv_buf.tail[0].iov_len; ), - TP_printk("task:%u@%u fixup=%lu xdr=%zu/%u/%zu", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " fixup=%lu xdr=%zu/%u/%zu", __entry->task_id, __entry->client_id, __entry->fixup, __entry->headlen, __entry->pagelen, __entry->taillen ) @@ -1289,7 +1441,7 @@ TRACE_EVENT(xprtrdma_mrs_zap, __entry->client_id = task->tk_client->cl_clid; ), - TP_printk("task:%u@%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER, __entry->task_id, __entry->client_id ) ); @@ -1868,7 +2020,9 @@ TRACE_EVENT(svcrdma_post_send, ) ); -DEFINE_COMPLETION_EVENT(svcrdma_wc_send); +DEFINE_SEND_COMPLETION_EVENT(svcrdma_wc_send); +DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_send_flush); +DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_send_err); TRACE_EVENT(svcrdma_post_recv, TP_PROTO( @@ -1892,7 +2046,9 @@ TRACE_EVENT(svcrdma_post_recv, ) ); -DEFINE_RECEIVE_COMPLETION_EVENT(svcrdma_wc_receive); +DEFINE_RECEIVE_SUCCESS_EVENT(svcrdma_wc_recv); +DEFINE_RECEIVE_FLUSH_EVENT(svcrdma_wc_recv_flush); +DEFINE_RECEIVE_FLUSH_EVENT(svcrdma_wc_recv_err); TRACE_EVENT(svcrdma_rq_post_err, TP_PROTO( @@ -1956,8 +2112,42 @@ DEFINE_POST_CHUNK_EVENT(read); DEFINE_POST_CHUNK_EVENT(write); DEFINE_POST_CHUNK_EVENT(reply); -DEFINE_COMPLETION_EVENT(svcrdma_wc_read); -DEFINE_COMPLETION_EVENT(svcrdma_wc_write); +TRACE_EVENT(svcrdma_wc_read, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid, + unsigned int totalbytes, + const ktime_t posttime + ), + + TP_ARGS(wc, cid, totalbytes, posttime), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(s64, read_latency) + __field(unsigned int, totalbytes) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->totalbytes = totalbytes; + __entry->read_latency = ktime_us_delta(ktime_get(), posttime); + ), + + TP_printk("cq.id=%u cid=%d totalbytes=%u latency-us=%lld", + __entry->cq_id, __entry->completion_id, + __entry->totalbytes, __entry->read_latency + ) +); + +DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_flush); +DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_err); + +DEFINE_SEND_COMPLETION_EVENT(svcrdma_wc_write); +DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_flush); +DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_err); TRACE_EVENT(svcrdma_qp_error, TP_PROTO( diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 2d04eb96d418..3a99358c262b 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,6 +14,8 @@ #include <linux/net.h> #include <linux/tracepoint.h> +#include <trace/events/sunrpc_base.h> + TRACE_DEFINE_ENUM(SOCK_STREAM); TRACE_DEFINE_ENUM(SOCK_DGRAM); TRACE_DEFINE_ENUM(SOCK_RAW); @@ -62,6 +64,7 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, __field(size_t, head_len) __field(const void *, tail_base) __field(size_t, tail_len) + __field(unsigned int, page_base) __field(unsigned int, page_len) __field(unsigned int, msg_len) ), @@ -74,14 +77,18 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; __entry->tail_len = xdr->tail[0].iov_len; + __entry->page_base = xdr->page_base; __entry->page_len = xdr->page_len; __entry->msg_len = xdr->len; ), - TP_printk("task:%u@%u head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " head=[%p,%zu] page=%u(%u) tail=[%p,%zu] len=%u", __entry->task_id, __entry->client_id, - __entry->head_base, __entry->head_len, __entry->page_len, - __entry->tail_base, __entry->tail_len, __entry->msg_len + __entry->head_base, __entry->head_len, + __entry->page_len, __entry->page_base, + __entry->tail_base, __entry->tail_len, + __entry->msg_len ) ); @@ -114,7 +121,7 @@ DECLARE_EVENT_CLASS(rpc_clnt_class, __entry->client_id = clnt->cl_clid; ), - TP_printk("clid=%u", __entry->client_id) + TP_printk("client=" SUNRPC_TRACE_CLID_SPECIFIER, __entry->client_id) ); #define DEFINE_RPC_CLNT_EVENT(name) \ @@ -158,7 +165,8 @@ TRACE_EVENT(rpc_clnt_new, __assign_str(server, server); ), - TP_printk("client=%u peer=[%s]:%s program=%s server=%s", + TP_printk("client=" SUNRPC_TRACE_CLID_SPECIFIER + " peer=[%s]:%s program=%s server=%s", __entry->client_id, __get_str(addr), __get_str(port), __get_str(program), __get_str(server)) ); @@ -206,7 +214,8 @@ TRACE_EVENT(rpc_clnt_clone_err, __entry->error = error; ), - TP_printk("client=%u error=%d", __entry->client_id, __entry->error) + TP_printk("client=" SUNRPC_TRACE_CLID_SPECIFIER " error=%d", + __entry->client_id, __entry->error) ); @@ -248,7 +257,7 @@ DECLARE_EVENT_CLASS(rpc_task_status, __entry->status = task->tk_status; ), - TP_printk("task:%u@%u status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " status=%d", __entry->task_id, __entry->client_id, __entry->status) ); @@ -288,7 +297,7 @@ TRACE_EVENT(rpc_request, __assign_str(procname, rpc_proc_name(task)); ), - TP_printk("task:%u@%u %sv%d %s (%ssync)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " %sv%d %s (%ssync)", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procname), __entry->async ? "a": "" @@ -348,7 +357,8 @@ DECLARE_EVENT_CLASS(rpc_task_running, __entry->flags = task->tk_flags; ), - TP_printk("task:%u@%d flags=%s runstate=%s status=%d action=%ps", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " flags=%s runstate=%s status=%d action=%ps", __entry->task_id, __entry->client_id, rpc_show_task_flags(__entry->flags), rpc_show_runstate(__entry->runstate), @@ -372,6 +382,7 @@ DEFINE_RPC_RUNNING_EVENT(complete); DEFINE_RPC_RUNNING_EVENT(timeout); DEFINE_RPC_RUNNING_EVENT(signalled); DEFINE_RPC_RUNNING_EVENT(end); +DEFINE_RPC_RUNNING_EVENT(call_done); DECLARE_EVENT_CLASS(rpc_task_queued, @@ -400,7 +411,8 @@ DECLARE_EVENT_CLASS(rpc_task_queued, __assign_str(q_name, rpc_qname(q)); ), - TP_printk("task:%u@%d flags=%s runstate=%s status=%d timeout=%lu queue=%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " flags=%s runstate=%s status=%d timeout=%lu queue=%s", __entry->task_id, __entry->client_id, rpc_show_task_flags(__entry->flags), rpc_show_runstate(__entry->runstate), @@ -436,7 +448,7 @@ DECLARE_EVENT_CLASS(rpc_failure, __entry->client_id = task->tk_client->cl_clid; ), - TP_printk("task:%u@%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER, __entry->task_id, __entry->client_id) ); @@ -478,7 +490,8 @@ DECLARE_EVENT_CLASS(rpc_reply_event, __assign_str(servername, task->tk_xprt->servername); ), - TP_printk("task:%u@%d server=%s xid=0x%08x %sv%d %s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " server=%s xid=0x%08x %sv%d %s", __entry->task_id, __entry->client_id, __get_str(servername), __entry->xid, __get_str(progname), __entry->version, __get_str(procname)) @@ -538,7 +551,8 @@ TRACE_EVENT(rpc_buf_alloc, __entry->status = status; ), - TP_printk("task:%u@%u callsize=%zu recvsize=%zu status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " callsize=%zu recvsize=%zu status=%d", __entry->task_id, __entry->client_id, __entry->callsize, __entry->recvsize, __entry->status ) @@ -567,7 +581,8 @@ TRACE_EVENT(rpc_call_rpcerror, __entry->rpc_status = rpc_status; ), - TP_printk("task:%u@%u tk_status=%d rpc_status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " tk_status=%d rpc_status=%d", __entry->task_id, __entry->client_id, __entry->tk_status, __entry->rpc_status) ); @@ -607,7 +622,8 @@ TRACE_EVENT(rpc_stats_latency, __entry->execute = ktime_to_us(execute); ), - TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu", __entry->task_id, __entry->client_id, __entry->xid, __get_str(progname), __entry->version, __get_str(procname), __entry->backlog, __entry->rtt, __entry->execute) @@ -651,8 +667,8 @@ TRACE_EVENT(rpc_xdr_overflow, __entry->version = task->tk_client->cl_vers; __assign_str(procedure, task->tk_msg.rpc_proc->p_name); } else { - __entry->task_id = 0; - __entry->client_id = 0; + __entry->task_id = -1; + __entry->client_id = -1; __assign_str(progname, "unknown"); __entry->version = 0; __assign_str(procedure, "unknown"); @@ -668,8 +684,8 @@ TRACE_EVENT(rpc_xdr_overflow, __entry->len = xdr->buf->len; ), - TP_printk( - "task:%u@%u %sv%d %s requested=%zu p=%p end=%p xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " %sv%d %s requested=%zu p=%p end=%p xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procedure), __entry->requested, __entry->p, __entry->end, @@ -727,8 +743,8 @@ TRACE_EVENT(rpc_xdr_alignment, __entry->len = xdr->buf->len; ), - TP_printk( - "task:%u@%u %sv%d %s offset=%zu copied=%u xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " %sv%d %s offset=%zu copied=%u xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procedure), __entry->offset, __entry->copied, @@ -917,7 +933,8 @@ TRACE_EVENT(rpc_socket_nospace, __entry->remaining = rqst->rq_slen - transport->xmit.offset; ), - TP_printk("task:%u@%u total=%u remaining=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " total=%u remaining=%u", __entry->task_id, __entry->client_id, __entry->total, __entry->remaining ) @@ -925,18 +942,18 @@ TRACE_EVENT(rpc_socket_nospace, #define rpc_show_xprt_state(x) \ __print_flags(x, "|", \ - { (1UL << XPRT_LOCKED), "LOCKED"}, \ - { (1UL << XPRT_CONNECTED), "CONNECTED"}, \ - { (1UL << XPRT_CONNECTING), "CONNECTING"}, \ - { (1UL << XPRT_CLOSE_WAIT), "CLOSE_WAIT"}, \ - { (1UL << XPRT_BOUND), "BOUND"}, \ - { (1UL << XPRT_BINDING), "BINDING"}, \ - { (1UL << XPRT_CLOSING), "CLOSING"}, \ - { (1UL << XPRT_OFFLINE), "OFFLINE"}, \ - { (1UL << XPRT_REMOVE), "REMOVE"}, \ - { (1UL << XPRT_CONGESTED), "CONGESTED"}, \ - { (1UL << XPRT_CWND_WAIT), "CWND_WAIT"}, \ - { (1UL << XPRT_WRITE_SPACE), "WRITE_SPACE"}) + { BIT(XPRT_LOCKED), "LOCKED" }, \ + { BIT(XPRT_CONNECTED), "CONNECTED" }, \ + { BIT(XPRT_CONNECTING), "CONNECTING" }, \ + { BIT(XPRT_CLOSE_WAIT), "CLOSE_WAIT" }, \ + { BIT(XPRT_BOUND), "BOUND" }, \ + { BIT(XPRT_BINDING), "BINDING" }, \ + { BIT(XPRT_CLOSING), "CLOSING" }, \ + { BIT(XPRT_OFFLINE), "OFFLINE" }, \ + { BIT(XPRT_REMOVE), "REMOVE" }, \ + { BIT(XPRT_CONGESTED), "CONGESTED" }, \ + { BIT(XPRT_CWND_WAIT), "CWND_WAIT" }, \ + { BIT(XPRT_WRITE_SPACE), "WRITE_SPACE" }) DECLARE_EVENT_CLASS(rpc_xprt_lifetime_class, TP_PROTO( @@ -1042,8 +1059,8 @@ TRACE_EVENT(xprt_transmit, __entry->status = status; ), - TP_printk( - "task:%u@%u xid=0x%08x seqno=%u status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x seqno=%u status=%d", __entry->task_id, __entry->client_id, __entry->xid, __entry->seqno, __entry->status) ); @@ -1082,8 +1099,8 @@ TRACE_EVENT(xprt_retransmit, __assign_str(procname, rpc_proc_name(task)); ), - TP_printk( - "task:%u@%u xid=0x%08x %sv%d %s ntrans=%d timeout=%lu", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x %sv%d %s ntrans=%d timeout=%lu", __entry->task_id, __entry->client_id, __entry->xid, __get_str(progname), __entry->version, __get_str(procname), __entry->ntrans, __entry->timeout @@ -1137,7 +1154,8 @@ DECLARE_EVENT_CLASS(xprt_writelock_event, xprt->snd_task->tk_pid : -1; ), - TP_printk("task:%u@%u snd_task:%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " snd_task:" SUNRPC_TRACE_PID_SPECIFIER, __entry->task_id, __entry->client_id, __entry->snd_task_id) ); @@ -1185,7 +1203,9 @@ DECLARE_EVENT_CLASS(xprt_cong_event, __entry->wait = test_bit(XPRT_CWND_WAIT, &xprt->state); ), - TP_printk("task:%u@%u snd_task:%u cong=%lu cwnd=%lu%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " snd_task:" SUNRPC_TRACE_PID_SPECIFIER + " cong=%lu cwnd=%lu%s", __entry->task_id, __entry->client_id, __entry->snd_task_id, __entry->cong, __entry->cwnd, __entry->wait ? " (wait)" : "") @@ -1223,7 +1243,7 @@ TRACE_EVENT(xprt_reserve, __entry->xid = be32_to_cpu(rqst->rq_xid); ), - TP_printk("task:%u@%u xid=0x%08x", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x", __entry->task_id, __entry->client_id, __entry->xid ) ); @@ -1312,7 +1332,8 @@ TRACE_EVENT(rpcb_getport, __assign_str(servername, task->tk_xprt->servername); ), - TP_printk("task:%u@%u server=%s program=%u version=%u protocol=%d bind_version=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " server=%s program=%u version=%u protocol=%d bind_version=%u", __entry->task_id, __entry->client_id, __get_str(servername), __entry->program, __entry->version, __entry->protocol, __entry->bind_version @@ -1342,7 +1363,7 @@ TRACE_EVENT(rpcb_setport, __entry->port = port; ), - TP_printk("task:%u@%u status=%d port=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " status=%d port=%u", __entry->task_id, __entry->client_id, __entry->status, __entry->port ) @@ -1496,6 +1517,7 @@ DECLARE_EVENT_CLASS(svc_xdr_buf_class, __field(size_t, head_len) __field(const void *, tail_base) __field(size_t, tail_len) + __field(unsigned int, page_base) __field(unsigned int, page_len) __field(unsigned int, msg_len) ), @@ -1506,14 +1528,17 @@ DECLARE_EVENT_CLASS(svc_xdr_buf_class, __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; __entry->tail_len = xdr->tail[0].iov_len; + __entry->page_base = xdr->page_base; __entry->page_len = xdr->page_len; __entry->msg_len = xdr->len; ), - TP_printk("xid=0x%08x head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", + TP_printk("xid=0x%08x head=[%p,%zu] page=%u(%u) tail=[%p,%zu] len=%u", __entry->xid, - __entry->head_base, __entry->head_len, __entry->page_len, - __entry->tail_base, __entry->tail_len, __entry->msg_len + __entry->head_base, __entry->head_len, + __entry->page_len, __entry->page_base, + __entry->tail_base, __entry->tail_len, + __entry->msg_len ) ); @@ -1859,6 +1884,24 @@ TRACE_EVENT(svc_wake_up, TP_printk("pid=%d", __entry->pid) ); +TRACE_EVENT(svc_alloc_arg_err, + TP_PROTO( + unsigned int pages + ), + + TP_ARGS(pages), + + TP_STRUCT__entry( + __field(unsigned int, pages) + ), + + TP_fast_assign( + __entry->pages = pages; + ), + + TP_printk("pages=%u", __entry->pages) +); + TRACE_EVENT(svc_handle_xprt, TP_PROTO(struct svc_xprt *xprt, int len), diff --git a/include/trace/events/sunrpc_base.h b/include/trace/events/sunrpc_base.h new file mode 100644 index 000000000000..588557d07ea8 --- /dev/null +++ b/include/trace/events/sunrpc_base.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 Oracle and/or its affiliates. + * + * Common types and format specifiers for sunrpc. + */ + +#if !defined(_TRACE_SUNRPC_BASE_H) +#define _TRACE_SUNRPC_BASE_H + +#include <linux/tracepoint.h> + +#define SUNRPC_TRACE_PID_SPECIFIER "%08x" +#define SUNRPC_TRACE_CLID_SPECIFIER "%08x" +#define SUNRPC_TRACE_TASK_SPECIFIER \ + "task:" SUNRPC_TRACE_PID_SPECIFIER "@" SUNRPC_TRACE_CLID_SPECIFIER + +#endif /* _TRACE_SUNRPC_BASE_H */ diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index fe929e7b77ca..7572f2f46ee8 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -45,6 +45,7 @@ #define SA_UNSUPPORTED 0x00000400 #define SA_EXPOSE_TAGBITS 0x00000800 /* 0x00010000 used on mips */ +/* 0x00800000 used for internal SA_IMMUTABLE */ /* 0x01000000 used on x86 */ /* 0x02000000 used on x86 */ /* diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index ca5fbb59fa42..999777d32dcf 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -411,7 +411,9 @@ enum { ETHTOOL_A_PAUSE_STAT_TX_FRAMES, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, - /* add new constants above here */ + /* add new constants above here + * adjust ETHTOOL_PAUSE_STAT_CNT if adding non-stats! + */ __ETHTOOL_A_PAUSE_STAT_CNT, ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 78f0719cc2a3..1daa45268de2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1130,6 +1130,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_BINARY_STATS_FD 203 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 +#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h deleted file mode 100644 index e29e8accc4f4..000000000000 --- a/include/uapi/linux/nfsd/nfsfh.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * This file describes the layout of the file handles as passed - * over the wire. - * - * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> - */ - -#ifndef _UAPI_LINUX_NFSD_FH_H -#define _UAPI_LINUX_NFSD_FH_H - -#include <linux/types.h> -#include <linux/nfs.h> -#include <linux/nfs2.h> -#include <linux/nfs3.h> -#include <linux/nfs4.h> - -/* - * This is the old "dentry style" Linux NFSv2 file handle. - * - * The xino and xdev fields are currently used to transport the - * ino/dev of the exported inode. - */ -struct nfs_fhbase_old { - __u32 fb_dcookie; /* dentry cookie - always 0xfeebbaca */ - __u32 fb_ino; /* our inode number */ - __u32 fb_dirino; /* dir inode number, 0 for directories */ - __u32 fb_dev; /* our device */ - __u32 fb_xdev; - __u32 fb_xino; - __u32 fb_generation; -}; - -/* - * This is the new flexible, extensible style NFSv2/v3/v4 file handle. - * - * The file handle starts with a sequence of four-byte words. - * The first word contains a version number (1) and three descriptor bytes - * that tell how the remaining 3 variable length fields should be handled. - * These three bytes are auth_type, fsid_type and fileid_type. - * - * All four-byte values are in host-byte-order. - * - * The auth_type field is deprecated and must be set to 0. - * - * The fsid_type identifies how the filesystem (or export point) is - * encoded. - * Current values: - * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number - * NOTE: we cannot use the kdev_t device id value, because kdev_t.h - * says we mustn't. We must break it up and reassemble. - * 1 - 4 byte user specified identifier - * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED - * 3 - 4 byte device id, encoded for user-space, 4 byte inode number - * 4 - 4 byte inode number and 4 byte uuid - * 5 - 8 byte uuid - * 6 - 16 byte uuid - * 7 - 8 byte inode number and 16 byte uuid - * - * The fileid_type identified how the file within the filesystem is encoded. - * The values for this field are filesystem specific, exccept that - * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' - * in include/linux/exportfs.h for currently registered values. - */ -struct nfs_fhbase_new { - union { - struct { - __u8 fb_version_aux; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type_aux; - __u8 fb_fsid_type_aux; - __u8 fb_fileid_type_aux; - __u32 fb_auth[1]; - /* __u32 fb_fsid[0]; floating */ - /* __u32 fb_fileid[0]; floating */ - }; - struct { - __u8 fb_version; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type; - __u8 fb_fsid_type; - __u8 fb_fileid_type; - __u32 fb_auth_flex[]; /* flexible-array member */ - }; - }; -}; - -struct knfsd_fh { - unsigned int fh_size; /* significant for NFSv3. - * Points to the current size while building - * a new file handle - */ - union { - struct nfs_fhbase_old fh_old; - __u32 fh_pad[NFS4_FHSIZE/4]; - struct nfs_fhbase_new fh_new; - } fh_base; -}; - -#define ofh_dcookie fh_base.fh_old.fb_dcookie -#define ofh_ino fh_base.fh_old.fb_ino -#define ofh_dirino fh_base.fh_old.fb_dirino -#define ofh_dev fh_base.fh_old.fb_dev -#define ofh_xdev fh_base.fh_old.fb_xdev -#define ofh_xino fh_base.fh_old.fb_xino -#define ofh_generation fh_base.fh_old.fb_generation - -#define fh_version fh_base.fh_new.fb_version -#define fh_fsid_type fh_base.fh_new.fb_fsid_type -#define fh_auth_type fh_base.fh_new.fb_auth_type -#define fh_fileid_type fh_base.fh_new.fb_fileid_type -#define fh_fsid fh_base.fh_new.fb_auth_flex - -/* Do not use, provided for userspace compatiblity. */ -#define fh_auth fh_base.fh_new.fb_auth - -#endif /* _UAPI_LINUX_NFSD_FH_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 43bd7f713c39..bb73e9a0b24f 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) @@ -268,5 +268,8 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ # define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ # define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 #endif /* _LINUX_PRCTL_H */ diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index f950bff75e97..03e5b776e597 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -14,6 +14,7 @@ #include <linux/const.h> #include <linux/ioctl.h> +#include <linux/types.h> /* * The struct used to pass data via the following ioctl. Similar to the @@ -66,6 +67,17 @@ struct rtc_pll_info { long pll_clock; /* base PLL frequency */ }; +struct rtc_param { + __u64 param; + union { + __u64 uvalue; + __s64 svalue; + __u64 ptr; + }; + __u32 index; + __u32 __pad; +}; + /* * ioctl calls that are permitted to the /dev/rtc interface, if * any of the RTC drivers are enabled. @@ -95,6 +107,9 @@ struct rtc_pll_info { #define RTC_PLL_GET _IOR('p', 0x11, struct rtc_pll_info) /* Get PLL correction */ #define RTC_PLL_SET _IOW('p', 0x12, struct rtc_pll_info) /* Set PLL correction */ +#define RTC_PARAM_GET _IOW('p', 0x13, struct rtc_param) /* Get parameter */ +#define RTC_PARAM_SET _IOW('p', 0x14, struct rtc_param) /* Set parameter */ + #define RTC_VL_DATA_INVALID _BITUL(0) /* Voltage too low, RTC data is invalid */ #define RTC_VL_BACKUP_LOW _BITUL(1) /* Backup voltage is low */ #define RTC_VL_BACKUP_EMPTY _BITUL(2) /* Backup empty or not present */ @@ -114,7 +129,21 @@ struct rtc_pll_info { #define RTC_FEATURE_ALARM 0 #define RTC_FEATURE_ALARM_RES_MINUTE 1 #define RTC_FEATURE_NEED_WEEK_DAY 2 -#define RTC_FEATURE_CNT 3 +#define RTC_FEATURE_ALARM_RES_2S 3 +#define RTC_FEATURE_UPDATE_INTERRUPT 4 +#define RTC_FEATURE_CORRECTION 5 +#define RTC_FEATURE_BACKUP_SWITCH_MODE 6 +#define RTC_FEATURE_CNT 7 + +/* parameter list */ +#define RTC_PARAM_FEATURES 0 +#define RTC_PARAM_CORRECTION 1 +#define RTC_PARAM_BACKUP_SWITCH_MODE 2 + +#define RTC_BSM_DISABLED 0 +#define RTC_BSM_DIRECT 1 +#define RTC_BSM_LEVEL 2 +#define RTC_BSM_STANDBY 3 #define RTC_MAX_FREQ 8192 diff --git a/include/xen/arm/hypercall.h b/include/xen/arm/hypercall.h index b40485e54d80..9d7dd1c65a21 100644 --- a/include/xen/arm/hypercall.h +++ b/include/xen/arm/hypercall.h @@ -53,7 +53,6 @@ unsigned long HYPERVISOR_hvm_op(int op, void *arg); int HYPERVISOR_memory_op(unsigned int cmd, void *arg); int HYPERVISOR_physdev_op(int cmd, void *arg); int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args); -int HYPERVISOR_tmem_op(void *arg); int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type); int HYPERVISOR_dm_op(domid_t domid, unsigned int nr_bufs, struct xen_dm_op_buf *bufs); @@ -74,18 +73,4 @@ HYPERVISOR_suspend(unsigned long start_info_mfn) return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); } -static inline void -MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, - unsigned int new_val, unsigned long flags) -{ - BUG(); -} - -static inline void -MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, - int count, int *success_count, domid_t domid) -{ - BUG(); -} - #endif /* _ASM_ARM_XEN_HYPERCALL_H */ diff --git a/include/xen/balloon.h b/include/xen/balloon.h index 6dbdb0b3fd03..e93d4f0088c5 100644 --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -26,9 +26,6 @@ extern struct balloon_stats balloon_stats; void balloon_set_new_target(unsigned long target); -int alloc_xenballooned_pages(int nr_pages, struct page **pages); -void free_xenballooned_pages(int nr_pages, struct page **pages); - #ifdef CONFIG_XEN_BALLOON void xen_balloon_init(void); #else diff --git a/include/xen/interface/callback.h b/include/xen/interface/callback.h index dc3193f4b581..c67822a25ea6 100644 --- a/include/xen/interface/callback.h +++ b/include/xen/interface/callback.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * callback.h * * Register guest OS callbacks with Xen. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2006, Ian Campbell */ diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h index 449bd383cb76..38deb1214613 100644 --- a/include/xen/interface/elfnote.h +++ b/include/xen/interface/elfnote.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * elfnote.h * * Definitions used for the Xen ELF notes. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2006, Ian Campbell, XenSource Ltd. */ diff --git a/include/xen/interface/event_channel.h b/include/xen/interface/event_channel.h index cf80e338fbb0..5f8da466e8a9 100644 --- a/include/xen/interface/event_channel.h +++ b/include/xen/interface/event_channel.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * event_channel.h * diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h index 5a7bdefa06a8..53f760378e39 100644 --- a/include/xen/interface/features.h +++ b/include/xen/interface/features.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * features.h * diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index 7fb7112d667c..3eeabbc7ee09 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -1,27 +1,10 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * grant_table.h * * Interface for granting foreign access to page frames, and receiving * page-ownership transfers. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2004, K A Fraser */ diff --git a/include/xen/interface/hvm/dm_op.h b/include/xen/interface/hvm/dm_op.h index ee9e480bc559..08d972f87c7b 100644 --- a/include/xen/interface/hvm/dm_op.h +++ b/include/xen/interface/hvm/dm_op.h @@ -1,23 +1,6 @@ +/* SPDX-License-Identifier: MIT */ /* * Copyright (c) 2016, Citrix Systems Inc - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. */ #ifndef __XEN_PUBLIC_HVM_DM_OP_H__ diff --git a/include/xen/interface/hvm/hvm_op.h b/include/xen/interface/hvm/hvm_op.h index 25d945ef17de..f3097e79bb03 100644 --- a/include/xen/interface/hvm/hvm_op.h +++ b/include/xen/interface/hvm/hvm_op.h @@ -1,22 +1,4 @@ -/* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_HVM_HVM_OP_H__ #define __XEN_PUBLIC_HVM_HVM_OP_H__ diff --git a/include/xen/interface/hvm/hvm_vcpu.h b/include/xen/interface/hvm/hvm_vcpu.h index bfc2138e0bf5..cbf93493275c 100644 --- a/include/xen/interface/hvm/hvm_vcpu.h +++ b/include/xen/interface/hvm/hvm_vcpu.h @@ -1,22 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2015, Roger Pau Monne <roger.pau@citrix.com> */ diff --git a/include/xen/interface/hvm/params.h b/include/xen/interface/hvm/params.h index 4d61fc58d99d..4e2c94b3c466 100644 --- a/include/xen/interface/hvm/params.h +++ b/include/xen/interface/hvm/params.h @@ -1,22 +1,4 @@ -/* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_HVM_PARAMS_H__ #define __XEN_PUBLIC_HVM_PARAMS_H__ diff --git a/include/xen/interface/hvm/start_info.h b/include/xen/interface/hvm/start_info.h index 50af9ea2ff1e..e33557c0b4e9 100644 --- a/include/xen/interface/hvm/start_info.h +++ b/include/xen/interface/hvm/start_info.h @@ -1,22 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2016, Citrix Systems, Inc. */ diff --git a/include/xen/interface/io/9pfs.h b/include/xen/interface/io/9pfs.h index 5b6c19dae5e2..f1a4c5ad2fd1 100644 --- a/include/xen/interface/io/9pfs.h +++ b/include/xen/interface/io/9pfs.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * 9pfs.h -- Xen 9PFS transport * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (C) 2017 Stefano Stabellini <stefano@aporeto.com> */ diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index 5e40041c7e95..ba1e9f5b630e 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * blkif.h * diff --git a/include/xen/interface/io/console.h b/include/xen/interface/io/console.h index 85ca8b02695a..cf17e89ed861 100644 --- a/include/xen/interface/io/console.h +++ b/include/xen/interface/io/console.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * console.h * diff --git a/include/xen/interface/io/displif.h b/include/xen/interface/io/displif.h index d43ca0361f86..18417b017869 100644 --- a/include/xen/interface/io/displif.h +++ b/include/xen/interface/io/displif.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * displif.h * * Unified display device I/O interface for Xen guest OSes. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (C) 2016-2017 EPAM Systems Inc. * * Authors: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> diff --git a/include/xen/interface/io/fbif.h b/include/xen/interface/io/fbif.h index 974a51ed9165..60ca808cef97 100644 --- a/include/xen/interface/io/fbif.h +++ b/include/xen/interface/io/fbif.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * fbif.h -- Xen virtual frame buffer device * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (C) 2005 Anthony Liguori <aliguori@us.ibm.com> * Copyright (C) 2006 Red Hat, Inc., Markus Armbruster <armbru@redhat.com> */ diff --git a/include/xen/interface/io/kbdif.h b/include/xen/interface/io/kbdif.h index 5c7630d7376e..b8b08aa53325 100644 --- a/include/xen/interface/io/kbdif.h +++ b/include/xen/interface/io/kbdif.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * kbdif.h -- Xen virtual keyboard/mouse * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (C) 2005 Anthony Liguori <aliguori@us.ibm.com> * Copyright (C) 2006 Red Hat, Inc., Markus Armbruster <armbru@redhat.com> */ diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index 2194322c3c7f..cb0c1a25d5d4 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * xen_netif.h * * Unified network-device I/O interface for Xen guest OSes. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2003-2004, Keir Fraser */ diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h index d9922ae36eb5..d1a87b62daae 100644 --- a/include/xen/interface/io/pciif.h +++ b/include/xen/interface/io/pciif.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * PCI Backend/Frontend Common Data Structures & Macros * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Author: Ryan Wilson <hap9@epoch.ncsc.mil> */ #ifndef __XEN_PCI_COMMON_H__ diff --git a/include/xen/interface/io/protocols.h b/include/xen/interface/io/protocols.h index 6a89dc1bf225..22099bb4079f 100644 --- a/include/xen/interface/io/protocols.h +++ b/include/xen/interface/io/protocols.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PROTOCOLS_H__ #define __XEN_PROTOCOLS_H__ diff --git a/include/xen/interface/io/pvcalls.h b/include/xen/interface/io/pvcalls.h index ccf97b817e72..b6680fdbe2a8 100644 --- a/include/xen/interface/io/pvcalls.h +++ b/include/xen/interface/io/pvcalls.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: MIT */ + #ifndef __XEN_PUBLIC_IO_XEN_PVCALLS_H__ #define __XEN_PUBLIC_IO_XEN_PVCALLS_H__ diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index b39cdbc522ec..2470ec45ebb2 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * ring.h * * Shared producer-consumer ring macros. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Tim Deegan and Andrew Warfield November 2004. */ diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h index 2aac8f73614c..445657cdb1de 100644 --- a/include/xen/interface/io/sndif.h +++ b/include/xen/interface/io/sndif.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * sndif.h * * Unified sound-device I/O interface for Xen guest OSes. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (C) 2013-2015 GlobalLogic Inc. * Copyright (C) 2016-2017 EPAM Systems Inc. * diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h index d07d7aca8d1c..1f6047d3de44 100644 --- a/include/xen/interface/io/vscsiif.h +++ b/include/xen/interface/io/vscsiif.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * vscsiif.h * * Based on the blkif.h code. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright(c) FUJITSU Limited 2008. */ diff --git a/include/xen/interface/io/xenbus.h b/include/xen/interface/io/xenbus.h index fb8716112251..44456e2853fc 100644 --- a/include/xen/interface/io/xenbus.h +++ b/include/xen/interface/io/xenbus.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /***************************************************************************** * xenbus.h * diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index 1517c7e93a3a..d40a44f09b16 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /* * Details of the "wire" protocol between Xen Store Daemon and client * library or guest kernel. diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h index 447004861f00..1a371a825c55 100644 --- a/include/xen/interface/memory.h +++ b/include/xen/interface/memory.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * memory.h * diff --git a/include/xen/interface/nmi.h b/include/xen/interface/nmi.h index 73d9b0a2974e..b665fdbef1fd 100644 --- a/include/xen/interface/nmi.h +++ b/include/xen/interface/nmi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * nmi.h * diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index 610dba9b620a..a237af867873 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -1,22 +1,4 @@ -/* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_PHYSDEV_H__ #define __XEN_PUBLIC_PHYSDEV_H__ diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h index 732efb08c3e1..655d92e803e1 100644 --- a/include/xen/interface/platform.h +++ b/include/xen/interface/platform.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * platform.h * * Hardware platform operations. Intended for use by domain-0 kernel. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2002-2006, K Fraser */ diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h index a4c4d735d781..4dac0634ffff 100644 --- a/include/xen/interface/sched.h +++ b/include/xen/interface/sched.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * sched.h * * Scheduler state interactions * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2005, Keir Fraser <keir@xensource.com> */ diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h index 504c71601511..c7cc28ad8d63 100644 --- a/include/xen/interface/vcpu.h +++ b/include/xen/interface/vcpu.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * vcpu.h * * VCPU initialisation, query, and hotplug. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2005, Keir Fraser <keir@xensource.com> */ diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h index 8772b552c006..37d6588873d6 100644 --- a/include/xen/interface/version.h +++ b/include/xen/interface/version.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * version.h * diff --git a/include/xen/interface/xen-mca.h b/include/xen/interface/xen-mca.h index 7483a78d2425..464aa6b3a5f9 100644 --- a/include/xen/interface/xen-mca.h +++ b/include/xen/interface/xen-mca.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * arch-x86/mca.h * Guest OS machine check interface to x86 Xen. diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h index 5ee37a296481..5e9916939268 100644 --- a/include/xen/interface/xen.h +++ b/include/xen/interface/xen.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * xen.h * * Guest OS interface to Xen. * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Copyright (c) 2004, K A Fraser */ diff --git a/include/xen/interface/xenpmu.h b/include/xen/interface/xenpmu.h index ad603eab24b3..e2ee73d91bd6 100644 --- a/include/xen/interface/xenpmu.h +++ b/include/xen/interface/xenpmu.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_XENPMU_H__ #define __XEN_PUBLIC_XENPMU_H__ diff --git a/include/xen/pci.h b/include/xen/pci.h new file mode 100644 index 000000000000..b8337cf85fd1 --- /dev/null +++ b/include/xen/pci.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __XEN_PCI_H__ +#define __XEN_PCI_H__ + +#if defined(CONFIG_XEN_DOM0) +int xen_find_device_domain_owner(struct pci_dev *dev); +int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); +int xen_unregister_device_domain_owner(struct pci_dev *dev); +#else +static inline int xen_find_device_domain_owner(struct pci_dev *dev) +{ + return -1; +} + +static inline int xen_register_device_domain_owner(struct pci_dev *dev, + uint16_t domain) +{ + return -1; +} + +static inline int xen_unregister_device_domain_owner(struct pci_dev *dev) +{ + return -1; +} +#endif + +#endif diff --git a/include/xen/xen.h b/include/xen/xen.h index 43efba045acc..9f031b5faa54 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -52,13 +52,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, extern u64 xen_saved_max_mem_size; #endif -#ifdef CONFIG_XEN_UNPOPULATED_ALLOC int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages); void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); -#else -#define xen_alloc_unpopulated_pages alloc_xenballooned_pages -#define xen_free_unpopulated_pages free_xenballooned_pages -#include <xen/balloon.h> -#endif #endif /* _XEN_XEN_H */ diff --git a/init/Kconfig b/init/Kconfig index 21b1f4870c80..45bcaa8e7481 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1896,6 +1896,7 @@ choice config SLAB bool "SLAB" + depends on !PREEMPT_RT select HAVE_HARDENED_USERCOPY_ALLOCATOR help The regular slab allocator that is established and known to work @@ -1916,6 +1917,7 @@ config SLUB config SLOB depends on EXPERT bool "SLOB (Simple Allocator)" + depends on !PREEMPT_RT help SLOB replaces the stock allocator with a drastically simpler allocator. SLOB is generally more space efficient but diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 327e3996eadb..2405e39d800f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -390,6 +390,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, i = end_new; insn = prog->insnsi + end_old; } + if (bpf_pseudo_func(insn)) { + ret = bpf_adj_delta_to_imm(insn, pos, end_old, + end_new, i, probe_pass); + if (ret) + return ret; + continue; + } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0dca726ebfd..890b3ec375a3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -240,12 +240,6 @@ static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_KFUNC_CALL; } -static bool bpf_pseudo_func(const struct bpf_insn *insn) -{ - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; -} - struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; @@ -1960,16 +1954,10 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) return -EPERM; } - if (bpf_pseudo_func(insn)) { - ret = add_subprog(env, i + insn->imm + 1); - if (ret >= 0) - /* remember subprog */ - insn[1].imm = ret; - } else if (bpf_pseudo_call(insn)) { + if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) ret = add_subprog(env, i + insn->imm + 1); - } else { + else ret = add_kfunc_call(env, insn->imm, insn->off); - } if (ret < 0) return ret; @@ -3088,9 +3076,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { - if (size != BPF_REG_SIZE) { - u8 scalar_size = 0; + u8 spill_size = 1; + + for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) + spill_size++; + if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); @@ -3101,10 +3092,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno < 0) return 0; - for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--) - scalar_size++; - - if (!(off % BPF_REG_SIZE) && size == scalar_size) { + if (!(off % BPF_REG_SIZE) && size == spill_size) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ @@ -3128,12 +3116,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } - for (i = 1; i < BPF_REG_SIZE; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { - verbose(env, "corrupted spill memory\n"); - return -EACCES; - } - } if (dst_regno >= 0) { /* restore register state from stack */ @@ -9393,7 +9375,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->src_reg == BPF_PSEUDO_FUNC) { struct bpf_prog_aux *aux = env->prog->aux; - u32 subprogno = insn[1].imm; + u32 subprogno = find_subprog(env, + env->insn_idx + insn->imm + 1); if (!aux->func_info) { verbose(env, "missing btf func_info\n"); @@ -12563,14 +12546,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - if (bpf_pseudo_func(insn)) { - env->insn_aux_data[i].call_imm = insn->imm; - /* subprog is encoded in insn[1].imm */ + if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; - } - if (!bpf_pseudo_call(insn)) - continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. @@ -12591,6 +12569,12 @@ static int jit_subprogs(struct bpf_verifier_env *env) env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; + if (bpf_pseudo_func(insn)) + /* jit (e.g. x86_64) may emit fewer instructions + * if it learns a u32 imm is the same as a u64 imm. + * Force a non zero here. + */ + insn[1].imm = 1; } err = bpf_prog_alloc_jited_linfo(prog); @@ -12675,7 +12659,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (bpf_pseudo_func(insn)) { - subprog = insn[1].imm; + subprog = insn->off; insn[0].imm = (u32)(long)func[subprog]->bpf_func; insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; continue; @@ -12726,7 +12710,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { insn[0].imm = env->insn_aux_data[i].call_imm; - insn[1].imm = find_subprog(env, i + insn[0].imm + 1); + insn[1].imm = insn->off; + insn->off = 0; continue; } if (!bpf_pseudo_call(insn)) diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index c240302f56e2..4508201847d2 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -47,14 +47,18 @@ bool syscall_user_dispatch(struct pt_regs *regs) * access_ok() is performed once, at prctl time, when * the selector is loaded by userspace. */ - if (unlikely(__get_user(state, sd->selector))) - do_exit(SIGSEGV); + if (unlikely(__get_user(state, sd->selector))) { + force_fatal_sig(SIGSEGV); + return true; + } if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW)) return false; - if (state != SYSCALL_DISPATCH_FILTER_BLOCK) - do_exit(SIGSYS); + if (state != SYSCALL_DISPATCH_FILTER_BLOCK) { + force_fatal_sig(SIGSYS); + return true; + } } sd->on_dispatch = true; diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 76e67d1e02d4..4b84c8e7884b 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -202,6 +202,9 @@ static __always_inline struct kcsan_ctx *get_ctx(void) return in_task() ? ¤t->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx); } +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip); + /* Check scoped accesses; never inline because this is a slow-path! */ static noinline void kcsan_check_scoped_accesses(void) { @@ -210,14 +213,16 @@ static noinline void kcsan_check_scoped_accesses(void) struct kcsan_scoped_access *scoped_access; ctx->scoped_accesses.prev = NULL; /* Avoid recursion. */ - list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) - __kcsan_check_access(scoped_access->ptr, scoped_access->size, scoped_access->type); + list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) { + check_access(scoped_access->ptr, scoped_access->size, + scoped_access->type, scoped_access->ip); + } ctx->scoped_accesses.prev = prev_save; } /* Rules for generic atomic accesses. Called from fast-path. */ static __always_inline bool -is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx) +is_atomic(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) { if (type & KCSAN_ACCESS_ATOMIC) return true; @@ -254,7 +259,7 @@ is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx } static __always_inline bool -should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx) +should_watch(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) { /* * Never set up watchpoints when memory operations are atomic. @@ -263,7 +268,7 @@ should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx * * should not count towards skipped instructions, and (2) to actually * decrement kcsan_atomic_next for consecutive instruction stream. */ - if (is_atomic(ptr, size, type, ctx)) + if (is_atomic(ctx, ptr, size, type)) return false; if (this_cpu_dec_return(kcsan_skip) >= 0) @@ -350,6 +355,7 @@ void kcsan_restore_irqtrace(struct task_struct *task) static noinline void kcsan_found_watchpoint(const volatile void *ptr, size_t size, int type, + unsigned long ip, atomic_long_t *watchpoint, long encoded_watchpoint) { @@ -396,7 +402,7 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr, if (consumed) { kcsan_save_irqtrace(current); - kcsan_report_set_info(ptr, size, type, watchpoint - watchpoints); + kcsan_report_set_info(ptr, size, type, ip, watchpoint - watchpoints); kcsan_restore_irqtrace(current); } else { /* @@ -416,7 +422,7 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr, } static noinline void -kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) +kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned long ip) { const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; @@ -568,8 +574,8 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) if (is_assert && value_change == KCSAN_VALUE_CHANGE_TRUE) atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); - kcsan_report_known_origin(ptr, size, type, value_change, - watchpoint - watchpoints, + kcsan_report_known_origin(ptr, size, type, ip, + value_change, watchpoint - watchpoints, old, new, access_mask); } else if (value_change == KCSAN_VALUE_CHANGE_TRUE) { /* Inferring a race, since the value should not have changed. */ @@ -578,8 +584,10 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) if (is_assert) atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); - if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) - kcsan_report_unknown_origin(ptr, size, type, old, new, access_mask); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) { + kcsan_report_unknown_origin(ptr, size, type, ip, + old, new, access_mask); + } } /* @@ -596,8 +604,8 @@ out: user_access_restore(ua_flags); } -static __always_inline void check_access(const volatile void *ptr, size_t size, - int type) +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) { const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; atomic_long_t *watchpoint; @@ -625,13 +633,12 @@ static __always_inline void check_access(const volatile void *ptr, size_t size, */ if (unlikely(watchpoint != NULL)) - kcsan_found_watchpoint(ptr, size, type, watchpoint, - encoded_watchpoint); + kcsan_found_watchpoint(ptr, size, type, ip, watchpoint, encoded_watchpoint); else { struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */ - if (unlikely(should_watch(ptr, size, type, ctx))) - kcsan_setup_watchpoint(ptr, size, type); + if (unlikely(should_watch(ctx, ptr, size, type))) + kcsan_setup_watchpoint(ptr, size, type, ip); else if (unlikely(ctx->scoped_accesses.prev)) kcsan_check_scoped_accesses(); } @@ -757,7 +764,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, { struct kcsan_ctx *ctx = get_ctx(); - __kcsan_check_access(ptr, size, type); + check_access(ptr, size, type, _RET_IP_); ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */ @@ -765,6 +772,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, sa->ptr = ptr; sa->size = size; sa->type = type; + sa->ip = _RET_IP_; if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */ INIT_LIST_HEAD(&ctx->scoped_accesses); @@ -796,13 +804,13 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) ctx->disable_count--; - __kcsan_check_access(sa->ptr, sa->size, sa->type); + check_access(sa->ptr, sa->size, sa->type, sa->ip); } EXPORT_SYMBOL(kcsan_end_scoped_access); void __kcsan_check_access(const volatile void *ptr, size_t size, int type) { - check_access(ptr, size, type); + check_access(ptr, size, type, _RET_IP_); } EXPORT_SYMBOL(__kcsan_check_access); @@ -823,7 +831,7 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_read##size(void *ptr); \ void __tsan_read##size(void *ptr) \ { \ - check_access(ptr, size, 0); \ + check_access(ptr, size, 0, _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_read##size); \ void __tsan_unaligned_read##size(void *ptr) \ @@ -832,7 +840,7 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_write##size(void *ptr); \ void __tsan_write##size(void *ptr) \ { \ - check_access(ptr, size, KCSAN_ACCESS_WRITE); \ + check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_write##size); \ void __tsan_unaligned_write##size(void *ptr) \ @@ -842,7 +850,8 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_read_write##size(void *ptr) \ { \ check_access(ptr, size, \ - KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE); \ + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE, \ + _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_read_write##size); \ void __tsan_unaligned_read_write##size(void *ptr) \ @@ -858,14 +867,14 @@ DEFINE_TSAN_READ_WRITE(16); void __tsan_read_range(void *ptr, size_t size); void __tsan_read_range(void *ptr, size_t size) { - check_access(ptr, size, 0); + check_access(ptr, size, 0, _RET_IP_); } EXPORT_SYMBOL(__tsan_read_range); void __tsan_write_range(void *ptr, size_t size); void __tsan_write_range(void *ptr, size_t size) { - check_access(ptr, size, KCSAN_ACCESS_WRITE); + check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); } EXPORT_SYMBOL(__tsan_write_range); @@ -886,7 +895,8 @@ EXPORT_SYMBOL(__tsan_write_range); IS_ALIGNED((unsigned long)ptr, size); \ if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic) \ return; \ - check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0); \ + check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0, \ + _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_volatile_read##size); \ void __tsan_unaligned_volatile_read##size(void *ptr) \ @@ -901,7 +911,8 @@ EXPORT_SYMBOL(__tsan_write_range); return; \ check_access(ptr, size, \ KCSAN_ACCESS_WRITE | \ - (is_atomic ? KCSAN_ACCESS_ATOMIC : 0)); \ + (is_atomic ? KCSAN_ACCESS_ATOMIC : 0), \ + _RET_IP_); \ } \ EXPORT_SYMBOL(__tsan_volatile_write##size); \ void __tsan_unaligned_volatile_write##size(void *ptr) \ @@ -955,7 +966,7 @@ EXPORT_SYMBOL(__tsan_init); u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder) \ { \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ - check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC); \ + check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ return __atomic_load_n(ptr, memorder); \ } \ @@ -965,7 +976,7 @@ EXPORT_SYMBOL(__tsan_init); { \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ - KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ __atomic_store_n(ptr, v, memorder); \ } \ @@ -978,7 +989,7 @@ EXPORT_SYMBOL(__tsan_init); if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ - KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ return __atomic_##op##suffix(ptr, v, memorder); \ } \ @@ -1010,7 +1021,7 @@ EXPORT_SYMBOL(__tsan_init); if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ - KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ return __atomic_compare_exchange_n(ptr, exp, val, weak, mo, fail_mo); \ } \ @@ -1025,7 +1036,7 @@ EXPORT_SYMBOL(__tsan_init); if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ - KCSAN_ACCESS_ATOMIC); \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ __atomic_compare_exchange_n(ptr, &exp, val, 0, mo, fail_mo); \ return exp; \ diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h index f36e25c497ed..ae33c2a7f07e 100644 --- a/kernel/kcsan/kcsan.h +++ b/kernel/kcsan/kcsan.h @@ -121,7 +121,7 @@ enum kcsan_value_change { * to be consumed by the reporting thread. No report is printed yet. */ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type, - int watchpoint_idx); + unsigned long ip, int watchpoint_idx); /* * The calling thread observed that the watchpoint it set up was hit and @@ -129,14 +129,14 @@ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_typ * thread. */ void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type, - enum kcsan_value_change value_change, int watchpoint_idx, - u64 old, u64 new, u64 mask); + unsigned long ip, enum kcsan_value_change value_change, + int watchpoint_idx, u64 old, u64 new, u64 mask); /* * No other thread was observed to race with the access, but the data value * before and after the stall differs. Reports a race of "unknown origin". */ void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type, - u64 old, u64 new, u64 mask); + unsigned long ip, u64 old, u64 new, u64 mask); #endif /* _KERNEL_KCSAN_KCSAN_H */ diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index dc55fd5a36fc..660729238588 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -29,6 +29,11 @@ #include <linux/types.h> #include <trace/events/printk.h> +#define KCSAN_TEST_REQUIRES(test, cond) do { \ + if (!(cond)) \ + kunit_skip((test), "Test requires: " #cond); \ +} while (0) + #ifdef CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE #define __KCSAN_ACCESS_RW(alt) (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) #else @@ -205,10 +210,12 @@ static bool report_matches(const struct expect_report *r) "read-write" : "write") : "read"); + const bool is_atomic = (ty & KCSAN_ACCESS_ATOMIC); + const bool is_scoped = (ty & KCSAN_ACCESS_SCOPED); const char *const access_type_aux = - (ty & KCSAN_ACCESS_ATOMIC) ? - " (marked)" : - ((ty & KCSAN_ACCESS_SCOPED) ? " (scoped)" : ""); + (is_atomic && is_scoped) ? " (marked, scoped)" + : (is_atomic ? " (marked)" + : (is_scoped ? " (scoped)" : "")); if (i == 1) { /* Access 2 */ @@ -333,7 +340,10 @@ static noinline void test_kernel_assert_bits_nochange(void) ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS); } -/* To check that scoped assertions do trigger anywhere in scope. */ +/* + * Scoped assertions do trigger anywhere in scope. However, the report should + * still only point at the start of the scope. + */ static noinline void test_enter_scope(void) { int x = 0; @@ -488,17 +498,24 @@ static void test_concurrent_races(struct kunit *test) __no_kcsan static void test_novalue_change(struct kunit *test) { - const struct expect_report expect = { + const struct expect_report expect_rw = { .access = { { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, { test_kernel_read, &test_var, sizeof(test_var), 0 }, }, }; + const struct expect_report expect_ww = { + .access = { + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; bool match_expect = false; + test_kernel_write_nochange(); /* Reset value. */ begin_test_checks(test_kernel_write_nochange, test_kernel_read); do { - match_expect = report_matches(&expect); + match_expect = report_matches(&expect_rw) || report_matches(&expect_ww); } while (!end_test_checks(match_expect)); if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY)) KUNIT_EXPECT_FALSE(test, match_expect); @@ -513,17 +530,24 @@ static void test_novalue_change(struct kunit *test) __no_kcsan static void test_novalue_change_exception(struct kunit *test) { - const struct expect_report expect = { + const struct expect_report expect_rw = { .access = { { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, { test_kernel_read, &test_var, sizeof(test_var), 0 }, }, }; + const struct expect_report expect_ww = { + .access = { + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; bool match_expect = false; + test_kernel_write_nochange_rcu(); /* Reset value. */ begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read); do { - match_expect = report_matches(&expect); + match_expect = report_matches(&expect_rw) || report_matches(&expect_ww); } while (!end_test_checks(match_expect)); KUNIT_EXPECT_TRUE(test, match_expect); } @@ -642,8 +666,7 @@ static void test_read_plain_atomic_write(struct kunit *test) }; bool match_expect = false; - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) - return; + KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)); begin_test_checks(test_kernel_read, test_kernel_write_atomic); do { @@ -665,8 +688,7 @@ static void test_read_plain_atomic_rmw(struct kunit *test) }; bool match_expect = false; - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) - return; + KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)); begin_test_checks(test_kernel_read, test_kernel_atomic_rmw); do { @@ -828,22 +850,22 @@ static void test_assert_exclusive_writer_scoped(struct kunit *test) { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, }, }; - const struct expect_report expect_anywhere = { + const struct expect_report expect_inscope = { .access = { { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, }, }; bool match_expect_start = false; - bool match_expect_anywhere = false; + bool match_expect_inscope = false; begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange); do { match_expect_start |= report_matches(&expect_start); - match_expect_anywhere |= report_matches(&expect_anywhere); - } while (!end_test_checks(match_expect_start && match_expect_anywhere)); + match_expect_inscope |= report_matches(&expect_inscope); + } while (!end_test_checks(match_expect_inscope)); KUNIT_EXPECT_TRUE(test, match_expect_start); - KUNIT_EXPECT_TRUE(test, match_expect_anywhere); + KUNIT_EXPECT_FALSE(test, match_expect_inscope); } __no_kcsan @@ -872,9 +894,9 @@ static void test_assert_exclusive_access_scoped(struct kunit *test) do { match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2); match_expect_inscope |= report_matches(&expect_inscope); - } while (!end_test_checks(match_expect_start && match_expect_inscope)); + } while (!end_test_checks(match_expect_inscope)); KUNIT_EXPECT_TRUE(test, match_expect_start); - KUNIT_EXPECT_TRUE(test, match_expect_inscope); + KUNIT_EXPECT_FALSE(test, match_expect_inscope); } /* @@ -1224,7 +1246,7 @@ static void kcsan_test_exit(void) tracepoint_synchronize_unregister(); } -late_initcall(kcsan_test_init); +late_initcall_sync(kcsan_test_init); module_exit(kcsan_test_exit); MODULE_LICENSE("GPL v2"); diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c index 21137929d428..fc15077991c4 100644 --- a/kernel/kcsan/report.c +++ b/kernel/kcsan/report.c @@ -8,6 +8,7 @@ #include <linux/debug_locks.h> #include <linux/delay.h> #include <linux/jiffies.h> +#include <linux/kallsyms.h> #include <linux/kernel.h> #include <linux/lockdep.h> #include <linux/preempt.h> @@ -31,6 +32,7 @@ struct access_info { int access_type; int task_pid; int cpu_id; + unsigned long ip; }; /* @@ -245,6 +247,10 @@ static const char *get_access_type(int type) return "write (scoped)"; case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: return "write (marked, scoped)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE: + return "read-write (scoped)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: + return "read-write (marked, scoped)"; default: BUG(); } @@ -300,6 +306,48 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries return skip; } +/* + * Skips to the first entry that matches the function of @ip, and then replaces + * that entry with @ip, returning the entries to skip. + */ +static int +replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip) +{ + unsigned long symbolsize, offset; + unsigned long target_func; + int skip; + + if (kallsyms_lookup_size_offset(ip, &symbolsize, &offset)) + target_func = ip - offset; + else + goto fallback; + + for (skip = 0; skip < num_entries; ++skip) { + unsigned long func = stack_entries[skip]; + + if (!kallsyms_lookup_size_offset(func, &symbolsize, &offset)) + goto fallback; + func -= offset; + + if (func == target_func) { + stack_entries[skip] = ip; + return skip; + } + } + +fallback: + /* Should not happen; the resulting stack trace is likely misleading. */ + WARN_ONCE(1, "Cannot find frame for %pS in stack trace", (void *)ip); + return get_stack_skipnr(stack_entries, num_entries); +} + +static int +sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip) +{ + return ip ? replace_stack_entry(stack_entries, num_entries, ip) : + get_stack_skipnr(stack_entries, num_entries); +} + /* Compares symbolized strings of addr1 and addr2. */ static int sym_strcmp(void *addr1, void *addr2) { @@ -327,12 +375,12 @@ static void print_verbose_info(struct task_struct *task) static void print_report(enum kcsan_value_change value_change, const struct access_info *ai, - const struct other_info *other_info, + struct other_info *other_info, u64 old, u64 new, u64 mask) { unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 }; int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1); - int skipnr = get_stack_skipnr(stack_entries, num_stack_entries); + int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip); unsigned long this_frame = stack_entries[skipnr]; unsigned long other_frame = 0; int other_skipnr = 0; /* silence uninit warnings */ @@ -344,8 +392,9 @@ static void print_report(enum kcsan_value_change value_change, return; if (other_info) { - other_skipnr = get_stack_skipnr(other_info->stack_entries, - other_info->num_stack_entries); + other_skipnr = sanitize_stack_entries(other_info->stack_entries, + other_info->num_stack_entries, + other_info->ai.ip); other_frame = other_info->stack_entries[other_skipnr]; /* @value_change is only known for the other thread */ @@ -576,21 +625,23 @@ discard: } static struct access_info prepare_access_info(const volatile void *ptr, size_t size, - int access_type) + int access_type, unsigned long ip) { return (struct access_info) { .ptr = ptr, .size = size, .access_type = access_type, .task_pid = in_task() ? task_pid_nr(current) : -1, - .cpu_id = raw_smp_processor_id() + .cpu_id = raw_smp_processor_id(), + /* Only replace stack entry with @ip if scoped access. */ + .ip = (access_type & KCSAN_ACCESS_SCOPED) ? ip : 0, }; } void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type, - int watchpoint_idx) + unsigned long ip, int watchpoint_idx) { - const struct access_info ai = prepare_access_info(ptr, size, access_type); + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); unsigned long flags; kcsan_disable_current(); @@ -603,10 +654,10 @@ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_typ } void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type, - enum kcsan_value_change value_change, int watchpoint_idx, - u64 old, u64 new, u64 mask) + unsigned long ip, enum kcsan_value_change value_change, + int watchpoint_idx, u64 old, u64 new, u64 mask) { - const struct access_info ai = prepare_access_info(ptr, size, access_type); + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); struct other_info *other_info = &other_infos[watchpoint_idx]; unsigned long flags = 0; @@ -637,9 +688,9 @@ out: } void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type, - u64 old, u64 new, u64 mask) + unsigned long ip, u64 old, u64 new, u64 mask) { - const struct access_info ai = prepare_access_info(ptr, size, access_type); + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); unsigned long flags; kcsan_disable_current(); diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c index 7f29cb0f5e63..b4295a3892b7 100644 --- a/kernel/kcsan/selftest.c +++ b/kernel/kcsan/selftest.c @@ -18,7 +18,7 @@ #define ITERS_PER_TEST 2000 /* Test requirements. */ -static bool test_requires(void) +static bool __init test_requires(void) { /* random should be initialized for the below tests */ return prandom_u32() + prandom_u32() != 0; @@ -28,14 +28,18 @@ static bool test_requires(void) * Test watchpoint encode and decode: check that encoding some access's info, * and then subsequent decode preserves the access's info. */ -static bool test_encode_decode(void) +static bool __init test_encode_decode(void) { int i; for (i = 0; i < ITERS_PER_TEST; ++i) { size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1; bool is_write = !!prandom_u32_max(2); + unsigned long verif_masked_addr; + long encoded_watchpoint; + bool verif_is_write; unsigned long addr; + size_t verif_size; prandom_bytes(&addr, sizeof(addr)); if (addr < PAGE_SIZE) @@ -44,53 +48,37 @@ static bool test_encode_decode(void) if (WARN_ON(!check_encodable(addr, size))) return false; - /* Encode and decode */ - { - const long encoded_watchpoint = - encode_watchpoint(addr, size, is_write); - unsigned long verif_masked_addr; - size_t verif_size; - bool verif_is_write; - - /* Check special watchpoints */ - if (WARN_ON(decode_watchpoint( - INVALID_WATCHPOINT, &verif_masked_addr, - &verif_size, &verif_is_write))) - return false; - if (WARN_ON(decode_watchpoint( - CONSUMED_WATCHPOINT, &verif_masked_addr, - &verif_size, &verif_is_write))) - return false; - - /* Check decoding watchpoint returns same data */ - if (WARN_ON(!decode_watchpoint( - encoded_watchpoint, &verif_masked_addr, - &verif_size, &verif_is_write))) - return false; - if (WARN_ON(verif_masked_addr != - (addr & WATCHPOINT_ADDR_MASK))) - goto fail; - if (WARN_ON(verif_size != size)) - goto fail; - if (WARN_ON(is_write != verif_is_write)) - goto fail; - - continue; -fail: - pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n", - __func__, is_write ? "write" : "read", size, - addr, encoded_watchpoint, - verif_is_write ? "write" : "read", verif_size, - verif_masked_addr); + encoded_watchpoint = encode_watchpoint(addr, size, is_write); + + /* Check special watchpoints */ + if (WARN_ON(decode_watchpoint(INVALID_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write))) return false; - } + if (WARN_ON(decode_watchpoint(CONSUMED_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + + /* Check decoding watchpoint returns same data */ + if (WARN_ON(!decode_watchpoint(encoded_watchpoint, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + if (WARN_ON(verif_masked_addr != (addr & WATCHPOINT_ADDR_MASK))) + goto fail; + if (WARN_ON(verif_size != size)) + goto fail; + if (WARN_ON(is_write != verif_is_write)) + goto fail; + + continue; +fail: + pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n", + __func__, is_write ? "write" : "read", size, addr, encoded_watchpoint, + verif_is_write ? "write" : "read", verif_size, verif_masked_addr); + return false; } return true; } /* Test access matching function. */ -static bool test_matching_access(void) +static bool __init test_matching_access(void) { if (WARN_ON(!matching_access(10, 1, 10, 1))) return false; diff --git a/kernel/kthread.c b/kernel/kthread.c index 4a4d7092a2d8..7113003fab63 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -433,7 +433,7 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its - * argument. @threadfn() can either call do_exit() directly if it is a + * argument. @threadfn() can either return directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero diff --git a/kernel/pid.c b/kernel/pid.c index efe87db44683..2fc0a16ec77b 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -540,6 +540,42 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) } /** + * pidfd_get_task() - Get the task associated with a pidfd + * + * @pidfd: pidfd for which to get the task + * @flags: flags associated with this pidfd + * + * Return the task associated with @pidfd. The function takes a reference on + * the returned task. The caller is responsible for releasing that reference. + * + * Currently, the process identified by @pidfd is always a thread-group leader. + * This restriction currently exists for all aspects of pidfds including pidfd + * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling + * (only supports thread group leaders). + * + * Return: On success, the task_struct associated with the pidfd. + * On error, a negative errno number will be returned. + */ +struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) +{ + unsigned int f_flags; + struct pid *pid; + struct task_struct *task; + + pid = pidfd_get_pid(pidfd, &f_flags); + if (IS_ERR(pid)) + return ERR_CAST(pid); + + task = get_pid_task(pid, PIDTYPE_TGID); + put_pid(pid); + if (!task) + return ERR_PTR(-ESRCH); + + *flags = f_flags; + return task; +} + +/** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference diff --git a/kernel/reboot.c b/kernel/reboot.c index f7440c0c7e43..6bcc5d6a6572 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -33,6 +33,7 @@ EXPORT_SYMBOL(cad_pid); #define DEFAULT_REBOOT_MODE #endif enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; +EXPORT_SYMBOL_GPL(reboot_mode); enum reboot_mode panic_reboot_mode = REBOOT_UNDEFINED; /* @@ -359,7 +360,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, case LINUX_REBOOT_CMD_HALT: kernel_halt(); do_exit(0); - panic("cannot halt"); case LINUX_REBOOT_CMD_POWER_OFF: kernel_power_off(); diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 48ac72696012..517f72b008f5 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -135,6 +135,10 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, if (!static_branch_likely(&sched_smt_present)) return -ENODEV; + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD != PIDTYPE_PID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD_GROUP != PIDTYPE_TGID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_PROCESS_GROUP != PIDTYPE_PGID); + if (type > PIDTYPE_PGID || cmd >= PR_SCHED_CORE_MAX || pid < 0 || (cmd != PR_SCHED_CORE_GET && uaddr)) return -EINVAL; diff --git a/kernel/signal.c b/kernel/signal.c index 6f3476dc7873..7c4b7ae714d4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1323,6 +1323,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool blocked = sigismember(&t->blocked, sig); if (blocked || ignored || sigdfl) { action->sa.sa_handler = SIG_DFL; + action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) { sigdelset(&t->blocked, sig); recalc_sigpending_and_wake(t); @@ -1649,6 +1650,19 @@ void force_sig(int sig) } EXPORT_SYMBOL(force_sig); +void force_fatal_sig(int sig) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info_to_task(&info, current, true); +} + /* * When things go south during signal handling, we * will force a SIGSEGV. And if the signal that caused @@ -1657,15 +1671,10 @@ EXPORT_SYMBOL(force_sig); */ void force_sigsegv(int sig) { - struct task_struct *p = current; - - if (sig == SIGSEGV) { - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL; - spin_unlock_irqrestore(&p->sighand->siglock, flags); - } - force_sig(SIGSEGV); + if (sig == SIGSEGV) + force_fatal_sig(SIGSEGV); + else + force_sig(SIGSEGV); } int force_sig_fault_to_task(int sig, int code, void __user *addr @@ -2704,7 +2713,8 @@ relock: if (!signr) break; /* will return 0 */ - if (unlikely(current->ptrace) && signr != SIGKILL) { + if (unlikely(current->ptrace) && (signr != SIGKILL) && + !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { signr = ptrace_signal(signr, &ksig->info); if (!signr) continue; @@ -4054,6 +4064,10 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) k = &p->sighand->action[sig-1]; spin_lock_irq(&p->sighand->siglock); + if (k->sa.sa_flags & SA_IMMUTABLE) { + spin_unlock_irq(&p->sighand->siglock); + return -EINVAL; + } if (oact) *oact = *k; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 007a3ded0358..30bc880c3849 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5602,10 +5602,11 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) } } + mutex_unlock(&ftrace_lock); + /* Removing the tmp_ops will add the updated direct callers to the functions */ unregister_ftrace_function(&tmp_ops); - mutex_unlock(&ftrace_lock); out_direct: mutex_unlock(&direct_mutex); return err; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f6520d0a4c8c..2699e9e562b1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5228,6 +5228,9 @@ void ring_buffer_reset(struct trace_buffer *buffer) struct ring_buffer_per_cpu *cpu_buffer; int cpu; + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; @@ -5246,6 +5249,8 @@ void ring_buffer_reset(struct trace_buffer *buffer) atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); } + + mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_reset); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0abc9a413b4d..8a10046c775f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1953,9 +1953,10 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field->type) goto free; - if (field->filter_type == FILTER_STATIC_STRING) + if (field->filter_type == FILTER_STATIC_STRING) { hist_field->fn = hist_field_string; - else if (field->filter_type == FILTER_DYN_STRING) + hist_field->size = field->size; + } else if (field->filter_type == FILTER_DYN_STRING) hist_field->fn = hist_field_dynstring; else hist_field->fn = hist_field_pstring; @@ -2580,7 +2581,8 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, operand1_str = str; str = sep+1; - if (!operand1_str || !str) + /* Binary operator requires both operands */ + if (*operand1_str == '\0' || *str == '\0') goto free; operand_flags = 0; @@ -3025,7 +3027,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, char *str = elt_data->field_var_str[j++]; char *val_str = (char *)(uintptr_t)var_val; - strscpy(str, val_str, STR_VAR_LEN_MAX); + strscpy(str, val_str, val->size); var_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, var_val); @@ -4920,7 +4922,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, str = elt_data->field_var_str[idx]; val_str = (char *)(uintptr_t)hist_val; - strscpy(str, val_str, STR_VAR_LEN_MAX); + strscpy(str, val_str, hist_field->size); hist_val = (u64)(uintptr_t)str; } diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 3e4a1651e329..7520d43aed55 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -55,7 +55,8 @@ struct osnoise_instance { struct list_head list; struct trace_array *tr; }; -struct list_head osnoise_instances; + +static struct list_head osnoise_instances; static bool osnoise_has_registered_instances(void) { diff --git a/lib/test_hmm.c b/lib/test_hmm.c index c259842f6d44..e2ce8f9b7605 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -613,8 +613,7 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, */ rpage->zone_device_data = dmirror; - *dst = migrate_pfn(page_to_pfn(dpage)) | - MIGRATE_PFN_LOCKED; + *dst = migrate_pfn(page_to_pfn(dpage)); if ((*src & MIGRATE_PFN_WRITE) || (!spage && args->vma->vm_flags & VM_WRITE)) *dst |= MIGRATE_PFN_WRITE; @@ -1137,7 +1136,7 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args, lock_page(dpage); xa_erase(&dmirror->pt, addr >> PAGE_SHIFT); copy_highpage(dpage, spage); - *dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + *dst = migrate_pfn(page_to_pfn(dpage)); if (*src & MIGRATE_PFN_WRITE) *dst |= MIGRATE_PFN_WRITE; } diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index dc892119e88f..7355cb534e4f 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -106,6 +106,16 @@ static int __init early_kasan_flag_stacktrace(char *arg) } early_param("kasan.stacktrace", early_kasan_flag_stacktrace); +static inline const char *kasan_mode_info(void) +{ + if (kasan_mode == KASAN_MODE_ASYNC) + return "async"; + else if (kasan_mode == KASAN_MODE_ASYMM) + return "asymm"; + else + return "sync"; +} + /* kasan_init_hw_tags_cpu() is called for each CPU. */ void kasan_init_hw_tags_cpu(void) { @@ -177,7 +187,9 @@ void __init kasan_init_hw_tags(void) break; } - pr_info("KernelAddressSanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized (hw-tags, mode=%s, stacktrace=%s)\n", + kasan_mode_info(), + kasan_stack_collection_enabled() ? "on" : "off"); } void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags) diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c index bd3f540feb47..77f13f391b57 100644 --- a/mm/kasan/sw_tags.c +++ b/mm/kasan/sw_tags.c @@ -42,7 +42,7 @@ void __init kasan_init_sw_tags(void) for_each_possible_cpu(cpu) per_cpu(prng_state, cpu) = (u32)get_cycles(); - pr_info("KernelAddressSanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized (sw-tags)\n"); } /* diff --git a/mm/madvise.c b/mm/madvise.c index 0734db8d53a7..8c927202bbe6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1235,7 +1235,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, struct iovec iovstack[UIO_FASTIOV], iovec; struct iovec *iov = iovstack; struct iov_iter iter; - struct pid *pid; struct task_struct *task; struct mm_struct *mm; size_t total_len; @@ -1250,18 +1249,12 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, if (ret < 0) goto out; - pid = pidfd_get_pid(pidfd, &f_flags); - if (IS_ERR(pid)) { - ret = PTR_ERR(pid); + task = pidfd_get_task(pidfd, &f_flags); + if (IS_ERR(task)) { + ret = PTR_ERR(task); goto free_iov; } - task = get_pid_task(pid, PIDTYPE_PID); - if (!task) { - ret = -ESRCH; - goto put_pid; - } - if (!process_madvise_behavior_valid(behavior)) { ret = -EINVAL; goto release_task; @@ -1301,8 +1294,6 @@ release_mm: mmput(mm); release_task: put_task_struct(task); -put_pid: - put_pid(pid); free_iov: kfree(iov); out: diff --git a/mm/memblock.c b/mm/memblock.c index 659bf0ffb086..1018e50566f3 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -287,7 +287,7 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || - end == MEMBLOCK_ALLOC_KASAN) + end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ @@ -1387,8 +1387,11 @@ again: return 0; done: - /* Skip kmemleak for kasan_init() due to high volume. */ - if (end != MEMBLOCK_ALLOC_KASAN) + /* + * Skip kmemleak for those places like kasan_init() and + * early_pgtable_alloc() due to high volume. + */ + if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * The min_count is set to 0 so that memblock allocated * blocks are never reported as leaks. This is because many diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 508bcea7df56..781605e92015 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2058,13 +2058,11 @@ again: memcg->move_lock_task = current; memcg->move_lock_flags = flags; } -EXPORT_SYMBOL(folio_memcg_lock); void lock_page_memcg(struct page *page) { folio_memcg_lock(page_folio(page)); } -EXPORT_SYMBOL(lock_page_memcg); static void __folio_memcg_unlock(struct mem_cgroup *memcg) { @@ -2092,13 +2090,11 @@ void folio_memcg_unlock(struct folio *folio) { __folio_memcg_unlock(folio_memcg(folio)); } -EXPORT_SYMBOL(folio_memcg_unlock); void unlock_page_memcg(struct page *page) { folio_memcg_unlock(page_folio(page)); } -EXPORT_SYMBOL(unlock_page_memcg); struct obj_stock { #ifdef CONFIG_MEMCG_KMEM diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f64ebb6226cb..07c875fdeaf0 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -58,7 +58,6 @@ #include <linux/ratelimit.h> #include <linux/page-isolation.h> #include <linux/pagewalk.h> -#include <linux/shmem_fs.h> #include "internal.h" #include "ras/ras_event.h" @@ -868,7 +867,6 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) { int ret; struct address_space *mapping; - bool extra_pins; delete_from_lru_cache(p); @@ -898,23 +896,17 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) } /* - * The shmem page is kept in page cache instead of truncating - * so is expected to have an extra refcount after error-handling. - */ - extra_pins = shmem_mapping(mapping); - - /* * Truncation is a bit tricky. Enable it per file system for now. * * Open: to take i_rwsem or not for this? Right now we don't. */ ret = truncate_error_page(p, page_to_pfn(p), mapping); - if (has_extra_refcount(ps, p, extra_pins)) - ret = MF_FAILED; - out: unlock_page(p); + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index a11e948593df..cf25b00f03c8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -404,12 +404,6 @@ int folio_migrate_mapping(struct address_space *mapping, newzone = folio_zone(newfolio); xas_lock_irq(&xas); - if (folio_ref_count(folio) != expected_count || - xas_load(&xas) != folio) { - xas_unlock_irq(&xas); - return -EAGAIN; - } - if (!folio_ref_freeze(folio, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; @@ -2368,7 +2362,6 @@ again: * can't be dropped from it). */ get_page(page); - migrate->cpages++; /* * Optimize for the common case where page is only mapped once @@ -2378,7 +2371,7 @@ again: if (trylock_page(page)) { pte_t swp_pte; - mpfn |= MIGRATE_PFN_LOCKED; + migrate->cpages++; ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ @@ -2412,6 +2405,9 @@ again: if (pte_present(pte)) unmapped++; + } else { + put_page(page); + mpfn = 0; } next: @@ -2516,15 +2512,17 @@ static bool migrate_vma_check_page(struct page *page) } /* - * migrate_vma_prepare() - lock pages and isolate them from the lru + * migrate_vma_unmap() - replace page mapping with special migration pte entry * @migrate: migrate struct containing all migration information * - * This locks pages that have been collected by migrate_vma_collect(). Once each - * page is locked it is isolated from the lru (for non-device pages). Finally, - * the ref taken by migrate_vma_collect() is dropped, as locked pages cannot be - * migrated by concurrent kernel threads. + * Isolate pages from the LRU and replace mappings (CPU page table pte) with a + * special migration pte entry and check if it has been pinned. Pinned pages are + * restored because we cannot migrate them. + * + * This is the last step before we call the device driver callback to allocate + * destination memory and copy contents of original page over to new page. */ -static void migrate_vma_prepare(struct migrate_vma *migrate) +static void migrate_vma_unmap(struct migrate_vma *migrate) { const unsigned long npages = migrate->npages; const unsigned long start = migrate->start; @@ -2533,32 +2531,12 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) lru_add_drain(); - for (i = 0; (i < npages) && migrate->cpages; i++) { + for (i = 0; i < npages; i++) { struct page *page = migrate_pfn_to_page(migrate->src[i]); - bool remap = true; if (!page) continue; - if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) { - /* - * Because we are migrating several pages there can be - * a deadlock between 2 concurrent migration where each - * are waiting on each other page lock. - * - * Make migrate_vma() a best effort thing and backoff - * for any page we can not lock right away. - */ - if (!trylock_page(page)) { - migrate->src[i] = 0; - migrate->cpages--; - put_page(page); - continue; - } - remap = false; - migrate->src[i] |= MIGRATE_PFN_LOCKED; - } - /* ZONE_DEVICE pages are not on LRU */ if (!is_zone_device_page(page)) { if (!PageLRU(page) && allow_drain) { @@ -2568,16 +2546,9 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) } if (isolate_lru_page(page)) { - if (remap) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; - } else { - migrate->src[i] = 0; - unlock_page(page); - migrate->cpages--; - put_page(page); - } + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; continue; } @@ -2585,80 +2556,20 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) put_page(page); } - if (!migrate_vma_check_page(page)) { - if (remap) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; - - if (!is_zone_device_page(page)) { - get_page(page); - putback_lru_page(page); - } - } else { - migrate->src[i] = 0; - unlock_page(page); - migrate->cpages--; + if (page_mapped(page)) + try_to_migrate(page, 0); - if (!is_zone_device_page(page)) - putback_lru_page(page); - else - put_page(page); + if (page_mapped(page) || !migrate_vma_check_page(page)) { + if (!is_zone_device_page(page)) { + get_page(page); + putback_lru_page(page); } - } - } - - for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); - - if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) - continue; - - remove_migration_pte(page, migrate->vma, addr, page); - - migrate->src[i] = 0; - unlock_page(page); - put_page(page); - restore--; - } -} - -/* - * migrate_vma_unmap() - replace page mapping with special migration pte entry - * @migrate: migrate struct containing all migration information - * - * Replace page mapping (CPU page table pte) with a special migration pte entry - * and check again if it has been pinned. Pinned pages are restored because we - * cannot migrate them. - * - * This is the last step before we call the device driver callback to allocate - * destination memory and copy contents of original page over to new page. - */ -static void migrate_vma_unmap(struct migrate_vma *migrate) -{ - const unsigned long npages = migrate->npages; - const unsigned long start = migrate->start; - unsigned long addr, i, restore = 0; - - for (i = 0; i < npages; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); - if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE)) + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; continue; - - if (page_mapped(page)) { - try_to_migrate(page, 0); - if (page_mapped(page)) - goto restore; } - - if (migrate_vma_check_page(page)) - continue; - -restore: - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; } for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) { @@ -2671,12 +2582,8 @@ restore: migrate->src[i] = 0; unlock_page(page); + put_page(page); restore--; - - if (is_zone_device_page(page)) - put_page(page); - else - putback_lru_page(page); } } @@ -2699,8 +2606,8 @@ restore: * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE * flag set). Once these are allocated and copied, the caller must update each * corresponding entry in the dst array with the pfn value of the destination - * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set - * (destination pages must have their struct pages locked, via lock_page()). + * page and with MIGRATE_PFN_VALID. Destination pages must be locked via + * lock_page(). * * Note that the caller does not have to migrate all the pages that are marked * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from @@ -2770,8 +2677,6 @@ int migrate_vma_setup(struct migrate_vma *args) migrate_vma_collect(args); if (args->cpages) - migrate_vma_prepare(args); - if (args->cpages) migrate_vma_unmap(args); /* diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 195b3661da3d..1ddabefcfb5a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -1150,21 +1150,14 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) struct task_struct *p; unsigned int f_flags; bool reap = false; - struct pid *pid; long ret = 0; if (flags) return -EINVAL; - pid = pidfd_get_pid(pidfd, &f_flags); - if (IS_ERR(pid)) - return PTR_ERR(pid); - - task = get_pid_task(pid, PIDTYPE_TGID); - if (!task) { - ret = -ESRCH; - goto put_pid; - } + task = pidfd_get_task(pidfd, &f_flags); + if (IS_ERR(task)) + return PTR_ERR(task); /* * Make sure to choose a thread which still has a reference to mm @@ -1204,8 +1197,6 @@ drop_mm: mmput(mm); put_task: put_task_struct(task); -put_pid: - put_pid(pid); return ret; #else return -ENOSYS; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2d498bb62248..a613f8ef6a02 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2967,7 +2967,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); */ void folio_wait_stable(struct folio *folio) { - if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) + if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); diff --git a/mm/page_owner.c b/mm/page_owner.c index 79936db59859..4f924957ce7a 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -125,7 +125,7 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags) return handle; } -void __reset_page_owner(struct page *page, unsigned int order) +void __reset_page_owner(struct page *page, unsigned short order) { int i; struct page_ext *page_ext; @@ -149,7 +149,7 @@ void __reset_page_owner(struct page *page, unsigned int order) static inline void __set_page_owner_handle(struct page_ext *page_ext, depot_stack_handle_t handle, - unsigned int order, gfp_t gfp_mask) + unsigned short order, gfp_t gfp_mask) { struct page_owner *page_owner; int i; @@ -169,7 +169,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext, } } -noinline void __set_page_owner(struct page *page, unsigned int order, +noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext = lookup_page_ext(page); diff --git a/mm/shmem.c b/mm/shmem.c index 23c91a8beb78..dc038ce78700 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2456,7 +2456,6 @@ shmem_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; - int ret = 0; /* i_rwsem is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | @@ -2467,15 +2466,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, return -EPERM; } - ret = shmem_getpage(inode, index, pagep, SGP_WRITE); - - if (*pagep && PageHWPoison(*pagep)) { - unlock_page(*pagep); - put_page(*pagep); - ret = -EIO; - } - - return ret; + return shmem_getpage(inode, index, pagep, SGP_WRITE); } static int @@ -2562,12 +2553,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (sgp == SGP_CACHE) set_page_dirty(page); unlock_page(page); - - if (PageHWPoison(page)) { - put_page(page); - error = -EIO; - break; - } } /* @@ -2960,28 +2945,6 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) return shmem_unlink(dir, dentry); } -static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) -{ - bool old_is_dir = d_is_dir(old_dentry); - bool new_is_dir = d_is_dir(new_dentry); - - if (old_dir != new_dir && old_is_dir != new_is_dir) { - if (old_is_dir) { - drop_nlink(old_dir); - inc_nlink(new_dir); - } else { - drop_nlink(new_dir); - inc_nlink(old_dir); - } - } - old_dir->i_ctime = old_dir->i_mtime = - new_dir->i_ctime = new_dir->i_mtime = - d_inode(old_dentry)->i_ctime = - d_inode(new_dentry)->i_ctime = current_time(old_dir); - - return 0; -} - static int shmem_whiteout(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry) { @@ -3027,7 +2990,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns, return -EINVAL; if (flags & RENAME_EXCHANGE) - return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry); + return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; @@ -3129,8 +3092,7 @@ static const char *shmem_get_link(struct dentry *dentry, page = find_get_page(inode->i_mapping, 0); if (!page) return ERR_PTR(-ECHILD); - if (PageHWPoison(page) || - !PageUptodate(page)) { + if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } @@ -3138,11 +3100,6 @@ static const char *shmem_get_link(struct dentry *dentry, error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); - if (page && PageHWPoison(page)) { - unlock_page(page); - put_page(page); - return ERR_PTR(-ECHILD); - } unlock_page(page); } set_delayed_call(done, shmem_put_link, page); @@ -3793,13 +3750,6 @@ static void shmem_destroy_inodecache(void) kmem_cache_destroy(shmem_inode_cachep); } -/* Keep the page in page cache instead of truncating it */ -static int shmem_error_remove_page(struct address_space *mapping, - struct page *page) -{ - return 0; -} - const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, @@ -3810,7 +3760,7 @@ const struct address_space_operations shmem_aops = { #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif - .error_remove_page = shmem_error_remove_page, + .error_remove_page = generic_error_remove_page, }; EXPORT_SYMBOL(shmem_aops); @@ -4221,10 +4171,6 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, page = ERR_PTR(error); else unlock_page(page); - - if (PageHWPoison(page)) - page = ERR_PTR(-EIO); - return page; #else /* diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0780c2a57ff1..ac6f036298cd 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -232,11 +232,6 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, goto out; } - if (PageHWPoison(page)) { - ret = -EIO; - goto out_release; - } - ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, page, false, wp_copy); if (ret) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 55275ef9a31a..a3a0a5e994f5 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -123,9 +123,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) } vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); - - /* Get rid of the vlan's reference to real_dev */ - dev_put(real_dev); } int vlan_check_real_dev(struct net_device *real_dev, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 90330b893134..ab6dee28536d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -843,6 +843,9 @@ static void vlan_dev_free(struct net_device *dev) free_percpu(vlan->vlan_pcpu_stats); vlan->vlan_pcpu_stats = NULL; + + /* Get rid of the vlan's reference to real_dev */ + dev_put(vlan->real_dev); } void vlan_setup(struct net_device *dev) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index fbcb15c7c29b..93730d30af54 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -890,7 +890,7 @@ out: batadv_tp_vars_put(tp_vars); - do_exit(0); + return 0; } /** diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 9bc55ecb37f9..8452b0fbb78c 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -75,6 +75,13 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) skcb->addr.pgn = (cf->can_id >> 8) & J1939_PGN_MAX; /* set default message type */ skcb->addr.type = J1939_TP; + + if (!j1939_address_is_valid(skcb->addr.sa)) { + netdev_err_once(priv->ndev, "%s: sa is broadcast address, ignoring!\n", + __func__); + goto done; + } + if (j1939_pgn_is_pdu1(skcb->addr.pgn)) { /* Type 1: with destination address */ skcb->addr.da = skcb->addr.pgn; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 6c0a0ebdd024..a271688780a2 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -2023,6 +2023,11 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) extd = J1939_ETP; fallthrough; case J1939_TP_CMD_BAM: + if (cmd == J1939_TP_CMD_BAM && !j1939_cb_is_broadcast(skcb)) { + netdev_err_once(priv->ndev, "%s: BAM to unicast (%02x), ignoring!\n", + __func__, skcb->addr.sa); + return; + } fallthrough; case J1939_TP_CMD_RTS: if (skcb->addr.type != extd) @@ -2085,6 +2090,12 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) break; case J1939_ETP_CMD_ABORT: /* && J1939_TP_CMD_ABORT */ + if (j1939_cb_is_broadcast(skcb)) { + netdev_err_once(priv->ndev, "%s: abort to broadcast (%02x), ignoring!\n", + __func__, skcb->addr.sa); + return; + } + if (j1939_tp_im_transmitter(skcb)) j1939_xtp_rx_abort(priv, skb, true); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 013cbdb6cfe2..6a6898ee4049 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1153,12 +1153,11 @@ static int build_initial_monmap(struct ceph_mon_client *monc) int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) { - int err = 0; + int err; dout("init\n"); memset(monc, 0, sizeof(*monc)); monc->client = cl; - monc->monmap = NULL; mutex_init(&monc->mutex); err = build_initial_monmap(monc); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index ff8624a7c964..1c5815530e0d 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5310,14 +5310,14 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) ceph_msgpool_destroy(&osdc->msgpool_op_reply); } -static int osd_req_op_copy_from_init(struct ceph_osd_request *req, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags) +int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u32 dst_fadvise_flags, + u32 truncate_seq, u64 truncate_size, + u8 copy_from_flags) { struct ceph_osd_req_op *op; struct page **pages; @@ -5346,49 +5346,7 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req, op->indata_len, 0, false, true); return 0; } - -int ceph_osdc_copy_from(struct ceph_osd_client *osdc, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - struct ceph_object_id *dst_oid, - struct ceph_object_locator *dst_oloc, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags) -{ - struct ceph_osd_request *req; - int ret; - - req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); - if (!req) - return -ENOMEM; - - req->r_flags = CEPH_OSD_FLAG_WRITE; - - ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); - ceph_oid_copy(&req->r_t.base_oid, dst_oid); - - ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid, - src_oloc, src_fadvise_flags, - dst_fadvise_flags, truncate_seq, - truncate_size, copy_from_flags); - if (ret) - goto out; - - ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); - if (ret) - goto out; - - ceph_osdc_start_request(osdc, req, false); - ret = ceph_osdc_wait_request(osdc, req); - -out: - ceph_osdc_put_request(req); - return ret; -} -EXPORT_SYMBOL(ceph_osdc_copy_from); +EXPORT_SYMBOL(osd_req_op_copy_from_init); int __init ceph_osdc_setup(void) { diff --git a/net/core/datagram.c b/net/core/datagram.c index 15ab9ffb27fe..ee290776c661 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -646,7 +646,8 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { sk_wmem_queued_add(sk, truesize); - sk_mem_charge(sk, truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/core/dev.c b/net/core/dev.c index edeb811c454e..15ac064b5562 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6928,7 +6928,7 @@ void napi_disable(struct napi_struct *n) might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - do { + for ( ; ; ) { val = READ_ONCE(n->state); if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); @@ -6937,7 +6937,10 @@ void napi_disable(struct napi_struct *n) new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); - } while (cmpxchg(&n->state, val, new) != val); + + if (cmpxchg(&n->state, val, new) == val) + break; + } hrtimer_cancel(&n->timer); diff --git a/net/core/devlink.c b/net/core/devlink.c index 6b5ee862429e..5ba4f9434acd 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -66,7 +66,7 @@ struct devlink { u8 reload_failed:1; refcount_t refcount; struct completion comp; - char priv[0] __aligned(NETDEV_ALIGN); + char priv[] __aligned(NETDEV_ALIGN); }; void *devlink_priv(struct devlink *devlink) diff --git a/net/core/filter.c b/net/core/filter.c index 8e8d3b49c297..e471c9b09670 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -9756,22 +9756,46 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, struct bpf_insn *insn) { - /* si->dst_reg = skb->data */ + int reg; + int temp_reg_off = offsetof(struct sk_buff, cb) + + offsetof(struct sk_skb_cb, temp_reg); + + if (si->src_reg == si->dst_reg) { + /* We need an extra register, choose and save a register. */ + reg = BPF_REG_9; + if (si->src_reg == reg || si->dst_reg == reg) + reg--; + if (si->src_reg == reg || si->dst_reg == reg) + reg--; + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off); + } else { + reg = si->dst_reg; + } + + /* reg = skb->data */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), - si->dst_reg, si->src_reg, + reg, si->src_reg, offsetof(struct sk_buff, data)); /* AX = skb->len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, len)); - /* si->dst_reg = skb->data + skb->len */ - *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + /* reg = skb->data + skb->len */ + *insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX); /* AX = skb->data_len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, data_len)); - /* si->dst_reg = skb->data + skb->len - skb->data_len */ - *insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX); + + /* reg = skb->data + skb->len - skb->data_len */ + *insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX); + + if (si->src_reg == si->dst_reg) { + /* Restore the saved register */ + *insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg); + *insn++ = BPF_MOV64_REG(si->dst_reg, reg); + *insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off); + } return insn; } @@ -9782,11 +9806,33 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; + int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): insn = bpf_convert_data_end_access(si, insn); break; + case offsetof(struct __sk_buff, cb[0]) ... + offsetofend(struct __sk_buff, cb[4]) - 1: + BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); + BUILD_BUG_ON((offsetof(struct sk_buff, cb) + + offsetof(struct sk_skb_cb, data)) % + sizeof(__u64)); + + prog->cb_access = 1; + off = si->off; + off -= offsetof(struct __sk_buff, cb[0]); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct sk_skb_cb, data); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); + else + *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); + break; + + default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); @@ -10423,8 +10469,10 @@ BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ - if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED)) - return -ESOCKTNOSUPPORT; /* reject connected sockets */ + if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) + return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ + if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) + return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 67a9188d8a49..ba2f38246f07 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3433,8 +3433,9 @@ static inline void skb_split_no_header(struct sk_buff *skb, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; - skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); @@ -3449,19 +3450,7 @@ EXPORT_SYMBOL(skb_split); */ static int skb_prepare_for_shift(struct sk_buff *skb) { - int ret = 0; - - if (skb_cloned(skb)) { - /* Save and restore truesize: pskb_expand_head() may reallocate - * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we - * cannot change truesize at this point. - */ - unsigned int save_truesize = skb->truesize; - - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - skb->truesize = save_truesize; - } - return ret; + return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** diff --git a/net/core/sock.c b/net/core/sock.c index 9862eefce21e..8f2b2f2c0e7b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -976,7 +976,7 @@ static int sock_reserve_memory(struct sock *sk, int bytes) bool charged; int pages; - if (!mem_cgroup_sockets_enabled || !sk->sk_memcg) + if (!mem_cgroup_sockets_enabled || !sk->sk_memcg || !sk_has_account(sk)) return -EOPNOTSUPP; if (!bytes) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index e252b8ec2b85..f39ef79ced67 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -511,12 +511,6 @@ static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } -static bool sk_is_tcp(const struct sock *sk) -{ - return sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP; -} - static bool sock_map_redirect_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index cd60b94fc175..de1c849a0a70 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -101,6 +101,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct dsa_port *dp; u8 *extraction; u16 vlan_tpid; + u64 rew_val; /* Revert skb->data by the amount consumed by the DSA master, * so it points to the beginning of the frame. @@ -130,6 +131,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, ocelot_xfh_get_qos_class(extraction, &qos_class); ocelot_xfh_get_tag_type(extraction, &tag_type); ocelot_xfh_get_vlan_tci(extraction, &vlan_tci); + ocelot_xfh_get_rew_val(extraction, &rew_val); skb->dev = dsa_master_find_slave(netdev, 0, src_port); if (!skb->dev) @@ -143,6 +145,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, dsa_default_offload_fwd_mark(skb); skb->priority = qos_class; + OCELOT_SKB_CB(skb)->tstamp_lo = rew_val; /* Ocelot switches copy frames unmodified to the CPU. However, it is * possible for the user to request a VLAN modification through diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 9009f412151e..ee1e5806bc93 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -56,8 +56,7 @@ static int pause_reply_size(const struct ethnl_req_info *req_base, if (req_base->flags & ETHTOOL_FLAG_STATS) n += nla_total_size(0) + /* _PAUSE_STATS */ - nla_total_size_64bit(sizeof(u64)) * - (ETHTOOL_A_PAUSE_STAT_MAX - 2); + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3c6498dab6bd..b7796b4cf0a0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -862,6 +862,7 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, if (likely(skb)) { bool mem_scheduled; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); @@ -1318,6 +1319,15 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); + /* skb changing from pure zc to mixed, must charge zc */ + if (unlikely(skb_zcopy_pure(skb))) { + if (!sk_wmem_schedule(sk, skb->data_len)) + goto wait_for_space; + + sk_mem_charge(sk, skb->data_len); + skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; + } + if (!sk_wmem_schedule(sk, copy)) goto wait_for_space; @@ -1338,8 +1348,16 @@ new_segment: } pfrag->offset += copy; } else { - if (!sk_wmem_schedule(sk, copy)) - goto wait_for_space; + /* First append to a fragless skb builds initial + * pure zerocopy skb + */ + if (!skb->len) + skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; + + if (!skb_zcopy_pure(skb)) { + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; + } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5f4d6f45d87f..f70aa0932bd6 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -172,6 +172,41 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, return ret; } +static int tcp_bpf_recvmsg_parser(struct sock *sk, + struct msghdr *msg, + size_t len, + int nonblock, + int flags, + int *addr_len) +{ + struct sk_psock *psock; + int copied; + + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + + psock = sk_psock_get(sk); + if (unlikely(!psock)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + + lock_sock(sk); +msg_bytes_ready: + copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + if (!copied) { + long timeo; + int data; + + timeo = sock_rcvtimeo(sk, nonblock); + data = tcp_msg_wait_data(sk, psock, timeo); + if (data && !sk_psock_queue_empty(psock)) + goto msg_bytes_ready; + copied = -EAGAIN; + } + release_sock(sk); + sk_psock_put(sk, psock); + return copied; +} + static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -464,6 +499,8 @@ enum { enum { TCP_BPF_BASE, TCP_BPF_TX, + TCP_BPF_RX, + TCP_BPF_TXRX, TCP_BPF_NUM_CFGS, }; @@ -475,7 +512,6 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], struct proto *base) { prot[TCP_BPF_BASE] = *base; - prot[TCP_BPF_BASE].unhash = sock_map_unhash; prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable; @@ -483,6 +519,12 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage; + + prot[TCP_BPF_RX] = prot[TCP_BPF_BASE]; + prot[TCP_BPF_RX].recvmsg = tcp_bpf_recvmsg_parser; + + prot[TCP_BPF_TXRX] = prot[TCP_BPF_TX]; + prot[TCP_BPF_TXRX].recvmsg = tcp_bpf_recvmsg_parser; } static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops) @@ -520,6 +562,10 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; + if (psock->progs.stream_verdict || psock->progs.skb_verdict) { + config = (config == TCP_BPF_TX) ? TCP_BPF_TXRX : TCP_BPF_RX; + } + if (restore) { if (inet_csk_has_ulp(sk)) { /* TLS does not have an unhash proto in SW cases, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6fbbf1558033..2e6e5a70168e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -408,13 +408,13 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) return tp->snd_una != tp->snd_up; } -#define OPTION_SACK_ADVERTISE (1 << 0) -#define OPTION_TS (1 << 1) -#define OPTION_MD5 (1 << 2) -#define OPTION_WSCALE (1 << 3) -#define OPTION_FAST_OPEN_COOKIE (1 << 8) -#define OPTION_SMC (1 << 9) -#define OPTION_MPTCP (1 << 10) +#define OPTION_SACK_ADVERTISE BIT(0) +#define OPTION_TS BIT(1) +#define OPTION_MD5 BIT(2) +#define OPTION_WSCALE BIT(3) +#define OPTION_FAST_OPEN_COOKIE BIT(8) +#define OPTION_SMC BIT(9) +#define OPTION_MPTCP BIT(10) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -1559,7 +1559,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; } - if (skb_unclone(skb, gfp)) + if (skb_unclone_keeptruesize(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -1667,7 +1667,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { u32 delta_truesize; - if (skb_unclone(skb, GFP_ATOMIC)) + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; delta_truesize = __pskb_trim_head(skb, len); @@ -1677,7 +1677,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); - sk_mem_uncharge(sk, delta_truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, delta_truesize); } /* Any change of skb->len requires recalculation of tso factor. */ @@ -2295,7 +2296,9 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) + if (unlikely(TCP_SKB_CB(skb)->eor) || + tcp_has_tx_tstamp(skb) || + !skb_pure_zcopy_same(skb, next)) return false; len -= skb->len; @@ -3166,7 +3169,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { - if (skb_unclone(skb, GFP_ATOMIC)) + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; diff = tcp_skb_pcount(skb); diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 5daa1c3ed83b..a8b5784afb1a 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -378,7 +378,7 @@ static int __net_init seg6_net_init(struct net *net) kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; - }; + } #endif return 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2cc9b0e53ad1..551fce49841d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1263,7 +1263,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); - newinet = inet_sk(newsk); newnp = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 12c12619ee35..e43b31d25fb6 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -700,9 +700,9 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) ret = encap_rcv(sk, skb); if (ret <= 0) { - __UDP_INC_STATS(sock_net(sk), - UDP_MIB_INDATAGRAMS, - is_udplite); + __UDP6_INC_STATS(sock_net(sk), + UDP_MIB_INDATAGRAMS, + is_udplite); return -ret; } } diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index d344b02a1cde..871cf6266125 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -33,6 +33,19 @@ static int mctp_release(struct socket *sock) return 0; } +/* Generic sockaddr checks, padding checks only so far */ +static bool mctp_sockaddr_is_ok(const struct sockaddr_mctp *addr) +{ + return !addr->__smctp_pad0 && !addr->__smctp_pad1; +} + +static bool mctp_sockaddr_ext_is_ok(const struct sockaddr_mctp_ext *addr) +{ + return !addr->__smctp_pad0[0] && + !addr->__smctp_pad0[1] && + !addr->__smctp_pad0[2]; +} + static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { struct sock *sk = sock->sk; @@ -52,6 +65,9 @@ static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen) /* it's a valid sockaddr for MCTP, cast and do protocol checks */ smctp = (struct sockaddr_mctp *)addr; + if (!mctp_sockaddr_is_ok(smctp)) + return -EINVAL; + lock_sock(sk); /* TODO: allow rebind */ @@ -87,6 +103,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) return -EINVAL; if (addr->smctp_family != AF_MCTP) return -EINVAL; + if (!mctp_sockaddr_is_ok(addr)) + return -EINVAL; if (addr->smctp_tag & ~(MCTP_TAG_MASK | MCTP_TAG_OWNER)) return -EINVAL; @@ -124,7 +142,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); - if (extaddr->smctp_halen > sizeof(cb->haddr)) { + if (!mctp_sockaddr_ext_is_ok(extaddr) || + extaddr->smctp_halen > sizeof(cb->haddr)) { rc = -EINVAL; goto err_free; } @@ -198,11 +217,13 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, addr = msg->msg_name; addr->smctp_family = AF_MCTP; + addr->__smctp_pad0 = 0; addr->smctp_network = cb->net; addr->smctp_addr.s_addr = hdr->src; addr->smctp_type = type; addr->smctp_tag = hdr->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); + addr->__smctp_pad1 = 0; msg->msg_namelen = sizeof(*addr); if (msk->addr_ext) { @@ -211,6 +232,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(*ae); ae->smctp_ifindex = cb->ifindex; ae->smctp_halen = cb->halen; + memset(ae->__smctp_pad0, 0x0, sizeof(ae->__smctp_pad0)); memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr)); memcpy(ae->smctp_haddr, cb->haddr, cb->halen); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 816f74dadfa3..39c523bd775c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -47,6 +47,8 @@ #include <net/ip_vs.h> +MODULE_ALIAS_GENL_FAMILY(IPVS_GENL_NAME); + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ static DEFINE_MUTEX(__ip_vs_mutex); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4c3fbaaeb103..4acc4b8e9fe5 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -560,7 +560,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, goto nla_put_failure; if (indev && entskb->dev && - entskb->mac_header != entskb->network_header) { + skb_mac_header_was_set(entskb)) { struct nfqnl_msg_packet_hw phw; int len; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 49089c50872e..334f63c9529e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1664,31 +1664,37 @@ static const struct genl_ops nfc_genl_ops[] = { .cmd = NFC_CMD_DEV_UP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dev_up, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEV_DOWN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dev_down, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_START_POLL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_start_poll, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_STOP_POLL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_stop_poll, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEP_LINK_UP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dep_link_up, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEP_LINK_DOWN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dep_link_down, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_GET_TARGET, @@ -1706,26 +1712,31 @@ static const struct genl_ops nfc_genl_ops[] = { .cmd = NFC_CMD_LLC_SET_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_set_params, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_LLC_SDREQ, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_sdreq, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_FW_DOWNLOAD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_fw_download, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_ENABLE_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_enable_se, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DISABLE_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_disable_se, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_GET_SE, @@ -1737,21 +1748,25 @@ static const struct genl_ops nfc_genl_ops[] = { .cmd = NFC_CMD_SE_IO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_se_io, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_ACTIVATE_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_activate_target, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_VENDOR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_vendor_cmd, + .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEACTIVATE_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_deactivate_target, + .flags = GENL_ADMIN_PERM, }, }; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 9ab068fa2672..377f896bdedc 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -95,18 +95,22 @@ static ktime_t sched_base_time(const struct sched_gate_list *sched) return ns_to_ktime(sched->base_time); } -static ktime_t taprio_get_time(struct taprio_sched *q) +static ktime_t taprio_mono_to_any(const struct taprio_sched *q, ktime_t mono) { - ktime_t mono = ktime_get(); + /* This pairs with WRITE_ONCE() in taprio_parse_clockid() */ + enum tk_offsets tk_offset = READ_ONCE(q->tk_offset); - switch (q->tk_offset) { + switch (tk_offset) { case TK_OFFS_MAX: return mono; default: - return ktime_mono_to_any(mono, q->tk_offset); + return ktime_mono_to_any(mono, tk_offset); } +} - return KTIME_MAX; +static ktime_t taprio_get_time(const struct taprio_sched *q) +{ + return taprio_mono_to_any(q, ktime_get()); } static void taprio_free_sched_cb(struct rcu_head *head) @@ -319,7 +323,7 @@ static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) return 0; } - return ktime_mono_to_any(skb->skb_mstamp_ns, q->tk_offset); + return taprio_mono_to_any(q, skb->skb_mstamp_ns); } /* There are a few scenarios where we will have to modify the txtime from @@ -1352,6 +1356,7 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, } } else if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { int clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + enum tk_offsets tk_offset; /* We only support static clockids and we don't allow * for it to be modified after the first init. @@ -1366,22 +1371,24 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, switch (clockid) { case CLOCK_REALTIME: - q->tk_offset = TK_OFFS_REAL; + tk_offset = TK_OFFS_REAL; break; case CLOCK_MONOTONIC: - q->tk_offset = TK_OFFS_MAX; + tk_offset = TK_OFFS_MAX; break; case CLOCK_BOOTTIME: - q->tk_offset = TK_OFFS_BOOT; + tk_offset = TK_OFFS_BOOT; break; case CLOCK_TAI: - q->tk_offset = TK_OFFS_TAI; + tk_offset = TK_OFFS_TAI; break; default: NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); err = -EINVAL; goto out; } + /* This pairs with READ_ONCE() in taprio_mono_to_any */ + WRITE_ONCE(q->tk_offset, tk_offset); q->clockid = clockid; } else { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index fb3da4d8f4a3..354c1c4de19b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -326,11 +326,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, struct sctp_packet *packet; int len; - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. @@ -415,6 +410,12 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (!new_asoc) goto nomem; + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + if (sctp_assoc_set_bind_addr_from_ep(new_asoc, sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) @@ -780,6 +781,10 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, } } + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } /* Delay state machine commands until later. * @@ -1517,11 +1522,6 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( struct sctp_packet *packet; int len; - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. @@ -1594,6 +1594,12 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( if (!new_asoc) goto nomem; + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + if (sctp_assoc_set_bind_addr_from_ep(new_asoc, sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) goto nomem; @@ -2255,8 +2261,7 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } /* Update socket peer label if first association. */ - if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } @@ -4893,9 +4898,6 @@ static enum sctp_disposition sctp_sf_violation_chunk( { static const char err_str[] = "The following chunk violates protocol:"; - if (!asoc) - return sctp_sf_violation(net, ep, asoc, type, arg, commands); - return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, sizeof(err_str)); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6b937bfd4751..33391254fa82 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9412,7 +9412,6 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; struct sctp_sock *sp = sctp_sk(sk); - struct sctp_endpoint *ep = sp->ep; newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; @@ -9457,9 +9456,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, net_enable_timestamp(); /* Set newsk security attributes from original sk and connection - * security attribute from ep. + * security attribute from asoc. */ - security_sctp_sk_clone(ep, sk, newsk); + security_sctp_sk_clone(asoc, sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0cf7ed2f5d41..59284da9116d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -149,14 +149,18 @@ static int __smc_release(struct smc_sock *smc) sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } else { - if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) - sock_put(sk); /* passive closing */ - if (sk->sk_state == SMC_LISTEN) { - /* wake up clcsock accept */ - rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + if (sk->sk_state != SMC_CLOSED) { + if (sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ + if (sk->sk_state == SMC_LISTEN) { + /* wake up clcsock accept */ + rc = kernel_sock_shutdown(smc->clcsock, + SHUT_RDWR); + } + sk->sk_state = SMC_CLOSED; + sk->sk_state_change(sk); } - sk->sk_state = SMC_CLOSED; - sk->sk_state_change(sk); smc_restore_fallback_changes(smc); } diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h index b4c36795a928..ec17f29646f5 100644 --- a/net/smc/smc_tracepoint.h +++ b/net/smc/smc_tracepoint.h @@ -99,7 +99,7 @@ TRACE_EVENT(smcr_link_down, __entry->location = location; ), - TP_printk("lnk=%p lgr=%p state=%d dev=%s location=%p", + TP_printk("lnk=%p lgr=%p state=%d dev=%s location=%pS", __entry->lnk, __entry->lgr, __entry->state, __get_str(name), __entry->location) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 9c0343568d2a..1a72c67afed5 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -27,18 +27,10 @@ static struct workqueue_struct *strp_wq; -struct _strp_msg { - /* Internal cb structure. struct strp_msg must be first for passing - * to upper layer. - */ - struct strp_msg strp; - int accum_len; -}; - static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) { return (struct _strp_msg *)((void *)skb->cb + - offsetof(struct qdisc_skb_cb, data)); + offsetof(struct sk_skb_cb, strp)); } /* Lower lock held */ diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index 6e4dbd577a39..d435bffc6199 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -162,8 +162,10 @@ static int rpc_parse_scope_id(struct net *net, const char *buf, const size_t buflen, const char *delim, struct sockaddr_in6 *sin6) { - char *p; + char p[IPV6_SCOPE_ID_LEN + 1]; size_t len; + u32 scope_id = 0; + struct net_device *dev; if ((buf + buflen) == delim) return 1; @@ -175,29 +177,23 @@ static int rpc_parse_scope_id(struct net *net, const char *buf, return 0; len = (buf + buflen) - delim - 1; - p = kmemdup_nul(delim + 1, len, GFP_KERNEL); - if (p) { - u32 scope_id = 0; - struct net_device *dev; - - dev = dev_get_by_name(net, p); - if (dev != NULL) { - scope_id = dev->ifindex; - dev_put(dev); - } else { - if (kstrtou32(p, 10, &scope_id) != 0) { - kfree(p); - return 0; - } - } - - kfree(p); - - sin6->sin6_scope_id = scope_id; - return 1; + if (len > IPV6_SCOPE_ID_LEN) + return 0; + + memcpy(p, delim + 1, len); + p[len] = 0; + + dev = dev_get_by_name(net, p); + if (dev != NULL) { + scope_id = dev->ifindex; + dev_put(dev); + } else { + if (kstrtou32(p, 10, &scope_id) != 0) + return 0; } - return 0; + sin6->sin6_scope_id = scope_id; + return 1; } static size_t rpc_pton6(struct net *net, const char *buf, const size_t buflen, diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 1f2817195549..b87565b64928 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -781,7 +781,7 @@ gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq) svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS); xdr_seq = kmalloc(4, GFP_KERNEL); if (!xdr_seq) - return -1; + return -ENOMEM; *xdr_seq = htonl(seq); iov.iov_base = xdr_seq; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f056ff931444..a312ea2bc440 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1076,24 +1076,21 @@ void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) static void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) { - - if (clnt != NULL) { - rpc_task_set_transport(task, clnt); - task->tk_client = clnt; - refcount_inc(&clnt->cl_count); - if (clnt->cl_softrtry) - task->tk_flags |= RPC_TASK_SOFT; - if (clnt->cl_softerr) - task->tk_flags |= RPC_TASK_TIMEOUT; - if (clnt->cl_noretranstimeo) - task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; - if (atomic_read(&clnt->cl_swapper)) - task->tk_flags |= RPC_TASK_SWAPPER; - /* Add to the client's list of all tasks */ - spin_lock(&clnt->cl_lock); - list_add_tail(&task->tk_task, &clnt->cl_tasks); - spin_unlock(&clnt->cl_lock); - } + rpc_task_set_transport(task, clnt); + task->tk_client = clnt; + refcount_inc(&clnt->cl_count); + if (clnt->cl_softrtry) + task->tk_flags |= RPC_TASK_SOFT; + if (clnt->cl_softerr) + task->tk_flags |= RPC_TASK_TIMEOUT; + if (clnt->cl_noretranstimeo) + task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; + if (atomic_read(&clnt->cl_swapper)) + task->tk_flags |= RPC_TASK_SWAPPER; + /* Add to the client's list of all tasks */ + spin_lock(&clnt->cl_lock); + list_add_tail(&task->tk_task, &clnt->cl_tasks); + spin_unlock(&clnt->cl_lock); } static void diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c045f63d11fa..e2c835482791 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -277,9 +277,17 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static void rpc_task_set_debuginfo(struct rpc_task *task) { - static atomic_t rpc_pid; + struct rpc_clnt *clnt = task->tk_client; - task->tk_pid = atomic_inc_return(&rpc_pid); + /* Might be a task carrying a reverse-direction operation */ + if (!clnt) { + static atomic_t rpc_pid; + + task->tk_pid = atomic_inc_return(&rpc_pid); + return; + } + + task->tk_pid = atomic_inc_return(&clnt->cl_pid); } #else static inline void rpc_task_set_debuginfo(struct rpc_task *task) @@ -829,6 +837,7 @@ void rpc_exit_task(struct rpc_task *task) else if (task->tk_client) rpc_count_iostats(task, task->tk_client->cl_metrics); if (task->tk_ops->rpc_call_done != NULL) { + trace_rpc_task_call_done(task, task->tk_ops->rpc_call_done); task->tk_ops->rpc_call_done(task, task->tk_calldata); if (task->tk_action != NULL) { /* Always release the RPC slot and buffer memory */ @@ -903,8 +912,10 @@ static void __rpc_execute(struct rpc_task *task) /* * Lockless check for whether task is sleeping or not. */ - if (!RPC_IS_QUEUED(task)) + if (!RPC_IS_QUEUED(task)) { + cond_resched(); continue; + } /* * Signalled tasks should exit rather than sleep. @@ -1230,8 +1241,7 @@ static int rpciod_start(void) if (!wq) goto out_failed; rpciod_workqueue = wq; - /* Note: highpri because network receive is latency sensitive */ - wq = alloc_workqueue("xprtiod", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_HIGHPRI, 0); + wq = alloc_workqueue("xprtiod", WQ_UNBOUND | WQ_MEM_RECLAIM, 0); if (!wq) goto free_rpciod; xprtiod_workqueue = wq; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index a3bbe5ce4570..4292278a9552 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1186,45 +1186,6 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif -static int -svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp) -{ - struct kvec *argv = &rqstp->rq_arg.head[0]; - struct kvec *resv = &rqstp->rq_res.head[0]; - const struct svc_procedure *procp = rqstp->rq_procinfo; - - /* - * Decode arguments - * XXX: why do we ignore the return value? - */ - if (procp->pc_decode && - !procp->pc_decode(rqstp, argv->iov_base)) { - *statp = rpc_garbage_args; - return 1; - } - - *statp = procp->pc_func(rqstp); - - if (*statp == rpc_drop_reply || - test_bit(RQ_DROPME, &rqstp->rq_flags)) - return 0; - - if (rqstp->rq_auth_stat != rpc_auth_ok) - return 1; - - if (*statp != rpc_success) - return 1; - - /* Encode reply */ - if (procp->pc_encode && - !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) { - dprintk("svc: failed to encode reply\n"); - /* serv->sv_stats->rpcsystemerr++; */ - *statp = rpc_system_err; - } - return 1; -} - __be32 svc_generic_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, @@ -1291,7 +1252,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) __be32 *statp; u32 prog, vers; __be32 rpc_stat; - int auth_res; + int auth_res, rc; __be32 *reply_statp; rpc_stat = rpc_success; @@ -1392,28 +1353,18 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) svc_reserve_auth(rqstp, procp->pc_xdrressize<<2); /* Call the function that processes the request. */ - if (!process.dispatch) { - if (!svc_generic_dispatch(rqstp, statp)) - goto release_dropit; - if (*statp == rpc_garbage_args) - goto err_garbage; - } else { - dprintk("svc: calling dispatcher\n"); - if (!process.dispatch(rqstp, statp)) - goto release_dropit; /* Release reply info */ - } - + rc = process.dispatch(rqstp, statp); + if (procp->pc_release) + procp->pc_release(rqstp); + if (!rc) + goto dropit; if (rqstp->rq_auth_stat != rpc_auth_ok) - goto err_release_bad_auth; + goto err_bad_auth; /* Check RPC status result */ if (*statp != rpc_success) resv->iov_len = ((void*)statp) - resv->iov_base + 4; - /* Release reply info */ - if (procp->pc_release) - procp->pc_release(rqstp); - if (procp->pc_encode == NULL) goto dropit; @@ -1422,9 +1373,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto close_xprt; return 1; /* Caller can now send it */ -release_dropit: - if (procp->pc_release) - procp->pc_release(rqstp); dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ dprintk("svc: svc_process dropit\n"); @@ -1451,9 +1399,6 @@ err_bad_rpc: svc_putnl(resv, 2); goto sendit; -err_release_bad_auth: - if (procp->pc_release) - procp->pc_release(rqstp); err_bad_auth: dprintk("svc: authentication failed (%d)\n", be32_to_cpu(rqstp->rq_auth_stat)); @@ -1676,16 +1621,17 @@ EXPORT_SYMBOL_GPL(svc_encode_result_payload); /** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on - * @pages: list of pages containing data payload - * @first: buffer containing first section of write payload - * @total: total number of bytes of write payload + * @payload: xdr_buf containing only the write data payload * * Fills in rqstp::rq_vec, and returns the number of elements. */ -unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages, - struct kvec *first, size_t total) +unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, + struct xdr_buf *payload) { + struct page **pages = payload->pages; + struct kvec *first = payload->head; struct kvec *vec = rqstp->rq_vec; + size_t total = payload->len; unsigned int i; /* Some types of transport can present the write payload diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 6316bd2b8f37..1e99ba1b9d72 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -687,6 +687,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) set_current_state(TASK_RUNNING); return -EINTR; } + trace_svc_alloc_arg_err(pages); schedule_timeout(msecs_to_jiffies(500)); } rqstp->rq_page_end = &rqstp->rq_pages[pages]; diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 9a6f17e18f73..2766dd21935b 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -109,8 +109,10 @@ static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj, struct sock_xprt *sock; ssize_t ret = -1; - if (!xprt) - return 0; + if (!xprt || !xprt_connected(xprt)) { + xprt_put(xprt); + return -ENOTCONN; + } sock = container_of(xprt, struct sock_xprt, xprt); if (kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) @@ -129,8 +131,10 @@ static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj, struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj); ssize_t ret; - if (!xprt) - return 0; + if (!xprt || !xprt_connected(xprt)) { + xprt_put(xprt); + return -ENOTCONN; + } ret = sprintf(buf, "last_used=%lu\ncur_cong=%lu\ncong_win=%lu\n" "max_num_slots=%u\nmin_num_slots=%u\nnum_reqs=%u\n" diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index ca10ba2626f2..df194cc07035 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1633,7 +1633,7 @@ EXPORT_SYMBOL_GPL(xdr_buf_subsegment); * Sets up @subbuf to represent a portion of @xdr. The portion * starts at the current offset in @xdr, and extends for a length * of @nbytes. If this is successful, @xdr is advanced to the next - * position following that portion. + * XDR data item following that portion. * * Return values: * %true: @subbuf has been initialized, and @xdr has been advanced. @@ -1642,29 +1642,31 @@ EXPORT_SYMBOL_GPL(xdr_buf_subsegment); bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf, unsigned int nbytes) { - unsigned int remaining, offset, len; + unsigned int start = xdr_stream_pos(xdr); + unsigned int remaining, len; - if (xdr_buf_subsegment(xdr->buf, subbuf, xdr_stream_pos(xdr), nbytes)) + /* Extract @subbuf and bounds-check the fn arguments */ + if (xdr_buf_subsegment(xdr->buf, subbuf, start, nbytes)) return false; - if (subbuf->head[0].iov_len) - if (!__xdr_inline_decode(xdr, subbuf->head[0].iov_len)) - return false; - - remaining = subbuf->page_len; - offset = subbuf->page_base; - while (remaining) { - len = min_t(unsigned int, remaining, PAGE_SIZE) - offset; - + /* Advance @xdr by @nbytes */ + for (remaining = nbytes; remaining;) { if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr)) return false; - if (!__xdr_inline_decode(xdr, len)) - return false; + len = (char *)xdr->end - (char *)xdr->p; + if (remaining <= len) { + xdr->p = (__be32 *)((char *)xdr->p + + (remaining + xdr_pad_size(nbytes))); + break; + } + + xdr->p = (__be32 *)((char *)xdr->p + len); + xdr->end = xdr->p; remaining -= len; - offset = 0; } + xdr_stream_set_pos(xdr, start + nbytes); return true; } EXPORT_SYMBOL_GPL(xdr_stream_subsegment); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index cfd681700d1a..a02de2bddb28 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -246,11 +246,9 @@ EXPORT_SYMBOL_GPL(xprt_find_transport_ident); static void xprt_clear_locked(struct rpc_xprt *xprt) { xprt->snd_task = NULL; - if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - smp_mb__before_atomic(); - clear_bit(XPRT_LOCKED, &xprt->state); - smp_mb__after_atomic(); - } else + if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) + clear_bit_unlock(XPRT_LOCKED, &xprt->state); + else queue_work(xprtiod_workqueue, &xprt->task_cleanup); } @@ -737,6 +735,8 @@ static void xprt_autoclose(struct work_struct *work) unsigned int pflags = memalloc_nofs_save(); trace_xprt_disconnect_auto(xprt); + xprt->connect_cookie++; + smp_mb__before_atomic(); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); xprt->ops->close(xprt); xprt_release_write(xprt, NULL); @@ -767,7 +767,8 @@ EXPORT_SYMBOL_GPL(xprt_disconnect_done); */ static void xprt_schedule_autoclose_locked(struct rpc_xprt *xprt) { - set_bit(XPRT_CLOSE_WAIT, &xprt->state); + if (test_and_set_bit(XPRT_CLOSE_WAIT, &xprt->state)) + return; if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(xprtiod_workqueue, &xprt->task_cleanup); else if (xprt->snd_task && !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) @@ -1603,15 +1604,14 @@ xprt_transmit(struct rpc_task *task) { struct rpc_rqst *next, *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - int counter, status; + int status; spin_lock(&xprt->queue_lock); - counter = 0; - while (!list_empty(&xprt->xmit_queue)) { - if (++counter == 20) + for (;;) { + next = list_first_entry_or_null(&xprt->xmit_queue, + struct rpc_rqst, rq_xmit); + if (!next) break; - next = list_first_entry(&xprt->xmit_queue, - struct rpc_rqst, rq_xmit); xprt_pin_rqst(next); spin_unlock(&xprt->queue_lock); status = xprt_request_transmit(next, task); @@ -1619,13 +1619,16 @@ xprt_transmit(struct rpc_task *task) status = 0; spin_lock(&xprt->queue_lock); xprt_unpin_rqst(next); - if (status == 0) { - if (!xprt_request_data_received(task) || - test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) - continue; - } else if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) - task->tk_status = status; - break; + if (status < 0) { + if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) + task->tk_status = status; + break; + } + /* Was @task transmitted, and has it received a reply? */ + if (xprt_request_data_received(task) && + !test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) + break; + cond_resched_lock(&xprt->queue_lock); } spin_unlock(&xprt->queue_lock); } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f700b34a5bfd..ff699307e820 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -515,8 +515,8 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * a single ib_post_send() call. */ prev = &first; - while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { - + mr = rpcrdma_mr_pop(&req->rl_registered); + do { trace_xprtrdma_mr_localinv(mr); r_xprt->rx_stats.local_inv_needed++; @@ -533,7 +533,8 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) *prev = last; prev = &last->next; - } + } while ((mr = rpcrdma_mr_pop(&req->rl_registered))); + mr = container_of(last, struct rpcrdma_mr, mr_invwr); /* Strong send queue ordering guarantees that when the @@ -617,8 +618,8 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * a single ib_post_send() call. */ prev = &first; - while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { - + mr = rpcrdma_mr_pop(&req->rl_registered); + do { trace_xprtrdma_mr_localinv(mr); r_xprt->rx_stats.local_inv_needed++; @@ -635,7 +636,7 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) *prev = last; prev = &last->next; - } + } while ((mr = rpcrdma_mr_pop(&req->rl_registered))); /* Strong send queue ordering guarantees that when the * last WR in the chain completes, all WRs in the chain @@ -666,3 +667,38 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ rpcrdma_force_disconnect(ep); } + +/** + * frwr_wp_create - Create an MR for padding Write chunks + * @r_xprt: transport resources to use + * + * Return 0 on success, negative errno on failure. + */ +int frwr_wp_create(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_ep *ep = r_xprt->rx_ep; + struct rpcrdma_mr_seg seg; + struct rpcrdma_mr *mr; + + mr = rpcrdma_mr_get(r_xprt); + if (!mr) + return -EAGAIN; + mr->mr_req = NULL; + ep->re_write_pad_mr = mr; + + seg.mr_len = XDR_UNIT; + seg.mr_page = virt_to_page(ep->re_write_pad); + seg.mr_offset = offset_in_page(ep->re_write_pad); + if (IS_ERR(frwr_map(r_xprt, &seg, 1, true, xdr_zero, mr))) + return -EIO; + trace_xprtrdma_mr_fastreg(mr); + + mr->mr_cqe.done = frwr_wc_fastreg; + mr->mr_regwr.wr.next = NULL; + mr->mr_regwr.wr.wr_cqe = &mr->mr_cqe; + mr->mr_regwr.wr.num_sge = 0; + mr->mr_regwr.wr.opcode = IB_WR_REG_MR; + mr->mr_regwr.wr.send_flags = 0; + + return ib_post_send(ep->re_id->qp, &mr->mr_regwr.wr, NULL); +} diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index c335c1361564..8035a983c8ce 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -255,15 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = 0; } - if (type == rpcrdma_readch) - goto out; - - /* When encoding a Write chunk, some servers need to see an - * extra segment for non-XDR-aligned Write chunks. The upper - * layer provides space in the tail iovec that may be used - * for this purpose. - */ - if (type == rpcrdma_writech && r_xprt->rx_ep->re_implicit_roundup) + if (type == rpcrdma_readch || type == rpcrdma_writech) goto out; if (xdrbuf->tail[0].iov_len) @@ -405,6 +397,7 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, enum rpcrdma_chunktype wtype) { struct xdr_stream *xdr = &req->rl_stream; + struct rpcrdma_ep *ep = r_xprt->rx_ep; struct rpcrdma_mr_seg *seg; struct rpcrdma_mr *mr; int nsegs, nchunks; @@ -443,6 +436,18 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, nsegs -= mr->mr_nents; } while (nsegs); + if (xdr_pad_size(rqst->rq_rcv_buf.page_len)) { + if (encode_rdma_segment(xdr, ep->re_write_pad_mr) < 0) + return -EMSGSIZE; + + trace_xprtrdma_chunk_wp(rqst->rq_task, ep->re_write_pad_mr, + nsegs); + r_xprt->rx_stats.write_chunk_count++; + r_xprt->rx_stats.total_rdma_request += mr->mr_length; + nchunks++; + nsegs -= mr->mr_nents; + } + /* Update count of segments in this Write chunk */ *segcount = cpu_to_be32(nchunks); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 6be23ce7a93d..cf76a6ad127b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -330,9 +330,9 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) /* WARNING: Only wc->wr_cqe and wc->status are reliable */ ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe); - trace_svcrdma_wc_receive(wc, &ctxt->rc_cid); if (wc->status != IB_WC_SUCCESS) goto flushed; + trace_svcrdma_wc_recv(wc, &ctxt->rc_cid); /* If receive posting fails, the connection is about to be * lost anyway. The server will not be able to send a reply @@ -345,7 +345,7 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) */ if (rdma->sc_pending_recvs < rdma->sc_max_requests) if (!svc_rdma_refresh_recvs(rdma, rdma->sc_recv_batch, false)) - goto flushed; + goto dropped; /* All wc fields are now known to be valid */ ctxt->rc_byte_len = wc->byte_len; @@ -360,6 +360,11 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) return; flushed: + if (wc->status == IB_WC_WR_FLUSH_ERR) + trace_svcrdma_wc_recv_flush(wc, &ctxt->rc_cid); + else + trace_svcrdma_wc_recv_err(wc, &ctxt->rc_cid); +dropped: svc_rdma_recv_ctxt_put(rdma, ctxt); svc_xprt_deferred_close(&rdma->sc_xprt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index e27433f08ca7..5f0155fdefc7 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -155,6 +155,7 @@ struct svc_rdma_chunk_ctxt { struct ib_cqe cc_cqe; struct svcxprt_rdma *cc_rdma; struct list_head cc_rwctxts; + ktime_t cc_posttime; int cc_sqecount; enum ib_wc_status cc_status; struct completion cc_done; @@ -267,7 +268,16 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) struct svc_rdma_write_info *info = container_of(cc, struct svc_rdma_write_info, wi_cc); - trace_svcrdma_wc_write(wc, &cc->cc_cid); + switch (wc->status) { + case IB_WC_SUCCESS: + trace_svcrdma_wc_write(wc, &cc->cc_cid); + break; + case IB_WC_WR_FLUSH_ERR: + trace_svcrdma_wc_write_flush(wc, &cc->cc_cid); + break; + default: + trace_svcrdma_wc_write_err(wc, &cc->cc_cid); + } svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); @@ -320,11 +330,22 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_chunk_ctxt *cc = container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe); - struct svcxprt_rdma *rdma = cc->cc_rdma; + struct svc_rdma_read_info *info; - trace_svcrdma_wc_read(wc, &cc->cc_cid); + switch (wc->status) { + case IB_WC_SUCCESS: + info = container_of(cc, struct svc_rdma_read_info, ri_cc); + trace_svcrdma_wc_read(wc, &cc->cc_cid, info->ri_totalbytes, + cc->cc_posttime); + break; + case IB_WC_WR_FLUSH_ERR: + trace_svcrdma_wc_read_flush(wc, &cc->cc_cid); + break; + default: + trace_svcrdma_wc_read_err(wc, &cc->cc_cid); + } - svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); + svc_rdma_wake_send_waiters(cc->cc_rdma, cc->cc_sqecount); cc->cc_status = wc->status; complete(&cc->cc_done); return; @@ -363,6 +384,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) do { if (atomic_sub_return(cc->cc_sqecount, &rdma->sc_sq_avail) > 0) { + cc->cc_posttime = ktime_get(); ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr); if (ret) break; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 599021b2391d..22a871e6fe4d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -280,13 +280,21 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) struct svc_rdma_send_ctxt *ctxt = container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe); - trace_svcrdma_wc_send(wc, &ctxt->sc_cid); - svc_rdma_wake_send_waiters(rdma, 1); complete(&ctxt->sc_done); if (unlikely(wc->status != IB_WC_SUCCESS)) - svc_xprt_deferred_close(&rdma->sc_xprt); + goto flushed; + + trace_svcrdma_wc_send(wc, &ctxt->sc_cid); + return; + +flushed: + if (wc->status != IB_WC_WR_FLUSH_ERR) + trace_svcrdma_wc_send_err(wc, &ctxt->sc_cid); + else + trace_svcrdma_wc_send_flush(wc, &ctxt->sc_cid); + svc_xprt_deferred_close(&rdma->sc_xprt); } /** diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index aaec3c9be8db..3d3673ba9e1e 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -205,14 +205,12 @@ static void rpcrdma_update_cm_private(struct rpcrdma_ep *ep, unsigned int rsize, wsize; /* Default settings for RPC-over-RDMA Version One */ - ep->re_implicit_roundup = xprt_rdma_pad_optimize; rsize = RPCRDMA_V1_DEF_INLINE_SIZE; wsize = RPCRDMA_V1_DEF_INLINE_SIZE; if (pmsg && pmsg->cp_magic == rpcrdma_cmp_magic && pmsg->cp_version == RPCRDMA_CMP_VERSION) { - ep->re_implicit_roundup = true; rsize = rpcrdma_decode_buffer_size(pmsg->cp_send_size); wsize = rpcrdma_decode_buffer_size(pmsg->cp_recv_size); } @@ -551,6 +549,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt) goto out; } rpcrdma_mrs_create(r_xprt); + frwr_wp_create(r_xprt); out: trace_xprtrdma_connect(r_xprt, rc); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index d91f54eae00b..c79f92eeda76 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -68,13 +68,14 @@ /* * RDMA Endpoint -- connection endpoint details */ +struct rpcrdma_mr; struct rpcrdma_ep { struct kref re_kref; struct rdma_cm_id *re_id; struct ib_pd *re_pd; unsigned int re_max_rdma_segs; unsigned int re_max_fr_depth; - bool re_implicit_roundup; + struct rpcrdma_mr *re_write_pad_mr; enum ib_mr_type re_mrtype; struct completion re_done; unsigned int re_send_count; @@ -97,6 +98,8 @@ struct rpcrdma_ep { unsigned int re_inline_recv; /* negotiated */ atomic_t re_completion_ids; + + char re_write_pad[XDR_UNIT]; }; /* Pre-allocate extra Work Requests for handling reverse-direction @@ -535,6 +538,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs); void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); +int frwr_wp_create(struct rpcrdma_xprt *r_xprt); /* * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 04f1b78bcbca..ae48c9c84ee1 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1134,6 +1134,7 @@ static void xs_run_error_worker(struct sock_xprt *transport, unsigned int nr) static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { + xprt->connect_cookie++; smp_mb__before_atomic(); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); @@ -1153,14 +1154,13 @@ static void xs_error_report(struct sock *sk) struct sock_xprt *transport; struct rpc_xprt *xprt; - read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) - goto out; + return; transport = container_of(xprt, struct sock_xprt, xprt); transport->xprt_err = -sk->sk_err; if (transport->xprt_err == 0) - goto out; + return; dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -transport->xprt_err); trace_rpc_socket_error(xprt, sk->sk_socket, transport->xprt_err); @@ -1168,8 +1168,6 @@ static void xs_error_report(struct sock *sk) /* barrier ensures xprt_err is set before XPRT_SOCK_WAKE_ERROR */ smp_mb__before_atomic(); xs_run_error_worker(transport, XPRT_SOCK_WAKE_ERROR); - out: - read_unlock_bh(&sk->sk_callback_lock); } static void xs_reset_transport(struct sock_xprt *transport) @@ -1188,7 +1186,7 @@ static void xs_reset_transport(struct sock_xprt *transport) kernel_sock_shutdown(sock, SHUT_RDWR); mutex_lock(&transport->recv_mutex); - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); transport->inet = NULL; transport->sock = NULL; transport->file = NULL; @@ -1197,10 +1195,10 @@ static void xs_reset_transport(struct sock_xprt *transport) xs_restore_old_callbacks(transport, sk); xprt_clear_connected(xprt); - write_unlock_bh(&sk->sk_callback_lock); xs_sock_reset_connection_flags(xprt); /* Reset stream record info */ xs_stream_reset_connect(transport); + release_sock(sk); mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); @@ -1364,7 +1362,6 @@ static void xs_data_ready(struct sock *sk) { struct rpc_xprt *xprt; - read_lock_bh(&sk->sk_callback_lock); dprintk("RPC: xs_data_ready...\n"); xprt = xprt_from_sock(sk); if (xprt != NULL) { @@ -1379,7 +1376,6 @@ static void xs_data_ready(struct sock *sk) if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) queue_work(xprtiod_workqueue, &transport->recv_worker); } - read_unlock_bh(&sk->sk_callback_lock); } /* @@ -1408,9 +1404,8 @@ static void xs_tcp_state_change(struct sock *sk) struct rpc_xprt *xprt; struct sock_xprt *transport; - read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) - goto out; + return; dprintk("RPC: xs_tcp_state_change client %p...\n", xprt); dprintk("RPC: state %x conn %d dead %d zapped %d sk_shutdown %d\n", sk->sk_state, xprt_connected(xprt), @@ -1471,8 +1466,6 @@ static void xs_tcp_state_change(struct sock *sk) /* Trigger the socket release */ xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); } - out: - read_unlock_bh(&sk->sk_callback_lock); } static void xs_write_space(struct sock *sk) @@ -1511,13 +1504,9 @@ out: */ static void xs_udp_write_space(struct sock *sk) { - read_lock_bh(&sk->sk_callback_lock); - /* from net/core/sock.c:sock_def_write_space */ if (sock_writeable(sk)) xs_write_space(sk); - - read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1532,13 +1521,9 @@ static void xs_udp_write_space(struct sock *sk) */ static void xs_tcp_write_space(struct sock *sk) { - read_lock_bh(&sk->sk_callback_lock); - /* from net/core/stream.c:sk_stream_write_space */ if (sk_stream_is_writeable(sk)) xs_write_space(sk); - - read_unlock_bh(&sk->sk_callback_lock); } static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt) @@ -1833,7 +1818,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, if (!transport->inet) { struct sock *sk = sock->sk; - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); xs_save_old_callbacks(transport, sk); @@ -1849,7 +1834,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, transport->sock = sock; transport->inet = sk; - write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); } xs_stream_start_connect(transport); @@ -2031,7 +2016,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) if (!transport->inet) { struct sock *sk = sock->sk; - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); xs_save_old_callbacks(transport, sk); @@ -2048,7 +2033,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) xs_set_memalloc(xprt); - write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); } xs_udp_do_set_buffer_size(xprt); @@ -2174,7 +2159,6 @@ static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt, static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - int ret = -ENOTCONN; if (!transport->inet) { struct sock *sk = sock->sk; @@ -2194,7 +2178,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) xs_tcp_set_socket_timeouts(xprt, sock); tcp_sock_set_nodelay(sk); - write_lock_bh(&sk->sk_callback_lock); + lock_sock(sk); xs_save_old_callbacks(transport, sk); @@ -2214,11 +2198,11 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->sock = sock; transport->inet = sk; - write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); } if (!xprt_bound(xprt)) - goto out; + return -ENOTCONN; xs_set_memalloc(xprt); @@ -2226,22 +2210,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* Tell the socket layer to start connecting... */ set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); - ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); - switch (ret) { - case 0: - xs_set_srcport(transport, sock); - fallthrough; - case -EINPROGRESS: - /* SYN_SENT! */ - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - break; - case -EADDRNOTAVAIL: - /* Source port number is unavailable. Try a new one! */ - transport->srcport = 0; - } -out: - return ret; + return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); } /** @@ -2256,14 +2225,14 @@ static void xs_tcp_setup_socket(struct work_struct *work) container_of(work, struct sock_xprt, connect_worker.work); struct socket *sock = transport->sock; struct rpc_xprt *xprt = &transport->xprt; - int status = -EIO; + int status; if (!sock) { sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP, true); if (IS_ERR(sock)) { - status = PTR_ERR(sock); + xprt_wake_pending_tasks(xprt, PTR_ERR(sock)); goto out; } } @@ -2280,21 +2249,21 @@ static void xs_tcp_setup_socket(struct work_struct *work) xprt, -status, xprt_connected(xprt), sock->sk->sk_state); switch (status) { - default: - printk("%s: connect returned unhandled error %d\n", - __func__, status); - fallthrough; - case -EADDRNOTAVAIL: - /* We're probably in TIME_WAIT. Get rid of existing socket, - * and retry - */ - xs_tcp_force_close(xprt); - break; case 0: + xs_set_srcport(transport, sock); + fallthrough; case -EINPROGRESS: + /* SYN_SENT! */ + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + fallthrough; case -EALREADY: - xprt_unlock_connect(xprt, transport); - return; + goto out_unlock; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; + status = -EAGAIN; + break; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. @@ -2306,18 +2275,22 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: - /* xs_tcp_force_close() wakes tasks with a fixed error code. - * We need to wake them first to ensure the correct error code. - */ - xprt_wake_pending_tasks(xprt, status); - xs_tcp_force_close(xprt); - goto out; + break; + default: + printk("%s: connect returned unhandled error %d\n", + __func__, status); + status = -EAGAIN; } - status = -EAGAIN; + + /* xs_tcp_force_close() wakes tasks with a fixed error code. + * We need to wake them first to ensure the correct error code. + */ + xprt_wake_pending_tasks(xprt, status); + xs_tcp_force_close(xprt); out: xprt_clear_connecting(xprt); +out_unlock: xprt_unlock_connect(xprt, transport); - xprt_wake_pending_tasks(xprt, status); } /** @@ -2341,7 +2314,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); - if (transport->sock != NULL) { + if (transport->sock != NULL && !xprt_connecting(xprt)) { dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", xprt, xprt->reestablish_timeout / HZ); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7d851eb3a683..ed0df839c38c 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1322,6 +1322,8 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, * non-blocking call. */ err = -EALREADY; + if (flags & O_NONBLOCK) + goto out; break; default: if ((sk->sk_state == TCP_LISTEN) || diff --git a/scripts/coccinelle/misc/do_div.cocci b/scripts/coccinelle/misc/do_div.cocci new file mode 100644 index 000000000000..79db083c5208 --- /dev/null +++ b/scripts/coccinelle/misc/do_div.cocci @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0-only +/// do_div() does a 64-by-32 division. +/// When the divisor is long, unsigned long, u64, or s64, +/// do_div() truncates it to 32 bits, this means it can test +/// non-zero and be truncated to 0 for division on 64bit platforms. +/// +//# This makes an effort to find those inappropriate do_div() calls. +// +// Confidence: Moderate +// Copyright: (C) 2020 Wen Yang, Alibaba. +// Comments: +// Options: --no-includes --include-headers + +virtual context +virtual org +virtual report + +@initialize:python@ +@@ + +def get_digit_type_and_value(str): + is_digit = False + value = 0 + + try: + if (str.isdigit()): + is_digit = True + value = int(str, 0) + elif (str.upper().endswith('ULL')): + is_digit = True + value = int(str[:-3], 0) + elif (str.upper().endswith('LL')): + is_digit = True + value = int(str[:-2], 0) + elif (str.upper().endswith('UL')): + is_digit = True + value = int(str[:-2], 0) + elif (str.upper().endswith('L')): + is_digit = True + value = int(str[:-1], 0) + elif (str.upper().endswith('U')): + is_digit = True + value = int(str[:-1], 0) + except Exception as e: + print('Error:',e) + is_digit = False + value = 0 + finally: + return is_digit, value + +def filter_out_safe_constants(str): + is_digit, value = get_digit_type_and_value(str) + if (is_digit): + if (value >= 0x100000000): + return True + else: + return False + else: + return True + +def construct_warnings(suggested_fun): + msg="WARNING: do_div() does a 64-by-32 division, please consider using %s instead." + return msg % suggested_fun + +@depends on context@ +expression f; +long l: script:python() { filter_out_safe_constants(l) }; +unsigned long ul : script:python() { filter_out_safe_constants(ul) }; +u64 ul64 : script:python() { filter_out_safe_constants(ul64) }; +s64 sl64 : script:python() { filter_out_safe_constants(sl64) }; + +@@ +( +* do_div(f, l); +| +* do_div(f, ul); +| +* do_div(f, ul64); +| +* do_div(f, sl64); +) + +@r depends on (org || report)@ +expression f; +position p; +long l: script:python() { filter_out_safe_constants(l) }; +unsigned long ul : script:python() { filter_out_safe_constants(ul) }; +u64 ul64 : script:python() { filter_out_safe_constants(ul64) }; +s64 sl64 : script:python() { filter_out_safe_constants(sl64) }; +@@ +( +do_div@p(f, l); +| +do_div@p(f, ul); +| +do_div@p(f, ul64); +| +do_div@p(f, sl64); +) + +@script:python depends on org@ +p << r.p; +ul << r.ul; +@@ + +coccilib.org.print_todo(p[0], construct_warnings("div64_ul")) + +@script:python depends on org@ +p << r.p; +l << r.l; +@@ + +coccilib.org.print_todo(p[0], construct_warnings("div64_long")) + +@script:python depends on org@ +p << r.p; +ul64 << r.ul64; +@@ + +coccilib.org.print_todo(p[0], construct_warnings("div64_u64")) + +@script:python depends on org@ +p << r.p; +sl64 << r.sl64; +@@ + +coccilib.org.print_todo(p[0], construct_warnings("div64_s64")) + +@script:python depends on report@ +p << r.p; +ul << r.ul; +@@ + +coccilib.report.print_report(p[0], construct_warnings("div64_ul")) + +@script:python depends on report@ +p << r.p; +l << r.l; +@@ + +coccilib.report.print_report(p[0], construct_warnings("div64_long")) + +@script:python depends on report@ +p << r.p; +sl64 << r.sl64; +@@ + +coccilib.report.print_report(p[0], construct_warnings("div64_s64")) + +@script:python depends on report@ +p << r.p; +ul64 << r.ul64; +@@ + +coccilib.report.print_report(p[0], construct_warnings("div64_u64")) diff --git a/scripts/remove-stale-files b/scripts/remove-stale-files index c3eb81c3f7de..0114c41e6938 100755 --- a/scripts/remove-stale-files +++ b/scripts/remove-stale-files @@ -28,4 +28,9 @@ if [ -n "${building_out_of_srctree}" ]; then do rm -f arch/arm/boot/compressed/${f} done + + for f in uart-ath79.c ashldi3.c bswapdi.c bswapsi.c + do + rm -f arch/mips/boot/compressed/${f} + done fi diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 2ee3b3d29f10..0797edb2fb3d 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -812,8 +812,6 @@ struct multi_transaction { }; #define MULTI_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct multi_transaction)) -/* TODO: replace with per file lock */ -static DEFINE_SPINLOCK(multi_transaction_lock); static void multi_transaction_kref(struct kref *kref) { @@ -847,10 +845,10 @@ static void multi_transaction_set(struct file *file, AA_BUG(n > MULTI_TRANSACTION_LIMIT); new->size = n; - spin_lock(&multi_transaction_lock); + spin_lock(&file->f_lock); old = (struct multi_transaction *) file->private_data; file->private_data = new; - spin_unlock(&multi_transaction_lock); + spin_unlock(&file->f_lock); put_multi_transaction(old); } @@ -879,9 +877,10 @@ static ssize_t multi_transaction_read(struct file *file, char __user *buf, struct multi_transaction *t; ssize_t ret; - spin_lock(&multi_transaction_lock); + spin_lock(&file->f_lock); t = get_multi_transaction(file->private_data); - spin_unlock(&multi_transaction_lock); + spin_unlock(&file->f_lock); + if (!t) return 0; @@ -1358,7 +1357,7 @@ static int rawdata_open(struct inode *inode, struct file *file) struct aa_loaddata *loaddata; struct rawdata_f_data *private; - if (!policy_view_capable(NULL)) + if (!aa_current_policy_view_capable(NULL)) return -EACCES; loaddata = __aa_get_loaddata(inode->i_private); @@ -2114,7 +2113,7 @@ static struct aa_profile *__first_profile(struct aa_ns *root, /** * __next_profile - step to the next profile in a profile tree - * @profile: current profile in tree (NOT NULL) + * @p: current profile in tree (NOT NULL) * * Perform a depth first traversal on the profile tree in a namespace * @@ -2265,7 +2264,7 @@ static const struct seq_operations aa_sfs_profiles_op = { static int profiles_open(struct inode *inode, struct file *file) { - if (!policy_view_capable(NULL)) + if (!aa_current_policy_view_capable(NULL)) return -EACCES; return seq_open(file, &aa_sfs_profiles_op); diff --git a/security/apparmor/include/file.h b/security/apparmor/include/file.h index d4f8948517d9..7517605a183d 100644 --- a/security/apparmor/include/file.h +++ b/security/apparmor/include/file.h @@ -167,7 +167,7 @@ int aa_audit_file(struct aa_profile *profile, struct aa_perms *perms, * @perms: permission table indexed by the matched state accept entry of @dfa * @trans: transition table for indexed by named x transitions * - * File permission are determined by matching a path against @dfa and then + * File permission are determined by matching a path against @dfa and * then using the value of the accept entry for the matching state as * an index into @perms. If a named exec transition is required it is * looked up in the transition table. diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h index 1e90384b1523..9101c2c76d9e 100644 --- a/security/apparmor/include/label.h +++ b/security/apparmor/include/label.h @@ -77,10 +77,6 @@ struct aa_labelset { #define __labelset_for_each(LS, N) \ for ((N) = rb_first(&(LS)->root); (N); (N) = rb_next(N)) -void aa_labelset_destroy(struct aa_labelset *ls); -void aa_labelset_init(struct aa_labelset *ls); - - enum label_flags { FLAG_HAT = 1, /* profile is a hat */ FLAG_UNCONFINED = 2, /* label unconfined only if all */ @@ -148,6 +144,7 @@ do { \ #define __label_make_stale(X) ((X)->flags |= FLAG_STALE) #define labels_ns(X) (vec_ns(&((X)->vec[0]), (X)->size)) #define labels_set(X) (&labels_ns(X)->labels) +#define labels_view(X) labels_ns(X) #define labels_profile(X) ((X)->vec[(X)->size - 1]) diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h index 7d27db740bc2..e2e8df0c6f1c 100644 --- a/security/apparmor/include/lib.h +++ b/security/apparmor/include/lib.h @@ -31,12 +31,17 @@ #define AA_WARN(X) WARN((X), "APPARMOR WARN %s: %s\n", __func__, #X) -#define AA_BUG(X, args...) AA_BUG_FMT((X), "" args) +#define AA_BUG(X, args...) \ + do { \ + _Pragma("GCC diagnostic ignored \"-Wformat-zero-length\""); \ + AA_BUG_FMT((X), "" args); \ + _Pragma("GCC diagnostic warning \"-Wformat-zero-length\""); \ + } while (0) #ifdef CONFIG_SECURITY_APPARMOR_DEBUG_ASSERTS #define AA_BUG_FMT(X, fmt, args...) \ WARN((X), "AppArmor WARN %s: (" #X "): " fmt, __func__, ##args) #else -#define AA_BUG_FMT(X, fmt, args...) +#define AA_BUG_FMT(X, fmt, args...) no_printk(fmt, ##args) #endif #define AA_ERROR(fmt, args...) \ diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index b5b4b8190e65..cb5ef21991b7 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -301,9 +301,11 @@ static inline int AUDIT_MODE(struct aa_profile *profile) return profile->audit; } -bool policy_view_capable(struct aa_ns *ns); -bool policy_admin_capable(struct aa_ns *ns); +bool aa_policy_view_capable(struct aa_label *label, struct aa_ns *ns); +bool aa_policy_admin_capable(struct aa_label *label, struct aa_ns *ns); int aa_may_manage_policy(struct aa_label *label, struct aa_ns *ns, u32 mask); +bool aa_current_policy_view_capable(struct aa_ns *ns); +bool aa_current_policy_admin_capable(struct aa_ns *ns); #endif /* __AA_POLICY_H */ diff --git a/security/apparmor/label.c b/security/apparmor/label.c index e68bcedca976..0b0265da1926 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -425,8 +425,7 @@ struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp) AA_BUG(size < 1); /* + 1 for null terminator entry on vec */ - new = kzalloc(sizeof(*new) + sizeof(struct aa_profile *) * (size + 1), - gfp); + new = kzalloc(struct_size(new, vec, size + 1), gfp); AA_DEBUG("%s (%p)\n", __func__, new); if (!new) goto fail; @@ -1454,7 +1453,7 @@ bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp) if (label->hname || labels_ns(label) != ns) return res; - if (aa_label_acntsxprint(&name, ns, label, FLAGS_NONE, gfp) == -1) + if (aa_label_acntsxprint(&name, ns, label, FLAGS_NONE, gfp) < 0) return res; ls = labels_set(label); @@ -1704,7 +1703,7 @@ int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, /** * aa_label_acntsxprint - allocate a __counted string buffer and print label - * @strp: buffer to write to. (MAY BE NULL if @size == 0) + * @strp: buffer to write to. * @ns: namespace profile is being viewed from * @label: label to view (NOT NULL) * @flags: flags controlling what label info is printed diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index f72406fe1bf2..0d6585056f3d 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1402,7 +1402,7 @@ static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_admin_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; return param_set_bool(val, kp); } @@ -1411,7 +1411,7 @@ static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_view_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_bool(buffer, kp); } @@ -1420,7 +1420,7 @@ static int param_set_aabool(const char *val, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_admin_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; return param_set_bool(val, kp); } @@ -1429,7 +1429,7 @@ static int param_get_aabool(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_view_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_bool(buffer, kp); } @@ -1455,7 +1455,7 @@ static int param_get_aauint(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_view_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_uint(buffer, kp); } @@ -1526,7 +1526,7 @@ static int param_get_aacompressionlevel(char *buffer, { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_view_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_int(buffer, kp); } @@ -1535,7 +1535,7 @@ static int param_get_audit(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_view_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return sprintf(buffer, "%s", audit_mode_names[aa_g_audit]); } @@ -1548,7 +1548,7 @@ static int param_set_audit(const char *val, const struct kernel_param *kp) return -EINVAL; if (!val) return -EINVAL; - if (apparmor_initialized && !policy_admin_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = match_string(audit_mode_names, AUDIT_MAX_INDEX, val); @@ -1563,7 +1563,7 @@ static int param_get_mode(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; - if (apparmor_initialized && !policy_view_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return sprintf(buffer, "%s", aa_profile_mode_names[aa_g_profile_mode]); @@ -1577,7 +1577,7 @@ static int param_set_mode(const char *val, const struct kernel_param *kp) return -EINVAL; if (!val) return -EINVAL; - if (apparmor_initialized && !policy_admin_capable(NULL)) + if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = match_string(aa_profile_mode_names, APPARMOR_MODE_NAMES_MAX_INDEX, @@ -1713,7 +1713,7 @@ static int __init alloc_buffers(void) static int apparmor_dointvec(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - if (!policy_admin_capable(NULL)) + if (!aa_current_policy_admin_capable(NULL)) return -EPERM; if (!apparmor_enabled) return -EINVAL; @@ -1773,32 +1773,16 @@ static unsigned int apparmor_ip_postroute(void *priv, } -static unsigned int apparmor_ipv4_postroute(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return apparmor_ip_postroute(priv, skb, state); -} - -#if IS_ENABLED(CONFIG_IPV6) -static unsigned int apparmor_ipv6_postroute(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return apparmor_ip_postroute(priv, skb, state); -} -#endif - static const struct nf_hook_ops apparmor_nf_ops[] = { { - .hook = apparmor_ipv4_postroute, + .hook = apparmor_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { - .hook = apparmor_ipv6_postroute, + .hook = apparmor_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_FIRST, diff --git a/security/apparmor/path.c b/security/apparmor/path.c index b02dfdbff7cd..45ec994b558d 100644 --- a/security/apparmor/path.c +++ b/security/apparmor/path.c @@ -83,7 +83,7 @@ static int disconnect(const struct path *path, char *buf, char **name, * * Returns: %0 else error code if path lookup fails * When no error the path name is returned in @name which points to - * to a position in @buf + * a position in @buf */ static int d_namespace_path(const struct path *path, char *buf, char **name, int flags, const char *disconnected) diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 4c010c9a6af1..b0cbc4906cb3 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -260,8 +260,7 @@ struct aa_profile *aa_alloc_profile(const char *hname, struct aa_proxy *proxy, struct aa_profile *profile; /* freed by free_profile - usually through aa_put_profile */ - profile = kzalloc(sizeof(*profile) + sizeof(struct aa_profile *) * 2, - gfp); + profile = kzalloc(struct_size(profile, label.vec, 2), gfp); if (!profile) return NULL; @@ -632,18 +631,35 @@ static int audit_policy(struct aa_label *label, const char *op, return error; } +/* don't call out to other LSMs in the stack for apparmor policy admin + * permissions + */ +static int policy_ns_capable(struct aa_label *label, + struct user_namespace *userns, int cap) +{ + int err; + + /* check for MAC_ADMIN cap in cred */ + err = cap_capable(current_cred(), userns, cap, CAP_OPT_NONE); + if (!err) + err = aa_capable(label, cap, CAP_OPT_NONE); + + return err; +} + /** - * policy_view_capable - check if viewing policy in at @ns is allowed - * ns: namespace being viewed by current task (may be NULL) + * aa_policy_view_capable - check if viewing policy in at @ns is allowed + * label: label that is trying to view policy in ns + * ns: namespace being viewed by @label (may be NULL if @label's ns) * Returns: true if viewing policy is allowed * * If @ns is NULL then the namespace being viewed is assumed to be the * tasks current namespace. */ -bool policy_view_capable(struct aa_ns *ns) +bool aa_policy_view_capable(struct aa_label *label, struct aa_ns *ns) { struct user_namespace *user_ns = current_user_ns(); - struct aa_ns *view_ns = aa_get_current_ns(); + struct aa_ns *view_ns = labels_view(label); bool root_in_user_ns = uid_eq(current_euid(), make_kuid(user_ns, 0)) || in_egroup_p(make_kgid(user_ns, 0)); bool response = false; @@ -655,20 +671,44 @@ bool policy_view_capable(struct aa_ns *ns) (unprivileged_userns_apparmor_policy != 0 && user_ns->level == view_ns->level))) response = true; - aa_put_ns(view_ns); return response; } -bool policy_admin_capable(struct aa_ns *ns) +bool aa_policy_admin_capable(struct aa_label *label, struct aa_ns *ns) { struct user_namespace *user_ns = current_user_ns(); - bool capable = ns_capable(user_ns, CAP_MAC_ADMIN); + bool capable = policy_ns_capable(label, user_ns, CAP_MAC_ADMIN) == 0; AA_DEBUG("cap_mac_admin? %d\n", capable); AA_DEBUG("policy locked? %d\n", aa_g_lock_policy); - return policy_view_capable(ns) && capable && !aa_g_lock_policy; + return aa_policy_view_capable(label, ns) && capable && + !aa_g_lock_policy; +} + +bool aa_current_policy_view_capable(struct aa_ns *ns) +{ + struct aa_label *label; + bool res; + + label = __begin_current_label_crit_section(); + res = aa_policy_view_capable(label, ns); + __end_current_label_crit_section(label); + + return res; +} + +bool aa_current_policy_admin_capable(struct aa_ns *ns) +{ + struct aa_label *label; + bool res; + + label = __begin_current_label_crit_section(); + res = aa_policy_admin_capable(label, ns); + __end_current_label_crit_section(label); + + return res; } /** @@ -694,7 +734,7 @@ int aa_may_manage_policy(struct aa_label *label, struct aa_ns *ns, u32 mask) return audit_policy(label, op, NULL, NULL, "policy_locked", -EACCES); - if (!policy_admin_capable(ns)) + if (!aa_policy_admin_capable(label, ns)) return audit_policy(label, op, NULL, NULL, "not policy admin", -EACCES); diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 4e1f96b216a8..0acca6f2a93f 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -39,7 +39,7 @@ /* * The AppArmor interface treats data as a type byte followed by the - * actual data. The interface has the notion of a a named entry + * actual data. The interface has the notion of a named entry * which has a name (AA_NAME typecode followed by name string) followed by * the entries typecode and data. Named types allow for optional * elements and extensions to be added and tested for without breaking diff --git a/security/apparmor/procattr.c b/security/apparmor/procattr.c index c929bf4a3df1..fde332e0ea7d 100644 --- a/security/apparmor/procattr.c +++ b/security/apparmor/procattr.c @@ -21,8 +21,6 @@ * @profile: the profile to print profile info about (NOT NULL) * @string: Returns - string containing the profile info (NOT NULL) * - * Returns: length of @string on success else error on failure - * * Requires: profile != NULL * * Creates a string containing the namespace_name://profile_name for diff --git a/security/security.c b/security/security.c index 95e30fadba78..c88167a414b4 100644 --- a/security/security.c +++ b/security/security.c @@ -2367,9 +2367,9 @@ int security_tun_dev_open(void *security) } EXPORT_SYMBOL(security_tun_dev_open); -int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb) +int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { - return call_int_hook(sctp_assoc_request, 0, ep, skb); + return call_int_hook(sctp_assoc_request, 0, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); @@ -2381,10 +2381,10 @@ int security_sctp_bind_connect(struct sock *sk, int optname, } EXPORT_SYMBOL(security_sctp_bind_connect); -void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { - call_void_hook(sctp_sk_clone, ep, sk, newsk); + call_void_hook(sctp_sk_clone, asoc, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index ea7b2876a5ae..62d30c0a30c2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5339,10 +5339,10 @@ static void selinux_sock_graft(struct sock *sk, struct socket *parent) * connect(2), sctp_connectx(3) or sctp_sendmsg(3) (with no association * already present). */ -static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, +static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { - struct sk_security_struct *sksec = ep->base.sk->sk_security; + struct sk_security_struct *sksec = asoc->base.sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; u8 peerlbl_active; @@ -5359,7 +5359,7 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ - err = selinux_skb_peerlbl_sid(skb, ep->base.sk->sk_family, + err = selinux_skb_peerlbl_sid(skb, asoc->base.sk->sk_family, &peer_sid); if (err) return err; @@ -5383,7 +5383,7 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, */ ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; - ad.u.net->sk = ep->base.sk; + ad.u.net->sk = asoc->base.sk; err = avc_has_perm(&selinux_state, sksec->peer_sid, peer_sid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); @@ -5392,7 +5392,7 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, } /* Compute the MLS component for the connection and store - * the information in ep. This will be used by SCTP TCP type + * the information in asoc. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. @@ -5401,11 +5401,11 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, if (err) return err; - ep->secid = conn_sid; - ep->peer_secid = peer_sid; + asoc->secid = conn_sid; + asoc->peer_secid = peer_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ - return selinux_netlbl_sctp_assoc_request(ep, skb); + return selinux_netlbl_sctp_assoc_request(asoc, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting @@ -5490,7 +5490,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ -static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; @@ -5502,8 +5502,8 @@ static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); - newsksec->sid = ep->secid; - newsksec->peer_sid = ep->peer_secid; + newsksec->sid = asoc->secid; + newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } diff --git a/security/selinux/include/netlabel.h b/security/selinux/include/netlabel.h index 0c58f62dc6ab..4d0456d3d459 100644 --- a/security/selinux/include/netlabel.h +++ b/security/selinux/include/netlabel.h @@ -39,7 +39,7 @@ int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family, u32 sid); -int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, +int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb); int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family); void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family); @@ -98,7 +98,7 @@ static inline int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, return 0; } -static inline int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, +static inline int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return 0; diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c index 29b88e81869b..1321f15799e2 100644 --- a/security/selinux/netlabel.c +++ b/security/selinux/netlabel.c @@ -261,30 +261,30 @@ skbuff_setsid_return: /** * selinux_netlbl_sctp_assoc_request - Label an incoming sctp association. - * @ep: incoming association endpoint. + * @asoc: incoming association. * @skb: the packet. * * Description: - * A new incoming connection is represented by @ep, ...... + * A new incoming connection is represented by @asoc, ...... * Returns zero on success, negative values on failure. * */ -int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, +int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { int rc; struct netlbl_lsm_secattr secattr; - struct sk_security_struct *sksec = ep->base.sk->sk_security; + struct sk_security_struct *sksec = asoc->base.sk->sk_security; struct sockaddr_in addr4; struct sockaddr_in6 addr6; - if (ep->base.sk->sk_family != PF_INET && - ep->base.sk->sk_family != PF_INET6) + if (asoc->base.sk->sk_family != PF_INET && + asoc->base.sk->sk_family != PF_INET6) return 0; netlbl_secattr_init(&secattr); rc = security_netlbl_sid_to_secattr(&selinux_state, - ep->secid, &secattr); + asoc->secid, &secattr); if (rc != 0) goto assoc_request_return; @@ -294,11 +294,11 @@ int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, if (ip_hdr(skb)->version == 4) { addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = ip_hdr(skb)->saddr; - rc = netlbl_conn_setattr(ep->base.sk, (void *)&addr4, &secattr); + rc = netlbl_conn_setattr(asoc->base.sk, (void *)&addr4, &secattr); } else if (IS_ENABLED(CONFIG_IPV6) && ip_hdr(skb)->version == 6) { addr6.sin6_family = AF_INET6; addr6.sin6_addr = ipv6_hdr(skb)->saddr; - rc = netlbl_conn_setattr(ep->base.sk, (void *)&addr6, &secattr); + rc = netlbl_conn_setattr(asoc->base.sk, (void *)&addr6, &secattr); } else { rc = -EAFNOSUPPORT; } diff --git a/sound/core/Makefile b/sound/core/Makefile index 350d704ced98..79e1407cd0de 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -19,6 +19,7 @@ snd-$(CONFIG_SND_JACK) += ctljack.o jack.o snd-pcm-y := pcm.o pcm_native.o pcm_lib.o pcm_misc.o \ pcm_memory.o memalloc.o snd-pcm-$(CONFIG_SND_PCM_TIMER) += pcm_timer.o +snd-pcm-$(CONFIG_SND_DMA_SGBUF) += sgbuf.o snd-pcm-$(CONFIG_SND_PCM_ELD) += pcm_drm_eld.o snd-pcm-$(CONFIG_SND_PCM_IEC958) += pcm_iec958.o diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 99cd0f67daa1..9fc971a704a9 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -183,8 +183,11 @@ EXPORT_SYMBOL_GPL(snd_devm_alloc_dir_pages); int snd_dma_buffer_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { - const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); + const struct snd_malloc_ops *ops; + if (!dmab) + return -ENOENT; + ops = snd_dma_get_ops(dmab); if (ops && ops->mmap) return ops->mmap(dmab, area); else @@ -549,60 +552,73 @@ static void snd_dma_noncontig_sync(struct snd_dma_buffer *dmab, } } -static const struct snd_malloc_ops snd_dma_noncontig_ops = { - .alloc = snd_dma_noncontig_alloc, - .free = snd_dma_noncontig_free, - .mmap = snd_dma_noncontig_mmap, - .sync = snd_dma_noncontig_sync, - /* re-use vmalloc helpers for get_* ops */ - .get_addr = snd_dma_vmalloc_get_addr, - .get_page = snd_dma_vmalloc_get_page, - .get_chunk_size = snd_dma_vmalloc_get_chunk_size, -}; +static inline void snd_dma_noncontig_iter_set(struct snd_dma_buffer *dmab, + struct sg_page_iter *piter, + size_t offset) +{ + struct sg_table *sgt = dmab->private_data; -/* x86-specific SG-buffer with WC pages */ -#ifdef CONFIG_SND_DMA_SGBUF -#define vmalloc_to_virt(v) (unsigned long)page_to_virt(vmalloc_to_page(v)) + __sg_page_iter_start(piter, sgt->sgl, sgt->orig_nents, + offset >> PAGE_SHIFT); +} -static void *snd_dma_sg_wc_alloc(struct snd_dma_buffer *dmab, size_t size) +static dma_addr_t snd_dma_noncontig_get_addr(struct snd_dma_buffer *dmab, + size_t offset) { - void *p = snd_dma_noncontig_alloc(dmab, size); - size_t ofs; + struct sg_dma_page_iter iter; - if (!p) - return NULL; - for (ofs = 0; ofs < size; ofs += PAGE_SIZE) - set_memory_uc(vmalloc_to_virt(p + ofs), 1); - return p; + snd_dma_noncontig_iter_set(dmab, &iter.base, offset); + __sg_page_iter_dma_next(&iter); + return sg_page_iter_dma_address(&iter) + offset % PAGE_SIZE; } -static void snd_dma_sg_wc_free(struct snd_dma_buffer *dmab) +static struct page *snd_dma_noncontig_get_page(struct snd_dma_buffer *dmab, + size_t offset) { - size_t ofs; + struct sg_page_iter iter; - for (ofs = 0; ofs < dmab->bytes; ofs += PAGE_SIZE) - set_memory_wb(vmalloc_to_virt(dmab->area + ofs), 1); - snd_dma_noncontig_free(dmab); + snd_dma_noncontig_iter_set(dmab, &iter, offset); + __sg_page_iter_next(&iter); + return sg_page_iter_page(&iter); } -static int snd_dma_sg_wc_mmap(struct snd_dma_buffer *dmab, - struct vm_area_struct *area) +static unsigned int +snd_dma_noncontig_get_chunk_size(struct snd_dma_buffer *dmab, + unsigned int ofs, unsigned int size) { - area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); - /* FIXME: dma_mmap_noncontiguous() works? */ - return -ENOENT; /* continue with the default mmap handler */ + struct sg_dma_page_iter iter; + unsigned int start, end; + unsigned long addr; + + start = ALIGN_DOWN(ofs, PAGE_SIZE); + end = ofs + size - 1; /* the last byte address */ + snd_dma_noncontig_iter_set(dmab, &iter.base, start); + if (!__sg_page_iter_dma_next(&iter)) + return 0; + /* check page continuity */ + addr = sg_page_iter_dma_address(&iter); + for (;;) { + start += PAGE_SIZE; + if (start > end) + break; + addr += PAGE_SIZE; + if (!__sg_page_iter_dma_next(&iter) || + sg_page_iter_dma_address(&iter) != addr) + return start - ofs; + } + /* ok, all on continuous pages */ + return size; } -const struct snd_malloc_ops snd_dma_sg_wc_ops = { - .alloc = snd_dma_sg_wc_alloc, - .free = snd_dma_sg_wc_free, - .mmap = snd_dma_sg_wc_mmap, +static const struct snd_malloc_ops snd_dma_noncontig_ops = { + .alloc = snd_dma_noncontig_alloc, + .free = snd_dma_noncontig_free, + .mmap = snd_dma_noncontig_mmap, .sync = snd_dma_noncontig_sync, - .get_addr = snd_dma_vmalloc_get_addr, - .get_page = snd_dma_vmalloc_get_page, - .get_chunk_size = snd_dma_vmalloc_get_chunk_size, + .get_addr = snd_dma_noncontig_get_addr, + .get_page = snd_dma_noncontig_get_page, + .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; -#endif /* CONFIG_SND_DMA_SGBUF */ /* * Non-coherent pages allocator @@ -663,17 +679,20 @@ static const struct snd_malloc_ops *dma_ops[] = { [SNDRV_DMA_TYPE_DEV_WC] = &snd_dma_wc_ops, [SNDRV_DMA_TYPE_NONCONTIG] = &snd_dma_noncontig_ops, [SNDRV_DMA_TYPE_NONCOHERENT] = &snd_dma_noncoherent_ops, -#ifdef CONFIG_SND_DMA_SGBUF - [SNDRV_DMA_TYPE_DEV_WC_SG] = &snd_dma_sg_wc_ops, -#endif #ifdef CONFIG_GENERIC_ALLOCATOR [SNDRV_DMA_TYPE_DEV_IRAM] = &snd_dma_iram_ops, #endif /* CONFIG_GENERIC_ALLOCATOR */ #endif /* CONFIG_HAS_DMA */ +#ifdef CONFIG_SND_DMA_SGBUF + [SNDRV_DMA_TYPE_DEV_SG] = &snd_dma_sg_ops, + [SNDRV_DMA_TYPE_DEV_WC_SG] = &snd_dma_sg_ops, +#endif }; static const struct snd_malloc_ops *snd_dma_get_ops(struct snd_dma_buffer *dmab) { + if (WARN_ON_ONCE(!dmab)) + return NULL; if (WARN_ON_ONCE(dmab->dev.type <= SNDRV_DMA_TYPE_UNKNOWN || dmab->dev.type >= ARRAY_SIZE(dma_ops))) return NULL; diff --git a/sound/core/sgbuf.c b/sound/core/sgbuf.c new file mode 100644 index 000000000000..8352a5cdb19f --- /dev/null +++ b/sound/core/sgbuf.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Scatter-Gather buffer + * + * Copyright (c) by Takashi Iwai <tiwai@suse.de> + */ + +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <linux/export.h> +#include <sound/memalloc.h> +#include "memalloc_local.h" + +struct snd_sg_page { + void *buf; + dma_addr_t addr; +}; + +struct snd_sg_buf { + int size; /* allocated byte size */ + int pages; /* allocated pages */ + int tblsize; /* allocated table size */ + struct snd_sg_page *table; /* address table */ + struct page **page_table; /* page table (for vmap/vunmap) */ + struct device *dev; +}; + +/* table entries are align to 32 */ +#define SGBUF_TBL_ALIGN 32 +#define sgbuf_align_table(tbl) ALIGN((tbl), SGBUF_TBL_ALIGN) + +static void snd_dma_sg_free(struct snd_dma_buffer *dmab) +{ + struct snd_sg_buf *sgbuf = dmab->private_data; + struct snd_dma_buffer tmpb; + int i; + + if (!sgbuf) + return; + + vunmap(dmab->area); + dmab->area = NULL; + + tmpb.dev.type = SNDRV_DMA_TYPE_DEV; + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + tmpb.dev.type = SNDRV_DMA_TYPE_DEV_WC; + tmpb.dev.dev = sgbuf->dev; + for (i = 0; i < sgbuf->pages; i++) { + if (!(sgbuf->table[i].addr & ~PAGE_MASK)) + continue; /* continuous pages */ + tmpb.area = sgbuf->table[i].buf; + tmpb.addr = sgbuf->table[i].addr & PAGE_MASK; + tmpb.bytes = (sgbuf->table[i].addr & ~PAGE_MASK) << PAGE_SHIFT; + snd_dma_free_pages(&tmpb); + } + + kfree(sgbuf->table); + kfree(sgbuf->page_table); + kfree(sgbuf); + dmab->private_data = NULL; +} + +#define MAX_ALLOC_PAGES 32 + +static void *snd_dma_sg_alloc(struct snd_dma_buffer *dmab, size_t size) +{ + struct snd_sg_buf *sgbuf; + unsigned int i, pages, chunk, maxpages; + struct snd_dma_buffer tmpb; + struct snd_sg_page *table; + struct page **pgtable; + int type = SNDRV_DMA_TYPE_DEV; + pgprot_t prot = PAGE_KERNEL; + void *area; + + dmab->private_data = sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); + if (!sgbuf) + return NULL; + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) { + type = SNDRV_DMA_TYPE_DEV_WC; +#ifdef pgprot_noncached + prot = pgprot_noncached(PAGE_KERNEL); +#endif + } + sgbuf->dev = dmab->dev.dev; + pages = snd_sgbuf_aligned_pages(size); + sgbuf->tblsize = sgbuf_align_table(pages); + table = kcalloc(sgbuf->tblsize, sizeof(*table), GFP_KERNEL); + if (!table) + goto _failed; + sgbuf->table = table; + pgtable = kcalloc(sgbuf->tblsize, sizeof(*pgtable), GFP_KERNEL); + if (!pgtable) + goto _failed; + sgbuf->page_table = pgtable; + + /* allocate pages */ + maxpages = MAX_ALLOC_PAGES; + while (pages > 0) { + chunk = pages; + /* don't be too eager to take a huge chunk */ + if (chunk > maxpages) + chunk = maxpages; + chunk <<= PAGE_SHIFT; + if (snd_dma_alloc_pages_fallback(type, dmab->dev.dev, + chunk, &tmpb) < 0) { + if (!sgbuf->pages) + goto _failed; + size = sgbuf->pages * PAGE_SIZE; + break; + } + chunk = tmpb.bytes >> PAGE_SHIFT; + for (i = 0; i < chunk; i++) { + table->buf = tmpb.area; + table->addr = tmpb.addr; + if (!i) + table->addr |= chunk; /* mark head */ + table++; + *pgtable++ = virt_to_page(tmpb.area); + tmpb.area += PAGE_SIZE; + tmpb.addr += PAGE_SIZE; + } + sgbuf->pages += chunk; + pages -= chunk; + if (chunk < maxpages) + maxpages = chunk; + } + + sgbuf->size = size; + area = vmap(sgbuf->page_table, sgbuf->pages, VM_MAP, prot); + if (!area) + goto _failed; + return area; + + _failed: + snd_dma_sg_free(dmab); /* free the table */ + return NULL; +} + +static dma_addr_t snd_dma_sg_get_addr(struct snd_dma_buffer *dmab, + size_t offset) +{ + struct snd_sg_buf *sgbuf = dmab->private_data; + dma_addr_t addr; + + addr = sgbuf->table[offset >> PAGE_SHIFT].addr; + addr &= ~((dma_addr_t)PAGE_SIZE - 1); + return addr + offset % PAGE_SIZE; +} + +static struct page *snd_dma_sg_get_page(struct snd_dma_buffer *dmab, + size_t offset) +{ + struct snd_sg_buf *sgbuf = dmab->private_data; + unsigned int idx = offset >> PAGE_SHIFT; + + if (idx >= (unsigned int)sgbuf->pages) + return NULL; + return sgbuf->page_table[idx]; +} + +static unsigned int snd_dma_sg_get_chunk_size(struct snd_dma_buffer *dmab, + unsigned int ofs, + unsigned int size) +{ + struct snd_sg_buf *sg = dmab->private_data; + unsigned int start, end, pg; + + start = ofs >> PAGE_SHIFT; + end = (ofs + size - 1) >> PAGE_SHIFT; + /* check page continuity */ + pg = sg->table[start].addr >> PAGE_SHIFT; + for (;;) { + start++; + if (start > end) + break; + pg++; + if ((sg->table[start].addr >> PAGE_SHIFT) != pg) + return (start << PAGE_SHIFT) - ofs; + } + /* ok, all on continuous pages */ + return size; +} + +static int snd_dma_sg_mmap(struct snd_dma_buffer *dmab, + struct vm_area_struct *area) +{ + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); + return -ENOENT; /* continue with the default mmap handler */ +} + +const struct snd_malloc_ops snd_dma_sg_ops = { + .alloc = snd_dma_sg_alloc, + .free = snd_dma_sg_free, + .get_addr = snd_dma_sg_get_addr, + .get_page = snd_dma_sg_get_page, + .get_chunk_size = snd_dma_sg_get_chunk_size, + .mmap = snd_dma_sg_mmap, +}; diff --git a/sound/core/timer.c b/sound/core/timer.c index 92b7008fcdb8..b3214baa8919 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -624,13 +624,13 @@ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop) if (!timer) return -EINVAL; spin_lock_irqsave(&timer->lock, flags); + list_del_init(&timeri->ack_list); + list_del_init(&timeri->active_list); if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START))) { result = -EBUSY; goto unlock; } - list_del_init(&timeri->ack_list); - list_del_init(&timeri->active_list); if (timer->card && timer->card->shutdown) goto unlock; if (stop) { @@ -665,23 +665,22 @@ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop) static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop) { unsigned long flags; + bool running; spin_lock_irqsave(&slave_active_lock, flags); - if (!(timeri->flags & SNDRV_TIMER_IFLG_RUNNING)) { - spin_unlock_irqrestore(&slave_active_lock, flags); - return -EBUSY; - } + running = timeri->flags & SNDRV_TIMER_IFLG_RUNNING; timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; if (timeri->timer) { spin_lock(&timeri->timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); - snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : - SNDRV_TIMER_EVENT_PAUSE); + if (running) + snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : + SNDRV_TIMER_EVENT_PAUSE); spin_unlock(&timeri->timer->lock); } spin_unlock_irqrestore(&slave_active_lock, flags); - return 0; + return running ? 0 : -EBUSY; } /* diff --git a/sound/firewire/Kconfig b/sound/firewire/Kconfig index fd109bea4c53..22b6c779682a 100644 --- a/sound/firewire/Kconfig +++ b/sound/firewire/Kconfig @@ -169,6 +169,7 @@ config SND_FIREWIRE_MOTU * 828 * 896 * 828mk2 + * 896hd * Traveler * Ultralite * 8pre @@ -176,7 +177,9 @@ config SND_FIREWIRE_MOTU * 828mk3 (Hybrid) * Ultralite mk3 (FireWire only) * Ultralite mk3 (Hybrid) + * Traveler mk3 * Audio Express + * Track 16 * 4pre To compile this driver as a module, choose M here: the module diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c index ac66f08acd6b..53dbd4d4b0d0 100644 --- a/sound/firewire/fireworks/fireworks_stream.c +++ b/sound/firewire/fireworks/fireworks_stream.c @@ -50,8 +50,9 @@ static int init_stream(struct snd_efw *efw, struct amdtp_stream *stream) efw->firmware_version == 0x5070300 || efw->firmware_version == 0x5080000)) efw->tx_stream.flags |= CIP_UNALIGHED_DBC; - // AudioFire9 always reports wrong dbs. - if (efw->is_af9) + // AudioFire9 always reports wrong dbs. Onyx 1200F with the latest firmware (v4.6.0) + // also report wrong dbs at 88.2 kHz or greater. + if (efw->is_af9 || efw->firmware_version == 0x4060000) efw->tx_stream.flags |= CIP_WRONG_DBS; // Firmware version 5.5 reports fixed interval for dbc. if (efw->firmware_version == 0x5050000) diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c index 05608e8ca0bc..8a0426920a76 100644 --- a/sound/firewire/motu/motu-protocol-v3.c +++ b/sound/firewire/motu/motu-protocol-v3.c @@ -16,6 +16,7 @@ #define V3_CLOCK_SRC_INTERNAL 0x00 #define V3_CLOCK_SRC_WORD_ON_BNC 0x01 #define V3_CLOCK_SRC_SPH 0x02 +#define V3_CLOCK_SRC_AESEBU_ON_XLR 0x08 #define V3_CLOCK_SRC_SPDIF_ON_COAX 0x10 #define V3_CLOCK_SRC_OPT_IFACE_A 0x18 #define V3_CLOCK_SRC_OPT_IFACE_B 0x19 @@ -126,6 +127,9 @@ int snd_motu_protocol_v3_get_clock_source(struct snd_motu *motu, case V3_CLOCK_SRC_SPH: *src = SND_MOTU_CLOCK_SOURCE_SPH; break; + case V3_CLOCK_SRC_AESEBU_ON_XLR: + *src = SND_MOTU_CLOCK_SOURCE_AESEBU_ON_XLR; + break; case V3_CLOCK_SRC_SPDIF_ON_COAX: *src = SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX; break; @@ -185,7 +189,7 @@ int snd_motu_protocol_v3_switch_fetching_mode(struct snd_motu *motu, sizeof(reg)); } -static int detect_packet_formats_828mk3(struct snd_motu *motu, u32 data) +static int detect_packet_formats_with_opt_ifaces(struct snd_motu *motu, u32 data) { if (data & V3_ENABLE_OPT_IN_IFACE_A) { if (data & V3_NO_ADAT_OPT_IN_IFACE_A) { @@ -255,8 +259,11 @@ int snd_motu_protocol_v3_cache_packet_formats(struct snd_motu *motu) motu->spec->rx_fixed_pcm_chunks, sizeof(motu->rx_packet_formats.pcm_chunks)); - if (motu->spec == &snd_motu_spec_828mk3_fw || motu->spec == &snd_motu_spec_828mk3_hybrid) - return detect_packet_formats_828mk3(motu, data); + if (motu->spec == &snd_motu_spec_828mk3_fw || + motu->spec == &snd_motu_spec_828mk3_hybrid || + motu->spec == &snd_motu_spec_traveler_mk3 || + motu->spec == &snd_motu_spec_track16) + return detect_packet_formats_with_opt_ifaces(motu, data); else return 0; } @@ -281,6 +288,16 @@ const struct snd_motu_spec snd_motu_spec_828mk3_hybrid = { .rx_fixed_pcm_chunks = {14, 14, 14}, // Additional 4 dummy chunks at higher rate. }; +const struct snd_motu_spec snd_motu_spec_traveler_mk3 = { + .name = "TravelerMk3", + .protocol_version = SND_MOTU_PROTOCOL_V3, + .flags = SND_MOTU_SPEC_RX_MIDI_3RD_Q | + SND_MOTU_SPEC_TX_MIDI_3RD_Q | + SND_MOTU_SPEC_COMMAND_DSP, + .tx_fixed_pcm_chunks = {18, 14, 10}, + .rx_fixed_pcm_chunks = {14, 14, 10}, +}; + const struct snd_motu_spec snd_motu_spec_ultralite_mk3 = { .name = "UltraLiteMk3", .protocol_version = SND_MOTU_PROTOCOL_V3, @@ -301,6 +318,16 @@ const struct snd_motu_spec snd_motu_spec_audio_express = { .rx_fixed_pcm_chunks = {10, 10, 0}, }; +const struct snd_motu_spec snd_motu_spec_track16 = { + .name = "Track16", + .protocol_version = SND_MOTU_PROTOCOL_V3, + .flags = SND_MOTU_SPEC_RX_MIDI_3RD_Q | + SND_MOTU_SPEC_TX_MIDI_3RD_Q | + SND_MOTU_SPEC_COMMAND_DSP, + .tx_fixed_pcm_chunks = {14, 14, 14}, + .rx_fixed_pcm_chunks = {6, 6, 6}, +}; + const struct snd_motu_spec snd_motu_spec_4pre = { .name = "4pre", .protocol_version = SND_MOTU_PROTOCOL_V3, diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c index 5fc7ae475537..f8b7fe38751c 100644 --- a/sound/firewire/motu/motu.c +++ b/sound/firewire/motu/motu.c @@ -169,9 +169,11 @@ static const struct ieee1394_device_id motu_id_table[] = { SND_MOTU_DEV_ENTRY(0x00000f, &snd_motu_spec_8pre), SND_MOTU_DEV_ENTRY(0x000015, &snd_motu_spec_828mk3_fw), // FireWire only. SND_MOTU_DEV_ENTRY(0x000019, &snd_motu_spec_ultralite_mk3), // FireWire only. + SND_MOTU_DEV_ENTRY(0x00001b, &snd_motu_spec_traveler_mk3), SND_MOTU_DEV_ENTRY(0x000030, &snd_motu_spec_ultralite_mk3), // Hybrid. SND_MOTU_DEV_ENTRY(0x000035, &snd_motu_spec_828mk3_hybrid), // Hybrid. SND_MOTU_DEV_ENTRY(0x000033, &snd_motu_spec_audio_express), + SND_MOTU_DEV_ENTRY(0x000039, &snd_motu_spec_track16), SND_MOTU_DEV_ENTRY(0x000045, &snd_motu_spec_4pre), { } }; diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index 79704ae6a73e..4189f2192284 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -138,8 +138,10 @@ extern const struct snd_motu_spec snd_motu_spec_8pre; extern const struct snd_motu_spec snd_motu_spec_828mk3_fw; extern const struct snd_motu_spec snd_motu_spec_828mk3_hybrid; +extern const struct snd_motu_spec snd_motu_spec_traveler_mk3; extern const struct snd_motu_spec snd_motu_spec_ultralite_mk3; extern const struct snd_motu_spec snd_motu_spec_audio_express; +extern const struct snd_motu_spec snd_motu_spec_track16; extern const struct snd_motu_spec snd_motu_spec_4pre; int amdtp_motu_init(struct amdtp_stream *s, struct fw_unit *unit, diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7762718cf429..fe51163f2d82 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2327,7 +2327,8 @@ static int azx_probe_continue(struct azx *chip) out_free: if (err < 0) { - azx_free(chip); + pci_set_drvdata(pci, NULL); + snd_card_free(chip->card); return err; } @@ -2364,6 +2365,7 @@ static void azx_remove(struct pci_dev *pci) cancel_delayed_work_sync(&hda->probe_work); device_lock(&pci->dev); + pci_set_drvdata(pci, NULL); snd_card_free(card); } } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8a3e2fe42106..2f1727faec69 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6739,6 +6739,7 @@ enum { ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS, + ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -8450,6 +8451,15 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc245_fixup_hp_gpio_led, }, + [ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11120 }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8486,6 +8496,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x141f, "Acer Spin SP513-54N", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), @@ -8625,6 +8636,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8728, "HP EliteBook 840 G7", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), @@ -8687,6 +8699,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x1970, "ASUS UX550VE", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1982, "ASUS B1400CEPE", ALC256_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), @@ -8750,11 +8763,15 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5015, "Clevo NH5[58]H[HJK]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5017, "Clevo NH7[79]H[HJK]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50a3, "Clevo NJ51GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50b3, "Clevo NK50S[BEZ]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50b6, "Clevo NK50S5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50b8, "Clevo NK50SZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50d5, "Clevo NP50D5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50e1, "Clevo NH5[58]HPQ", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50e2, "Clevo NH7[79]HPQ", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50f0, "Clevo NH50A[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50f2, "Clevo NH50E[PR]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x50f3, "Clevo NH58DPQ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 75aa2ea733a5..96c12dfb24cf 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -468,8 +468,11 @@ struct hdsp { unsigned char ss_out_channels; u32 io_loopback; /* output loopback channel states*/ - struct snd_dma_buffer *capture_dma_buf; - struct snd_dma_buffer *playback_dma_buf; + /* DMA buffers; those are copied instances from the original snd_dma_buf + * objects (which are managed via devres) for the address alignments + */ + struct snd_dma_buffer capture_dma_buf; + struct snd_dma_buffer playback_dma_buf; unsigned char *capture_buffer; /* suitably aligned address */ unsigned char *playback_buffer; /* suitably aligned address */ @@ -3764,30 +3767,32 @@ static void snd_hdsp_proc_init(struct hdsp *hdsp) static int snd_hdsp_initialize_memory(struct hdsp *hdsp) { - unsigned long pb_bus, cb_bus; + struct snd_dma_buffer *capture_dma, *playback_dma; - hdsp->capture_dma_buf = - snd_hammerfall_get_buffer(hdsp->pci, HDSP_DMA_AREA_BYTES); - hdsp->playback_dma_buf = - snd_hammerfall_get_buffer(hdsp->pci, HDSP_DMA_AREA_BYTES); - if (!hdsp->capture_dma_buf || !hdsp->playback_dma_buf) { + capture_dma = snd_hammerfall_get_buffer(hdsp->pci, HDSP_DMA_AREA_BYTES); + playback_dma = snd_hammerfall_get_buffer(hdsp->pci, HDSP_DMA_AREA_BYTES); + if (!capture_dma || !playback_dma) { dev_err(hdsp->card->dev, "%s: no buffers available\n", hdsp->card_name); return -ENOMEM; } - /* Align to bus-space 64K boundary */ + /* copy to the own data for alignment */ + hdsp->capture_dma_buf = *capture_dma; + hdsp->playback_dma_buf = *playback_dma; - cb_bus = ALIGN(hdsp->capture_dma_buf->addr, 0x10000ul); - pb_bus = ALIGN(hdsp->playback_dma_buf->addr, 0x10000ul); + /* Align to bus-space 64K boundary */ + hdsp->capture_dma_buf.addr = ALIGN(capture_dma->addr, 0x10000ul); + hdsp->playback_dma_buf.addr = ALIGN(playback_dma->addr, 0x10000ul); /* Tell the card where it is */ + hdsp_write(hdsp, HDSP_inputBufferAddress, hdsp->capture_dma_buf.addr); + hdsp_write(hdsp, HDSP_outputBufferAddress, hdsp->playback_dma_buf.addr); - hdsp_write(hdsp, HDSP_inputBufferAddress, cb_bus); - hdsp_write(hdsp, HDSP_outputBufferAddress, pb_bus); - - hdsp->capture_buffer = hdsp->capture_dma_buf->area + (cb_bus - hdsp->capture_dma_buf->addr); - hdsp->playback_buffer = hdsp->playback_dma_buf->area + (pb_bus - hdsp->playback_dma_buf->addr); + hdsp->capture_dma_buf.area += hdsp->capture_dma_buf.addr - capture_dma->addr; + hdsp->playback_dma_buf.area += hdsp->playback_dma_buf.addr - playback_dma->addr; + hdsp->capture_buffer = hdsp->capture_dma_buf.area; + hdsp->playback_buffer = hdsp->playback_dma_buf.area; return 0; } @@ -4507,7 +4512,7 @@ static int snd_hdsp_playback_open(struct snd_pcm_substream *substream) snd_pcm_set_sync(substream); runtime->hw = snd_hdsp_playback_subinfo; - snd_pcm_set_runtime_buffer(substream, hdsp->playback_dma_buf); + snd_pcm_set_runtime_buffer(substream, &hdsp->playback_dma_buf); hdsp->playback_pid = current->pid; hdsp->playback_substream = substream; @@ -4583,7 +4588,7 @@ static int snd_hdsp_capture_open(struct snd_pcm_substream *substream) snd_pcm_set_sync(substream); runtime->hw = snd_hdsp_capture_subinfo; - snd_pcm_set_runtime_buffer(substream, hdsp->capture_dma_buf); + snd_pcm_set_runtime_buffer(substream, &hdsp->capture_dma_buf); hdsp->capture_pid = current->pid; hdsp->capture_substream = substream; diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index e76f737ac9e8..7755e19aa776 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -208,8 +208,11 @@ struct snd_rme9652 { unsigned char ds_channels; unsigned char ss_channels; /* different for hammerfall/hammerfall-light */ - struct snd_dma_buffer *playback_dma_buf; - struct snd_dma_buffer *capture_dma_buf; + /* DMA buffers; those are copied instances from the original snd_dma_buf + * objects (which are managed via devres) for the address alignments + */ + struct snd_dma_buffer playback_dma_buf; + struct snd_dma_buffer capture_dma_buf; unsigned char *capture_buffer; /* suitably aligned address */ unsigned char *playback_buffer; /* suitably aligned address */ @@ -1719,30 +1722,32 @@ static void snd_rme9652_card_free(struct snd_card *card) static int snd_rme9652_initialize_memory(struct snd_rme9652 *rme9652) { - unsigned long pb_bus, cb_bus; + struct snd_dma_buffer *capture_dma, *playback_dma; - rme9652->capture_dma_buf = - snd_hammerfall_get_buffer(rme9652->pci, RME9652_DMA_AREA_BYTES); - rme9652->playback_dma_buf = - snd_hammerfall_get_buffer(rme9652->pci, RME9652_DMA_AREA_BYTES); - if (!rme9652->capture_dma_buf || !rme9652->playback_dma_buf) { + capture_dma = snd_hammerfall_get_buffer(rme9652->pci, RME9652_DMA_AREA_BYTES); + playback_dma = snd_hammerfall_get_buffer(rme9652->pci, RME9652_DMA_AREA_BYTES); + if (!capture_dma || !playback_dma) { dev_err(rme9652->card->dev, "%s: no buffers available\n", rme9652->card_name); return -ENOMEM; } - /* Align to bus-space 64K boundary */ + /* copy to the own data for alignment */ + rme9652->capture_dma_buf = *capture_dma; + rme9652->playback_dma_buf = *playback_dma; - cb_bus = ALIGN(rme9652->capture_dma_buf->addr, 0x10000ul); - pb_bus = ALIGN(rme9652->playback_dma_buf->addr, 0x10000ul); + /* Align to bus-space 64K boundary */ + rme9652->capture_dma_buf.addr = ALIGN(capture_dma->addr, 0x10000ul); + rme9652->playback_dma_buf.addr = ALIGN(playback_dma->addr, 0x10000ul); /* Tell the card where it is */ + rme9652_write(rme9652, RME9652_rec_buffer, rme9652->capture_dma_buf.addr); + rme9652_write(rme9652, RME9652_play_buffer, rme9652->playback_dma_buf.addr); - rme9652_write(rme9652, RME9652_rec_buffer, cb_bus); - rme9652_write(rme9652, RME9652_play_buffer, pb_bus); - - rme9652->capture_buffer = rme9652->capture_dma_buf->area + (cb_bus - rme9652->capture_dma_buf->addr); - rme9652->playback_buffer = rme9652->playback_dma_buf->area + (pb_bus - rme9652->playback_dma_buf->addr); + rme9652->capture_dma_buf.area += rme9652->capture_dma_buf.addr - capture_dma->addr; + rme9652->playback_dma_buf.area += rme9652->playback_dma_buf.addr - playback_dma->addr; + rme9652->capture_buffer = rme9652->capture_dma_buf.area; + rme9652->playback_buffer = rme9652->playback_dma_buf.area; return 0; } @@ -2259,7 +2264,7 @@ static int snd_rme9652_playback_open(struct snd_pcm_substream *substream) snd_pcm_set_sync(substream); runtime->hw = snd_rme9652_playback_subinfo; - snd_pcm_set_runtime_buffer(substream, rme9652->playback_dma_buf); + snd_pcm_set_runtime_buffer(substream, &rme9652->playback_dma_buf); if (rme9652->capture_substream == NULL) { rme9652_stop(rme9652); @@ -2318,7 +2323,7 @@ static int snd_rme9652_capture_open(struct snd_pcm_substream *substream) snd_pcm_set_sync(substream); runtime->hw = snd_rme9652_capture_subinfo; - snd_pcm_set_runtime_buffer(substream, rme9652->capture_dma_buf); + snd_pcm_set_runtime_buffer(substream, &rme9652->capture_dma_buf); if (rme9652->playback_substream == NULL) { rme9652_stop(rme9652); diff --git a/sound/synth/emux/emux.c b/sound/synth/emux/emux.c index 49d1976a132c..5ed8e36d2e04 100644 --- a/sound/synth/emux/emux.c +++ b/sound/synth/emux/emux.c @@ -88,7 +88,7 @@ int snd_emux_register(struct snd_emux *emu, struct snd_card *card, int index, ch emu->name = kstrdup(name, GFP_KERNEL); emu->voices = kcalloc(emu->max_voices, sizeof(struct snd_emux_voice), GFP_KERNEL); - if (emu->voices == NULL) + if (emu->name == NULL || emu->voices == NULL) return -ENOMEM; /* create soundfont list */ diff --git a/tools/Makefile b/tools/Makefile index 5da1fde03a9a..db2f7b8ebed5 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -24,7 +24,6 @@ help: @echo ' intel-speed-select - Intel Speed Select tool' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' - @echo ' liblockdep - user-space wrapper for kernel locking-validator' @echo ' objtool - an ELF object analysis tool' @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @@ -72,9 +71,6 @@ cgroup counter firewire hv guest bootconfig spi usb virtio vm bpf iio gpio objto bpf/%: FORCE $(call descend,$@) -liblockdep: FORCE - $(call descend,lib/lockdep) - libapi: FORCE $(call descend,lib/api) @@ -101,7 +97,7 @@ freefall: FORCE kvm_stat: FORCE $(call descend,kvm/$@) -all: acpi cgroup counter cpupower gpio hv firewire liblockdep \ +all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ virtio vm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ @@ -116,9 +112,6 @@ cpupower_install: cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: $(call descend,$(@:_install=),install) -liblockdep_install: - $(call descend,lib/lockdep,install) - selftests_install: $(call descend,testing/$(@:_install=),install) @@ -135,7 +128,7 @@ kvm_stat_install: $(call descend,kvm/$(@:_install=),install) install: acpi_install cgroup_install counter_install cpupower_install gpio_install \ - hv_install firewire_install iio_install liblockdep_install \ + hv_install firewire_install iio_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ @@ -151,9 +144,6 @@ cpupower_clean: cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean: $(call descend,$(@:_clean=),clean) -liblockdep_clean: - $(call descend,lib/lockdep,clean) - libapi_clean: $(call descend,lib/api,clean) @@ -185,7 +175,7 @@ build_clean: clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \ vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ - freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ + freefall_clean build_clean libbpf_clean libsubcmd_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ intel-speed-select_clean tracing_clean diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index c0c30e56988f..7cfba11c3014 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -22,24 +22,29 @@ else _OUTPUT := $(CURDIR) endif BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/ + LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/ LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf +LIBBPF := $(LIBBPF_OUTPUT)libbpf.a -LIBBPF = $(LIBBPF_OUTPUT)libbpf.a -LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/ -LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a +LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ +LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include +LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf +LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a # We need to copy hashmap.h and nlattr.h which is not otherwise exported by # libbpf, but still required by bpftool. LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h) ifeq ($(BPFTOOL_VERSION),) BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) endif -$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR): +$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): $(QUIET_MKDIR)mkdir -p $@ $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) @@ -52,7 +57,12 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_ $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ - ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \ + ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers + +$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_BOOTSTRAP_HDRS_DIR) $< $(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT) $(call QUIET_CLEAN, libbpf) @@ -172,11 +182,11 @@ else $(Q)cp "$(VMLINUX_H)" $@ endif -$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF) +$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) $(QUIET_CLANG)$(CLANG) \ -I$(if $(OUTPUT),$(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ - -I$(LIBBPF_INCLUDE) \ + -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ -g -O2 -Wall -target bpf -c $< -o $@ && $(LLVM_STRIP) -g $@ $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) @@ -209,8 +219,10 @@ $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS) -$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT) - $(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $< +$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT) + $(QUIET_CC)$(HOSTCC) \ + $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),$(CFLAGS)) \ + -c -MMD -o $@ $< $(OUTPUT)%.o: %.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< @@ -257,6 +269,6 @@ doc-uninstall: FORCE: .SECONDARY: -.PHONY: all FORCE clean install-bin install uninstall +.PHONY: all FORCE bootstrap clean install-bin install uninstall .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 43bd7f713c39..de45fcd2dcbe 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index c09cbb868c9f..725701235fd8 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -515,6 +515,7 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; @@ -522,7 +523,8 @@ int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, _ attr.value = ptr_to_u64(value); attr.flags = flags; - return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_map_delete_elem(int fd, const void *key) diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore deleted file mode 100644 index 6c308ac4388c..000000000000 --- a/tools/lib/lockdep/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -liblockdep.so.* diff --git a/tools/lib/lockdep/Build b/tools/lib/lockdep/Build deleted file mode 100644 index 6f667355b068..000000000000 --- a/tools/lib/lockdep/Build +++ /dev/null @@ -1 +0,0 @@ -liblockdep-y += common.o lockdep.o preload.o rbtree.o diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile deleted file mode 100644 index 9dafb8cb752f..000000000000 --- a/tools/lib/lockdep/Makefile +++ /dev/null @@ -1,162 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# file format version -FILE_VERSION = 1 - -LIBLOCKDEP_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion) - -# Makefiles suck: This macro sets a default value of $(2) for the -# variable named by $(1), unless the variable has been set by -# environment or command line. This is necessary for CC and AR -# because make sets default values, so the simpler ?= approach -# won't work as expected. -define allow-override - $(if $(or $(findstring environment,$(origin $(1))),\ - $(findstring command line,$(origin $(1)))),,\ - $(eval $(1) = $(2))) -endef - -# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix. -$(call allow-override,CC,$(CROSS_COMPILE)gcc) -$(call allow-override,AR,$(CROSS_COMPILE)ar) -$(call allow-override,LD,$(CROSS_COMPILE)ld) - -INSTALL = install - -# Use DESTDIR for installing into a different root directory. -# This is useful for building a package. The program will be -# installed in this directory as if it was the root directory. -# Then the build tool can move it later. -DESTDIR ?= -DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' - -prefix ?= /usr/local -libdir_relative = lib -libdir = $(prefix)/$(libdir_relative) -bindir_relative = bin -bindir = $(prefix)/$(bindir_relative) - -export DESTDIR DESTDIR_SQ INSTALL - -MAKEFLAGS += --no-print-directory - -include ../../scripts/Makefile.include - -# copy a bit from Linux kbuild - -ifeq ("$(origin V)", "command line") - VERBOSE = $(V) -endif -ifndef VERBOSE - VERBOSE = 0 -endif - -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(CURDIR))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -#$(info Determined 'srctree' to be $(srctree)) -endif - -# Shell quotes -libdir_SQ = $(subst ','\'',$(libdir)) -bindir_SQ = $(subst ','\'',$(bindir)) - -LIB_IN := $(OUTPUT)liblockdep-in.o - -BIN_FILE = lockdep -LIB_FILE = $(OUTPUT)liblockdep.a $(OUTPUT)liblockdep.so.$(LIBLOCKDEP_VERSION) - -CONFIG_INCLUDES = -CONFIG_LIBS = -CONFIG_FLAGS = - -OBJ = $@ -N = - -export Q VERBOSE - -INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) - -# Set compile option CFLAGS if not set elsewhere -CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g -CFLAGS += -fPIC -CFLAGS += -Wall - -override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ) - -ifeq ($(VERBOSE),1) - Q = - print_shared_lib_compile = - print_install = -else - Q = @ - print_shared_lib_compile = echo ' LD '$(OBJ); - print_static_lib_build = echo ' LD '$(OBJ); - print_install = echo ' INSTALL '$1' to $(DESTDIR_SQ)$2'; -endif - -all: - -export srctree OUTPUT CC LD CFLAGS V -include $(srctree)/tools/build/Makefile.include - -do_compile_shared_library = \ - ($(print_shared_lib_compile) \ - $(CC) $(LDFLAGS) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='$(@F)';$(shell ln -sf $(@F) $(@D)/liblockdep.so)) - -do_build_static_lib = \ - ($(print_static_lib_build) \ - $(RM) $@; $(AR) rcs $@ $^) - -CMD_TARGETS = $(LIB_FILE) - -TARGETS = $(CMD_TARGETS) - - -all: fixdep all_cmd - -all_cmd: $(CMD_TARGETS) - -$(LIB_IN): force - $(Q)$(MAKE) $(build)=liblockdep - -$(OUTPUT)liblockdep.so.$(LIBLOCKDEP_VERSION): $(LIB_IN) - $(Q)$(do_compile_shared_library) - -$(OUTPUT)liblockdep.a: $(LIB_IN) - $(Q)$(do_build_static_lib) - -tags: force - $(RM) tags - find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \ - --regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/' - -TAGS: force - $(RM) TAGS - find . -name '*.[ch]' | xargs etags \ - --regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/' - -define do_install - $(print_install) \ - if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ - fi; \ - $(INSTALL) $1 '$(DESTDIR_SQ)$2' -endef - -install_lib: all_cmd - $(Q)$(call do_install,$(LIB_FILE),$(libdir_SQ)) - $(Q)$(call do_install,$(BIN_FILE),$(bindir_SQ)) - -install: install_lib - -clean: - $(RM) $(OUTPUT)*.o *~ $(TARGETS) $(OUTPUT)*.a $(OUTPUT)*liblockdep*.so* $(VERSION_FILES) $(OUTPUT).*.d $(OUTPUT).*.cmd - $(RM) tags TAGS - -PHONY += force -force: - -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable so we can use it in if_changed and friends. -.PHONY: $(PHONY) diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c deleted file mode 100644 index 5c3b58cce8a9..000000000000 --- a/tools/lib/lockdep/common.c +++ /dev/null @@ -1,29 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stddef.h> -#include <stdbool.h> -#include <linux/compiler.h> -#include <linux/lockdep.h> -#include <unistd.h> -#include <sys/syscall.h> - -static __thread struct task_struct current_obj; - -/* lockdep wants these */ -bool debug_locks = true; -bool debug_locks_silent; - -__attribute__((destructor)) static void liblockdep_exit(void) -{ - debug_check_no_locks_held(); -} - -struct task_struct *__curr(void) -{ - if (current_obj.pid == 0) { - /* Makes lockdep output pretty */ - prctl(PR_GET_NAME, current_obj.comm); - current_obj.pid = syscall(__NR_gettid); - } - - return ¤t_obj; -} diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h deleted file mode 100644 index a6d7ee5f18ba..000000000000 --- a/tools/lib/lockdep/include/liblockdep/common.h +++ /dev/null @@ -1,54 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_COMMON_H -#define _LIBLOCKDEP_COMMON_H - -#include <pthread.h> - -#define NR_LOCKDEP_CACHING_CLASSES 2 -#define MAX_LOCKDEP_SUBCLASSES 8UL - -#ifndef CALLER_ADDR0 -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#endif - -#ifndef _RET_IP_ -#define _RET_IP_ CALLER_ADDR0 -#endif - -#ifndef _THIS_IP_ -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) -#endif - -struct lockdep_subclass_key { - char __one_byte; -}; - -struct lock_class_key { - struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES]; -}; - -struct lockdep_map { - struct lock_class_key *key; - struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; - const char *name; -#ifdef CONFIG_LOCK_STAT - int cpu; - unsigned long ip; -#endif -}; - -void lockdep_init_map(struct lockdep_map *lock, const char *name, - struct lock_class_key *key, int subclass); -void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, - struct lockdep_map *nest_lock, unsigned long ip); -void lock_release(struct lockdep_map *lock, unsigned long ip); -void lockdep_reset_lock(struct lockdep_map *lock); -void lockdep_register_key(struct lock_class_key *key); -void lockdep_unregister_key(struct lock_class_key *key); -extern void debug_check_no_locks_freed(const void *from, unsigned long len); - -#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ - { .name = (_name), .key = (void *)(_key), } - -#endif diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h deleted file mode 100644 index bd106b82759b..000000000000 --- a/tools/lib/lockdep/include/liblockdep/mutex.h +++ /dev/null @@ -1,73 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_MUTEX_H -#define _LIBLOCKDEP_MUTEX_H - -#include <pthread.h> -#include "common.h" - -struct liblockdep_pthread_mutex { - pthread_mutex_t mutex; - struct lock_class_key key; - struct lockdep_map dep_map; -}; - -typedef struct liblockdep_pthread_mutex liblockdep_pthread_mutex_t; - -#define LIBLOCKDEP_PTHREAD_MUTEX_INITIALIZER(mtx) \ - (const struct liblockdep_pthread_mutex) { \ - .mutex = PTHREAD_MUTEX_INITIALIZER, \ - .dep_map = STATIC_LOCKDEP_MAP_INIT(#mtx, &((&(mtx))->dep_map)), \ -} - -static inline int __mutex_init(liblockdep_pthread_mutex_t *lock, - const char *name, - struct lock_class_key *key, - const pthread_mutexattr_t *__mutexattr) -{ - lockdep_init_map(&lock->dep_map, name, key, 0); - return pthread_mutex_init(&lock->mutex, __mutexattr); -} - -#define liblockdep_pthread_mutex_init(mutex, mutexattr) \ -({ \ - lockdep_register_key(&(mutex)->key); \ - __mutex_init((mutex), #mutex, &(mutex)->key, (mutexattr)); \ -}) - -static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock) -{ - lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); - return pthread_mutex_lock(&lock->mutex); -} - -static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock) -{ - lock_release(&lock->dep_map, (unsigned long)_RET_IP_); - return pthread_mutex_unlock(&lock->mutex); -} - -static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock) -{ - lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); - return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0; -} - -static inline int liblockdep_pthread_mutex_destroy(liblockdep_pthread_mutex_t *lock) -{ - lockdep_reset_lock(&lock->dep_map); - lockdep_unregister_key(&lock->key); - return pthread_mutex_destroy(&lock->mutex); -} - -#ifdef __USE_LIBLOCKDEP - -#define pthread_mutex_t liblockdep_pthread_mutex_t -#define pthread_mutex_init liblockdep_pthread_mutex_init -#define pthread_mutex_lock liblockdep_pthread_mutex_lock -#define pthread_mutex_unlock liblockdep_pthread_mutex_unlock -#define pthread_mutex_trylock liblockdep_pthread_mutex_trylock -#define pthread_mutex_destroy liblockdep_pthread_mutex_destroy - -#endif - -#endif diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h deleted file mode 100644 index 6d5d2932bf4d..000000000000 --- a/tools/lib/lockdep/include/liblockdep/rwlock.h +++ /dev/null @@ -1,87 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_RWLOCK_H -#define _LIBLOCKDEP_RWLOCK_H - -#include <pthread.h> -#include "common.h" - -struct liblockdep_pthread_rwlock { - pthread_rwlock_t rwlock; - struct lockdep_map dep_map; -}; - -typedef struct liblockdep_pthread_rwlock liblockdep_pthread_rwlock_t; - -#define LIBLOCKDEP_PTHREAD_RWLOCK_INITIALIZER(rwl) \ - (struct liblockdep_pthread_rwlock) { \ - .rwlock = PTHREAD_RWLOCK_INITIALIZER, \ - .dep_map = STATIC_LOCKDEP_MAP_INIT(#rwl, &((&(rwl))->dep_map)), \ -} - -static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock, - const char *name, - struct lock_class_key *key, - const pthread_rwlockattr_t *attr) -{ - lockdep_init_map(&lock->dep_map, name, key, 0); - - return pthread_rwlock_init(&lock->rwlock, attr); -} - -#define liblockdep_pthread_rwlock_init(lock, attr) \ -({ \ - static struct lock_class_key __key; \ - \ - __rwlock_init((lock), #lock, &__key, (attr)); \ -}) - -static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock) -{ - lock_acquire(&lock->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_); - return pthread_rwlock_rdlock(&lock->rwlock); - -} - -static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock) -{ - lock_release(&lock->dep_map, (unsigned long)_RET_IP_); - return pthread_rwlock_unlock(&lock->rwlock); -} - -static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock) -{ - lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); - return pthread_rwlock_wrlock(&lock->rwlock); -} - -static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock) -{ - lock_acquire(&lock->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_); - return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0; -} - -static inline int liblockdep_pthread_rwlock_trywrlock(liblockdep_pthread_rwlock_t *lock) -{ - lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); - return pthread_rwlock_trywrlock(&lock->rwlock) == 0 ? 1 : 0; -} - -static inline int liblockdep_rwlock_destroy(liblockdep_pthread_rwlock_t *lock) -{ - return pthread_rwlock_destroy(&lock->rwlock); -} - -#ifdef __USE_LIBLOCKDEP - -#define pthread_rwlock_t liblockdep_pthread_rwlock_t -#define pthread_rwlock_init liblockdep_pthread_rwlock_init -#define pthread_rwlock_rdlock liblockdep_pthread_rwlock_rdlock -#define pthread_rwlock_unlock liblockdep_pthread_rwlock_unlock -#define pthread_rwlock_wrlock liblockdep_pthread_rwlock_wrlock -#define pthread_rwlock_tryrdlock liblockdep_pthread_rwlock_tryrdlock -#define pthread_rwlock_trywrlock liblockdep_pthread_rwlock_trywrlock -#define pthread_rwlock_destroy liblockdep_rwlock_destroy - -#endif - -#endif diff --git a/tools/lib/lockdep/lockdep b/tools/lib/lockdep/lockdep deleted file mode 100755 index 49af9fe19f5b..000000000000 --- a/tools/lib/lockdep/lockdep +++ /dev/null @@ -1,3 +0,0 @@ -#!/bin/bash - -LD_PRELOAD="./liblockdep.so $LD_PRELOAD" "$@" diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c deleted file mode 100644 index 348a9d0fb766..000000000000 --- a/tools/lib/lockdep/lockdep.c +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/lockdep.h> -#include <stdlib.h> - -/* Trivial API wrappers, we don't (yet) have RCU in user-space: */ -#define hlist_for_each_entry_rcu hlist_for_each_entry -#define hlist_add_head_rcu hlist_add_head -#define hlist_del_rcu hlist_del -#define list_for_each_entry_rcu list_for_each_entry -#define list_add_tail_rcu list_add_tail - -u32 prandom_u32(void) -{ - /* Used only by lock_pin_lock() which is dead code */ - abort(); -} - -void print_irqtrace_events(struct task_struct *curr) -{ - abort(); -} - -static struct new_utsname *init_utsname(void) -{ - static struct new_utsname n = (struct new_utsname) { - .release = "liblockdep", - .version = LIBLOCKDEP_VERSION, - }; - - return &n; -} - -#include "../../../kernel/locking/lockdep.c" diff --git a/tools/lib/lockdep/lockdep_internals.h b/tools/lib/lockdep/lockdep_internals.h deleted file mode 100644 index 29d0c954cc24..000000000000 --- a/tools/lib/lockdep/lockdep_internals.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../kernel/locking/lockdep_internals.h" diff --git a/tools/lib/lockdep/lockdep_states.h b/tools/lib/lockdep/lockdep_states.h deleted file mode 100644 index 248d235efda9..000000000000 --- a/tools/lib/lockdep/lockdep_states.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../kernel/locking/lockdep_states.h" diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c deleted file mode 100644 index 8f1adbe887b2..000000000000 --- a/tools/lib/lockdep/preload.c +++ /dev/null @@ -1,443 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <pthread.h> -#include <stdio.h> -#include <dlfcn.h> -#include <stdlib.h> -#include <sysexits.h> -#include <unistd.h> -#include "include/liblockdep/mutex.h" -#include "../../include/linux/rbtree.h" - -/** - * struct lock_lookup - liblockdep's view of a single unique lock - * @orig: pointer to the original pthread lock, used for lookups - * @dep_map: lockdep's dep_map structure - * @key: lockdep's key structure - * @node: rb-tree node used to store the lock in a global tree - * @name: a unique name for the lock - */ -struct lock_lookup { - void *orig; /* Original pthread lock, used for lookups */ - struct lockdep_map dep_map; /* Since all locks are dynamic, we need - * a dep_map and a key for each lock */ - /* - * Wait, there's no support for key classes? Yup :( - * Most big projects wrap the pthread api with their own calls to - * be compatible with different locking methods. This means that - * "classes" will be brokes since the function that creates all - * locks will point to a generic locking function instead of the - * actual code that wants to do the locking. - */ - struct lock_class_key key; - struct rb_node node; -#define LIBLOCKDEP_MAX_LOCK_NAME 22 - char name[LIBLOCKDEP_MAX_LOCK_NAME]; -}; - -/* This is where we store our locks */ -static struct rb_root locks = RB_ROOT; -static pthread_rwlock_t locks_rwlock = PTHREAD_RWLOCK_INITIALIZER; - -/* pthread mutex API */ - -#ifdef __GLIBC__ -extern int __pthread_mutex_init(pthread_mutex_t *mutex, const pthread_mutexattr_t *attr); -extern int __pthread_mutex_lock(pthread_mutex_t *mutex); -extern int __pthread_mutex_trylock(pthread_mutex_t *mutex); -extern int __pthread_mutex_unlock(pthread_mutex_t *mutex); -extern int __pthread_mutex_destroy(pthread_mutex_t *mutex); -#else -#define __pthread_mutex_init NULL -#define __pthread_mutex_lock NULL -#define __pthread_mutex_trylock NULL -#define __pthread_mutex_unlock NULL -#define __pthread_mutex_destroy NULL -#endif -static int (*ll_pthread_mutex_init)(pthread_mutex_t *mutex, - const pthread_mutexattr_t *attr) = __pthread_mutex_init; -static int (*ll_pthread_mutex_lock)(pthread_mutex_t *mutex) = __pthread_mutex_lock; -static int (*ll_pthread_mutex_trylock)(pthread_mutex_t *mutex) = __pthread_mutex_trylock; -static int (*ll_pthread_mutex_unlock)(pthread_mutex_t *mutex) = __pthread_mutex_unlock; -static int (*ll_pthread_mutex_destroy)(pthread_mutex_t *mutex) = __pthread_mutex_destroy; - -/* pthread rwlock API */ - -#ifdef __GLIBC__ -extern int __pthread_rwlock_init(pthread_rwlock_t *rwlock, const pthread_rwlockattr_t *attr); -extern int __pthread_rwlock_destroy(pthread_rwlock_t *rwlock); -extern int __pthread_rwlock_wrlock(pthread_rwlock_t *rwlock); -extern int __pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock); -extern int __pthread_rwlock_rdlock(pthread_rwlock_t *rwlock); -extern int __pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock); -extern int __pthread_rwlock_unlock(pthread_rwlock_t *rwlock); -#else -#define __pthread_rwlock_init NULL -#define __pthread_rwlock_destroy NULL -#define __pthread_rwlock_wrlock NULL -#define __pthread_rwlock_trywrlock NULL -#define __pthread_rwlock_rdlock NULL -#define __pthread_rwlock_tryrdlock NULL -#define __pthread_rwlock_unlock NULL -#endif - -static int (*ll_pthread_rwlock_init)(pthread_rwlock_t *rwlock, - const pthread_rwlockattr_t *attr) = __pthread_rwlock_init; -static int (*ll_pthread_rwlock_destroy)(pthread_rwlock_t *rwlock) = __pthread_rwlock_destroy; -static int (*ll_pthread_rwlock_rdlock)(pthread_rwlock_t *rwlock) = __pthread_rwlock_rdlock; -static int (*ll_pthread_rwlock_tryrdlock)(pthread_rwlock_t *rwlock) = __pthread_rwlock_tryrdlock; -static int (*ll_pthread_rwlock_trywrlock)(pthread_rwlock_t *rwlock) = __pthread_rwlock_trywrlock; -static int (*ll_pthread_rwlock_wrlock)(pthread_rwlock_t *rwlock) = __pthread_rwlock_wrlock; -static int (*ll_pthread_rwlock_unlock)(pthread_rwlock_t *rwlock) = __pthread_rwlock_unlock; - -enum { none, prepare, done, } __init_state; -static void init_preload(void); -static void try_init_preload(void) -{ - if (__init_state != done) - init_preload(); -} - -static struct rb_node **__get_lock_node(void *lock, struct rb_node **parent) -{ - struct rb_node **node = &locks.rb_node; - struct lock_lookup *l; - - *parent = NULL; - - while (*node) { - l = rb_entry(*node, struct lock_lookup, node); - - *parent = *node; - if (lock < l->orig) - node = &l->node.rb_left; - else if (lock > l->orig) - node = &l->node.rb_right; - else - return node; - } - - return node; -} - -#ifndef LIBLOCKDEP_STATIC_ENTRIES -#define LIBLOCKDEP_STATIC_ENTRIES 1024 -#endif - -static struct lock_lookup __locks[LIBLOCKDEP_STATIC_ENTRIES]; -static int __locks_nr; - -static inline bool is_static_lock(struct lock_lookup *lock) -{ - return lock >= __locks && lock < __locks + ARRAY_SIZE(__locks); -} - -static struct lock_lookup *alloc_lock(void) -{ - if (__init_state != done) { - /* - * Some programs attempt to initialize and use locks in their - * allocation path. This means that a call to malloc() would - * result in locks being initialized and locked. - * - * Why is it an issue for us? dlsym() below will try allocating - * to give us the original function. Since this allocation will - * result in a locking operations, we have to let pthread deal - * with it, but we can't! we don't have the pointer to the - * original API since we're inside dlsym() trying to get it - */ - - int idx = __locks_nr++; - if (idx >= ARRAY_SIZE(__locks)) { - dprintf(STDERR_FILENO, - "LOCKDEP error: insufficient LIBLOCKDEP_STATIC_ENTRIES\n"); - exit(EX_UNAVAILABLE); - } - return __locks + idx; - } - - return malloc(sizeof(struct lock_lookup)); -} - -static inline void free_lock(struct lock_lookup *lock) -{ - if (likely(!is_static_lock(lock))) - free(lock); -} - -/** - * __get_lock - find or create a lock instance - * @lock: pointer to a pthread lock function - * - * Try to find an existing lock in the rbtree using the provided pointer. If - * one wasn't found - create it. - */ -static struct lock_lookup *__get_lock(void *lock) -{ - struct rb_node **node, *parent; - struct lock_lookup *l; - - ll_pthread_rwlock_rdlock(&locks_rwlock); - node = __get_lock_node(lock, &parent); - ll_pthread_rwlock_unlock(&locks_rwlock); - if (*node) { - return rb_entry(*node, struct lock_lookup, node); - } - - /* We didn't find the lock, let's create it */ - l = alloc_lock(); - if (l == NULL) - return NULL; - - l->orig = lock; - /* - * Currently the name of the lock is the ptr value of the pthread lock, - * while not optimal, it makes debugging a bit easier. - * - * TODO: Get the real name of the lock using libdwarf - */ - sprintf(l->name, "%p", lock); - lockdep_init_map(&l->dep_map, l->name, &l->key, 0); - - ll_pthread_rwlock_wrlock(&locks_rwlock); - /* This might have changed since the last time we fetched it */ - node = __get_lock_node(lock, &parent); - rb_link_node(&l->node, parent, node); - rb_insert_color(&l->node, &locks); - ll_pthread_rwlock_unlock(&locks_rwlock); - - return l; -} - -static void __del_lock(struct lock_lookup *lock) -{ - ll_pthread_rwlock_wrlock(&locks_rwlock); - rb_erase(&lock->node, &locks); - ll_pthread_rwlock_unlock(&locks_rwlock); - free_lock(lock); -} - -int pthread_mutex_init(pthread_mutex_t *mutex, - const pthread_mutexattr_t *attr) -{ - int r; - - /* - * We keep trying to init our preload module because there might be - * code in init sections that tries to touch locks before we are - * initialized, in that case we'll need to manually call preload - * to get us going. - * - * Funny enough, kernel's lockdep had the same issue, and used - * (almost) the same solution. See look_up_lock_class() in - * kernel/locking/lockdep.c for details. - */ - try_init_preload(); - - r = ll_pthread_mutex_init(mutex, attr); - if (r == 0) - /* - * We do a dummy initialization here so that lockdep could - * warn us if something fishy is going on - such as - * initializing a held lock. - */ - __get_lock(mutex); - - return r; -} - -int pthread_mutex_lock(pthread_mutex_t *mutex) -{ - int r; - - try_init_preload(); - - lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL, - (unsigned long)_RET_IP_); - /* - * Here's the thing with pthread mutexes: unlike the kernel variant, - * they can fail. - * - * This means that the behaviour here is a bit different from what's - * going on in the kernel: there we just tell lockdep that we took the - * lock before actually taking it, but here we must deal with the case - * that locking failed. - * - * To do that we'll "release" the lock if locking failed - this way - * we'll get lockdep doing the correct checks when we try to take - * the lock, and if that fails - we'll be back to the correct - * state by releasing it. - */ - r = ll_pthread_mutex_lock(mutex); - if (r) - lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_mutex_trylock(pthread_mutex_t *mutex) -{ - int r; - - try_init_preload(); - - lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); - r = ll_pthread_mutex_trylock(mutex); - if (r) - lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_mutex_unlock(pthread_mutex_t *mutex) -{ - int r; - - try_init_preload(); - - lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); - /* - * Just like taking a lock, only in reverse! - * - * If we fail releasing the lock, tell lockdep we're holding it again. - */ - r = ll_pthread_mutex_unlock(mutex); - if (r) - lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_mutex_destroy(pthread_mutex_t *mutex) -{ - try_init_preload(); - - /* - * Let's see if we're releasing a lock that's held. - * - * TODO: Hook into free() and add that check there as well. - */ - debug_check_no_locks_freed(mutex, sizeof(*mutex)); - __del_lock(__get_lock(mutex)); - return ll_pthread_mutex_destroy(mutex); -} - -/* This is the rwlock part, very similar to what happened with mutex above */ -int pthread_rwlock_init(pthread_rwlock_t *rwlock, - const pthread_rwlockattr_t *attr) -{ - int r; - - try_init_preload(); - - r = ll_pthread_rwlock_init(rwlock, attr); - if (r == 0) - __get_lock(rwlock); - - return r; -} - -int pthread_rwlock_destroy(pthread_rwlock_t *rwlock) -{ - try_init_preload(); - - debug_check_no_locks_freed(rwlock, sizeof(*rwlock)); - __del_lock(__get_lock(rwlock)); - return ll_pthread_rwlock_destroy(rwlock); -} - -int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock) -{ - int r; - - init_preload(); - - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_); - r = ll_pthread_rwlock_rdlock(rwlock); - if (r) - lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock) -{ - int r; - - init_preload(); - - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_); - r = ll_pthread_rwlock_tryrdlock(rwlock); - if (r) - lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock) -{ - int r; - - init_preload(); - - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); - r = ll_pthread_rwlock_trywrlock(rwlock); - if (r) - lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock) -{ - int r; - - init_preload(); - - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); - r = ll_pthread_rwlock_wrlock(rwlock); - if (r) - lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); - - return r; -} - -int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) -{ - int r; - - init_preload(); - - lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); - r = ll_pthread_rwlock_unlock(rwlock); - if (r) - lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); - - return r; -} - -__attribute__((constructor)) static void init_preload(void) -{ - if (__init_state == done) - return; - -#ifndef __GLIBC__ - __init_state = prepare; - - ll_pthread_mutex_init = dlsym(RTLD_NEXT, "pthread_mutex_init"); - ll_pthread_mutex_lock = dlsym(RTLD_NEXT, "pthread_mutex_lock"); - ll_pthread_mutex_trylock = dlsym(RTLD_NEXT, "pthread_mutex_trylock"); - ll_pthread_mutex_unlock = dlsym(RTLD_NEXT, "pthread_mutex_unlock"); - ll_pthread_mutex_destroy = dlsym(RTLD_NEXT, "pthread_mutex_destroy"); - - ll_pthread_rwlock_init = dlsym(RTLD_NEXT, "pthread_rwlock_init"); - ll_pthread_rwlock_destroy = dlsym(RTLD_NEXT, "pthread_rwlock_destroy"); - ll_pthread_rwlock_rdlock = dlsym(RTLD_NEXT, "pthread_rwlock_rdlock"); - ll_pthread_rwlock_tryrdlock = dlsym(RTLD_NEXT, "pthread_rwlock_tryrdlock"); - ll_pthread_rwlock_wrlock = dlsym(RTLD_NEXT, "pthread_rwlock_wrlock"); - ll_pthread_rwlock_trywrlock = dlsym(RTLD_NEXT, "pthread_rwlock_trywrlock"); - ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock"); -#endif - - __init_state = done; -} diff --git a/tools/lib/lockdep/rbtree.c b/tools/lib/lockdep/rbtree.c deleted file mode 100644 index 297c304571f8..000000000000 --- a/tools/lib/lockdep/rbtree.c +++ /dev/null @@ -1 +0,0 @@ -#include "../../lib/rbtree.c" diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh deleted file mode 100755 index 11f425662b43..000000000000 --- a/tools/lib/lockdep/run_tests.sh +++ /dev/null @@ -1,47 +0,0 @@ -#! /bin/bash -# SPDX-License-Identifier: GPL-2.0 - -if ! make >/dev/null; then - echo "Building liblockdep failed." - echo "FAILED!" - exit 1 -fi - -find tests -name '*.c' | sort | while read -r i; do - testname=$(basename "$i" .c) - echo -ne "$testname... " - if gcc -o "tests/$testname" -pthread "$i" liblockdep.a -Iinclude -D__USE_LIBLOCKDEP && - timeout 1 "tests/$testname" 2>&1 | /bin/bash "tests/${testname}.sh"; then - echo "PASSED!" - else - echo "FAILED!" - fi - rm -f "tests/$testname" -done - -find tests -name '*.c' | sort | while read -r i; do - testname=$(basename "$i" .c) - echo -ne "(PRELOAD) $testname... " - if gcc -o "tests/$testname" -pthread -Iinclude "$i" && - timeout 1 ./lockdep "tests/$testname" 2>&1 | - /bin/bash "tests/${testname}.sh"; then - echo "PASSED!" - else - echo "FAILED!" - fi - rm -f "tests/$testname" -done - -find tests -name '*.c' | sort | while read -r i; do - testname=$(basename "$i" .c) - echo -ne "(PRELOAD + Valgrind) $testname... " - if gcc -o "tests/$testname" -pthread -Iinclude "$i" && - { timeout 10 valgrind --read-var-info=yes ./lockdep "./tests/$testname" >& "tests/${testname}.vg.out"; true; } && - /bin/bash "tests/${testname}.sh" < "tests/${testname}.vg.out" && - ! grep -Eq '(^==[0-9]*== (Invalid |Uninitialised ))|Mismatched free|Source and destination overlap| UME ' "tests/${testname}.vg.out"; then - echo "PASSED!" - else - echo "FAILED!" - fi - rm -f "tests/$testname" -done diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c deleted file mode 100644 index 63c7ce97bda3..000000000000 --- a/tools/lib/lockdep/tests/AA.c +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> - -int main(void) -{ - pthread_mutex_t a; - - pthread_mutex_init(&a, NULL); - - pthread_mutex_lock(&a); - pthread_mutex_lock(&a); - - return 0; -} diff --git a/tools/lib/lockdep/tests/AA.sh b/tools/lib/lockdep/tests/AA.sh deleted file mode 100644 index f39b32865074..000000000000 --- a/tools/lib/lockdep/tests/AA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible recursive locking detected' diff --git a/tools/lib/lockdep/tests/ABA.c b/tools/lib/lockdep/tests/ABA.c deleted file mode 100644 index efa39b23f05d..000000000000 --- a/tools/lib/lockdep/tests/ABA.c +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> - -void main(void) -{ - pthread_mutex_t a, b; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - - pthread_mutex_lock(&a); - pthread_mutex_lock(&b); - pthread_mutex_lock(&a); -} diff --git a/tools/lib/lockdep/tests/ABA.sh b/tools/lib/lockdep/tests/ABA.sh deleted file mode 100644 index f39b32865074..000000000000 --- a/tools/lib/lockdep/tests/ABA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible recursive locking detected' diff --git a/tools/lib/lockdep/tests/ABBA.c b/tools/lib/lockdep/tests/ABBA.c deleted file mode 100644 index 543789bc3e37..000000000000 --- a/tools/lib/lockdep/tests/ABBA.c +++ /dev/null @@ -1,26 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> -#include "common.h" - -void main(void) -{ - pthread_mutex_t a, b; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(b, a); - - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(b, a); - - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/ABBA.sh b/tools/lib/lockdep/tests/ABBA.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABBA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/ABBA_2threads.c b/tools/lib/lockdep/tests/ABBA_2threads.c deleted file mode 100644 index 39325ef8a2ac..000000000000 --- a/tools/lib/lockdep/tests/ABBA_2threads.c +++ /dev/null @@ -1,47 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include <pthread.h> - -pthread_mutex_t a = PTHREAD_MUTEX_INITIALIZER; -pthread_mutex_t b = PTHREAD_MUTEX_INITIALIZER; -pthread_barrier_t bar; - -void *ba_lock(void *arg) -{ - int ret, i; - - pthread_mutex_lock(&b); - - if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD) - pthread_barrier_destroy(&bar); - - pthread_mutex_lock(&a); - - pthread_mutex_unlock(&a); - pthread_mutex_unlock(&b); -} - -int main(void) -{ - pthread_t t; - - pthread_barrier_init(&bar, NULL, 2); - - if (pthread_create(&t, NULL, ba_lock, NULL)) { - fprintf(stderr, "pthread_create() failed\n"); - return 1; - } - pthread_mutex_lock(&a); - - if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD) - pthread_barrier_destroy(&bar); - - pthread_mutex_lock(&b); - - pthread_mutex_unlock(&b); - pthread_mutex_unlock(&a); - - pthread_join(t, NULL); - - return 0; -} diff --git a/tools/lib/lockdep/tests/ABBA_2threads.sh b/tools/lib/lockdep/tests/ABBA_2threads.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABBA_2threads.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/ABBCCA.c b/tools/lib/lockdep/tests/ABBCCA.c deleted file mode 100644 index 48446129d496..000000000000 --- a/tools/lib/lockdep/tests/ABBCCA.c +++ /dev/null @@ -1,20 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> -#include "common.h" - -void main(void) -{ - pthread_mutex_t a, b, c; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - pthread_mutex_init(&c, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(b, c); - LOCK_UNLOCK_2(c, a); - - pthread_mutex_destroy(&c); - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/ABBCCA.sh b/tools/lib/lockdep/tests/ABBCCA.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABBCCA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/ABBCCDDA.c b/tools/lib/lockdep/tests/ABBCCDDA.c deleted file mode 100644 index 3570bf7b3804..000000000000 --- a/tools/lib/lockdep/tests/ABBCCDDA.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> -#include "common.h" - -void main(void) -{ - pthread_mutex_t a, b, c, d; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - pthread_mutex_init(&c, NULL); - pthread_mutex_init(&d, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(b, c); - LOCK_UNLOCK_2(c, d); - LOCK_UNLOCK_2(d, a); - - pthread_mutex_destroy(&d); - pthread_mutex_destroy(&c); - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/ABBCCDDA.sh b/tools/lib/lockdep/tests/ABBCCDDA.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABBCCDDA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/ABCABC.c b/tools/lib/lockdep/tests/ABCABC.c deleted file mode 100644 index a1c4659894cd..000000000000 --- a/tools/lib/lockdep/tests/ABCABC.c +++ /dev/null @@ -1,20 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> -#include "common.h" - -void main(void) -{ - pthread_mutex_t a, b, c; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - pthread_mutex_init(&c, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(c, a); - LOCK_UNLOCK_2(b, c); - - pthread_mutex_destroy(&c); - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/ABCABC.sh b/tools/lib/lockdep/tests/ABCABC.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABCABC.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/ABCDBCDA.c b/tools/lib/lockdep/tests/ABCDBCDA.c deleted file mode 100644 index 335af1c90ab5..000000000000 --- a/tools/lib/lockdep/tests/ABCDBCDA.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> -#include "common.h" - -void main(void) -{ - pthread_mutex_t a, b, c, d; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - pthread_mutex_init(&c, NULL); - pthread_mutex_init(&d, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(c, d); - LOCK_UNLOCK_2(b, c); - LOCK_UNLOCK_2(d, a); - - pthread_mutex_destroy(&d); - pthread_mutex_destroy(&c); - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/ABCDBCDA.sh b/tools/lib/lockdep/tests/ABCDBCDA.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABCDBCDA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/ABCDBDDA.c b/tools/lib/lockdep/tests/ABCDBDDA.c deleted file mode 100644 index 3c5972863049..000000000000 --- a/tools/lib/lockdep/tests/ABCDBDDA.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> -#include "common.h" - -void main(void) -{ - pthread_mutex_t a, b, c, d; - - pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); - pthread_mutex_init(&c, NULL); - pthread_mutex_init(&d, NULL); - - LOCK_UNLOCK_2(a, b); - LOCK_UNLOCK_2(c, d); - LOCK_UNLOCK_2(b, d); - LOCK_UNLOCK_2(d, a); - - pthread_mutex_destroy(&d); - pthread_mutex_destroy(&c); - pthread_mutex_destroy(&b); - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/ABCDBDDA.sh b/tools/lib/lockdep/tests/ABCDBDDA.sh deleted file mode 100644 index fc31c607a5a8..000000000000 --- a/tools/lib/lockdep/tests/ABCDBDDA.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible circular locking dependency detected' diff --git a/tools/lib/lockdep/tests/WW.c b/tools/lib/lockdep/tests/WW.c deleted file mode 100644 index eee88df7fc41..000000000000 --- a/tools/lib/lockdep/tests/WW.c +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/rwlock.h> - -void main(void) -{ - pthread_rwlock_t a, b; - - pthread_rwlock_init(&a, NULL); - pthread_rwlock_init(&b, NULL); - - pthread_rwlock_wrlock(&a); - pthread_rwlock_rdlock(&b); - pthread_rwlock_wrlock(&a); -} diff --git a/tools/lib/lockdep/tests/WW.sh b/tools/lib/lockdep/tests/WW.sh deleted file mode 100644 index f39b32865074..000000000000 --- a/tools/lib/lockdep/tests/WW.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: possible recursive locking detected' diff --git a/tools/lib/lockdep/tests/common.h b/tools/lib/lockdep/tests/common.h deleted file mode 100644 index 3026c29ccb5c..000000000000 --- a/tools/lib/lockdep/tests/common.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_TEST_COMMON_H -#define _LIBLOCKDEP_TEST_COMMON_H - -#define LOCK_UNLOCK_2(a, b) \ - do { \ - pthread_mutex_lock(&(a)); \ - pthread_mutex_lock(&(b)); \ - pthread_mutex_unlock(&(b)); \ - pthread_mutex_unlock(&(a)); \ - } while(0) - -#endif diff --git a/tools/lib/lockdep/tests/unlock_balance.c b/tools/lib/lockdep/tests/unlock_balance.c deleted file mode 100644 index dba25064b50a..000000000000 --- a/tools/lib/lockdep/tests/unlock_balance.c +++ /dev/null @@ -1,15 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <liblockdep/mutex.h> - -void main(void) -{ - pthread_mutex_t a; - - pthread_mutex_init(&a, NULL); - - pthread_mutex_lock(&a); - pthread_mutex_unlock(&a); - pthread_mutex_unlock(&a); - - pthread_mutex_destroy(&a); -} diff --git a/tools/lib/lockdep/tests/unlock_balance.sh b/tools/lib/lockdep/tests/unlock_balance.sh deleted file mode 100644 index c6e3952303fe..000000000000 --- a/tools/lib/lockdep/tests/unlock_balance.sh +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -grep -q 'WARNING: bad unlock balance detected' diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c index 6ede48bde91b..954964f0ac3d 100644 --- a/tools/testing/selftests/bpf/prog_tests/netcnt.c +++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c @@ -8,7 +8,7 @@ #define CG_NAME "/netcnt" -void test_netcnt(void) +void serial_test_netcnt(void) { union percpu_net_cnt *percpu_netcnt = NULL; struct bpf_cgroup_storage_key key; diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c index 172c999e523c..d29ebfeef9c5 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #define _GNU_SOURCE +#include <stdio.h> #include <sched.h> #include <sys/mount.h> #include <sys/stat.h> @@ -29,44 +30,106 @@ static int read_iter(char *file) static int fn(void) { - int err, duration = 0; + struct stat a, b, c; + int err, map; err = unshare(CLONE_NEWNS); - if (CHECK(err, "unshare", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "unshare")) goto out; err = mount("", "/", "", MS_REC | MS_PRIVATE, NULL); - if (CHECK(err, "mount /", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount /")) goto out; err = umount(TDIR); - if (CHECK(err, "umount " TDIR, "failed: %d\n", errno)) + if (!ASSERT_OK(err, "umount " TDIR)) goto out; err = mount("none", TDIR, "tmpfs", 0, NULL); - if (CHECK(err, "mount", "mount root failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount tmpfs")) goto out; err = mkdir(TDIR "/fs1", 0777); - if (CHECK(err, "mkdir "TDIR"/fs1", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mkdir " TDIR "/fs1")) goto out; err = mkdir(TDIR "/fs2", 0777); - if (CHECK(err, "mkdir "TDIR"/fs2", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mkdir " TDIR "/fs2")) goto out; err = mount("bpf", TDIR "/fs1", "bpf", 0, NULL); - if (CHECK(err, "mount bpffs "TDIR"/fs1", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs1")) goto out; err = mount("bpf", TDIR "/fs2", "bpf", 0, NULL); - if (CHECK(err, "mount bpffs " TDIR "/fs2", "failed: %d\n", errno)) + if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs2")) goto out; err = read_iter(TDIR "/fs1/maps.debug"); - if (CHECK(err, "reading " TDIR "/fs1/maps.debug", "failed\n")) + if (!ASSERT_OK(err, "reading " TDIR "/fs1/maps.debug")) goto out; err = read_iter(TDIR "/fs2/progs.debug"); - if (CHECK(err, "reading " TDIR "/fs2/progs.debug", "failed\n")) + if (!ASSERT_OK(err, "reading " TDIR "/fs2/progs.debug")) goto out; + + err = mkdir(TDIR "/fs1/a", 0777); + if (!ASSERT_OK(err, "creating " TDIR "/fs1/a")) + goto out; + err = mkdir(TDIR "/fs1/a/1", 0777); + if (!ASSERT_OK(err, "creating " TDIR "/fs1/a/1")) + goto out; + err = mkdir(TDIR "/fs1/b", 0777); + if (!ASSERT_OK(err, "creating " TDIR "/fs1/b")) + goto out; + + map = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (!ASSERT_GT(map, 0, "create_map(ARRAY)")) + goto out; + err = bpf_obj_pin(map, TDIR "/fs1/c"); + if (!ASSERT_OK(err, "pin map")) + goto out; + close(map); + + /* Check that RENAME_EXCHANGE works for directories. */ + err = stat(TDIR "/fs1/a", &a); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/a)")) + goto out; + err = renameat2(0, TDIR "/fs1/a", 0, TDIR "/fs1/b", RENAME_EXCHANGE); + if (!ASSERT_OK(err, "renameat2(/fs1/a, /fs1/b, RENAME_EXCHANGE)")) + goto out; + err = stat(TDIR "/fs1/b", &b); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)")) + goto out; + if (!ASSERT_EQ(a.st_ino, b.st_ino, "b should have a's inode")) + goto out; + err = access(TDIR "/fs1/b/1", F_OK); + if (!ASSERT_OK(err, "access(" TDIR "/fs1/b/1)")) + goto out; + + /* Check that RENAME_EXCHANGE works for mixed file types. */ + err = stat(TDIR "/fs1/c", &c); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/map)")) + goto out; + err = renameat2(0, TDIR "/fs1/c", 0, TDIR "/fs1/b", RENAME_EXCHANGE); + if (!ASSERT_OK(err, "renameat2(/fs1/c, /fs1/b, RENAME_EXCHANGE)")) + goto out; + err = stat(TDIR "/fs1/b", &b); + if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)")) + goto out; + if (!ASSERT_EQ(c.st_ino, b.st_ino, "b should have c's inode")) + goto out; + err = access(TDIR "/fs1/c/1", F_OK); + if (!ASSERT_OK(err, "access(" TDIR "/fs1/c/1)")) + goto out; + + /* Check that RENAME_NOREPLACE works. */ + err = renameat2(0, TDIR "/fs1/b", 0, TDIR "/fs1/a", RENAME_NOREPLACE); + if (!ASSERT_ERR(err, "renameat2(RENAME_NOREPLACE)")) { + err = -EINVAL; + goto out; + } + err = access(TDIR "/fs1/b", F_OK); + if (!ASSERT_OK(err, "access(" TDIR "/fs1/b)")) + goto out; + out: umount(TDIR "/fs1"); umount(TDIR "/fs2"); diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c index df918b2469da..52f6995ff29c 100644 --- a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c @@ -23,6 +23,16 @@ struct callback_ctx { int output; }; +const volatile int bypass_unused = 1; + +static __u64 +unused_subprog(struct bpf_map *map, __u32 *key, __u64 *val, + struct callback_ctx *data) +{ + data->output = 0; + return 1; +} + static __u64 check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val, struct callback_ctx *data) @@ -54,6 +64,8 @@ int test_pkt_access(struct __sk_buff *skb) data.output = 0; bpf_for_each_map_elem(&arraymap, check_array_elem, &data, 0); + if (!bypass_unused) + bpf_for_each_map_elem(&arraymap, unused_subprog, &data, 0); arraymap_output = data.output; bpf_for_each_map_elem(&percpu_map, check_percpu_elem, (void *)0, 0); diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 351955c2bdfd..05f872740999 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -2,11 +2,11 @@ # SPDX-License-Identifier: GPL-2.0 # # Test topology: -# - - - - - - - - - - - - - - - - - - - - - - - - - -# | veth1 veth2 veth3 | ... init net +# - - - - - - - - - - - - - - - - - - - +# | veth1 veth2 veth3 | ns0 # - -| - - - - - - | - - - - - - | - - # --------- --------- --------- -# | veth0 | | veth0 | | veth0 | ... +# | veth0 | | veth0 | | veth0 | # --------- --------- --------- # ns1 ns2 ns3 # @@ -31,6 +31,7 @@ IFACES="" DRV_MODE="xdpgeneric xdpdrv xdpegress" PASS=0 FAIL=0 +LOG_DIR=$(mktemp -d) test_pass() { @@ -50,6 +51,7 @@ clean_up() ip link del veth$i 2> /dev/null ip netns del ns$i 2> /dev/null done + ip netns del ns0 2> /dev/null } # Kselftest framework requirement - SKIP code is 4. @@ -77,10 +79,12 @@ setup_ns() mode="xdpdrv" fi + ip netns add ns0 for i in $(seq $NUM); do ip netns add ns$i - ip link add veth$i type veth peer name veth0 netns ns$i - ip link set veth$i up + ip -n ns$i link add veth0 index 2 type veth \ + peer name veth$i netns ns0 index $((1 + $i)) + ip -n ns0 link set veth$i up ip -n ns$i link set veth0 up ip -n ns$i addr add 192.0.2.$i/24 dev veth0 @@ -91,7 +95,7 @@ setup_ns() xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" - veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}') + veth_mac[$i]=$(ip -n ns0 link show veth$i | awk '/link\/ether/ {print $2}') done } @@ -100,17 +104,17 @@ do_egress_tests() local mode=$1 # mac test - ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-3_${mode}.log & + ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & + ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & sleep 0.5 ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null sleep 0.5 - pkill -9 tcpdump + pkill tcpdump # mac check - grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" mac_ns1-2_${mode}.log && \ + grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-2_${mode}.log && \ test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2" - grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" mac_ns1-3_${mode}.log && \ + grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-3_${mode}.log && \ test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3" } @@ -121,46 +125,46 @@ do_ping_tests() # ping6 test: echo request should be redirect back to itself, not others ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 - ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ns1-1_${mode}.log & - ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ns1-3_${mode}.log & + ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & + ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & + ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & sleep 0.5 # ARP test - ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null + ip netns exec ns1 arping -q -c 2 -I veth0 192.0.2.254 # IPv4 test ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null # IPv6 test ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null sleep 0.5 - pkill -9 tcpdump + pkill tcpdump # All netns should receive the redirect arp requests - [ $(grep -c "who-has 192.0.2.254" ns1-1_${mode}.log) -gt 4 ] && \ + [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \ test_pass "$mode arp(F_BROADCAST) ns1-1" || \ test_fail "$mode arp(F_BROADCAST) ns1-1" - [ $(grep -c "who-has 192.0.2.254" ns1-2_${mode}.log) -le 4 ] && \ + [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-2_${mode}.log) -eq 2 ] && \ test_pass "$mode arp(F_BROADCAST) ns1-2" || \ test_fail "$mode arp(F_BROADCAST) ns1-2" - [ $(grep -c "who-has 192.0.2.254" ns1-3_${mode}.log) -le 4 ] && \ + [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-3_${mode}.log) -eq 2 ] && \ test_pass "$mode arp(F_BROADCAST) ns1-3" || \ test_fail "$mode arp(F_BROADCAST) ns1-3" # ns1 should not receive the redirect echo request, others should - [ $(grep -c "ICMP echo request" ns1-1_${mode}.log) -eq 4 ] && \ + [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \ test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \ test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" - [ $(grep -c "ICMP echo request" ns1-2_${mode}.log) -eq 4 ] && \ + [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 4 ] && \ test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \ test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" - [ $(grep -c "ICMP echo request" ns1-3_${mode}.log) -eq 4 ] && \ + [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-3_${mode}.log) -eq 4 ] && \ test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \ test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" # ns1 should receive the echo request, ns2 should not - [ $(grep -c "ICMP6, echo request" ns1-1_${mode}.log) -eq 4 ] && \ + [ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \ test_pass "$mode IPv6 (no flags) ns1-1" || \ test_fail "$mode IPv6 (no flags) ns1-1" - [ $(grep -c "ICMP6, echo request" ns1-2_${mode}.log) -eq 0 ] && \ + [ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 0 ] && \ test_pass "$mode IPv6 (no flags) ns1-2" || \ test_fail "$mode IPv6 (no flags) ns1-2" } @@ -176,9 +180,13 @@ do_tests() xdpgeneric) drv_p="-S";; esac - ./xdp_redirect_multi $drv_p $IFACES &> xdp_redirect_${mode}.log & + ip netns exec ns0 ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & xdp_pid=$! sleep 1 + if ! ps -p $xdp_pid > /dev/null; then + test_fail "$mode xdp_redirect_multi start failed" + return 1 + fi if [ "$mode" = "xdpegress" ]; then do_egress_tests $mode @@ -189,16 +197,16 @@ do_tests() kill $xdp_pid } -trap clean_up 0 2 3 6 9 +trap clean_up EXIT check_env -rm -f xdp_redirect_*.log ns*.log mac_ns*.log for mode in ${DRV_MODE}; do setup_ns $mode do_tests $mode clean_up done +rm -rf ${LOG_DIR} echo "Summary: PASS $PASS, FAIL $FAIL" [ $FAIL -eq 0 ] && exit 0 || exit 1 diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index c9991c3f3bd2..7ab3de108761 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -265,3 +265,20 @@ .result = ACCEPT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, +{ + "Spill a u32 scalar at fp-4 and then at fp-8", + .insns = { + /* r4 = 4321 */ + BPF_MOV32_IMM(BPF_REG_4, 4321), + /* *(u32 *)(r10 -4) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u64 *)(r10 -8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c index 3696a8f32c23..f5ffba341c17 100644 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -129,7 +129,7 @@ int main(int argc, char **argv) goto err_out; } - printf("Get interfaces"); + printf("Get interfaces:"); for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) { ifaces[i] = if_nametoindex(argv[optind + i]); if (!ifaces[i]) @@ -139,7 +139,7 @@ int main(int argc, char **argv) goto err_out; } if (ifaces[i] > MAX_INDEX_NUM) { - printf("Interface index to large\n"); + printf(" interface index too large\n"); goto err_out; } printf(" %d", ifaces[i]); diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index c23e89dea0b6..c4e34717826a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -73,7 +73,8 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += access_tracking_perf_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test +TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index f6b3794f306b..6a1a37f30494 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -82,6 +82,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index b7531c83b8ae..587fbe408b99 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -46,4 +46,6 @@ static inline bool cpu_has_svm(void) return ecx & CPUID_SVM; } +int open_sev_dev_path_or_exit(void); + #endif /* SELFTEST_KVM_SVM_UTILS_H */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 041004c0fda7..14bb4d5b6bb7 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -31,6 +31,19 @@ static void *align(void *x, size_t size) return (void *) (((size_t) x + mask) & ~mask); } +int open_path_or_exit(const char *path, int flags) +{ + int fd; + + fd = open(path, flags); + if (fd < 0) { + print_skip("%s not available (errno: %d)", path, errno); + exit(KSFT_SKIP); + } + + return fd; +} + /* * Open KVM_DEV_PATH if available, otherwise exit the entire program. * @@ -42,16 +55,7 @@ static void *align(void *x, size_t size) */ static int _open_kvm_dev_path_or_exit(int flags) { - int fd; - - fd = open(KVM_DEV_PATH, flags); - if (fd < 0) { - print_skip("%s not available, is KVM loaded? (errno: %d)", - KVM_DEV_PATH, errno); - exit(KSFT_SKIP); - } - - return fd; + return open_path_or_exit(KVM_DEV_PATH, flags); } int open_kvm_dev_path_or_exit(void) diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 161eba7cd128..0ebc03ce079c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -13,6 +13,8 @@ #include "processor.h" #include "svm_util.h" +#define SEV_DEV_PATH "/dev/sev" + struct gpr64_regs guest_regs; u64 rflags; @@ -172,3 +174,14 @@ void nested_svm_check_supported(void) exit(KSFT_SKIP); } } + +/* + * Open SEV_DEV_PATH if available, otherwise exit the entire program. + * + * Return: + * The opened file descriptor of /dev/sev. + */ +int open_sev_dev_path_or_exit(void) +{ + return open_path_or_exit(SEV_DEV_PATH, 0); +} diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c new file mode 100644 index 000000000000..5ba325cd64bf --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/kvm.h> +#include <linux/psp-sev.h> +#include <stdio.h> +#include <sys/ioctl.h> +#include <stdlib.h> +#include <errno.h> +#include <pthread.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "kselftest.h" +#include "../lib/kvm_util_internal.h" + +#define SEV_POLICY_ES 0b100 + +#define NR_MIGRATE_TEST_VCPUS 4 +#define NR_MIGRATE_TEST_VMS 3 +#define NR_LOCK_TESTING_THREADS 3 +#define NR_LOCK_TESTING_ITERATIONS 10000 + +static void sev_ioctl(int vm_fd, int cmd_id, void *data) +{ + struct kvm_sev_cmd cmd = { + .id = cmd_id, + .data = (uint64_t)data, + .sev_fd = open_sev_dev_path_or_exit(), + }; + int ret; + + ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); + TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS), + "%d failed: return code: %d, errno: %d, fw error: %d", + cmd_id, ret, errno, cmd.error); +} + +static struct kvm_vm *sev_vm_create(bool es) +{ + struct kvm_vm *vm; + struct kvm_sev_launch_start start = { 0 }; + int i; + + vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL); + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(vm, i); + if (es) + start.policy |= SEV_POLICY_ES; + sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) + sev_ioctl(vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + return vm; +} + +static struct kvm_vm *__vm_create(void) +{ + struct kvm_vm *vm; + int i; + + vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(vm, i); + + return vm; +} + +static int __sev_migrate_from(int dst_fd, int src_fd) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, + .args = { src_fd } + }; + + return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); +} + + +static void sev_migrate_from(int dst_fd, int src_fd) +{ + int ret; + + ret = __sev_migrate_from(dst_fd, src_fd); + TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno); +} + +static void test_sev_migrate_from(bool es) +{ + struct kvm_vm *src_vm; + struct kvm_vm *dst_vms[NR_MIGRATE_TEST_VMS]; + int i; + + src_vm = sev_vm_create(es); + for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) + dst_vms[i] = __vm_create(); + + /* Initial migration from the src to the first dst. */ + sev_migrate_from(dst_vms[0]->fd, src_vm->fd); + + for (i = 1; i < NR_MIGRATE_TEST_VMS; i++) + sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd); + + /* Migrate the guest back to the original VM. */ + sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + + kvm_vm_free(src_vm); + for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) + kvm_vm_free(dst_vms[i]); +} + +struct locking_thread_input { + struct kvm_vm *vm; + int source_fds[NR_LOCK_TESTING_THREADS]; +}; + +static void *locking_test_thread(void *arg) +{ + int i, j; + struct locking_thread_input *input = (struct locking_thread_input *)arg; + + for (i = 0; i < NR_LOCK_TESTING_ITERATIONS; ++i) { + j = i % NR_LOCK_TESTING_THREADS; + __sev_migrate_from(input->vm->fd, input->source_fds[j]); + } + + return NULL; +} + +static void test_sev_migrate_locking(void) +{ + struct locking_thread_input input[NR_LOCK_TESTING_THREADS]; + pthread_t pt[NR_LOCK_TESTING_THREADS]; + int i; + + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) { + input[i].vm = sev_vm_create(/* es= */ false); + input[0].source_fds[i] = input[i].vm->fd; + } + for (i = 1; i < NR_LOCK_TESTING_THREADS; ++i) + memcpy(input[i].source_fds, input[0].source_fds, + sizeof(input[i].source_fds)); + + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + pthread_create(&pt[i], NULL, locking_test_thread, &input[i]); + + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + pthread_join(pt[i], NULL); +} + +static void test_sev_migrate_parameters(void) +{ + struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_no_sev, + *sev_es_vm_no_vmsa; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); + vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm_no_sev = __vm_create(); + sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); + vm_vcpu_add(sev_es_vm_no_vmsa, 1); + + + ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(sev_es_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm_no_vmsa->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Migrations require SEV enabled. ret %d, errno: %d\n", ret, + errno); +} + +int main(int argc, char *argv[]) +{ + test_sev_migrate_from(/* es= */ false); + test_sev_migrate_from(/* es= */ true); + test_sev_migrate_locking(); + test_sev_migrate_parameters(); + return 0; +} diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index aee76d1bb9da..7615f29831eb 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -12,7 +12,7 @@ TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_a TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh -TEST_PROGS += altnames.sh icmp_redirect.sh ip6_gre_headroom.sh +TEST_PROGS += altnames.sh icmp.sh icmp_redirect.sh ip6_gre_headroom.sh TEST_PROGS += route_localnet.sh TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh @@ -30,7 +30,12 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh -TEST_PROGS_EXTENDED := in_netns.sh +TEST_PROGS += srv6_end_dt46_l3vpn_test.sh +TEST_PROGS += srv6_end_dt4_l3vpn_test.sh +TEST_PROGS += srv6_end_dt6_l3vpn_test.sh +TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh +TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh index f8cda822c1ce..1b27f2b0f196 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -80,7 +80,7 @@ test_gretap() test_ip6gretap() { - test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ipv6' \ "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index 472bd023e2a5..aff88f78e339 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -74,7 +74,7 @@ test_span_gre_ttl() mirror_install $swp1 ingress $tundev "matchall $tcflags" tc filter add dev $h3 ingress pref 77 prot $prot \ - flower ip_ttl 50 action pass + flower skip_hw ip_ttl 50 action pass mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 880e3ab9d088..c8a9b5bd841f 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -141,7 +141,7 @@ test_gretap() test_ip6gretap() { - test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ipv6' \ "mirror to ip6gretap" } @@ -218,6 +218,7 @@ test_ip6gretap_forbidden_egress() test_span_gre_untagged_egress() { local tundev=$1; shift + local ul_proto=$1; shift local what=$1; shift RET=0 @@ -225,7 +226,7 @@ test_span_gre_untagged_egress() mirror_install $swp1 ingress $tundev "matchall $tcflags" quick_test_span_gre_dir $tundev ingress - quick_test_span_vlan_dir $h3 555 ingress + quick_test_span_vlan_dir $h3 555 ingress "$ul_proto" h3_addr_add_del del $h3.555 bridge vlan add dev $swp3 vid 555 pvid untagged @@ -233,7 +234,7 @@ test_span_gre_untagged_egress() sleep 5 quick_test_span_gre_dir $tundev ingress - fail_test_span_vlan_dir $h3 555 ingress + fail_test_span_vlan_dir $h3 555 ingress "$ul_proto" h3_addr_add_del del $h3 bridge vlan add dev $swp3 vid 555 @@ -241,7 +242,7 @@ test_span_gre_untagged_egress() sleep 5 quick_test_span_gre_dir $tundev ingress - quick_test_span_vlan_dir $h3 555 ingress + quick_test_span_vlan_dir $h3 555 ingress "$ul_proto" mirror_uninstall $swp1 ingress @@ -250,12 +251,12 @@ test_span_gre_untagged_egress() test_gretap_untagged_egress() { - test_span_gre_untagged_egress gt4 "mirror to gretap" + test_span_gre_untagged_egress gt4 ip "mirror to gretap" } test_ip6gretap_untagged_egress() { - test_span_gre_untagged_egress gt6 "mirror to ip6gretap" + test_span_gre_untagged_egress gt6 ipv6 "mirror to ip6gretap" } test_span_gre_fdb_roaming() diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index 6406cd76a19d..3e8ebeff3019 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -115,13 +115,14 @@ do_test_span_vlan_dir_ips() local dev=$1; shift local vid=$1; shift local direction=$1; shift + local ul_proto=$1; shift local ip1=$1; shift local ip2=$1; shift # Install the capture as skip_hw to avoid double-counting of packets. # The traffic is meant for local box anyway, so will be trapped to # kernel. - vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype ip" + vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype $ul_proto" mirror_test v$h1 $ip1 $ip2 $dev 100 $expect mirror_test v$h2 $ip2 $ip1 $dev 100 $expect vlan_capture_uninstall $dev diff --git a/tools/testing/selftests/net/forwarding/mirror_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_vlan.sh index 9ab2ce77b332..0b44e148235e 100755 --- a/tools/testing/selftests/net/forwarding/mirror_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_vlan.sh @@ -85,9 +85,9 @@ test_tagged_vlan_dir() RET=0 mirror_install $swp1 $direction $swp3.555 "matchall $tcflags" - do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" \ + do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" ip \ 192.0.2.17 192.0.2.18 - do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" \ + do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" ip \ 192.0.2.17 192.0.2.18 mirror_uninstall $swp1 $direction diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh index facbb0c80443..fdeb44d621eb 100755 --- a/tools/testing/selftests/net/gre_gso.sh +++ b/tools/testing/selftests/net/gre_gso.sh @@ -116,17 +116,18 @@ gre_gst_test_checks() { local name=$1 local addr=$2 + local proto=$3 - $NS_EXEC nc -kl $port >/dev/null & + $NS_EXEC nc $proto -kl $port >/dev/null & PID=$! while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done - cat $TMPFILE | timeout 1 nc $addr $port + cat $TMPFILE | timeout 1 nc $proto -N $addr $port log_test $? 0 "$name - copy file w/ TSO" ethtool -K veth0 tso off - cat $TMPFILE | timeout 1 nc $addr $port + cat $TMPFILE | timeout 1 nc $proto -N $addr $port log_test $? 0 "$name - copy file w/ GSO" ethtool -K veth0 tso on @@ -155,7 +156,7 @@ gre6_gso_test() sleep 2 gre_gst_test_checks GREv6/v4 172.16.2.2 - gre_gst_test_checks GREv6/v6 2001:db8:1::2 + gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6 cleanup } diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c index c9f478b40996..b2eebf669b8c 100644 --- a/tools/testing/selftests/net/reuseport_bpf_numa.c +++ b/tools/testing/selftests/net/reuseport_bpf_numa.c @@ -211,12 +211,16 @@ static void test(int *rcv_fd, int len, int family, int proto) /* Forward iterate */ for (node = 0; node < len; ++node) { + if (!numa_bitmask_isbitset(numa_nodes_ptr, node)) + continue; send_from_node(node, family, proto); receive_on_node(rcv_fd, len, epfd, node, proto); } /* Reverse iterate */ for (node = len - 1; node >= 0; --node) { + if (!numa_bitmask_isbitset(numa_nodes_ptr, node)) + continue; send_from_node(node, family, proto); receive_on_node(rcv_fd, len, epfd, node, proto); } diff --git a/tools/testing/selftests/net/test_vxlan_under_vrf.sh b/tools/testing/selftests/net/test_vxlan_under_vrf.sh index 534c8b7699ab..ea5a7a808f12 100755 --- a/tools/testing/selftests/net/test_vxlan_under_vrf.sh +++ b/tools/testing/selftests/net/test_vxlan_under_vrf.sh @@ -101,6 +101,8 @@ setup-vm() { ip -netns hv-$id link set veth-tap master br0 ip -netns hv-$id link set veth-tap up + ip link set veth-hv address 02:1d:8d:dd:0c:6$id + ip link set veth-hv netns vm-$id ip -netns vm-$id addr add 10.0.0.$id/24 dev veth-hv ip -netns vm-$id link set veth-hv up diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index d3047e251fe9..e61fc4c32ba2 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -654,7 +654,6 @@ TEST_F(tls, recvmsg_single_max) TEST_F(tls, recvmsg_multiple) { unsigned int msg_iovlen = 1024; - unsigned int len_compared = 0; struct iovec vec[1024]; char *iov_base[1024]; unsigned int iov_len = 16; @@ -675,8 +674,6 @@ TEST_F(tls, recvmsg_multiple) hdr.msg_iovlen = msg_iovlen; hdr.msg_iov = vec; EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1); - for (i = 0; i < msg_iovlen; i++) - len_compared += iov_len; for (i = 0; i < msg_iovlen; i++) free(iov_base[i]); diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 76a24052f4b4..6a193425c367 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -293,19 +293,17 @@ static void usage(const char *filepath) static void parse_opts(int argc, char **argv) { + const char *bind_addr = NULL; int c; - /* bind to any by default */ - setup_sockaddr(PF_INET6, "::", &cfg_bind_addr); while ((c = getopt(argc, argv, "4b:C:Gl:n:p:rR:S:tv")) != -1) { switch (c) { case '4': cfg_family = PF_INET; cfg_alen = sizeof(struct sockaddr_in); - setup_sockaddr(PF_INET, "0.0.0.0", &cfg_bind_addr); break; case 'b': - setup_sockaddr(cfg_family, optarg, &cfg_bind_addr); + bind_addr = optarg; break; case 'C': cfg_connect_timeout_ms = strtoul(optarg, NULL, 0); @@ -341,6 +339,11 @@ static void parse_opts(int argc, char **argv) } } + if (!bind_addr) + bind_addr = cfg_family == PF_INET6 ? "::" : "0.0.0.0"; + + setup_sockaddr(cfg_family, bind_addr, &cfg_bind_addr); + if (optind != argc) usage(argv[0]); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3f6d450355f0..d31724500501 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3747,7 +3747,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; - if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) @@ -3957,7 +3957,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, void __user *argp = compat_ptr(arg); int r; - if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -4023,7 +4023,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; - if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged) + if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -4345,7 +4345,7 @@ static long kvm_vm_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; - if (kvm->mm != current->mm || kvm->vm_bugged) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: @@ -4556,7 +4556,7 @@ static long kvm_vm_compat_ioctl(struct file *filp, struct kvm *kvm = filp->private_data; int r; - if (kvm->mm != current->mm || kvm->vm_bugged) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT |